gitea/conjurer
1
0
Fork 0
mirror of https://github.com/migatu/conjurer.git synced 2026-07-20 08:42:10 +00:00
Code Issues Packages Projects Releases Wiki Activity

Tag: 0.2

Browse Source 
Intermediate commits (oldest → newest):
- Fixed version of spotify_dl
- I also modified yt_dlp. But I do not remember what I changed. Have fun
- Poprawiono obsluge rotowanych logow i troche ulepszono funkcje opowiadania o fabryczcce
- Fucking windows bugfix and playlist gen fix
This commit is contained in:
Polish Hammer
2025-10-30 16:58:49 +01:00
parent eba11cc901
commit 0147b22000
1109 changed files with 218521 additions and 231 deletions
Download Patch File Download Diff File Expand all files Collapse all files
yt_dlp/extractor/__init__.py
+42
View File
@@ -0,0 +1,42 @@
from ..compat.compat_utils import passthrough_module
passthrough_module(__name__, '.extractors')
del passthrough_module
def gen_extractor_classes():
""" Return a list of supported extractors.
The order does matter; the first extractor matched is the one handling the URL.
"""
from .extractors import _ALL_CLASSES
return _ALL_CLASSES
def gen_extractors():
""" Return a list of an instance of every supported extractor.
The order does matter; the first extractor matched is the one handling the URL.
"""
return [klass() for klass in gen_extractor_classes()]
def list_extractor_classes(age_limit=None):
"""Return a list of extractors that are suitable for the given age, sorted by extractor name"""
from .generic import GenericIE
yield from sorted(filter(
lambda ie: ie.is_suitable(age_limit) and ie != GenericIE,
gen_extractor_classes()), key=lambda ie: ie.IE_NAME.lower())
yield GenericIE
def list_extractors(age_limit=None):
"""Return a list of extractor instances that are suitable for the given age, sorted by extractor name"""
return [ie() for ie in list_extractor_classes(age_limit)]
def get_info_extractor(ie_name):
"""Returns the info extractor class with the given ie_name"""
from . import extractors
return getattr(extractors, f'{ie_name}IE')
yt_dlp/extractor/_extractors.py
+2429
View File
File diff suppressed because it is too large Load Diff
yt_dlp/extractor/abc.py
+313
View File
@@ -0,0 +1,313 @@
import hashlib
import hmac
import re
import time
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
dict_get,
ExtractorError,
js_to_json,
int_or_none,
parse_iso8601,
str_or_none,
try_get,
unescapeHTML,
update_url_query,
)
class ABCIE(InfoExtractor):
IE_NAME = 'abc.net.au'
_VALID_URL = r'https?://(?:www\.)?abc\.net\.au/(?:news|btn)/(?:[^/]+/){1,4}(?P<id>\d{5,})'
_TESTS = [{
'url': 'http://www.abc.net.au/news/2014-11-05/australia-to-staff-ebola-treatment-centre-in-sierra-leone/5868334',
'md5': 'cb3dd03b18455a661071ee1e28344d9f',
'info_dict': {
'id': '5868334',
'ext': 'mp4',
'title': 'Australia to help staff Ebola treatment centre in Sierra Leone',
'description': 'md5:809ad29c67a05f54eb41f2a105693a67',
},
'skip': 'this video has expired',
}, {
'url': 'http://www.abc.net.au/news/2015-08-17/warren-entsch-introduces-same-sex-marriage-bill/6702326',
'md5': '4ebd61bdc82d9a8b722f64f1f4b4d121',
'info_dict': {
'id': 'NvqvPeNZsHU',
'ext': 'mp4',
'upload_date': '20150816',
'uploader': 'ABC News (Australia)',
'description': 'Government backbencher Warren Entsch introduces a cross-party sponsored bill to legalise same-sex marriage, saying the bill is designed to promote "an inclusive Australia, not a divided one.". Read more here: http://ab.co/1Mwc6ef',
'uploader_id': 'NewsOnABC',
'title': 'Marriage Equality: Warren Entsch introduces same sex marriage bill',
},
'add_ie': ['Youtube'],
'skip': 'Not accessible from Travis CI server',
}, {
'url': 'http://www.abc.net.au/news/2015-10-23/nab-lifts-interest-rates-following-westpac-and-cba/6880080',
'md5': 'b96eee7c9edf4fc5a358a0252881cc1f',
'info_dict': {
'id': '6880080',
'ext': 'mp3',
'title': 'NAB lifts interest rates, following Westpac and CBA',
'description': 'md5:f13d8edc81e462fce4a0437c7dc04728',
},
}, {
'url': 'http://www.abc.net.au/news/2015-10-19/6866214',
'only_matching': True,
}, {
'url': 'https://www.abc.net.au/btn/classroom/wwi-centenary/10527914',
'info_dict': {
'id': '10527914',
'ext': 'mp4',
'title': 'WWI Centenary',
'description': 'md5:c2379ec0ca84072e86b446e536954546',
}
}, {
'url': 'https://www.abc.net.au/news/programs/the-world/2020-06-10/black-lives-matter-protests-spawn-support-for/12342074',
'info_dict': {
'id': '12342074',
'ext': 'mp4',
'title': 'Black Lives Matter protests spawn support for Papuans in Indonesia',
'description': 'md5:2961a17dc53abc558589ccd0fb8edd6f',
}
}, {
'url': 'https://www.abc.net.au/btn/newsbreak/btn-newsbreak-20200814/12560476',
'info_dict': {
'id': 'tDL8Ld4dK_8',
'ext': 'mp4',
'title': 'Fortnite Banned From Apple and Google App Stores',
'description': 'md5:a6df3f36ce8f816b74af4bd6462f5651',
'upload_date': '20200813',
'uploader': 'Behind the News',
'uploader_id': 'behindthenews',
}
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
mobj = re.search(r'<a\s+href="(?P<url>[^"]+)"\s+data-duration="\d+"\s+title="Download audio directly">', webpage)
if mobj:
urls_info = mobj.groupdict()
youtube = False
video = False
else:
mobj = re.search(r'<a href="(?P<url>http://www\.youtube\.com/watch\?v=[^"]+)"><span><strong>External Link:</strong>',
webpage)
if mobj is None:
mobj = re.search(r'<iframe width="100%" src="(?P<url>//www\.youtube-nocookie\.com/embed/[^?"]+)', webpage)
if mobj:
urls_info = mobj.groupdict()
youtube = True
video = True
if mobj is None:
mobj = re.search(r'(?P<type>)"sources": (?P<json_data>\[[^\]]+\]),', webpage)
if mobj is None:
mobj = re.search(
r'inline(?P<type>Video|Audio|YouTube)Data\.push\((?P<json_data>[^)]+)\);',
webpage)
if mobj is None:
expired = self._html_search_regex(r'(?s)class="expired-(?:video|audio)".+?<span>(.+?)</span>', webpage, 'expired', None)
if expired:
raise ExtractorError('%s said: %s' % (self.IE_NAME, expired), expected=True)
raise ExtractorError('Unable to extract video urls')
urls_info = self._parse_json(
mobj.group('json_data'), video_id, transform_source=js_to_json)
youtube = mobj.group('type') == 'YouTube'
video = mobj.group('type') == 'Video' or urls_info[0]['contentType'] == 'video/mp4'
if not isinstance(urls_info, list):
urls_info = [urls_info]
if youtube:
return self.playlist_result([
self.url_result(url_info['url']) for url_info in urls_info])
formats = []
for url_info in urls_info:
height = int_or_none(url_info.get('height'))
bitrate = int_or_none(url_info.get('bitrate'))
width = int_or_none(url_info.get('width'))
format_id = None
mobj = re.search(r'_(?:(?P<height>\d+)|(?P<bitrate>\d+)k)\.mp4$', url_info['url'])
if mobj:
height_from_url = mobj.group('height')
if height_from_url:
height = height or int_or_none(height_from_url)
width = width or int_or_none(url_info.get('label'))
else:
bitrate = bitrate or int_or_none(mobj.group('bitrate'))
format_id = str_or_none(url_info.get('label'))
formats.append({
'url': url_info['url'],
'vcodec': url_info.get('codec') if video else 'none',
'width': width,
'height': height,
'tbr': bitrate,
'filesize': int_or_none(url_info.get('filesize')),
'format_id': format_id
})
return {
'id': video_id,
'title': self._og_search_title(webpage),
'formats': formats,
'description': self._og_search_description(webpage),
'thumbnail': self._og_search_thumbnail(webpage),
}
class ABCIViewIE(InfoExtractor):
IE_NAME = 'abc.net.au:iview'
_VALID_URL = r'https?://iview\.abc\.net\.au/(?:[^/]+/)*video/(?P<id>[^/?#]+)'
_GEO_COUNTRIES = ['AU']
# ABC iview programs are normally available for 14 days only.
_TESTS = [{
'url': 'https://iview.abc.net.au/show/gruen/series/11/video/LE1927H001S00',
'md5': '67715ce3c78426b11ba167d875ac6abf',
'info_dict': {
'id': 'LE1927H001S00',
'ext': 'mp4',
'title': "Series 11 Ep 1",
'series': "Gruen",
'description': 'md5:52cc744ad35045baf6aded2ce7287f67',
'upload_date': '20190925',
'uploader_id': 'abc1',
'timestamp': 1569445289,
},
'params': {
'skip_download': True,
},
}]
def _real_extract(self, url):
video_id = self._match_id(url)
video_params = self._download_json(
'https://iview.abc.net.au/api/programs/' + video_id, video_id)
title = unescapeHTML(video_params.get('title') or video_params['seriesTitle'])
stream = next(s for s in video_params['playlist'] if s.get('type') in ('program', 'livestream'))
house_number = video_params.get('episodeHouseNumber') or video_id
path = '/auth/hls/sign?ts={0}&hn={1}&d=android-tablet'.format(
int(time.time()), house_number)
sig = hmac.new(
b'android.content.res.Resources',
path.encode('utf-8'), hashlib.sha256).hexdigest()
token = self._download_webpage(
'http://iview.abc.net.au{0}&sig={1}'.format(path, sig), video_id)
def tokenize_url(url, token):
return update_url_query(url, {
'hdnea': token,
})
for sd in ('1080', '720', 'sd', 'sd-low'):
sd_url = try_get(
stream, lambda x: x['streams']['hls'][sd], compat_str)
if not sd_url:
continue
formats = self._extract_m3u8_formats(
tokenize_url(sd_url, token), video_id, 'mp4',
entry_protocol='m3u8_native', m3u8_id='hls', fatal=False)
if formats:
break
subtitles = {}
src_vtt = stream.get('captions', {}).get('src-vtt')
if src_vtt:
subtitles['en'] = [{
'url': src_vtt,
'ext': 'vtt',
}]
is_live = video_params.get('livestream') == '1'
return {
'id': video_id,
'title': title,
'description': video_params.get('description'),
'thumbnail': video_params.get('thumbnail'),
'duration': int_or_none(video_params.get('eventDuration')),
'timestamp': parse_iso8601(video_params.get('pubDate'), ' '),
'series': unescapeHTML(video_params.get('seriesTitle')),
'series_id': video_params.get('seriesHouseNumber') or video_id[:7],
'season_number': int_or_none(self._search_regex(
r'\bSeries\s+(\d+)\b', title, 'season number', default=None)),
'episode_number': int_or_none(self._search_regex(
r'\bEp\s+(\d+)\b', title, 'episode number', default=None)),
'episode_id': house_number,
'uploader_id': video_params.get('channel'),
'formats': formats,
'subtitles': subtitles,
'is_live': is_live,
}
class ABCIViewShowSeriesIE(InfoExtractor):
IE_NAME = 'abc.net.au:iview:showseries'
_VALID_URL = r'https?://iview\.abc\.net\.au/show/(?P<id>[^/]+)(?:/series/\d+)?$'
_GEO_COUNTRIES = ['AU']
_TESTS = [{
'url': 'https://iview.abc.net.au/show/upper-middle-bogan',
'info_dict': {
'id': '124870-1',
'title': 'Series 1',
'description': 'md5:93119346c24a7c322d446d8eece430ff',
'series': 'Upper Middle Bogan',
'season': 'Series 1',
'thumbnail': r're:^https?://cdn\.iview\.abc\.net\.au/thumbs/.*\.jpg$'
},
'playlist_count': 8,
}, {
'url': 'https://iview.abc.net.au/show/upper-middle-bogan',
'info_dict': {
'id': 'CO1108V001S00',
'ext': 'mp4',
'title': 'Series 1 Ep 1 I\'m A Swan',
'description': 'md5:7b676758c1de11a30b79b4d301e8da93',
'series': 'Upper Middle Bogan',
'uploader_id': 'abc1',
'upload_date': '20210630',
'timestamp': 1625036400,
},
'params': {
'noplaylist': True,
'skip_download': 'm3u8',
},
}]
def _real_extract(self, url):
show_id = self._match_id(url)
webpage = self._download_webpage(url, show_id)
webpage_data = self._search_regex(
r'window\.__INITIAL_STATE__\s*=\s*[\'"](.+?)[\'"]\s*;',
webpage, 'initial state')
video_data = self._parse_json(
unescapeHTML(webpage_data).encode('utf-8').decode('unicode_escape'), show_id)
video_data = video_data['route']['pageData']['_embedded']
highlight = try_get(video_data, lambda x: x['highlightVideo']['shareUrl'])
if not self._yes_playlist(show_id, bool(highlight), video_label='highlight video'):
return self.url_result(highlight, ie=ABCIViewIE.ie_key())
series = video_data['selectedSeries']
return {
'_type': 'playlist',
'entries': [self.url_result(episode['shareUrl'])
for episode in series['_embedded']['videoEpisodes']],
'id': series.get('id'),
'title': dict_get(series, ('title', 'displaySubtitle')),
'description': series.get('description'),
'series': dict_get(series, ('showTitle', 'displayTitle')),
'season': dict_get(series, ('title', 'displaySubtitle')),
'thumbnail': series.get('thumbnail'),
}
yt_dlp/extractor/abcnews.py
+153
View File
@@ -0,0 +1,153 @@
from .amp import AMPIE
from .common import InfoExtractor
from ..utils import (
parse_duration,
parse_iso8601,
try_get,
)
class AbcNewsVideoIE(AMPIE):
IE_NAME = 'abcnews:video'
_VALID_URL = r'''(?x)
https?://
(?:
abcnews\.go\.com/
(?:
(?:[^/]+/)*video/(?P<display_id>[0-9a-z-]+)-|
video/(?:embed|itemfeed)\?.*?\bid=
)|
fivethirtyeight\.abcnews\.go\.com/video/embed/\d+/
)
(?P<id>\d+)
'''
_TESTS = [{
'url': 'http://abcnews.go.com/ThisWeek/video/week-exclusive-irans-foreign-minister-zarif-20411932',
'info_dict': {
'id': '20411932',
'ext': 'mp4',
'display_id': 'week-exclusive-irans-foreign-minister-zarif',
'title': '\'This Week\' Exclusive: Iran\'s Foreign Minister Zarif',
'description': 'George Stephanopoulos goes one-on-one with Iranian Foreign Minister Dr. Javad Zarif.',
'duration': 180,
'thumbnail': r're:^https?://.*\.jpg$',
'timestamp': 1380454200,
'upload_date': '20130929',
},
'params': {
# m3u8 download
'skip_download': True,
},
}, {
'url': 'http://abcnews.go.com/video/embed?id=46979033',
'only_matching': True,
}, {
'url': 'http://abcnews.go.com/2020/video/2020-husband-stands-teacher-jail-student-affairs-26119478',
'only_matching': True,
}, {
'url': 'http://abcnews.go.com/video/itemfeed?id=46979033',
'only_matching': True,
}, {
'url': 'https://abcnews.go.com/GMA/News/video/history-christmas-story-67894761',
'only_matching': True,
}]
def _real_extract(self, url):
mobj = self._match_valid_url(url)
display_id = mobj.group('display_id')
video_id = mobj.group('id')
info_dict = self._extract_feed_info(
'http://abcnews.go.com/video/itemfeed?id=%s' % video_id)
info_dict.update({
'id': video_id,
'display_id': display_id,
})
return info_dict
class AbcNewsIE(InfoExtractor):
IE_NAME = 'abcnews'
_VALID_URL = r'https?://abcnews\.go\.com/(?:[^/]+/)+(?P<display_id>[0-9a-z-]+)/story\?id=(?P<id>\d+)'
_TESTS = [{
# Youtube Embeds
'url': 'https://abcnews.go.com/Entertainment/peter-billingsley-child-actor-christmas-story-hollywood-power/story?id=51286501',
'info_dict': {
'id': '51286501',
'title': "Peter Billingsley: From child actor in 'A Christmas Story' to Hollywood power player",
'description': 'Billingsley went from a child actor to Hollywood power player.',
},
'playlist_count': 5,
}, {
'url': 'http://abcnews.go.com/Entertainment/justin-timberlake-performs-stop-feeling-eurovision-2016/story?id=39125818',
'info_dict': {
'id': '38897857',
'ext': 'mp4',
'title': 'Justin Timberlake Drops Hints For Secret Single',
'description': 'Lara Spencer reports the buzziest stories of the day in "GMA" Pop News.',
'upload_date': '20160505',
'timestamp': 1462442280,
},
'params': {
# m3u8 download
'skip_download': True,
# The embedded YouTube video is blocked due to copyright issues
'playlist_items': '1',
},
'add_ie': ['AbcNewsVideo'],
}, {
'url': 'http://abcnews.go.com/Technology/exclusive-apple-ceo-tim-cook-iphone-cracking-software/story?id=37173343',
'only_matching': True,
}, {
# inline.type == 'video'
'url': 'http://abcnews.go.com/Technology/exclusive-apple-ceo-tim-cook-iphone-cracking-software/story?id=37173343',
'only_matching': True,
}]
def _real_extract(self, url):
story_id = self._match_id(url)
webpage = self._download_webpage(url, story_id)
story = self._parse_json(self._search_regex(
r"window\['__abcnews__'\]\s*=\s*({.+?});",
webpage, 'data'), story_id)['page']['content']['story']['everscroll'][0]
article_contents = story.get('articleContents') or {}
def entries():
featured_video = story.get('featuredVideo') or {}
feed = try_get(featured_video, lambda x: x['video']['feed'])
if feed:
yield {
'_type': 'url',
'id': featured_video.get('id'),
'title': featured_video.get('name'),
'url': feed,
'thumbnail': featured_video.get('images'),
'description': featured_video.get('description'),
'timestamp': parse_iso8601(featured_video.get('uploadDate')),
'duration': parse_duration(featured_video.get('duration')),
'ie_key': AbcNewsVideoIE.ie_key(),
}
for inline in (article_contents.get('inlines') or []):
inline_type = inline.get('type')
if inline_type == 'iframe':
iframe_url = try_get(inline, lambda x: x['attrs']['src'])
if iframe_url:
yield self.url_result(iframe_url)
elif inline_type == 'video':
video_id = inline.get('id')
if video_id:
yield {
'_type': 'url',
'id': video_id,
'url': 'http://abcnews.go.com/video/embed?id=' + video_id,
'thumbnail': inline.get('imgSrc') or inline.get('imgDefault'),
'description': inline.get('description'),
'duration': parse_duration(inline.get('duration')),
'ie_key': AbcNewsVideoIE.ie_key(),
}
return self.playlist_result(
entries(), story_id, article_contents.get('headline'),
article_contents.get('subHead'))
yt_dlp/extractor/abcotvs.py
+130
View File
@@ -0,0 +1,130 @@
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
dict_get,
int_or_none,
try_get,
)
class ABCOTVSIE(InfoExtractor):
IE_NAME = 'abcotvs'
IE_DESC = 'ABC Owned Television Stations'
_VALID_URL = r'https?://(?P<site>abc(?:7(?:news|ny|chicago)?|11|13|30)|6abc)\.com(?:(?:/[^/]+)*/(?P<display_id>[^/]+))?/(?P<id>\d+)'
_TESTS = [
{
'url': 'http://abc7news.com/entertainment/east-bay-museum-celebrates-vintage-synthesizers/472581/',
'info_dict': {
'id': '472548',
'display_id': 'east-bay-museum-celebrates-vintage-synthesizers',
'ext': 'mp4',
'title': 'East Bay museum celebrates synthesized music',
'description': 'md5:24ed2bd527096ec2a5c67b9d5a9005f3',
'thumbnail': r're:^https?://.*\.jpg$',
'timestamp': 1421118520,
'upload_date': '20150113',
},
'params': {
# m3u8 download
'skip_download': True,
},
},
{
'url': 'http://abc7news.com/472581',
'only_matching': True,
},
{
'url': 'https://6abc.com/man-75-killed-after-being-struck-by-vehicle-in-chester/5725182/',
'only_matching': True,
},
]
_SITE_MAP = {
'6abc': 'wpvi',
'abc11': 'wtvd',
'abc13': 'ktrk',
'abc30': 'kfsn',
'abc7': 'kabc',
'abc7chicago': 'wls',
'abc7news': 'kgo',
'abc7ny': 'wabc',
}
def _real_extract(self, url):
site, display_id, video_id = self._match_valid_url(url).groups()
display_id = display_id or video_id
station = self._SITE_MAP[site]
data = self._download_json(
'https://api.abcotvs.com/v2/content', display_id, query={
'id': video_id,
'key': 'otv.web.%s.story' % station,
'station': station,
})['data']
video = try_get(data, lambda x: x['featuredMedia']['video'], dict) or data
video_id = compat_str(dict_get(video, ('id', 'publishedKey'), video_id))
title = video.get('title') or video['linkText']
formats = []
m3u8_url = video.get('m3u8')
if m3u8_url:
formats = self._extract_m3u8_formats(
video['m3u8'].split('?')[0], display_id, 'mp4', m3u8_id='hls', fatal=False)
mp4_url = video.get('mp4')
if mp4_url:
formats.append({
'abr': 128,
'format_id': 'https',
'height': 360,
'url': mp4_url,
'width': 640,
})
image = video.get('image') or {}
return {
'id': video_id,
'display_id': display_id,
'title': title,
'description': dict_get(video, ('description', 'caption'), try_get(video, lambda x: x['meta']['description'])),
'thumbnail': dict_get(image, ('source', 'dynamicSource')),
'timestamp': int_or_none(video.get('date')),
'duration': int_or_none(video.get('length')),
'formats': formats,
}
class ABCOTVSClipsIE(InfoExtractor):
IE_NAME = 'abcotvs:clips'
_VALID_URL = r'https?://clips\.abcotvs\.com/(?:[^/]+/)*video/(?P<id>\d+)'
_TEST = {
'url': 'https://clips.abcotvs.com/kabc/video/214814',
'info_dict': {
'id': '214814',
'ext': 'mp4',
'title': 'SpaceX launch pad explosion destroys rocket, satellite',
'description': 'md5:9f186e5ad8f490f65409965ee9c7be1b',
'upload_date': '20160901',
'timestamp': 1472756695,
},
'params': {
# m3u8 download
'skip_download': True,
},
}
def _real_extract(self, url):
video_id = self._match_id(url)
video_data = self._download_json('https://clips.abcotvs.com/vogo/video/getByIds?ids=' + video_id, video_id)['results'][0]
title = video_data['title']
formats = self._extract_m3u8_formats(
video_data['videoURL'].split('?')[0], video_id, 'mp4')
return {
'id': video_id,
'title': title,
'description': video_data.get('description'),
'thumbnail': video_data.get('thumbnailURL'),
'duration': int_or_none(video_data.get('duration')),
'timestamp': int_or_none(video_data.get('pubDate')),
'formats': formats,
}
yt_dlp/extractor/abematv.py
+522
View File
@@ -0,0 +1,522 @@
import base64
import binascii
import functools
import hashlib
import hmac
import io
import json
import re
import struct
import time
import urllib.parse
import urllib.request
import urllib.response
import uuid
from .common import InfoExtractor
from ..aes import aes_ecb_decrypt
from ..utils import (
ExtractorError,
bytes_to_intlist,
decode_base_n,
int_or_none,
intlist_to_bytes,
OnDemandPagedList,
request_to_url,
time_seconds,
traverse_obj,
update_url_query,
)
# NOTE: network handler related code is temporary thing until network stack overhaul PRs are merged (#2861/#2862)
def add_opener(ydl, handler):
''' Add a handler for opening URLs, like _download_webpage '''
# https://github.com/python/cpython/blob/main/Lib/urllib/request.py#L426
# https://github.com/python/cpython/blob/main/Lib/urllib/request.py#L605
assert isinstance(ydl._opener, urllib.request.OpenerDirector)
ydl._opener.add_handler(handler)
def remove_opener(ydl, handler):
'''
Remove handler(s) for opening URLs
@param handler Either handler object itself or handler type.
Specifying handler type will remove all handler which isinstance returns True.
'''
# https://github.com/python/cpython/blob/main/Lib/urllib/request.py#L426
# https://github.com/python/cpython/blob/main/Lib/urllib/request.py#L605
opener = ydl._opener
assert isinstance(ydl._opener, urllib.request.OpenerDirector)
if isinstance(handler, (type, tuple)):
find_cp = lambda x: isinstance(x, handler)
else:
find_cp = lambda x: x is handler
removed = []
for meth in dir(handler):
if meth in ["redirect_request", "do_open", "proxy_open"]:
# oops, coincidental match
continue
i = meth.find("_")
protocol = meth[:i]
condition = meth[i + 1:]
if condition.startswith("error"):
j = condition.find("_") + i + 1
kind = meth[j + 1:]
try:
kind = int(kind)
except ValueError:
pass
lookup = opener.handle_error.get(protocol, {})
opener.handle_error[protocol] = lookup
elif condition == "open":
kind = protocol
lookup = opener.handle_open
elif condition == "response":
kind = protocol
lookup = opener.process_response
elif condition == "request":
kind = protocol
lookup = opener.process_request
else:
continue
handlers = lookup.setdefault(kind, [])
if handlers:
handlers[:] = [x for x in handlers if not find_cp(x)]
removed.append(x for x in handlers if find_cp(x))
if removed:
for x in opener.handlers:
if find_cp(x):
x.add_parent(None)
opener.handlers[:] = [x for x in opener.handlers if not find_cp(x)]
class AbemaLicenseHandler(urllib.request.BaseHandler):
handler_order = 499
STRTABLE = '123456789ABCDEFGHJKLMNPQRSTUVWXYZabcdefghijkmnopqrstuvwxyz'
HKEY = b'3AF0298C219469522A313570E8583005A642E73EDD58E3EA2FB7339D3DF1597E'
def __init__(self, ie: 'AbemaTVIE'):
# the protocol that this should really handle is 'abematv-license://'
# abematv_license_open is just a placeholder for development purposes
# ref. https://github.com/python/cpython/blob/f4c03484da59049eb62a9bf7777b963e2267d187/Lib/urllib/request.py#L510
setattr(self, 'abematv-license_open', getattr(self, 'abematv_license_open'))
self.ie = ie
def _get_videokey_from_ticket(self, ticket):
to_show = self.ie.get_param('verbose', False)
media_token = self.ie._get_media_token(to_show=to_show)
license_response = self.ie._download_json(
'https://license.abema.io/abematv-hls', None, note='Requesting playback license' if to_show else False,
query={'t': media_token},
data=json.dumps({
'kv': 'a',
'lt': ticket
}).encode('utf-8'),
headers={
'Content-Type': 'application/json',
})
res = decode_base_n(license_response['k'], table=self.STRTABLE)
encvideokey = bytes_to_intlist(struct.pack('>QQ', res >> 64, res & 0xffffffffffffffff))
h = hmac.new(
binascii.unhexlify(self.HKEY),
(license_response['cid'] + self.ie._DEVICE_ID).encode('utf-8'),
digestmod=hashlib.sha256)
enckey = bytes_to_intlist(h.digest())
return intlist_to_bytes(aes_ecb_decrypt(encvideokey, enckey))
def abematv_license_open(self, url):
url = request_to_url(url)
ticket = urllib.parse.urlparse(url).netloc
response_data = self._get_videokey_from_ticket(ticket)
return urllib.response.addinfourl(io.BytesIO(response_data), headers={
'Content-Length': len(response_data),
}, url=url, code=200)
class AbemaTVBaseIE(InfoExtractor):
_USERTOKEN = None
_DEVICE_ID = None
_MEDIATOKEN = None
_SECRETKEY = b'v+Gjs=25Aw5erR!J8ZuvRrCx*rGswhB&qdHd_SYerEWdU&a?3DzN9BRbp5KwY4hEmcj5#fykMjJ=AuWz5GSMY-d@H7DMEh3M@9n2G552Us$$k9cD=3TxwWe86!x#Zyhe'
@classmethod
def _generate_aks(cls, deviceid):
deviceid = deviceid.encode('utf-8')
# add 1 hour and then drop minute and secs
ts_1hour = int((time_seconds() // 3600 + 1) * 3600)
time_struct = time.gmtime(ts_1hour)
ts_1hour_str = str(ts_1hour).encode('utf-8')
tmp = None
def mix_once(nonce):
nonlocal tmp
h = hmac.new(cls._SECRETKEY, digestmod=hashlib.sha256)
h.update(nonce)
tmp = h.digest()
def mix_tmp(count):
nonlocal tmp
for i in range(count):
mix_once(tmp)
def mix_twist(nonce):
nonlocal tmp
mix_once(base64.urlsafe_b64encode(tmp).rstrip(b'=') + nonce)
mix_once(cls._SECRETKEY)
mix_tmp(time_struct.tm_mon)
mix_twist(deviceid)
mix_tmp(time_struct.tm_mday % 5)
mix_twist(ts_1hour_str)
mix_tmp(time_struct.tm_hour % 5)
return base64.urlsafe_b64encode(tmp).rstrip(b'=').decode('utf-8')
def _get_device_token(self):
if self._USERTOKEN:
return self._USERTOKEN
username, _ = self._get_login_info()
AbemaTVBaseIE._USERTOKEN = username and self.cache.load(self._NETRC_MACHINE, username)
if AbemaTVBaseIE._USERTOKEN:
# try authentication with locally stored token
try:
self._get_media_token(True)
return
except ExtractorError as e:
self.report_warning(f'Failed to login with cached user token; obtaining a fresh one ({e})')
AbemaTVBaseIE._DEVICE_ID = str(uuid.uuid4())
aks = self._generate_aks(self._DEVICE_ID)
user_data = self._download_json(
'https://api.abema.io/v1/users', None, note='Authorizing',
data=json.dumps({
'deviceId': self._DEVICE_ID,
'applicationKeySecret': aks,
}).encode('utf-8'),
headers={
'Content-Type': 'application/json',
})
AbemaTVBaseIE._USERTOKEN = user_data['token']
# don't allow adding it 2 times or more, though it's guarded
remove_opener(self._downloader, AbemaLicenseHandler)
add_opener(self._downloader, AbemaLicenseHandler(self))
return self._USERTOKEN
def _get_media_token(self, invalidate=False, to_show=True):
if not invalidate and self._MEDIATOKEN:
return self._MEDIATOKEN
AbemaTVBaseIE._MEDIATOKEN = self._download_json(
'https://api.abema.io/v1/media/token', None, note='Fetching media token' if to_show else False,
query={
'osName': 'android',
'osVersion': '6.0.1',
'osLang': 'ja_JP',
'osTimezone': 'Asia/Tokyo',
'appId': 'tv.abema',
'appVersion': '3.27.1'
}, headers={
'Authorization': f'bearer {self._get_device_token()}',
})['token']
return self._MEDIATOKEN
def _call_api(self, endpoint, video_id, query=None, note='Downloading JSON metadata'):
return self._download_json(
f'https://api.abema.io/{endpoint}', video_id, query=query or {},
note=note,
headers={
'Authorization': f'bearer {self._get_device_token()}',
})
def _extract_breadcrumb_list(self, webpage, video_id):
for jld in re.finditer(
r'(?is)</span></li></ul><script[^>]+type=(["\']?)application/ld\+json\1[^>]*>(?P<json_ld>.+?)</script>',
webpage):
jsonld = self._parse_json(jld.group('json_ld'), video_id, fatal=False)
if traverse_obj(jsonld, '@type') != 'BreadcrumbList':
continue
items = traverse_obj(jsonld, ('itemListElement', ..., 'name'))
if items:
return items
return []
class AbemaTVIE(AbemaTVBaseIE):
_VALID_URL = r'https?://abema\.tv/(?P<type>now-on-air|video/episode|channels/.+?/slots)/(?P<id>[^?/]+)'
_NETRC_MACHINE = 'abematv'
_TESTS = [{
'url': 'https://abema.tv/video/episode/194-25_s2_p1',
'info_dict': {
'id': '194-25_s2_p1',
'title': '第1話 「チーズケーキ」　「モーニング再び」',
'series': '異世界食堂２',
'series_number': 2,
'episode': '第1話 「チーズケーキ」　「モーニング再び」',
'episode_number': 1,
},
'skip': 'expired',
}, {
'url': 'https://abema.tv/channels/anime-live2/slots/E8tvAnMJ7a9a5d',
'info_dict': {
'id': 'E8tvAnMJ7a9a5d',
'title': 'ゆるキャン△ SEASON２ 全話一挙【無料ビデオ72時間】',
'series': 'ゆるキャン△ SEASON２',
'episode': 'ゆるキャン△ SEASON２ 全話一挙【無料ビデオ72時間】',
'series_number': 2,
'episode_number': 1,
'description': 'md5:9c5a3172ae763278f9303922f0ea5b17',
},
'skip': 'expired',
}, {
'url': 'https://abema.tv/video/episode/87-877_s1282_p31047',
'info_dict': {
'id': 'E8tvAnMJ7a9a5d',
'title': '第5話『光射す』',
'description': 'md5:56d4fc1b4f7769ded5f923c55bb4695d',
'thumbnail': r're:https://hayabusa\.io/.+',
'series': '相棒',
'episode': '第5話『光射す』',
},
'skip': 'expired',
}, {
'url': 'https://abema.tv/now-on-air/abema-anime',
'info_dict': {
'id': 'abema-anime',
# this varies
# 'title': '女子高生の無駄づかい 全話一挙【無料ビデオ72時間】',
'description': 'md5:55f2e61f46a17e9230802d7bcc913d5f',
'is_live': True,
},
'skip': 'Not supported until yt-dlp implements native live downloader OR AbemaTV can start a local HTTP server',
}]
_TIMETABLE = None
def _perform_login(self, username, password):
self._get_device_token()
if self.cache.load(self._NETRC_MACHINE, username) and self._get_media_token():
self.write_debug('Skipping logging in')
return
if '@' in username: # don't strictly check if it's email address or not
ep, method = 'user/email', 'email'
else:
ep, method = 'oneTimePassword', 'userId'
login_response = self._download_json(
f'https://api.abema.io/v1/auth/{ep}', None, note='Logging in',
data=json.dumps({
method: username,
'password': password
}).encode('utf-8'), headers={
'Authorization': f'bearer {self._get_device_token()}',
'Origin': 'https://abema.tv',
'Referer': 'https://abema.tv/',
'Content-Type': 'application/json',
})
AbemaTVBaseIE._USERTOKEN = login_response['token']
self._get_media_token(True)
self.cache.store(self._NETRC_MACHINE, username, AbemaTVBaseIE._USERTOKEN)
def _real_extract(self, url):
# starting download using infojson from this extractor is undefined behavior,
# and never be fixed in the future; you must trigger downloads by directly specifying URL.
# (unless there's a way to hook before downloading by extractor)
video_id, video_type = self._match_valid_url(url).group('id', 'type')
headers = {
'Authorization': 'Bearer ' + self._get_device_token(),
}
video_type = video_type.split('/')[-1]
webpage = self._download_webpage(url, video_id)
canonical_url = self._search_regex(
r'<link\s+rel="canonical"\s*href="(.+?)"', webpage, 'canonical URL',
default=url)
info = self._search_json_ld(webpage, video_id, default={})
title = self._search_regex(
r'<span\s*class=".+?EpisodeTitleBlock__title">(.+?)</span>', webpage, 'title', default=None)
if not title:
jsonld = None
for jld in re.finditer(
r'(?is)<span\s*class="com-m-Thumbnail__image">(?:</span>)?<script[^>]+type=(["\']?)application/ld\+json\1[^>]*>(?P<json_ld>.+?)</script>',
webpage):
jsonld = self._parse_json(jld.group('json_ld'), video_id, fatal=False)
if jsonld:
break
if jsonld:
title = jsonld.get('caption')
if not title and video_type == 'now-on-air':
if not self._TIMETABLE:
# cache the timetable because it goes to 5MiB in size (!!)
self._TIMETABLE = self._download_json(
'https://api.abema.io/v1/timetable/dataSet?debug=false', video_id,
headers=headers)
now = time_seconds(hours=9)
for slot in self._TIMETABLE.get('slots', []):
if slot.get('channelId') != video_id:
continue
if slot['startAt'] <= now and now < slot['endAt']:
title = slot['title']
break
# read breadcrumb on top of page
breadcrumb = self._extract_breadcrumb_list(webpage, video_id)
if breadcrumb:
# breadcrumb list translates to: (e.g. 1st test for this IE)
# Home > Anime (genre) > Isekai Shokudo 2 (series name) > Episode 1 "Cheese cakes" "Morning again" (episode title)
# hence this works
info['series'] = breadcrumb[-2]
info['episode'] = breadcrumb[-1]
if not title:
title = info['episode']
description = self._html_search_regex(
(r'<p\s+class="com-video-EpisodeDetailsBlock__content"><span\s+class=".+?">(.+?)</span></p><div',
r'<span\s+class=".+?SlotSummary.+?">(.+?)</span></div><div',),
webpage, 'description', default=None, group=1)
if not description:
og_desc = self._html_search_meta(
('description', 'og:description', 'twitter:description'), webpage)
if og_desc:
description = re.sub(r'''(?sx)
^(.+?)(?:
アニメの動画を無料で見るならABEMA！| # anime
等、.+ # applies for most of categories
)?
''', r'\1', og_desc)
# canonical URL may contain series and episode number
mobj = re.search(r's(\d+)_p(\d+)$', canonical_url)
if mobj:
seri = int_or_none(mobj.group(1), default=float('inf'))
epis = int_or_none(mobj.group(2), default=float('inf'))
info['series_number'] = seri if seri < 100 else None
# some anime like Detective Conan (though not available in AbemaTV)
# has more than 1000 episodes (1026 as of 2021/11/15)
info['episode_number'] = epis if epis < 2000 else None
is_live, m3u8_url = False, None
if video_type == 'now-on-air':
is_live = True
channel_url = 'https://api.abema.io/v1/channels'
if video_id == 'news-global':
channel_url = update_url_query(channel_url, {'division': '1'})
onair_channels = self._download_json(channel_url, video_id)
for ch in onair_channels['channels']:
if video_id == ch['id']:
m3u8_url = ch['playback']['hls']
break
else:
raise ExtractorError(f'Cannot find on-air {video_id} channel.', expected=True)
elif video_type == 'episode':
api_response = self._download_json(
f'https://api.abema.io/v1/video/programs/{video_id}', video_id,
note='Checking playability',
headers=headers)
ondemand_types = traverse_obj(api_response, ('terms', ..., 'onDemandType'))
if 3 not in ondemand_types:
# cannot acquire decryption key for these streams
self.report_warning('This is a premium-only stream')
m3u8_url = f'https://vod-abematv.akamaized.net/program/{video_id}/playlist.m3u8'
elif video_type == 'slots':
api_response = self._download_json(
f'https://api.abema.io/v1/media/slots/{video_id}', video_id,
note='Checking playability',
headers=headers)
if not traverse_obj(api_response, ('slot', 'flags', 'timeshiftFree'), default=False):
self.report_warning('This is a premium-only stream')
m3u8_url = f'https://vod-abematv.akamaized.net/slot/{video_id}/playlist.m3u8'
else:
raise ExtractorError('Unreachable')
if is_live:
self.report_warning("This is a livestream; yt-dlp doesn't support downloading natively, but FFmpeg cannot handle m3u8 manifests from AbemaTV")
self.report_warning('Please consider using Streamlink to download these streams (https://github.com/streamlink/streamlink)')
formats = self._extract_m3u8_formats(
m3u8_url, video_id, ext='mp4', live=is_live)
info.update({
'id': video_id,
'title': title,
'description': description,
'formats': formats,
'is_live': is_live,
})
return info
class AbemaTVTitleIE(AbemaTVBaseIE):
_VALID_URL = r'https?://abema\.tv/video/title/(?P<id>[^?/]+)'
_PAGE_SIZE = 25
_TESTS = [{
'url': 'https://abema.tv/video/title/90-1597',
'info_dict': {
'id': '90-1597',
'title': 'シャッフルアイランド',
},
'playlist_mincount': 2,
}, {
'url': 'https://abema.tv/video/title/193-132',
'info_dict': {
'id': '193-132',
'title': '真心が届く~僕とスターのオフィス・ラブ!?~',
},
'playlist_mincount': 16,
}, {
'url': 'https://abema.tv/video/title/25-102',
'info_dict': {
'id': '25-102',
'title': 'ソードアート・オンライン アリシゼーション',
},
'playlist_mincount': 24,
}]
def _fetch_page(self, playlist_id, series_version, page):
programs = self._call_api(
f'v1/video/series/{playlist_id}/programs', playlist_id,
note=f'Downloading page {page + 1}',
query={
'seriesVersion': series_version,
'offset': str(page * self._PAGE_SIZE),
'order': 'seq',
'limit': str(self._PAGE_SIZE),
})
yield from (
self.url_result(f'https://abema.tv/video/episode/{x}')
for x in traverse_obj(programs, ('programs', ..., 'id')))
def _entries(self, playlist_id, series_version):
return OnDemandPagedList(
functools.partial(self._fetch_page, playlist_id, series_version),
self._PAGE_SIZE)
def _real_extract(self, url):
playlist_id = self._match_id(url)
series_info = self._call_api(f'v1/video/series/{playlist_id}', playlist_id)
return self.playlist_result(
self._entries(playlist_id, series_info['version']), playlist_id=playlist_id,
playlist_title=series_info.get('title'),
playlist_description=series_info.get('content'))
yt_dlp/extractor/academicearth.py
+39
View File
@@ -0,0 +1,39 @@
import re
from .common import InfoExtractor
class AcademicEarthCourseIE(InfoExtractor):
_VALID_URL = r'^https?://(?:www\.)?academicearth\.org/playlists/(?P<id>[^?#/]+)'
IE_NAME = 'AcademicEarth:Course'
_TEST = {
'url': 'http://academicearth.org/playlists/laws-of-nature/',
'info_dict': {
'id': 'laws-of-nature',
'title': 'Laws of Nature',
'description': 'Introduce yourself to the laws of nature with these free online college lectures from Yale, Harvard, and MIT.',
},
'playlist_count': 3,
}
def _real_extract(self, url):
playlist_id = self._match_id(url)
webpage = self._download_webpage(url, playlist_id)
title = self._html_search_regex(
r'<h1 class="playlist-name"[^>]*?>(.*?)</h1>', webpage, 'title')
description = self._html_search_regex(
r'<p class="excerpt"[^>]*?>(.*?)</p>',
webpage, 'description', fatal=False)
urls = re.findall(
r'<li class="lecture-preview">\s*?<a target="_blank" href="([^"]+)">',
webpage)
entries = [self.url_result(u) for u in urls]
return {
'_type': 'playlist',
'id': playlist_id,
'title': title,
'description': description,
'entries': entries,
}
yt_dlp/extractor/acast.py
+121
View File
@@ -0,0 +1,121 @@
from .common import InfoExtractor
from ..utils import (
clean_html,
clean_podcast_url,
int_or_none,
parse_iso8601,
)
class ACastBaseIE(InfoExtractor):
def _extract_episode(self, episode, show_info):
title = episode['title']
info = {
'id': episode['id'],
'display_id': episode.get('episodeUrl'),
'url': clean_podcast_url(episode['url']),
'title': title,
'description': clean_html(episode.get('description') or episode.get('summary')),
'thumbnail': episode.get('image'),
'timestamp': parse_iso8601(episode.get('publishDate')),
'duration': int_or_none(episode.get('duration')),
'filesize': int_or_none(episode.get('contentLength')),
'season_number': int_or_none(episode.get('season')),
'episode': title,
'episode_number': int_or_none(episode.get('episode')),
}
info.update(show_info)
return info
def _extract_show_info(self, show):
return {
'creator': show.get('author'),
'series': show.get('title'),
}
def _call_api(self, path, video_id, query=None):
return self._download_json(
'https://feeder.acast.com/api/v1/shows/' + path, video_id, query=query)
class ACastIE(ACastBaseIE):
IE_NAME = 'acast'
_VALID_URL = r'''(?x)
https?://
(?:
(?:(?:embed|www)\.)?acast\.com/|
play\.acast\.com/s/
)
(?P<channel>[^/]+)/(?P<id>[^/#?]+)
'''
_TESTS = [{
'url': 'https://www.acast.com/sparpodcast/2.raggarmordet-rosterurdetforflutna',
'md5': 'f5598f3ad1e4776fed12ec1407153e4b',
'info_dict': {
'id': '2a92b283-1a75-4ad8-8396-499c641de0d9',
'ext': 'mp3',
'title': '2. Raggarmordet - Röster ur det förflutna',
'description': 'md5:a992ae67f4d98f1c0141598f7bebbf67',
'timestamp': 1477346700,
'upload_date': '20161024',
'duration': 2766,
'creator': 'Anton Berg & Martin Johnson',
'series': 'Spår',
'episode': '2. Raggarmordet - Röster ur det förflutna',
}
}, {
'url': 'http://embed.acast.com/adambuxton/ep.12-adam-joeschristmaspodcast2015',
'only_matching': True,
}, {
'url': 'https://play.acast.com/s/rattegangspodden/s04e09styckmordetihelenelund-del2-2',
'only_matching': True,
}, {
'url': 'https://play.acast.com/s/sparpodcast/2a92b283-1a75-4ad8-8396-499c641de0d9',
'only_matching': True,
}]
def _real_extract(self, url):
channel, display_id = self._match_valid_url(url).groups()
episode = self._call_api(
'%s/episodes/%s' % (channel, display_id),
display_id, {'showInfo': 'true'})
return self._extract_episode(
episode, self._extract_show_info(episode.get('show') or {}))
class ACastChannelIE(ACastBaseIE):
IE_NAME = 'acast:channel'
_VALID_URL = r'''(?x)
https?://
(?:
(?:www\.)?acast\.com/|
play\.acast\.com/s/
)
(?P<id>[^/#?]+)
'''
_TESTS = [{
'url': 'https://www.acast.com/todayinfocus',
'info_dict': {
'id': '4efc5294-5385-4847-98bd-519799ce5786',
'title': 'Today in Focus',
'description': 'md5:c09ce28c91002ce4ffce71d6504abaae',
},
'playlist_mincount': 200,
}, {
'url': 'http://play.acast.com/s/ft-banking-weekly',
'only_matching': True,
}]
@classmethod
def suitable(cls, url):
return False if ACastIE.suitable(url) else super(ACastChannelIE, cls).suitable(url)
def _real_extract(self, url):
show_slug = self._match_id(url)
show = self._call_api(show_slug, show_slug)
show_info = self._extract_show_info(show)
entries = []
for episode in (show.get('episodes') or []):
entries.append(self._extract_episode(episode, show_info))
return self.playlist_result(
entries, show.get('id'), show.get('title'), show.get('description'))
yt_dlp/extractor/acfun.py
+199
View File
@@ -0,0 +1,199 @@
from .common import InfoExtractor
from ..utils import (
float_or_none,
format_field,
int_or_none,
traverse_obj,
parse_codecs,
parse_qs,
)
class AcFunVideoBaseIE(InfoExtractor):
def _extract_metadata(self, video_id, video_info):
playjson = self._parse_json(video_info['ksPlayJson'], video_id)
formats, subtitles = [], {}
for video in traverse_obj(playjson, ('adaptationSet', 0, 'representation')):
fmts, subs = self._extract_m3u8_formats_and_subtitles(video['url'], video_id, 'mp4', fatal=False)
formats.extend(fmts)
self._merge_subtitles(subs, target=subtitles)
for f in fmts:
f.update({
'fps': float_or_none(video.get('frameRate')),
'width': int_or_none(video.get('width')),
'height': int_or_none(video.get('height')),
'tbr': float_or_none(video.get('avgBitrate')),
**parse_codecs(video.get('codecs', ''))
})
return {
'id': video_id,
'formats': formats,
'subtitles': subtitles,
'duration': float_or_none(video_info.get('durationMillis'), 1000),
'timestamp': int_or_none(video_info.get('uploadTime'), 1000),
'http_headers': {'Referer': 'https://www.acfun.cn/'},
}
class AcFunVideoIE(AcFunVideoBaseIE):
_VALID_URL = r'https?://www\.acfun\.cn/v/ac(?P<id>[_\d]+)'
_TESTS = [{
'url': 'https://www.acfun.cn/v/ac35457073',
'info_dict': {
'id': '35457073',
'ext': 'mp4',
'duration': 174.208,
'timestamp': 1656403967,
'title': '1 8 岁 现 状',
'description': '“赶紧回去！班主任查班了！”',
'uploader': '锤子game',
'uploader_id': '51246077',
'thumbnail': r're:^https?://.*\.(jpg|jpeg)',
'upload_date': '20220628',
'like_count': int,
'view_count': int,
'comment_count': int,
'tags': list,
},
}, {
# example for len(video_list) > 1
'url': 'https://www.acfun.cn/v/ac35468952_2',
'info_dict': {
'id': '35468952_2',
'ext': 'mp4',
'title': '【动画剧集】Rocket & Groot Season 1（2022）/火箭浣熊与格鲁特第1季 P02 S01E02 十拿九穩',
'duration': 90.459,
'uploader': '比令',
'uploader_id': '37259967',
'upload_date': '20220629',
'timestamp': 1656479962,
'tags': list,
'like_count': int,
'view_count': int,
'comment_count': int,
'thumbnail': r're:^https?://.*\.(jpg|jpeg)',
'description': 'md5:67583aaf3a0f933bd606bc8a2d3ebb17',
}
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
json_all = self._search_json(r'window.videoInfo\s*=', webpage, 'videoInfo', video_id)
title = json_all.get('title')
video_list = json_all.get('videoList') or []
video_internal_id = traverse_obj(json_all, ('currentVideoInfo', 'id'))
if video_internal_id and len(video_list) > 1:
part_idx, part_video_info = next(
(idx + 1, v) for (idx, v) in enumerate(video_list)
if v['id'] == video_internal_id)
title = f'{title} P{part_idx:02d} {part_video_info["title"]}'
return {
**self._extract_metadata(video_id, json_all['currentVideoInfo']),
'title': title,
'thumbnail': json_all.get('coverUrl'),
'description': json_all.get('description'),
'uploader': traverse_obj(json_all, ('user', 'name')),
'uploader_id': traverse_obj(json_all, ('user', 'href')),
'tags': traverse_obj(json_all, ('tagList', ..., 'name')),
'view_count': int_or_none(json_all.get('viewCount')),
'like_count': int_or_none(json_all.get('likeCountShow')),
'comment_count': int_or_none(json_all.get('commentCountShow')),
}
class AcFunBangumiIE(AcFunVideoBaseIE):
_VALID_URL = r'https?://www\.acfun\.cn/bangumi/(?P<id>aa[_\d]+)'
_TESTS = [{
'url': 'https://www.acfun.cn/bangumi/aa6002917_36188_1745457?ac=2',
'info_dict': {
'id': 'aa6002917_36188_1745457__2',
'ext': 'mp4',
'title': '【7月】租借女友 水原千鹤角色曲『DATE』特别PV',
'upload_date': '20200916',
'timestamp': 1600243813,
'duration': 92.091,
},
}, {
'url': 'https://www.acfun.cn/bangumi/aa5023171_36188_1750645',
'info_dict': {
'id': 'aa5023171_36188_1750645',
'ext': 'mp4',
'title': '红孩儿之趴趴蛙寻石记 第5话 ',
'duration': 760.0,
'season': '红孩儿之趴趴蛙寻石记',
'season_id': 5023171,
'season_number': 1, # series has only 1 season
'episode': 'Episode 5',
'episode_number': 5,
'upload_date': '20181223',
'timestamp': 1545552185,
'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)',
'comment_count': int,
},
}, {
'url': 'https://www.acfun.cn/bangumi/aa6065485_36188_1885061',
'info_dict': {
'id': 'aa6065485_36188_1885061',
'ext': 'mp4',
'title': '叽歪老表（第二季） 第5话 坚不可摧',
'season': '叽歪老表（第二季）',
'season_number': 2,
'season_id': 6065485,
'episode': '坚不可摧',
'episode_number': 5,
'upload_date': '20220324',
'timestamp': 1648082786,
'duration': 105.002,
'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)',
'comment_count': int,
},
}]
def _real_extract(self, url):
video_id = self._match_id(url)
ac_idx = parse_qs(url).get('ac', [None])[-1]
video_id = f'{video_id}{format_field(ac_idx, None, "__%s")}'
webpage = self._download_webpage(url, video_id)
json_bangumi_data = self._search_json(r'window.bangumiData\s*=', webpage, 'bangumiData', video_id)
if ac_idx:
video_info = json_bangumi_data['hlVideoInfo']
return {
**self._extract_metadata(video_id, video_info),
'title': video_info.get('title'),
}
video_info = json_bangumi_data['currentVideoInfo']
season_id = json_bangumi_data.get('bangumiId')
season_number = season_id and next((
idx for idx, v in enumerate(json_bangumi_data.get('relatedBangumis') or [], 1)
if v.get('id') == season_id), 1)
json_bangumi_list = self._search_json(
r'window\.bangumiList\s*=', webpage, 'bangumiList', video_id, fatal=False)
video_internal_id = int_or_none(traverse_obj(json_bangumi_data, ('currentVideoInfo', 'id')))
episode_number = video_internal_id and next((
idx for idx, v in enumerate(json_bangumi_list.get('items') or [], 1)
if v.get('videoId') == video_internal_id), None)
return {
**self._extract_metadata(video_id, video_info),
'title': json_bangumi_data.get('showTitle'),
'thumbnail': json_bangumi_data.get('image'),
'season': json_bangumi_data.get('bangumiTitle'),
'season_id': season_id,
'season_number': season_number,
'episode': json_bangumi_data.get('title'),
'episode_number': episode_number,
'comment_count': int_or_none(json_bangumi_data.get('commentCount')),
}
yt_dlp/extractor/adn.py
+259
View File
@@ -0,0 +1,259 @@
import base64
import binascii
import json
import os
import random
from .common import InfoExtractor
from ..aes import aes_cbc_decrypt_bytes, unpad_pkcs7
from ..compat import (
compat_HTTPError,
compat_b64decode,
)
from ..utils import (
ass_subtitles_timecode,
bytes_to_intlist,
bytes_to_long,
ExtractorError,
float_or_none,
int_or_none,
intlist_to_bytes,
long_to_bytes,
pkcs1pad,
strip_or_none,
try_get,
unified_strdate,
urlencode_postdata,
)
class ADNIE(InfoExtractor):
IE_DESC = 'Animation Digital Network'
_VALID_URL = r'https?://(?:www\.)?(?:animation|anime)digitalnetwork\.fr/video/[^/]+/(?P<id>\d+)'
_TESTS = [{
'url': 'https://animationdigitalnetwork.fr/video/fruits-basket/9841-episode-1-a-ce-soir',
'md5': '1c9ef066ceb302c86f80c2b371615261',
'info_dict': {
'id': '9841',
'ext': 'mp4',
'title': 'Fruits Basket - Episode 1',
'description': 'md5:14be2f72c3c96809b0ca424b0097d336',
'series': 'Fruits Basket',
'duration': 1437,
'release_date': '20190405',
'comment_count': int,
'average_rating': float,
'season_number': 1,
'episode': 'À ce soir !',
'episode_number': 1,
},
'skip': 'Only available in region (FR, ...)',
}, {
'url': 'http://animedigitalnetwork.fr/video/blue-exorcist-kyoto-saga/7778-episode-1-debut-des-hostilites',
'only_matching': True,
}]
_NETRC_MACHINE = 'animationdigitalnetwork'
_BASE = 'animationdigitalnetwork.fr'
_API_BASE_URL = 'https://gw.api.' + _BASE + '/'
_PLAYER_BASE_URL = _API_BASE_URL + 'player/'
_HEADERS = {}
_LOGIN_ERR_MESSAGE = 'Unable to log in'
_RSA_KEY = (0x9B42B08905199A5CCE2026274399CA560ECB209EE9878A708B1C0812E1BB8CB5D1FB7441861147C1A1F2F3A0476DD63A9CAC20D3E983613346850AA6CB38F16DC7D720FD7D86FC6E5B3D5BBC72E14CD0BF9E869F2CEA2CCAD648F1DCE38F1FF916CEFB2D339B64AA0264372344BC775E265E8A852F88144AB0BD9AA06C1A4ABB, 65537)
_POS_ALIGN_MAP = {
'start': 1,
'end': 3,
}
_LINE_ALIGN_MAP = {
'middle': 8,
'end': 4,
}
def _get_subtitles(self, sub_url, video_id):
if not sub_url:
return None
enc_subtitles = self._download_webpage(
sub_url, video_id, 'Downloading subtitles location', fatal=False) or '{}'
subtitle_location = (self._parse_json(enc_subtitles, video_id, fatal=False) or {}).get('location')
if subtitle_location:
enc_subtitles = self._download_webpage(
subtitle_location, video_id, 'Downloading subtitles data',
fatal=False, headers={'Origin': 'https://' + self._BASE})
if not enc_subtitles:
return None
# http://animationdigitalnetwork.fr/components/com_vodvideo/videojs/adn-vjs.min.js
dec_subtitles = unpad_pkcs7(aes_cbc_decrypt_bytes(
compat_b64decode(enc_subtitles[24:]),
binascii.unhexlify(self._K + '7fac1178830cfe0c'),
compat_b64decode(enc_subtitles[:24])))
subtitles_json = self._parse_json(dec_subtitles.decode(), None, fatal=False)
if not subtitles_json:
return None
subtitles = {}
for sub_lang, sub in subtitles_json.items():
ssa = '''[Script Info]
ScriptType:V4.00
[V4 Styles]
Format: Name,Fontname,Fontsize,PrimaryColour,SecondaryColour,TertiaryColour,BackColour,Bold,Italic,BorderStyle,Outline,Shadow,Alignment,MarginL,MarginR,MarginV,AlphaLevel,Encoding
Style: Default,Arial,18,16777215,16777215,16777215,0,-1,0,1,1,0,2,20,20,20,0,0
[Events]
Format: Marked,Start,End,Style,Name,MarginL,MarginR,MarginV,Effect,Text'''
for current in sub:
start, end, text, line_align, position_align = (
float_or_none(current.get('startTime')),
float_or_none(current.get('endTime')),
current.get('text'), current.get('lineAlign'),
current.get('positionAlign'))
if start is None or end is None or text is None:
continue
alignment = self._POS_ALIGN_MAP.get(position_align, 2) + self._LINE_ALIGN_MAP.get(line_align, 0)
ssa += os.linesep + 'Dialogue: Marked=0,%s,%s,Default,,0,0,0,,%s%s' % (
ass_subtitles_timecode(start),
ass_subtitles_timecode(end),
'{\\a%d}' % alignment if alignment != 2 else '',
text.replace('\n', '\\N').replace('<i>', '{\\i1}').replace('</i>', '{\\i0}'))
if sub_lang == 'vostf':
sub_lang = 'fr'
subtitles.setdefault(sub_lang, []).extend([{
'ext': 'json',
'data': json.dumps(sub),
}, {
'ext': 'ssa',
'data': ssa,
}])
return subtitles
def _perform_login(self, username, password):
try:
access_token = (self._download_json(
self._API_BASE_URL + 'authentication/login', None,
'Logging in', self._LOGIN_ERR_MESSAGE, fatal=False,
data=urlencode_postdata({
'password': password,
'rememberMe': False,
'source': 'Web',
'username': username,
})) or {}).get('accessToken')
if access_token:
self._HEADERS = {'authorization': 'Bearer ' + access_token}
except ExtractorError as e:
message = None
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401:
resp = self._parse_json(
e.cause.read().decode(), None, fatal=False) or {}
message = resp.get('message') or resp.get('code')
self.report_warning(message or self._LOGIN_ERR_MESSAGE)
def _real_extract(self, url):
video_id = self._match_id(url)
video_base_url = self._PLAYER_BASE_URL + 'video/%s/' % video_id
player = self._download_json(
video_base_url + 'configuration', video_id,
'Downloading player config JSON metadata',
headers=self._HEADERS)['player']
options = player['options']
user = options['user']
if not user.get('hasAccess'):
self.raise_login_required()
token = self._download_json(
user.get('refreshTokenUrl') or (self._PLAYER_BASE_URL + 'refresh/token'),
video_id, 'Downloading access token', headers={
'x-player-refresh-token': user['refreshToken']
}, data=b'')['token']
links_url = try_get(options, lambda x: x['video']['url']) or (video_base_url + 'link')
self._K = ''.join(random.choices('0123456789abcdef', k=16))
message = bytes_to_intlist(json.dumps({
'k': self._K,
't': token,
}))
# Sometimes authentication fails for no good reason, retry with
# a different random padding
links_data = None
for _ in range(3):
padded_message = intlist_to_bytes(pkcs1pad(message, 128))
n, e = self._RSA_KEY
encrypted_message = long_to_bytes(pow(bytes_to_long(padded_message), e, n))
authorization = base64.b64encode(encrypted_message).decode()
try:
links_data = self._download_json(
links_url, video_id, 'Downloading links JSON metadata', headers={
'X-Player-Token': authorization
}, query={
'freeWithAds': 'true',
'adaptive': 'false',
'withMetadata': 'true',
'source': 'Web'
})
break
except ExtractorError as e:
if not isinstance(e.cause, compat_HTTPError):
raise e
if e.cause.code == 401:
# This usually goes away with a different random pkcs1pad, so retry
continue
error = self._parse_json(e.cause.read(), video_id)
message = error.get('message')
if e.cause.code == 403 and error.get('code') == 'player-bad-geolocation-country':
self.raise_geo_restricted(msg=message)
raise ExtractorError(message)
else:
raise ExtractorError('Giving up retrying')
links = links_data.get('links') or {}
metas = links_data.get('metadata') or {}
sub_url = (links.get('subtitles') or {}).get('all')
video_info = links_data.get('video') or {}
title = metas['title']
formats = []
for format_id, qualities in (links.get('streaming') or {}).items():
if not isinstance(qualities, dict):
continue
for quality, load_balancer_url in qualities.items():
load_balancer_data = self._download_json(
load_balancer_url, video_id,
'Downloading %s %s JSON metadata' % (format_id, quality),
fatal=False) or {}
m3u8_url = load_balancer_data.get('location')
if not m3u8_url:
continue
m3u8_formats = self._extract_m3u8_formats(
m3u8_url, video_id, 'mp4', 'm3u8_native',
m3u8_id=format_id, fatal=False)
if format_id == 'vf':
for f in m3u8_formats:
f['language'] = 'fr'
formats.extend(m3u8_formats)
video = (self._download_json(
self._API_BASE_URL + 'video/%s' % video_id, video_id,
'Downloading additional video metadata', fatal=False) or {}).get('video') or {}
show = video.get('show') or {}
return {
'id': video_id,
'title': title,
'description': strip_or_none(metas.get('summary') or video.get('summary')),
'thumbnail': video_info.get('image') or player.get('image'),
'formats': formats,
'subtitles': self.extract_subtitles(sub_url, video_id),
'episode': metas.get('subtitle') or video.get('name'),
'episode_number': int_or_none(video.get('shortNumber')),
'series': show.get('title'),
'season_number': int_or_none(video.get('season')),
'duration': int_or_none(video_info.get('duration') or video.get('duration')),
'release_date': unified_strdate(video.get('releaseDate')),
'average_rating': float_or_none(video.get('rating') or metas.get('rating')),
'comment_count': int_or_none(video.get('commentsCount')),
}
yt_dlp/extractor/adobeconnect.py
+34
View File
@@ -0,0 +1,34 @@
from .common import InfoExtractor
from ..compat import (
compat_parse_qs,
compat_urlparse,
)
class AdobeConnectIE(InfoExtractor):
_VALID_URL = r'https?://\w+\.adobeconnect\.com/(?P<id>[\w-]+)'
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
title = self._html_extract_title(webpage)
qs = compat_parse_qs(self._search_regex(r"swfUrl\s*=\s*'([^']+)'", webpage, 'swf url').split('?')[1])
is_live = qs.get('isLive', ['false'])[0] == 'true'
formats = []
for con_string in qs['conStrings'][0].split(','):
formats.append({
'format_id': con_string.split('://')[0],
'app': compat_urlparse.quote('?' + con_string.split('?')[1] + 'flvplayerapp/' + qs['appInstance'][0]),
'ext': 'flv',
'play_path': 'mp4:' + qs['streamName'][0],
'rtmp_conn': 'S:' + qs['ticket'][0],
'rtmp_live': is_live,
'url': con_string,
})
return {
'id': video_id,
'title': title,
'formats': formats,
'is_live': is_live,
}
yt_dlp/extractor/adobepass.py
+1778
View File
File diff suppressed because it is too large Load Diff
yt_dlp/extractor/adobetv.py
+286
View File
@@ -0,0 +1,286 @@
import functools
import re
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
float_or_none,
int_or_none,
ISO639Utils,
join_nonempty,
OnDemandPagedList,
parse_duration,
str_or_none,
str_to_int,
unified_strdate,
)
class AdobeTVBaseIE(InfoExtractor):
def _call_api(self, path, video_id, query, note=None):
return self._download_json(
'http://tv.adobe.com/api/v4/' + path,
video_id, note, query=query)['data']
def _parse_subtitles(self, video_data, url_key):
subtitles = {}
for translation in video_data.get('translations', []):
vtt_path = translation.get(url_key)
if not vtt_path:
continue
lang = translation.get('language_w3c') or ISO639Utils.long2short(translation['language_medium'])
subtitles.setdefault(lang, []).append({
'ext': 'vtt',
'url': vtt_path,
})
return subtitles
def _parse_video_data(self, video_data):
video_id = compat_str(video_data['id'])
title = video_data['title']
s3_extracted = False
formats = []
for source in video_data.get('videos', []):
source_url = source.get('url')
if not source_url:
continue
f = {
'format_id': source.get('quality_level'),
'fps': int_or_none(source.get('frame_rate')),
'height': int_or_none(source.get('height')),
'tbr': int_or_none(source.get('video_data_rate')),
'width': int_or_none(source.get('width')),
'url': source_url,
}
original_filename = source.get('original_filename')
if original_filename:
if not (f.get('height') and f.get('width')):
mobj = re.search(r'_(\d+)x(\d+)', original_filename)
if mobj:
f.update({
'height': int(mobj.group(2)),
'width': int(mobj.group(1)),
})
if original_filename.startswith('s3://') and not s3_extracted:
formats.append({
'format_id': 'original',
'quality': 1,
'url': original_filename.replace('s3://', 'https://s3.amazonaws.com/'),
})
s3_extracted = True
formats.append(f)
return {
'id': video_id,
'title': title,
'description': video_data.get('description'),
'thumbnail': video_data.get('thumbnail'),
'upload_date': unified_strdate(video_data.get('start_date')),
'duration': parse_duration(video_data.get('duration')),
'view_count': str_to_int(video_data.get('playcount')),
'formats': formats,
'subtitles': self._parse_subtitles(video_data, 'vtt'),
}
class AdobeTVEmbedIE(AdobeTVBaseIE):
IE_NAME = 'adobetv:embed'
_VALID_URL = r'https?://tv\.adobe\.com/embed/\d+/(?P<id>\d+)'
_TEST = {
'url': 'https://tv.adobe.com/embed/22/4153',
'md5': 'c8c0461bf04d54574fc2b4d07ac6783a',
'info_dict': {
'id': '4153',
'ext': 'flv',
'title': 'Creating Graphics Optimized for BlackBerry',
'description': 'md5:eac6e8dced38bdaae51cd94447927459',
'thumbnail': r're:https?://.*\.jpg$',
'upload_date': '20091109',
'duration': 377,
'view_count': int,
},
}
def _real_extract(self, url):
video_id = self._match_id(url)
video_data = self._call_api(
'episode/' + video_id, video_id, {'disclosure': 'standard'})[0]
return self._parse_video_data(video_data)
class AdobeTVIE(AdobeTVBaseIE):
IE_NAME = 'adobetv'
_VALID_URL = r'https?://tv\.adobe\.com/(?:(?P<language>fr|de|es|jp)/)?watch/(?P<show_urlname>[^/]+)/(?P<id>[^/]+)'
_TEST = {
'url': 'http://tv.adobe.com/watch/the-complete-picture-with-julieanne-kost/quick-tip-how-to-draw-a-circle-around-an-object-in-photoshop/',
'md5': '9bc5727bcdd55251f35ad311ca74fa1e',
'info_dict': {
'id': '10981',
'ext': 'mp4',
'title': 'Quick Tip - How to Draw a Circle Around an Object in Photoshop',
'description': 'md5:99ec318dc909d7ba2a1f2b038f7d2311',
'thumbnail': r're:https?://.*\.jpg$',
'upload_date': '20110914',
'duration': 60,
'view_count': int,
},
}
def _real_extract(self, url):
language, show_urlname, urlname = self._match_valid_url(url).groups()
if not language:
language = 'en'
video_data = self._call_api(
'episode/get', urlname, {
'disclosure': 'standard',
'language': language,
'show_urlname': show_urlname,
'urlname': urlname,
})[0]
return self._parse_video_data(video_data)
class AdobeTVPlaylistBaseIE(AdobeTVBaseIE):
_PAGE_SIZE = 25
def _fetch_page(self, display_id, query, page):
page += 1
query['page'] = page
for element_data in self._call_api(
self._RESOURCE, display_id, query, 'Download Page %d' % page):
yield self._process_data(element_data)
def _extract_playlist_entries(self, display_id, query):
return OnDemandPagedList(functools.partial(
self._fetch_page, display_id, query), self._PAGE_SIZE)
class AdobeTVShowIE(AdobeTVPlaylistBaseIE):
IE_NAME = 'adobetv:show'
_VALID_URL = r'https?://tv\.adobe\.com/(?:(?P<language>fr|de|es|jp)/)?show/(?P<id>[^/]+)'
_TEST = {
'url': 'http://tv.adobe.com/show/the-complete-picture-with-julieanne-kost',
'info_dict': {
'id': '36',
'title': 'The Complete Picture with Julieanne Kost',
'description': 'md5:fa50867102dcd1aa0ddf2ab039311b27',
},
'playlist_mincount': 136,
}
_RESOURCE = 'episode'
_process_data = AdobeTVBaseIE._parse_video_data
def _real_extract(self, url):
language, show_urlname = self._match_valid_url(url).groups()
if not language:
language = 'en'
query = {
'disclosure': 'standard',
'language': language,
'show_urlname': show_urlname,
}
show_data = self._call_api(
'show/get', show_urlname, query)[0]
return self.playlist_result(
self._extract_playlist_entries(show_urlname, query),
str_or_none(show_data.get('id')),
show_data.get('show_name'),
show_data.get('show_description'))
class AdobeTVChannelIE(AdobeTVPlaylistBaseIE):
IE_NAME = 'adobetv:channel'
_VALID_URL = r'https?://tv\.adobe\.com/(?:(?P<language>fr|de|es|jp)/)?channel/(?P<id>[^/]+)(?:/(?P<category_urlname>[^/]+))?'
_TEST = {
'url': 'http://tv.adobe.com/channel/development',
'info_dict': {
'id': 'development',
},
'playlist_mincount': 96,
}
_RESOURCE = 'show'
def _process_data(self, show_data):
return self.url_result(
show_data['url'], 'AdobeTVShow', str_or_none(show_data.get('id')))
def _real_extract(self, url):
language, channel_urlname, category_urlname = self._match_valid_url(url).groups()
if not language:
language = 'en'
query = {
'channel_urlname': channel_urlname,
'language': language,
}
if category_urlname:
query['category_urlname'] = category_urlname
return self.playlist_result(
self._extract_playlist_entries(channel_urlname, query),
channel_urlname)
class AdobeTVVideoIE(AdobeTVBaseIE):
IE_NAME = 'adobetv:video'
_VALID_URL = r'https?://video\.tv\.adobe\.com/v/(?P<id>\d+)'
_EMBED_REGEX = [r'<iframe[^>]+src=[\'"](?P<url>(?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]']
_TEST = {
# From https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners
'url': 'https://video.tv.adobe.com/v/2456/',
'md5': '43662b577c018ad707a63766462b1e87',
'info_dict': {
'id': '2456',
'ext': 'mp4',
'title': 'New experience with Acrobat DC',
'description': 'New experience with Acrobat DC',
'duration': 248.667,
},
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
video_data = self._parse_json(self._search_regex(
r'var\s+bridge\s*=\s*([^;]+);', webpage, 'bridged data'), video_id)
title = video_data['title']
formats = []
sources = video_data.get('sources') or []
for source in sources:
source_src = source.get('src')
if not source_src:
continue
formats.append({
'filesize': int_or_none(source.get('kilobytes') or None, invscale=1000),
'format_id': join_nonempty(source.get('format'), source.get('label')),
'height': int_or_none(source.get('height') or None),
'tbr': int_or_none(source.get('bitrate') or None),
'width': int_or_none(source.get('width') or None),
'url': source_src,
})
# For both metadata and downloaded files the duration varies among
# formats. I just pick the max one
duration = max(filter(None, [
float_or_none(source.get('duration'), scale=1000)
for source in sources]))
return {
'id': video_id,
'formats': formats,
'title': title,
'description': video_data.get('description'),
'thumbnail': video_data.get('video', {}).get('poster'),
'duration': duration,
'subtitles': self._parse_subtitles(video_data, 'vttPath'),
}
yt_dlp/extractor/adultswim.py
+197
View File
@@ -0,0 +1,197 @@
import json
from .turner import TurnerBaseIE
from ..utils import (
determine_ext,
float_or_none,
int_or_none,
mimetype2ext,
parse_age_limit,
parse_iso8601,
strip_or_none,
try_get,
)
class AdultSwimIE(TurnerBaseIE):
_VALID_URL = r'https?://(?:www\.)?adultswim\.com/videos/(?P<show_path>[^/?#]+)(?:/(?P<episode_path>[^/?#]+))?'
_TESTS = [{
'url': 'http://adultswim.com/videos/rick-and-morty/pilot',
'info_dict': {
'id': 'rQxZvXQ4ROaSOqq-or2Mow',
'ext': 'mp4',
'title': 'Rick and Morty - Pilot',
'description': 'Rick moves in with his daughter\'s family and establishes himself as a bad influence on his grandson, Morty.',
'timestamp': 1543294800,
'upload_date': '20181127',
},
'params': {
# m3u8 download
'skip_download': True,
},
'expected_warnings': ['Unable to download f4m manifest'],
}, {
'url': 'http://www.adultswim.com/videos/tim-and-eric-awesome-show-great-job/dr-steve-brule-for-your-wine/',
'info_dict': {
'id': 'sY3cMUR_TbuE4YmdjzbIcQ',
'ext': 'mp4',
'title': 'Tim and Eric Awesome Show Great Job! - Dr. Steve Brule, For Your Wine',
'description': 'Dr. Brule reports live from Wine Country with a special report on wines. \nWatch Tim and Eric Awesome Show Great Job! episode #20, "Embarrassed" on Adult Swim.',
'upload_date': '20080124',
'timestamp': 1201150800,
},
'params': {
# m3u8 download
'skip_download': True,
},
'skip': '404 Not Found',
}, {
'url': 'http://www.adultswim.com/videos/decker/inside-decker-a-new-hero/',
'info_dict': {
'id': 'I0LQFQkaSUaFp8PnAWHhoQ',
'ext': 'mp4',
'title': 'Decker - Inside Decker: A New Hero',
'description': 'The guys recap the conclusion of the season. They announce a new hero, take a peek into the Victorville Film Archive and welcome back the talented James Dean.',
'timestamp': 1469480460,
'upload_date': '20160725',
},
'params': {
# m3u8 download
'skip_download': True,
},
'expected_warnings': ['Unable to download f4m manifest'],
}, {
'url': 'http://www.adultswim.com/videos/attack-on-titan',
'info_dict': {
'id': 'attack-on-titan',
'title': 'Attack on Titan',
'description': 'md5:41caa9416906d90711e31dc00cb7db7e',
},
'playlist_mincount': 12,
}, {
'url': 'http://www.adultswim.com/videos/streams/williams-stream',
'info_dict': {
'id': 'd8DEBj7QRfetLsRgFnGEyg',
'ext': 'mp4',
'title': r're:^Williams Stream \d{4}-\d{2}-\d{2} \d{2}:\d{2}$',
'description': 'original programming',
},
'params': {
# m3u8 download
'skip_download': True,
},
'skip': '404 Not Found',
}]
def _real_extract(self, url):
show_path, episode_path = self._match_valid_url(url).groups()
display_id = episode_path or show_path
query = '''query {
getShowBySlug(slug:"%s") {
%%s
}
}''' % show_path
if episode_path:
query = query % '''title
getVideoBySlug(slug:"%s") {
_id
auth
description
duration
episodeNumber
launchDate
mediaID
seasonNumber
poster
title
tvRating
}''' % episode_path
['getVideoBySlug']
else:
query = query % '''metaDescription
title
videos(first:1000,sort:["episode_number"]) {
edges {
node {
_id
slug
}
}
}'''
show_data = self._download_json(
'https://www.adultswim.com/api/search', display_id,
data=json.dumps({'query': query}).encode(),
headers={'Content-Type': 'application/json'})['data']['getShowBySlug']
if episode_path:
video_data = show_data['getVideoBySlug']
video_id = video_data['_id']
episode_title = title = video_data['title']
series = show_data.get('title')
if series:
title = '%s - %s' % (series, title)
info = {
'id': video_id,
'title': title,
'description': strip_or_none(video_data.get('description')),
'duration': float_or_none(video_data.get('duration')),
'formats': [],
'subtitles': {},
'age_limit': parse_age_limit(video_data.get('tvRating')),
'thumbnail': video_data.get('poster'),
'timestamp': parse_iso8601(video_data.get('launchDate')),
'series': series,
'season_number': int_or_none(video_data.get('seasonNumber')),
'episode': episode_title,
'episode_number': int_or_none(video_data.get('episodeNumber')),
}
auth = video_data.get('auth')
media_id = video_data.get('mediaID')
if media_id:
info.update(self._extract_ngtv_info(media_id, {
# CDN_TOKEN_APP_ID from:
# https://d2gg02c3xr550i.cloudfront.net/assets/asvp.e9c8bef24322d060ef87.bundle.js
'appId': 'eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJhcHBJZCI6ImFzLXR2ZS1kZXNrdG9wLXB0enQ2bSIsInByb2R1Y3QiOiJ0dmUiLCJuZXR3b3JrIjoiYXMiLCJwbGF0Zm9ybSI6ImRlc2t0b3AiLCJpYXQiOjE1MzI3MDIyNzl9.BzSCk-WYOZ2GMCIaeVb8zWnzhlgnXuJTCu0jGp_VaZE',
}, {
'url': url,
'site_name': 'AdultSwim',
'auth_required': auth,
}))
if not auth:
extract_data = self._download_json(
'https://www.adultswim.com/api/shows/v1/videos/' + video_id,
video_id, query={'fields': 'stream'}, fatal=False) or {}
assets = try_get(extract_data, lambda x: x['data']['video']['stream']['assets'], list) or []
for asset in assets:
asset_url = asset.get('url')
if not asset_url:
continue
ext = determine_ext(asset_url, mimetype2ext(asset.get('mime_type')))
if ext == 'm3u8':
info['formats'].extend(self._extract_m3u8_formats(
asset_url, video_id, 'mp4', m3u8_id='hls', fatal=False))
elif ext == 'f4m':
continue
# info['formats'].extend(self._extract_f4m_formats(
# asset_url, video_id, f4m_id='hds', fatal=False))
elif ext in ('scc', 'ttml', 'vtt'):
info['subtitles'].setdefault('en', []).append({
'url': asset_url,
})
return info
else:
entries = []
for edge in show_data.get('videos', {}).get('edges', []):
video = edge.get('node') or {}
slug = video.get('slug')
if not slug:
continue
entries.append(self.url_result(
'http://adultswim.com/videos/%s/%s' % (show_path, slug),
'AdultSwim', video.get('_id')))
return self.playlist_result(
entries, show_path, show_data.get('title'),
strip_or_none(show_data.get('metaDescription')))
yt_dlp/extractor/aenetworks.py
+338
View File
@@ -0,0 +1,338 @@
from .theplatform import ThePlatformIE
from ..utils import (
ExtractorError,
GeoRestrictedError,
int_or_none,
update_url_query,
urlencode_postdata,
)
class AENetworksBaseIE(ThePlatformIE): # XXX: Do not subclass from concrete IE
_BASE_URL_REGEX = r'''(?x)https?://
(?:(?:www|play|watch)\.)?
(?P<domain>
(?:history(?:vault)?|aetv|mylifetime|lifetimemovieclub)\.com|
fyi\.tv
)/'''
_THEPLATFORM_KEY = '43jXaGRQud'
_THEPLATFORM_SECRET = 'S10BPXHMlb'
_DOMAIN_MAP = {
'history.com': ('HISTORY', 'history'),
'aetv.com': ('AETV', 'aetv'),
'mylifetime.com': ('LIFETIME', 'lifetime'),
'lifetimemovieclub.com': ('LIFETIMEMOVIECLUB', 'lmc'),
'fyi.tv': ('FYI', 'fyi'),
'historyvault.com': (None, 'historyvault'),
'biography.com': (None, 'biography'),
}
def _extract_aen_smil(self, smil_url, video_id, auth=None):
query = {
'mbr': 'true',
'formats': 'M3U+none,MPEG-DASH+none,MPEG4,MP3',
}
if auth:
query['auth'] = auth
TP_SMIL_QUERY = [{
'assetTypes': 'high_video_ak',
'switch': 'hls_high_ak',
}, {
'assetTypes': 'high_video_s3',
}, {
'assetTypes': 'high_video_s3',
'switch': 'hls_high_fastly',
}]
formats = []
subtitles = {}
last_e = None
for q in TP_SMIL_QUERY:
q.update(query)
m_url = update_url_query(smil_url, q)
m_url = self._sign_url(m_url, self._THEPLATFORM_KEY, self._THEPLATFORM_SECRET)
try:
tp_formats, tp_subtitles = self._extract_theplatform_smil(
m_url, video_id, 'Downloading %s SMIL data' % (q.get('switch') or q['assetTypes']))
except ExtractorError as e:
if isinstance(e, GeoRestrictedError):
raise
last_e = e
continue
formats.extend(tp_formats)
subtitles = self._merge_subtitles(subtitles, tp_subtitles)
if last_e and not formats:
raise last_e
return {
'id': video_id,
'formats': formats,
'subtitles': subtitles,
}
def _extract_aetn_info(self, domain, filter_key, filter_value, url):
requestor_id, brand = self._DOMAIN_MAP[domain]
result = self._download_json(
'https://feeds.video.aetnd.com/api/v2/%s/videos' % brand,
filter_value, query={'filter[%s]' % filter_key: filter_value})['results'][0]
title = result['title']
video_id = result['id']
media_url = result['publicUrl']
theplatform_metadata = self._download_theplatform_metadata(self._search_regex(
r'https?://link\.theplatform\.com/s/([^?]+)', media_url, 'theplatform_path'), video_id)
info = self._parse_theplatform_metadata(theplatform_metadata)
auth = None
if theplatform_metadata.get('AETN$isBehindWall'):
resource = self._get_mvpd_resource(
requestor_id, theplatform_metadata['title'],
theplatform_metadata.get('AETN$PPL_pplProgramId') or theplatform_metadata.get('AETN$PPL_pplProgramId_OLD'),
theplatform_metadata['ratings'][0]['rating'])
auth = self._extract_mvpd_auth(
url, video_id, requestor_id, resource)
info.update(self._extract_aen_smil(media_url, video_id, auth))
info.update({
'title': title,
'series': result.get('seriesName'),
'season_number': int_or_none(result.get('tvSeasonNumber')),
'episode_number': int_or_none(result.get('tvSeasonEpisodeNumber')),
})
return info
class AENetworksIE(AENetworksBaseIE):
IE_NAME = 'aenetworks'
IE_DESC = 'A+E Networks: A&E, Lifetime, History.com, FYI Network and History Vault'
_VALID_URL = AENetworksBaseIE._BASE_URL_REGEX + r'''(?P<id>
shows/[^/]+/season-\d+/episode-\d+|
(?:
(?:movie|special)s/[^/]+|
(?:shows/[^/]+/)?videos
)/[^/?#&]+
)'''
_TESTS = [{
'url': 'http://www.history.com/shows/mountain-men/season-1/episode-1',
'info_dict': {
'id': '22253814',
'ext': 'mp4',
'title': 'Winter is Coming',
'description': 'md5:641f424b7a19d8e24f26dea22cf59d74',
'timestamp': 1338306241,
'upload_date': '20120529',
'uploader': 'AENE-NEW',
},
'params': {
# m3u8 download
'skip_download': True,
},
'add_ie': ['ThePlatform'],
'skip': 'This video is only available for users of participating TV providers.',
}, {
'url': 'http://www.aetv.com/shows/duck-dynasty/season-9/episode-1',
'info_dict': {
'id': '600587331957',
'ext': 'mp4',
'title': 'Inlawful Entry',
'description': 'md5:57c12115a2b384d883fe64ca50529e08',
'timestamp': 1452634428,
'upload_date': '20160112',
'uploader': 'AENE-NEW',
},
'params': {
# m3u8 download
'skip_download': True,
},
'add_ie': ['ThePlatform'],
}, {
'url': 'http://www.fyi.tv/shows/tiny-house-nation/season-1/episode-8',
'only_matching': True
}, {
'url': 'http://www.mylifetime.com/shows/project-runway-junior/season-1/episode-6',
'only_matching': True
}, {
'url': 'http://www.mylifetime.com/movies/center-stage-on-pointe/full-movie',
'only_matching': True
}, {
'url': 'https://watch.lifetimemovieclub.com/movies/10-year-reunion/full-movie',
'only_matching': True
}, {
'url': 'http://www.history.com/specials/sniper-into-the-kill-zone/full-special',
'only_matching': True
}, {
'url': 'https://www.aetv.com/specials/hunting-jonbenets-killer-the-untold-story/preview-hunting-jonbenets-killer-the-untold-story',
'only_matching': True
}, {
'url': 'http://www.history.com/videos/history-of-valentines-day',
'only_matching': True
}, {
'url': 'https://play.aetv.com/shows/duck-dynasty/videos/best-of-duck-dynasty-getting-quack-in-shape',
'only_matching': True
}]
def _real_extract(self, url):
domain, canonical = self._match_valid_url(url).groups()
return self._extract_aetn_info(domain, 'canonical', '/' + canonical, url)
class AENetworksListBaseIE(AENetworksBaseIE):
def _call_api(self, resource, slug, brand, fields):
return self._download_json(
'https://yoga.appsvcs.aetnd.com/graphql',
slug, query={'brand': brand}, data=urlencode_postdata({
'query': '''{
%s(slug: "%s") {
%s
}
}''' % (resource, slug, fields),
}))['data'][resource]
def _real_extract(self, url):
domain, slug = self._match_valid_url(url).groups()
_, brand = self._DOMAIN_MAP[domain]
playlist = self._call_api(self._RESOURCE, slug, brand, self._FIELDS)
base_url = 'http://watch.%s' % domain
entries = []
for item in (playlist.get(self._ITEMS_KEY) or []):
doc = self._get_doc(item)
canonical = doc.get('canonical')
if not canonical:
continue
entries.append(self.url_result(
base_url + canonical, AENetworksIE.ie_key(), doc.get('id')))
description = None
if self._PLAYLIST_DESCRIPTION_KEY:
description = playlist.get(self._PLAYLIST_DESCRIPTION_KEY)
return self.playlist_result(
entries, playlist.get('id'),
playlist.get(self._PLAYLIST_TITLE_KEY), description)
class AENetworksCollectionIE(AENetworksListBaseIE):
IE_NAME = 'aenetworks:collection'
_VALID_URL = AENetworksBaseIE._BASE_URL_REGEX + r'(?:[^/]+/)*(?:list|collections)/(?P<id>[^/?#&]+)/?(?:[?#&]|$)'
_TESTS = [{
'url': 'https://watch.historyvault.com/list/america-the-story-of-us',
'info_dict': {
'id': '282',
'title': 'America The Story of Us',
},
'playlist_mincount': 12,
}, {
'url': 'https://watch.historyvault.com/shows/america-the-story-of-us-2/season-1/list/america-the-story-of-us',
'only_matching': True
}, {
'url': 'https://www.historyvault.com/collections/mysteryquest',
'only_matching': True
}]
_RESOURCE = 'list'
_ITEMS_KEY = 'items'
_PLAYLIST_TITLE_KEY = 'display_title'
_PLAYLIST_DESCRIPTION_KEY = None
_FIELDS = '''id
display_title
items {
... on ListVideoItem {
doc {
canonical
id
}
}
}'''
def _get_doc(self, item):
return item.get('doc') or {}
class AENetworksShowIE(AENetworksListBaseIE):
IE_NAME = 'aenetworks:show'
_VALID_URL = AENetworksBaseIE._BASE_URL_REGEX + r'shows/(?P<id>[^/?#&]+)/?(?:[?#&]|$)'
_TESTS = [{
'url': 'http://www.history.com/shows/ancient-aliens',
'info_dict': {
'id': 'SERIES1574',
'title': 'Ancient Aliens',
'description': 'md5:3f6d74daf2672ff3ae29ed732e37ea7f',
},
'playlist_mincount': 150,
}]
_RESOURCE = 'series'
_ITEMS_KEY = 'episodes'
_PLAYLIST_TITLE_KEY = 'title'
_PLAYLIST_DESCRIPTION_KEY = 'description'
_FIELDS = '''description
id
title
episodes {
canonical
id
}'''
def _get_doc(self, item):
return item
class HistoryTopicIE(AENetworksBaseIE):
IE_NAME = 'history:topic'
IE_DESC = 'History.com Topic'
_VALID_URL = r'https?://(?:www\.)?history\.com/topics/[^/]+/(?P<id>[\w+-]+?)-video'
_TESTS = [{
'url': 'https://www.history.com/topics/valentines-day/history-of-valentines-day-video',
'info_dict': {
'id': '40700995724',
'ext': 'mp4',
'title': "History of Valentine’s Day",
'description': 'md5:7b57ea4829b391995b405fa60bd7b5f7',
'timestamp': 1375819729,
'upload_date': '20130806',
'uploader': 'AENE-NEW',
},
'params': {
# m3u8 download
'skip_download': True,
},
'add_ie': ['ThePlatform'],
}]
def _real_extract(self, url):
display_id = self._match_id(url)
return self.url_result(
'http://www.history.com/videos/' + display_id,
AENetworksIE.ie_key())
class HistoryPlayerIE(AENetworksBaseIE):
IE_NAME = 'history:player'
_VALID_URL = r'https?://(?:www\.)?(?P<domain>(?:history|biography)\.com)/player/(?P<id>\d+)'
def _real_extract(self, url):
domain, video_id = self._match_valid_url(url).groups()
return self._extract_aetn_info(domain, 'id', video_id, url)
class BiographyIE(AENetworksBaseIE):
_VALID_URL = r'https?://(?:www\.)?biography\.com/video/(?P<id>[^/?#&]+)'
_TESTS = [{
'url': 'https://www.biography.com/video/vincent-van-gogh-full-episode-2075049808',
'info_dict': {
'id': '30322987',
'ext': 'mp4',
'title': 'Vincent Van Gogh - Full Episode',
'description': 'A full biography about the most influential 20th century painter, Vincent Van Gogh.',
'timestamp': 1311970571,
'upload_date': '20110729',
'uploader': 'AENE-NEW',
},
'params': {
# m3u8 download
'skip_download': True,
},
'add_ie': ['ThePlatform'],
}]
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
player_url = self._search_regex(
r'<phoenix-iframe[^>]+src="(%s)' % HistoryPlayerIE._VALID_URL,
webpage, 'player URL')
return self.url_result(player_url, HistoryPlayerIE.ie_key())
yt_dlp/extractor/aeonco.py
+40
View File
@@ -0,0 +1,40 @@
from .common import InfoExtractor
from .vimeo import VimeoIE
class AeonCoIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?aeon\.co/videos/(?P<id>[^/?]+)'
_TESTS = [{
'url': 'https://aeon.co/videos/raw-solar-storm-footage-is-the-punk-rock-antidote-to-sleek-james-webb-imagery',
'md5': 'e5884d80552c9b6ea8d268a258753362',
'info_dict': {
'id': '1284717',
'ext': 'mp4',
'title': 'Brilliant Noise',
'thumbnail': 'https://i.vimeocdn.com/video/21006315-1a1e49da8b07fd908384a982b4ba9ff0268c509a474576ebdf7b1392f4acae3b-d_960',
'uploader': 'Semiconductor',
'uploader_id': 'semiconductor',
'uploader_url': 'https://vimeo.com/semiconductor',
'duration': 348
}
}, {
'url': 'https://aeon.co/videos/dazzling-timelapse-shows-how-microbes-spoil-our-food-and-sometimes-enrich-it',
'md5': '4e5f3dad9dbda0dbfa2da41a851e631e',
'info_dict': {
'id': '728595228',
'ext': 'mp4',
'title': 'Wrought',
'thumbnail': 'https://i.vimeocdn.com/video/1484618528-c91452611f9a4e4497735a533da60d45b2fe472deb0c880f0afaab0cd2efb22a-d_1280',
'uploader': 'Biofilm Productions',
'uploader_id': 'user140352216',
'uploader_url': 'https://vimeo.com/user140352216',
'duration': 1344
}
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
vimeo_id = self._search_regex(r'hosterId":\s*"(?P<id>[0-9]+)', webpage, 'vimeo id')
vimeo_url = VimeoIE._smuggle_referrer(f'https://player.vimeo.com/video/{vimeo_id}', 'https://aeon.co')
return self.url_result(vimeo_url, VimeoIE)
yt_dlp/extractor/afreecatv.py
+533
View File
@@ -0,0 +1,533 @@
import functools
import re
from .common import InfoExtractor
from ..utils import (
ExtractorError,
OnDemandPagedList,
date_from_str,
determine_ext,
int_or_none,
qualities,
traverse_obj,
unified_strdate,
unified_timestamp,
update_url_query,
url_or_none,
urlencode_postdata,
xpath_text,
)
class AfreecaTVIE(InfoExtractor):
IE_NAME = 'afreecatv'
IE_DESC = 'afreecatv.com'
_VALID_URL = r'''(?x)
https?://
(?:
(?:(?:live|afbbs|www)\.)?afreeca(?:tv)?\.com(?::\d+)?
(?:
/app/(?:index|read_ucc_bbs)\.cgi|
/player/[Pp]layer\.(?:swf|html)
)\?.*?\bnTitleNo=|
vod\.afreecatv\.com/(PLAYER/STATION|player)/
)
(?P<id>\d+)
'''
_NETRC_MACHINE = 'afreecatv'
_TESTS = [{
'url': 'http://live.afreecatv.com:8079/app/index.cgi?szType=read_ucc_bbs&szBjId=dailyapril&nStationNo=16711924&nBbsNo=18605867&nTitleNo=36164052&szSkin=',
'md5': 'f72c89fe7ecc14c1b5ce506c4996046e',
'info_dict': {
'id': '36164052',
'ext': 'mp4',
'title': '데일리 에이프릴 요정들의 시상식!',
'thumbnail': 're:^https?://(?:video|st)img.afreecatv.com/.*$',
'uploader': 'dailyapril',
'uploader_id': 'dailyapril',
'upload_date': '20160503',
},
'skip': 'Video is gone',
}, {
'url': 'http://afbbs.afreecatv.com:8080/app/read_ucc_bbs.cgi?nStationNo=16711924&nTitleNo=36153164&szBjId=dailyapril&nBbsNo=18605867',
'info_dict': {
'id': '36153164',
'title': "BJ유트루와 함께하는 '팅커벨 메이크업!'",
'thumbnail': 're:^https?://(?:video|st)img.afreecatv.com/.*$',
'uploader': 'dailyapril',
'uploader_id': 'dailyapril',
},
'playlist_count': 2,
'playlist': [{
'md5': 'd8b7c174568da61d774ef0203159bf97',
'info_dict': {
'id': '36153164_1',
'ext': 'mp4',
'title': "BJ유트루와 함께하는 '팅커벨 메이크업!'",
'upload_date': '20160502',
},
}, {
'md5': '58f2ce7f6044e34439ab2d50612ab02b',
'info_dict': {
'id': '36153164_2',
'ext': 'mp4',
'title': "BJ유트루와 함께하는 '팅커벨 메이크업!'",
'upload_date': '20160502',
},
}],
'skip': 'Video is gone',
}, {
'url': 'http://vod.afreecatv.com/PLAYER/STATION/18650793',
'info_dict': {
'id': '18650793',
'ext': 'mp4',
'title': '오늘은 다르다! 쏘님의 우월한 위아래~ 댄스리액션!',
'thumbnail': r're:^https?://.*\.jpg$',
'uploader': '윈아디',
'uploader_id': 'badkids',
'duration': 107,
},
'params': {
'skip_download': True,
},
}, {
'url': 'http://vod.afreecatv.com/PLAYER/STATION/10481652',
'info_dict': {
'id': '10481652',
'title': "BJ유트루와 함께하는 '팅커벨 메이크업!'",
'thumbnail': 're:^https?://(?:video|st)img.afreecatv.com/.*$',
'uploader': 'dailyapril',
'uploader_id': 'dailyapril',
'duration': 6492,
},
'playlist_count': 2,
'playlist': [{
'md5': 'd8b7c174568da61d774ef0203159bf97',
'info_dict': {
'id': '20160502_c4c62b9d_174361386_1',
'ext': 'mp4',
'title': "BJ유트루와 함께하는 '팅커벨 메이크업!' (part 1)",
'thumbnail': 're:^https?://(?:video|st)img.afreecatv.com/.*$',
'uploader': 'dailyapril',
'uploader_id': 'dailyapril',
'upload_date': '20160502',
'duration': 3601,
},
}, {
'md5': '58f2ce7f6044e34439ab2d50612ab02b',
'info_dict': {
'id': '20160502_39e739bb_174361386_2',
'ext': 'mp4',
'title': "BJ유트루와 함께하는 '팅커벨 메이크업!' (part 2)",
'thumbnail': 're:^https?://(?:video|st)img.afreecatv.com/.*$',
'uploader': 'dailyapril',
'uploader_id': 'dailyapril',
'upload_date': '20160502',
'duration': 2891,
},
}],
'params': {
'skip_download': True,
},
}, {
# non standard key
'url': 'http://vod.afreecatv.com/PLAYER/STATION/20515605',
'info_dict': {
'id': '20170411_BE689A0E_190960999_1_2_h',
'ext': 'mp4',
'title': '혼자사는여자집',
'thumbnail': 're:^https?://(?:video|st)img.afreecatv.com/.*$',
'uploader': '♥이슬이',
'uploader_id': 'dasl8121',
'upload_date': '20170411',
'duration': 213,
},
'params': {
'skip_download': True,
},
}, {
# PARTIAL_ADULT
'url': 'http://vod.afreecatv.com/PLAYER/STATION/32028439',
'info_dict': {
'id': '20180327_27901457_202289533_1',
'ext': 'mp4',
'title': '[생]빨개요♥ (part 1)',
'thumbnail': 're:^https?://(?:video|st)img.afreecatv.com/.*$',
'uploader': '[SA]서아',
'uploader_id': 'bjdyrksu',
'upload_date': '20180327',
'duration': 3601,
},
'params': {
'skip_download': True,
},
'expected_warnings': ['adult content'],
}, {
'url': 'http://www.afreecatv.com/player/Player.swf?szType=szBjId=djleegoon&nStationNo=11273158&nBbsNo=13161095&nTitleNo=36327652',
'only_matching': True,
}, {
'url': 'http://vod.afreecatv.com/PLAYER/STATION/15055030',
'only_matching': True,
}, {
'url': 'http://vod.afreecatv.com/player/15055030',
'only_matching': True,
}]
@staticmethod
def parse_video_key(key):
video_key = {}
m = re.match(r'^(?P<upload_date>\d{8})_\w+_(?P<part>\d+)$', key)
if m:
video_key['upload_date'] = m.group('upload_date')
video_key['part'] = int(m.group('part'))
return video_key
def _perform_login(self, username, password):
login_form = {
'szWork': 'login',
'szType': 'json',
'szUid': username,
'szPassword': password,
'isSaveId': 'false',
'szScriptVar': 'oLoginRet',
'szAction': '',
}
response = self._download_json(
'https://login.afreecatv.com/app/LoginAction.php', None,
'Logging in', data=urlencode_postdata(login_form))
_ERRORS = {
-4: 'Your account has been suspended due to a violation of our terms and policies.',
-5: 'https://member.afreecatv.com/app/user_delete_progress.php',
-6: 'https://login.afreecatv.com/membership/changeMember.php',
-8: "Hello! AfreecaTV here.\nThe username you have entered belongs to \n an account that requires a legal guardian's consent. \nIf you wish to use our services without restriction, \nplease make sure to go through the necessary verification process.",
-9: 'https://member.afreecatv.com/app/pop_login_block.php',
-11: 'https://login.afreecatv.com/afreeca/second_login.php',
-12: 'https://member.afreecatv.com/app/user_security.php',
0: 'The username does not exist or you have entered the wrong password.',
-1: 'The username does not exist or you have entered the wrong password.',
-3: 'You have entered your username/password incorrectly.',
-7: 'You cannot use your Global AfreecaTV account to access Korean AfreecaTV.',
-10: 'Sorry for the inconvenience. \nYour account has been blocked due to an unauthorized access. \nPlease contact our Help Center for assistance.',
-32008: 'You have failed to log in. Please contact our Help Center.',
}
result = int_or_none(response.get('RESULT'))
if result != 1:
error = _ERRORS.get(result, 'You have failed to log in.')
raise ExtractorError(
'Unable to login: %s said: %s' % (self.IE_NAME, error),
expected=True)
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
if re.search(r'alert\(["\']This video has been deleted', webpage):
raise ExtractorError(
'Video %s has been deleted' % video_id, expected=True)
station_id = self._search_regex(
r'nStationNo\s*=\s*(\d+)', webpage, 'station')
bbs_id = self._search_regex(
r'nBbsNo\s*=\s*(\d+)', webpage, 'bbs')
video_id = self._search_regex(
r'nTitleNo\s*=\s*(\d+)', webpage, 'title', default=video_id)
partial_view = False
adult_view = False
for _ in range(2):
query = {
'nTitleNo': video_id,
'nStationNo': station_id,
'nBbsNo': bbs_id,
}
if partial_view:
query['partialView'] = 'SKIP_ADULT'
if adult_view:
query['adultView'] = 'ADULT_VIEW'
video_xml = self._download_xml(
'http://afbbs.afreecatv.com:8080/api/video/get_video_info.php',
video_id, 'Downloading video info XML%s'
% (' (skipping adult)' if partial_view else ''),
video_id, headers={
'Referer': url,
}, query=query)
flag = xpath_text(video_xml, './track/flag', 'flag', default=None)
if flag and flag == 'SUCCEED':
break
if flag == 'PARTIAL_ADULT':
self.report_warning(
'In accordance with local laws and regulations, underage users are restricted from watching adult content. '
'Only content suitable for all ages will be downloaded. '
'Provide account credentials if you wish to download restricted content.')
partial_view = True
continue
elif flag == 'ADULT':
if not adult_view:
adult_view = True
continue
error = 'Only users older than 19 are able to watch this video. Provide account credentials to download this content.'
else:
error = flag
raise ExtractorError(
'%s said: %s' % (self.IE_NAME, error), expected=True)
else:
raise ExtractorError('Unable to download video info')
video_element = video_xml.findall('./track/video')[-1]
if video_element is None or video_element.text is None:
raise ExtractorError(
'Video %s does not exist' % video_id, expected=True)
video_url = video_element.text.strip()
title = xpath_text(video_xml, './track/title', 'title', fatal=True)
uploader = xpath_text(video_xml, './track/nickname', 'uploader')
uploader_id = xpath_text(video_xml, './track/bj_id', 'uploader id')
duration = int_or_none(xpath_text(
video_xml, './track/duration', 'duration'))
thumbnail = xpath_text(video_xml, './track/titleImage', 'thumbnail')
common_entry = {
'uploader': uploader,
'uploader_id': uploader_id,
'thumbnail': thumbnail,
}
info = common_entry.copy()
info.update({
'id': video_id,
'title': title,
'duration': duration,
})
if not video_url:
entries = []
file_elements = video_element.findall('./file')
one = len(file_elements) == 1
for file_num, file_element in enumerate(file_elements, start=1):
file_url = url_or_none(file_element.text)
if not file_url:
continue
key = file_element.get('key', '')
upload_date = unified_strdate(self._search_regex(
r'^(\d{8})_', key, 'upload date', default=None))
if upload_date is not None:
# sometimes the upload date isn't included in the file name
# instead, another random ID is, which may parse as a valid
# date but be wildly out of a reasonable range
parsed_date = date_from_str(upload_date)
if parsed_date.year < 2000 or parsed_date.year >= 2100:
upload_date = None
file_duration = int_or_none(file_element.get('duration'))
format_id = key if key else '%s_%s' % (video_id, file_num)
if determine_ext(file_url) == 'm3u8':
formats = self._extract_m3u8_formats(
file_url, video_id, 'mp4', entry_protocol='m3u8_native',
m3u8_id='hls',
note='Downloading part %d m3u8 information' % file_num)
else:
formats = [{
'url': file_url,
'format_id': 'http',
}]
if not formats and not self.get_param('ignore_no_formats'):
continue
file_info = common_entry.copy()
file_info.update({
'id': format_id,
'title': title if one else '%s (part %d)' % (title, file_num),
'upload_date': upload_date,
'duration': file_duration,
'formats': formats,
})
entries.append(file_info)
entries_info = info.copy()
entries_info.update({
'_type': 'multi_video',
'entries': entries,
})
return entries_info
info = {
'id': video_id,
'title': title,
'uploader': uploader,
'uploader_id': uploader_id,
'duration': duration,
'thumbnail': thumbnail,
}
if determine_ext(video_url) == 'm3u8':
info['formats'] = self._extract_m3u8_formats(
video_url, video_id, 'mp4', entry_protocol='m3u8_native',
m3u8_id='hls')
else:
app, playpath = video_url.split('mp4:')
info.update({
'url': app,
'ext': 'flv',
'play_path': 'mp4:' + playpath,
'rtmp_live': True, # downloading won't end without this
})
return info
class AfreecaTVLiveIE(AfreecaTVIE): # XXX: Do not subclass from concrete IE
IE_NAME = 'afreecatv:live'
_VALID_URL = r'https?://play\.afreeca(?:tv)?\.com/(?P<id>[^/]+)(?:/(?P<bno>\d+))?'
_TESTS = [{
'url': 'https://play.afreecatv.com/pyh3646/237852185',
'info_dict': {
'id': '237852185',
'ext': 'mp4',
'title': '【 우루과이 오늘은 무슨일이? 】',
'uploader': '박진우[JINU]',
'uploader_id': 'pyh3646',
'timestamp': 1640661495,
'is_live': True,
},
'skip': 'Livestream has ended',
}, {
'url': 'http://play.afreeca.com/pyh3646/237852185',
'only_matching': True,
}, {
'url': 'http://play.afreeca.com/pyh3646',
'only_matching': True,
}]
_LIVE_API_URL = 'https://live.afreecatv.com/afreeca/player_live_api.php'
_QUALITIES = ('sd', 'hd', 'hd2k', 'original')
def _real_extract(self, url):
broadcaster_id, broadcast_no = self._match_valid_url(url).group('id', 'bno')
password = self.get_param('videopassword')
info = self._download_json(self._LIVE_API_URL, broadcaster_id, fatal=False,
data=urlencode_postdata({'bid': broadcaster_id})) or {}
channel_info = info.get('CHANNEL') or {}
broadcaster_id = channel_info.get('BJID') or broadcaster_id
broadcast_no = channel_info.get('BNO') or broadcast_no
password_protected = channel_info.get('BPWD')
if not broadcast_no:
raise ExtractorError(f'Unable to extract broadcast number ({broadcaster_id} may not be live)', expected=True)
if password_protected == 'Y' and password is None:
raise ExtractorError(
'This livestream is protected by a password, use the --video-password option',
expected=True)
formats = []
quality_key = qualities(self._QUALITIES)
for quality_str in self._QUALITIES:
params = {
'bno': broadcast_no,
'stream_type': 'common',
'type': 'aid',
'quality': quality_str,
}
if password is not None:
params['pwd'] = password
aid_response = self._download_json(
self._LIVE_API_URL, broadcast_no, fatal=False,
data=urlencode_postdata(params),
note=f'Downloading access token for {quality_str} stream',
errnote=f'Unable to download access token for {quality_str} stream')
aid = traverse_obj(aid_response, ('CHANNEL', 'AID'))
if not aid:
continue
stream_base_url = channel_info.get('RMD') or 'https://livestream-manager.afreecatv.com'
stream_info = self._download_json(
f'{stream_base_url}/broad_stream_assign.html', broadcast_no, fatal=False,
query={
'return_type': channel_info.get('CDN', 'gcp_cdn'),
'broad_key': f'{broadcast_no}-common-{quality_str}-hls',
},
note=f'Downloading metadata for {quality_str} stream',
errnote=f'Unable to download metadata for {quality_str} stream') or {}
if stream_info.get('view_url'):
formats.append({
'format_id': quality_str,
'url': update_url_query(stream_info['view_url'], {'aid': aid}),
'ext': 'mp4',
'protocol': 'm3u8',
'quality': quality_key(quality_str),
})
station_info = self._download_json(
'https://st.afreecatv.com/api/get_station_status.php', broadcast_no,
query={'szBjId': broadcaster_id}, fatal=False,
note='Downloading channel metadata', errnote='Unable to download channel metadata') or {}
return {
'id': broadcast_no,
'title': channel_info.get('TITLE') or station_info.get('station_title'),
'uploader': channel_info.get('BJNICK') or station_info.get('station_name'),
'uploader_id': broadcaster_id,
'timestamp': unified_timestamp(station_info.get('broad_start')),
'formats': formats,
'is_live': True,
}
class AfreecaTVUserIE(InfoExtractor):
IE_NAME = 'afreecatv:user'
_VALID_URL = r'https?://bj\.afreeca(?:tv)?\.com/(?P<id>[^/]+)/vods/?(?P<slug_type>[^/]+)?'
_TESTS = [{
'url': 'https://bj.afreecatv.com/ryuryu24/vods/review',
'info_dict': {
'_type': 'playlist',
'id': 'ryuryu24',
'title': 'ryuryu24 - review',
},
'playlist_count': 218,
}, {
'url': 'https://bj.afreecatv.com/parang1995/vods/highlight',
'info_dict': {
'_type': 'playlist',
'id': 'parang1995',
'title': 'parang1995 - highlight',
},
'playlist_count': 997,
}, {
'url': 'https://bj.afreecatv.com/ryuryu24/vods',
'info_dict': {
'_type': 'playlist',
'id': 'ryuryu24',
'title': 'ryuryu24 - all',
},
'playlist_count': 221,
}, {
'url': 'https://bj.afreecatv.com/ryuryu24/vods/balloonclip',
'info_dict': {
'_type': 'playlist',
'id': 'ryuryu24',
'title': 'ryuryu24 - balloonclip',
},
'playlist_count': 0,
}]
_PER_PAGE = 60
def _fetch_page(self, user_id, user_type, page):
page += 1
info = self._download_json(f'https://bjapi.afreecatv.com/api/{user_id}/vods/{user_type}', user_id,
query={'page': page, 'per_page': self._PER_PAGE, 'orderby': 'reg_date'},
note=f'Downloading {user_type} video page {page}')
for item in info['data']:
yield self.url_result(
f'https://vod.afreecatv.com/player/{item["title_no"]}/', AfreecaTVIE, item['title_no'])
def _real_extract(self, url):
user_id, user_type = self._match_valid_url(url).group('id', 'slug_type')
user_type = user_type or 'all'
entries = OnDemandPagedList(functools.partial(self._fetch_page, user_id, user_type), self._PER_PAGE)
return self.playlist_result(entries, user_id, f'{user_id} - {user_type}')
yt_dlp/extractor/agora.py
+251
View File
@@ -0,0 +1,251 @@
import functools
import uuid
from .common import InfoExtractor
from ..utils import (
ExtractorError,
OnDemandPagedList,
int_or_none,
month_by_name,
parse_duration,
try_call,
)
class WyborczaVideoIE(InfoExtractor):
# this id is not an article id, it has to be extracted from the article
_VALID_URL = r'(?:wyborcza:video:|https?://wyborcza\.pl/(?:api-)?video/)(?P<id>\d+)'
IE_NAME = 'wyborcza:video'
_TESTS = [{
'url': 'wyborcza:video:26207634',
'info_dict': {
'id': '26207634',
'ext': 'mp4',
'title': '- Polska w 2020 r. jest innym państwem niż w 2015 r. Nie zmieniła się konstytucja, ale jest to już inny ustrój - mówi Adam Bodnar',
'description': ' ',
'uploader': 'Dorota Roman',
'duration': 2474,
'thumbnail': r're:https://.+\.jpg',
},
}, {
'url': 'https://wyborcza.pl/video/26207634',
'only_matching': True,
}, {
'url': 'https://wyborcza.pl/api-video/26207634',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
meta = self._download_json(f'https://wyborcza.pl/api-video/{video_id}', video_id)
formats = []
base_url = meta['redirector'].replace('http://', 'https://') + meta['basePath']
for quality in ('standard', 'high'):
if not meta['files'].get(quality):
continue
formats.append({
'url': base_url + meta['files'][quality],
'height': int_or_none(
self._search_regex(
r'p(\d+)[a-z]+\.mp4$', meta['files'][quality],
'mp4 video height', default=None)),
'format_id': quality,
})
if meta['files'].get('dash'):
formats.extend(self._extract_mpd_formats(base_url + meta['files']['dash'], video_id))
return {
'id': video_id,
'formats': formats,
'title': meta.get('title'),
'description': meta.get('lead'),
'uploader': meta.get('signature'),
'thumbnail': meta.get('imageUrl'),
'duration': meta.get('duration'),
}
class WyborczaPodcastIE(InfoExtractor):
_VALID_URL = r'''(?x)
https?://(?:www\.)?(?:
wyborcza\.pl/podcast(?:/0,172673\.html)?|
wysokieobcasy\.pl/wysokie-obcasy/0,176631\.html
)(?:\?(?:[^&#]+?&)*podcast=(?P<id>\d+))?
'''
_TESTS = [{
'url': 'https://wyborcza.pl/podcast/0,172673.html?podcast=100720#S.main_topic-K.C-B.6-L.1.podcast',
'info_dict': {
'id': '100720',
'ext': 'mp3',
'title': 'Cyfrodziewczyny. Kim były pionierki polskiej informatyki ',
'uploader': 'Michał Nogaś ',
'upload_date': '20210117',
'description': 'md5:49f0a06ffc4c1931210d3ab1416a651d',
'duration': 3684.0,
'thumbnail': r're:https://.+\.jpg',
},
}, {
'url': 'https://www.wysokieobcasy.pl/wysokie-obcasy/0,176631.html?podcast=100673',
'info_dict': {
'id': '100673',
'ext': 'mp3',
'title': 'Czym jest ubóstwo menstruacyjne i dlaczego dotyczy każdej i każdego z nas?',
'uploader': 'Agnieszka Urazińska ',
'upload_date': '20210115',
'description': 'md5:c161dc035f8dbb60077011fc41274899',
'duration': 1803.0,
'thumbnail': r're:https://.+\.jpg',
},
}, {
'url': 'https://wyborcza.pl/podcast',
'info_dict': {
'id': '334',
'title': 'Gościnnie: Wyborcza, 8:10',
'series': 'Gościnnie: Wyborcza, 8:10',
},
'playlist_mincount': 370,
}, {
'url': 'https://www.wysokieobcasy.pl/wysokie-obcasy/0,176631.html',
'info_dict': {
'id': '395',
'title': 'Gościnnie: Wysokie Obcasy',
'series': 'Gościnnie: Wysokie Obcasy',
},
'playlist_mincount': 12,
}]
def _real_extract(self, url):
podcast_id = self._match_id(url)
if not podcast_id: # playlist
podcast_id = '395' if 'wysokieobcasy.pl/' in url else '334'
return self.url_result(TokFMAuditionIE._create_url(podcast_id), TokFMAuditionIE, podcast_id)
meta = self._download_json('https://wyborcza.pl/api/podcast', podcast_id,
query={'guid': podcast_id, 'type': 'wo' if 'wysokieobcasy.pl/' in url else None})
day, month, year = self._search_regex(r'^(\d\d?) (\w+) (\d{4})$', meta.get('publishedDate'),
'upload date', group=(1, 2, 3), default=(None, None, None))
return {
'id': podcast_id,
'url': meta['url'],
'title': meta.get('title'),
'description': meta.get('description'),
'thumbnail': meta.get('imageUrl'),
'duration': parse_duration(meta.get('duration')),
'uploader': meta.get('author'),
'upload_date': try_call(lambda: f'{year}{month_by_name(month, lang="pl"):0>2}{day:0>2}'),
}
class TokFMPodcastIE(InfoExtractor):
_VALID_URL = r'(?:https?://audycje\.tokfm\.pl/podcast/|tokfm:podcast:)(?P<id>\d+),?'
IE_NAME = 'tokfm:podcast'
_TESTS = [{
'url': 'https://audycje.tokfm.pl/podcast/91275,-Systemowy-rasizm-Czy-zamieszki-w-USA-po-morderstwie-w-Minneapolis-doprowadza-do-zmian-w-sluzbach-panstwowych',
'info_dict': {
'id': '91275',
'ext': 'aac',
'title': 'md5:a9b15488009065556900169fb8061cce',
'episode': 'md5:a9b15488009065556900169fb8061cce',
'series': 'Analizy',
},
}]
def _real_extract(self, url):
media_id = self._match_id(url)
# in case it breaks see this but it returns a lot of useless data
# https://api.podcast.radioagora.pl/api4/getPodcasts?podcast_id=100091&with_guests=true&with_leaders_for_mobile=true
metadata = self._download_json(
f'https://audycje.tokfm.pl/getp/3{media_id}', media_id, 'Downloading podcast metadata')
if not metadata:
raise ExtractorError('No such podcast', expected=True)
metadata = metadata[0]
formats = []
for ext in ('aac', 'mp3'):
url_data = self._download_json(
f'https://api.podcast.radioagora.pl/api4/getSongUrl?podcast_id={media_id}&device_id={uuid.uuid4()}&ppre=false&audio={ext}',
media_id, 'Downloading podcast %s URL' % ext)
# prevents inserting the mp3 (default) multiple times
if 'link_ssl' in url_data and f'.{ext}' in url_data['link_ssl']:
formats.append({
'url': url_data['link_ssl'],
'ext': ext,
'vcodec': 'none',
'acodec': ext,
})
return {
'id': media_id,
'formats': formats,
'title': metadata.get('podcast_name'),
'series': metadata.get('series_name'),
'episode': metadata.get('podcast_name'),
}
class TokFMAuditionIE(InfoExtractor):
_VALID_URL = r'(?:https?://audycje\.tokfm\.pl/audycja/|tokfm:audition:)(?P<id>\d+),?'
IE_NAME = 'tokfm:audition'
_TESTS = [{
'url': 'https://audycje.tokfm.pl/audycja/218,Analizy',
'info_dict': {
'id': '218',
'title': 'Analizy',
'series': 'Analizy',
},
'playlist_count': 1635,
}]
_PAGE_SIZE = 30
_HEADERS = {
'User-Agent': 'Mozilla/5.0 (Linux; Android 9; Redmi 3S Build/PQ3A.190801.002; wv) AppleWebKit/537.36 (KHTML, like Gecko) Version/4.0 Chrome/87.0.4280.101 Mobile Safari/537.36',
}
@staticmethod
def _create_url(id):
return f'https://audycje.tokfm.pl/audycja/{id}'
def _real_extract(self, url):
audition_id = self._match_id(url)
data = self._download_json(
f'https://api.podcast.radioagora.pl/api4/getSeries?series_id={audition_id}',
audition_id, 'Downloading audition metadata', headers=self._HEADERS)
if not data:
raise ExtractorError('No such audition', expected=True)
data = data[0]
entries = OnDemandPagedList(functools.partial(
self._fetch_page, audition_id, data), self._PAGE_SIZE)
return {
'_type': 'playlist',
'id': audition_id,
'title': data.get('series_name'),
'series': data.get('series_name'),
'entries': entries,
}
def _fetch_page(self, audition_id, data, page):
for retry in self.RetryManager():
podcast_page = self._download_json(
f'https://api.podcast.radioagora.pl/api4/getPodcasts?series_id={audition_id}&limit=30&offset={page}&with_guests=true&with_leaders_for_mobile=true',
audition_id, f'Downloading podcast list page {page + 1}', headers=self._HEADERS)
if not podcast_page:
retry.error = ExtractorError('Agora returned empty page', expected=True)
for podcast in podcast_page:
yield {
'_type': 'url_transparent',
'url': podcast['podcast_sharing_url'],
'ie_key': TokFMPodcastIE.ie_key(),
'title': podcast.get('podcast_name'),
'episode': podcast.get('podcast_name'),
'description': podcast.get('podcast_description'),
'timestamp': int_or_none(podcast.get('podcast_timestamp')),
'series': data.get('series_name'),
}
yt_dlp/extractor/airmozilla.py
+63
View File
@@ -0,0 +1,63 @@
import re
from .common import InfoExtractor
from ..utils import (
int_or_none,
parse_duration,
parse_iso8601,
)
class AirMozillaIE(InfoExtractor):
_VALID_URL = r'https?://air\.mozilla\.org/(?P<id>[0-9a-z-]+)/?'
_TEST = {
'url': 'https://air.mozilla.org/privacy-lab-a-meetup-for-privacy-minded-people-in-san-francisco/',
'md5': '8d02f53ee39cf006009180e21df1f3ba',
'info_dict': {
'id': '6x4q2w',
'ext': 'mp4',
'title': 'Privacy Lab - a meetup for privacy minded people in San Francisco',
'thumbnail': r're:https?://.*/poster\.jpg',
'description': 'Brings together privacy professionals and others interested in privacy at for-profits, non-profits, and NGOs in an effort to contribute to the state of the ecosystem...',
'timestamp': 1422487800,
'upload_date': '20150128',
'location': 'SFO Commons',
'duration': 3780,
'view_count': int,
'categories': ['Main', 'Privacy'],
}
}
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
video_id = self._html_search_regex(r'//vid\.ly/(.*?)/embed', webpage, 'id')
embed_script = self._download_webpage('https://vid.ly/{0}/embed'.format(video_id), video_id)
jwconfig = self._parse_json(self._search_regex(
r'initCallback\((.*)\);', embed_script, 'metadata'), video_id)['config']
info_dict = self._parse_jwplayer_data(jwconfig, video_id)
view_count = int_or_none(self._html_search_regex(
r'Views since archived: ([0-9]+)',
webpage, 'view count', fatal=False))
timestamp = parse_iso8601(self._html_search_regex(
r'<time datetime="(.*?)"', webpage, 'timestamp', fatal=False))
duration = parse_duration(self._search_regex(
r'Duration:\s*(\d+\s*hours?\s*\d+\s*minutes?)',
webpage, 'duration', fatal=False))
info_dict.update({
'id': video_id,
'title': self._og_search_title(webpage),
'url': self._og_search_url(webpage),
'display_id': display_id,
'description': self._og_search_description(webpage),
'timestamp': timestamp,
'location': self._html_search_regex(r'Location: (.*)', webpage, 'location', default=None),
'duration': duration,
'view_count': view_count,
'categories': re.findall(r'<a href=".*?" class="channel">(.*?)</a>', webpage),
})
return info_dict
yt_dlp/extractor/airtv.py
+96
View File
@@ -0,0 +1,96 @@
from .common import InfoExtractor
from .youtube import YoutubeIE
from ..utils import (
determine_ext,
int_or_none,
mimetype2ext,
parse_iso8601,
traverse_obj
)
class AirTVIE(InfoExtractor):
_VALID_URL = r'https?://www\.air\.tv/watch\?v=(?P<id>\w+)'
_TESTS = [{
# without youtube_id
'url': 'https://www.air.tv/watch?v=W87jcWleSn2hXZN47zJZsQ',
'info_dict': {
'id': 'W87jcWleSn2hXZN47zJZsQ',
'ext': 'mp4',
'release_date': '20221003',
'release_timestamp': 1664792603,
'channel_id': 'vgfManQlRQKgoFQ8i8peFQ',
'title': 'md5:c12d49ed367c3dadaa67659aff43494c',
'upload_date': '20221003',
'duration': 151,
'view_count': int,
'thumbnail': 'https://cdn-sp-gcs.air.tv/videos/W/8/W87jcWleSn2hXZN47zJZsQ/b13fc56464f47d9d62a36d110b9b5a72-4096x2160_9.jpg',
'timestamp': 1664792603,
}
}, {
# with youtube_id
'url': 'https://www.air.tv/watch?v=sv57EC8tRXG6h8dNXFUU1Q',
'info_dict': {
'id': '2ZTqmpee-bQ',
'ext': 'mp4',
'comment_count': int,
'tags': 'count:11',
'channel_follower_count': int,
'like_count': int,
'uploader': 'Newsflare',
'thumbnail': 'https://i.ytimg.com/vi_webp/2ZTqmpee-bQ/maxresdefault.webp',
'availability': 'public',
'title': 'Geese Chase Alligator Across Golf Course',
'uploader_id': 'NewsflareBreaking',
'channel_url': 'https://www.youtube.com/channel/UCzSSoloGEz10HALUAbYhngQ',
'description': 'md5:99b21d9cea59330149efbd9706e208f5',
'age_limit': 0,
'channel_id': 'UCzSSoloGEz10HALUAbYhngQ',
'uploader_url': 'http://www.youtube.com/user/NewsflareBreaking',
'view_count': int,
'categories': ['News & Politics'],
'live_status': 'not_live',
'playable_in_embed': True,
'channel': 'Newsflare',
'duration': 37,
'upload_date': '20180511',
}
}]
def _get_formats_and_subtitle(self, json_data, video_id):
formats, subtitles = [], {}
for source in traverse_obj(json_data, 'sources', 'sources_desktop', ...):
ext = determine_ext(source.get('src'), mimetype2ext(source.get('type')))
if ext == 'm3u8':
fmts, subs = self._extract_m3u8_formats_and_subtitles(source.get('src'), video_id)
formats.extend(fmts)
self._merge_subtitles(subs, target=subtitles)
else:
formats.append({'url': source.get('src'), 'ext': ext})
return formats, subtitles
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
nextjs_json = self._search_nextjs_data(webpage, display_id)['props']['pageProps']['initialState']['videos'][display_id]
if nextjs_json.get('youtube_id'):
return self.url_result(
f'https://www.youtube.com/watch?v={nextjs_json.get("youtube_id")}', YoutubeIE)
formats, subtitles = self._get_formats_and_subtitle(nextjs_json, display_id)
return {
'id': display_id,
'title': nextjs_json.get('title') or self._html_search_meta('og:title', webpage),
'formats': formats,
'subtitles': subtitles,
'description': nextjs_json.get('description') or None,
'duration': int_or_none(nextjs_json.get('duration')),
'thumbnails': [
{'url': thumbnail}
for thumbnail in traverse_obj(nextjs_json, ('default_thumbnails', ...))],
'channel_id': traverse_obj(nextjs_json, 'channel', 'channel_slug'),
'timestamp': parse_iso8601(nextjs_json.get('created')),
'release_timestamp': parse_iso8601(nextjs_json.get('published')),
'view_count': int_or_none(nextjs_json.get('views')),
}
yt_dlp/extractor/aitube.py
+60
View File
@@ -0,0 +1,60 @@
from .common import InfoExtractor
from ..utils import int_or_none, merge_dicts
class AitubeKZVideoIE(InfoExtractor):
_VALID_URL = r'https?://aitube\.kz/(?:video|embed/)\?(?:[^\?]+)?id=(?P<id>[\w-]+)'
_TESTS = [{
# id paramater as first parameter
'url': 'https://aitube.kz/video?id=9291d29b-c038-49a1-ad42-3da2051d353c&playlistId=d55b1f5f-ef2a-4f23-b646-2a86275b86b7&season=1',
'info_dict': {
'id': '9291d29b-c038-49a1-ad42-3da2051d353c',
'ext': 'mp4',
'duration': 2174.0,
'channel_id': '94962f73-013b-432c-8853-1bd78ca860fe',
'like_count': int,
'channel': 'ASTANA TV',
'comment_count': int,
'view_count': int,
'description': 'Смотреть любимые сериалы и видео, поделиться видео и сериалами с друзьями и близкими',
'thumbnail': 'https://cdn.static02.aitube.kz/kz.aitudala.aitube.staticaccess/files/ddf2a2ff-bee3-409b-b5f2-2a8202bba75b',
'upload_date': '20221102',
'timestamp': 1667370519,
'title': 'Ангел хранитель 1 серия',
'channel_follower_count': int,
}
}, {
# embed url
'url': 'https://aitube.kz/embed/?id=9291d29b-c038-49a1-ad42-3da2051d353c',
'only_matching': True,
}, {
# id parameter is not as first paramater
'url': 'https://aitube.kz/video?season=1&id=9291d29b-c038-49a1-ad42-3da2051d353c&playlistId=d55b1f5f-ef2a-4f23-b646-2a86275b86b7',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
nextjs_data = self._search_nextjs_data(webpage, video_id)['props']['pageProps']['videoInfo']
json_ld_data = self._search_json_ld(webpage, video_id)
formats, subtitles = self._extract_m3u8_formats_and_subtitles(
f'https://api-http.aitube.kz/kz.aitudala.aitube.staticaccess/video/{video_id}/video', video_id)
return merge_dicts({
'id': video_id,
'title': nextjs_data.get('title') or self._html_search_meta(['name', 'og:title'], webpage),
'description': nextjs_data.get('description'),
'formats': formats,
'subtitles': subtitles,
'view_count': (nextjs_data.get('viewCount')
or int_or_none(self._html_search_meta('ya:ovs:views_total', webpage))),
'like_count': nextjs_data.get('likeCount'),
'channel': nextjs_data.get('channelTitle'),
'channel_id': nextjs_data.get('channelId'),
'thumbnail': nextjs_data.get('coverUrl'),
'comment_count': nextjs_data.get('commentCount'),
'channel_follower_count': int_or_none(nextjs_data.get('channelSubscriberCount')),
}, json_ld_data)
yt_dlp/extractor/aliexpress.py
+50
View File
@@ -0,0 +1,50 @@
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
float_or_none,
try_get,
)
class AliExpressLiveIE(InfoExtractor):
_VALID_URL = r'https?://live\.aliexpress\.com/live/(?P<id>\d+)'
_TEST = {
'url': 'https://live.aliexpress.com/live/2800002704436634',
'md5': 'e729e25d47c5e557f2630eaf99b740a5',
'info_dict': {
'id': '2800002704436634',
'ext': 'mp4',
'title': 'CASIMA7.22',
'thumbnail': r're:https?://.*\.jpg',
'uploader': 'CASIMA Official Store',
'timestamp': 1500717600,
'upload_date': '20170722',
},
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
data = self._parse_json(
self._search_regex(
r'(?s)runParams\s*=\s*({.+?})\s*;?\s*var',
webpage, 'runParams'),
video_id)
title = data['title']
formats = self._extract_m3u8_formats(
data['replyStreamUrl'], video_id, 'mp4',
entry_protocol='m3u8_native', m3u8_id='hls')
return {
'id': video_id,
'title': title,
'thumbnail': data.get('coverUrl'),
'uploader': try_get(
data, lambda x: x['followBar']['name'], compat_str),
'timestamp': float_or_none(data.get('startTimeLong'), scale=1000),
'formats': formats,
}
yt_dlp/extractor/aljazeera.py
+83
View File
@@ -0,0 +1,83 @@
import json
from .common import InfoExtractor
from ..utils import (
try_get,
)
class AlJazeeraIE(InfoExtractor):
_VALID_URL = r'https?://(?P<base>\w+\.aljazeera\.\w+)/(?P<type>programs?/[^/]+|(?:feature|video|new)s)?/\d{4}/\d{1,2}/\d{1,2}/(?P<id>[^/?&#]+)'
_TESTS = [{
'url': 'https://balkans.aljazeera.net/videos/2021/11/6/pojedini-domovi-u-sarajevu-jos-pod-vodom-mjestanima-se-dostavlja-hrana',
'info_dict': {
'id': '6280641530001',
'ext': 'mp4',
'title': 'Pojedini domovi u Sarajevu još pod vodom, mještanima se dostavlja hrana',
'timestamp': 1636219149,
'description': 'U sarajevskim naseljima Rajlovac i Reljevo stambeni objekti, ali i industrijska postrojenja i dalje su pod vodom.',
'upload_date': '20211106',
}
}, {
'url': 'https://balkans.aljazeera.net/videos/2021/11/6/djokovic-usao-u-finale-mastersa-u-parizu',
'info_dict': {
'id': '6280654936001',
'ext': 'mp4',
'title': 'Đoković ušao u finale Mastersa u Parizu',
'timestamp': 1636221686,
'description': 'Novak Đoković je u polufinalu Mastersa u Parizu nakon preokreta pobijedio Poljaka Huberta Hurkacza.',
'upload_date': '20211106',
},
}]
BRIGHTCOVE_URL_RE = r'https?://players.brightcove.net/(?P<account>\d+)/(?P<player_id>[a-zA-Z0-9]+)_(?P<embed>[^/]+)/index.html\?videoId=(?P<id>\d+)'
def _real_extract(self, url):
base, post_type, id = self._match_valid_url(url).groups()
wp = {
'balkans.aljazeera.net': 'ajb',
'chinese.aljazeera.net': 'chinese',
'mubasher.aljazeera.net': 'ajm',
}.get(base) or 'aje'
post_type = {
'features': 'post',
'program': 'episode',
'programs': 'episode',
'videos': 'video',
'news': 'news',
}[post_type.split('/')[0]]
video = self._download_json(
f'https://{base}/graphql', id, query={
'wp-site': wp,
'operationName': 'ArchipelagoSingleArticleQuery',
'variables': json.dumps({
'name': id,
'postType': post_type,
}),
}, headers={
'wp-site': wp,
})
video = try_get(video, lambda x: x['data']['article']['video']) or {}
video_id = video.get('id')
account = video.get('accountId') or '911432371001'
player_id = video.get('playerId') or 'csvTfAlKW'
embed = 'default'
if video_id is None:
webpage = self._download_webpage(url, id)
account, player_id, embed, video_id = self._search_regex(self.BRIGHTCOVE_URL_RE, webpage, 'video id',
group=(1, 2, 3, 4), default=(None, None, None, None))
if video_id is None:
return {
'_type': 'url_transparent',
'url': url,
'ie_key': 'Generic'
}
return {
'_type': 'url_transparent',
'url': f'https://players.brightcove.net/{account}/{player_id}_{embed}/index.html?videoId={video_id}',
'ie_key': 'BrightcoveNew'
}
yt_dlp/extractor/allocine.py
+125
View File
@@ -0,0 +1,125 @@
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
int_or_none,
qualities,
remove_end,
strip_or_none,
try_get,
unified_timestamp,
url_basename,
)
class AllocineIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?allocine\.fr/(?:article|video|film)/(?:fichearticle_gen_carticle=|player_gen_cmedia=|fichefilm_gen_cfilm=|video-)(?P<id>[0-9]+)(?:\.html)?'
_TESTS = [{
'url': 'http://www.allocine.fr/article/fichearticle_gen_carticle=18635087.html',
'md5': '0c9fcf59a841f65635fa300ac43d8269',
'info_dict': {
'id': '19546517',
'display_id': '18635087',
'ext': 'mp4',
'title': 'Astérix - Le Domaine des Dieux Teaser VF',
'description': 'md5:4a754271d9c6f16c72629a8a993ee884',
'thumbnail': r're:http://.*\.jpg',
'duration': 39,
'timestamp': 1404273600,
'upload_date': '20140702',
'view_count': int,
},
}, {
'url': 'http://www.allocine.fr/video/player_gen_cmedia=19540403&cfilm=222257.html',
'md5': 'd0cdce5d2b9522ce279fdfec07ff16e0',
'info_dict': {
'id': '19540403',
'display_id': '19540403',
'ext': 'mp4',
'title': 'Planes 2 Bande-annonce VF',
'description': 'Regardez la bande annonce du film Planes 2 (Planes 2 Bande-annonce VF). Planes 2, un film de Roberts Gannaway',
'thumbnail': r're:http://.*\.jpg',
'duration': 69,
'timestamp': 1385659800,
'upload_date': '20131128',
'view_count': int,
},
}, {
'url': 'http://www.allocine.fr/video/player_gen_cmedia=19544709&cfilm=181290.html',
'md5': '101250fb127ef9ca3d73186ff22a47ce',
'info_dict': {
'id': '19544709',
'display_id': '19544709',
'ext': 'mp4',
'title': 'Dragons 2 - Bande annonce finale VF',
'description': 'md5:6cdd2d7c2687d4c6aafe80a35e17267a',
'thumbnail': r're:http://.*\.jpg',
'duration': 144,
'timestamp': 1397589900,
'upload_date': '20140415',
'view_count': int,
},
}, {
'url': 'http://www.allocine.fr/video/video-19550147/',
'md5': '3566c0668c0235e2d224fd8edb389f67',
'info_dict': {
'id': '19550147',
'ext': 'mp4',
'title': 'Faux Raccord N°123 - Les gaffes de Cliffhanger',
'description': 'md5:bc734b83ffa2d8a12188d9eb48bb6354',
'thumbnail': r're:http://.*\.jpg',
},
}]
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
formats = []
quality = qualities(['ld', 'md', 'hd'])
model = self._html_search_regex(
r'data-model="([^"]+)"', webpage, 'data model', default=None)
if model:
model_data = self._parse_json(model, display_id)
video = model_data['videos'][0]
title = video['title']
for video_url in video['sources'].values():
video_id, format_id = url_basename(video_url).split('_')[:2]
formats.append({
'format_id': format_id,
'quality': quality(format_id),
'url': video_url,
})
duration = int_or_none(video.get('duration'))
view_count = int_or_none(video.get('view_count'))
timestamp = unified_timestamp(try_get(
video, lambda x: x['added_at']['date'], compat_str))
else:
video_id = display_id
media_data = self._download_json(
'http://www.allocine.fr/ws/AcVisiondataV5.ashx?media=%s' % video_id, display_id)
title = remove_end(strip_or_none(self._html_extract_title(webpage), ' - AlloCiné'))
for key, value in media_data['video'].items():
if not key.endswith('Path'):
continue
format_id = key[:-len('Path')]
formats.append({
'format_id': format_id,
'quality': quality(format_id),
'url': value,
})
duration, view_count, timestamp = [None] * 3
return {
'id': video_id,
'display_id': display_id,
'title': title,
'description': self._og_search_description(webpage),
'thumbnail': self._og_search_thumbnail(webpage),
'duration': duration,
'timestamp': timestamp,
'view_count': view_count,
'formats': formats,
}
yt_dlp/extractor/alphaporno.py
+75
View File
@@ -0,0 +1,75 @@
from .common import InfoExtractor
from ..utils import (
parse_iso8601,
parse_duration,
parse_filesize,
int_or_none,
)
class AlphaPornoIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?alphaporno\.com/videos/(?P<id>[^/]+)'
_TEST = {
'url': 'http://www.alphaporno.com/videos/sensual-striptease-porn-with-samantha-alexandra/',
'md5': 'feb6d3bba8848cd54467a87ad34bd38e',
'info_dict': {
'id': '258807',
'display_id': 'sensual-striptease-porn-with-samantha-alexandra',
'ext': 'mp4',
'title': 'Sensual striptease porn with Samantha Alexandra',
'thumbnail': r're:https?://.*\.jpg$',
'timestamp': 1418694611,
'upload_date': '20141216',
'duration': 387,
'filesize_approx': 54120000,
'tbr': 1145,
'categories': list,
'age_limit': 18,
}
}
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
video_id = self._search_regex(
r"video_id\s*:\s*'([^']+)'", webpage, 'video id', default=None)
video_url = self._search_regex(
r"video_url\s*:\s*'([^']+)'", webpage, 'video url')
ext = self._html_search_meta(
'encodingFormat', webpage, 'ext', default='.mp4')[1:]
title = self._search_regex(
[r'<meta content="([^"]+)" itemprop="description">',
r'class="title" itemprop="name">([^<]+)<'],
webpage, 'title')
thumbnail = self._html_search_meta('thumbnail', webpage, 'thumbnail')
timestamp = parse_iso8601(self._html_search_meta(
'uploadDate', webpage, 'upload date'))
duration = parse_duration(self._html_search_meta(
'duration', webpage, 'duration'))
filesize_approx = parse_filesize(self._html_search_meta(
'contentSize', webpage, 'file size'))
bitrate = int_or_none(self._html_search_meta(
'bitrate', webpage, 'bitrate'))
categories = self._html_search_meta(
'keywords', webpage, 'categories', default='').split(',')
age_limit = self._rta_search(webpage)
return {
'id': video_id,
'display_id': display_id,
'url': video_url,
'ext': ext,
'title': title,
'thumbnail': thumbnail,
'timestamp': timestamp,
'duration': duration,
'filesize_approx': filesize_approx,
'tbr': bitrate,
'categories': categories,
'age_limit': age_limit,
}
yt_dlp/extractor/alsace20tv.py
+83
View File
@@ -0,0 +1,83 @@
from .common import InfoExtractor
from ..utils import (
clean_html,
dict_get,
get_element_by_class,
int_or_none,
unified_strdate,
url_or_none,
)
class Alsace20TVBaseIE(InfoExtractor):
def _extract_video(self, video_id, url=None):
info = self._download_json(
'https://www.alsace20.tv/visionneuse/visio_v9_js.php?key=%s&habillage=0&mode=html' % (video_id, ),
video_id) or {}
title = info.get('titre')
formats = []
for res, fmt_url in (info.get('files') or {}).items():
formats.extend(
self._extract_smil_formats(fmt_url, video_id, fatal=False)
if '/smil:_' in fmt_url
else self._extract_mpd_formats(fmt_url, video_id, mpd_id=res, fatal=False))
webpage = (url and self._download_webpage(url, video_id, fatal=False)) or ''
thumbnail = url_or_none(dict_get(info, ('image', 'preview', )) or self._og_search_thumbnail(webpage))
upload_date = self._search_regex(r'/(\d{6})_', thumbnail, 'upload_date', default=None)
upload_date = unified_strdate('20%s-%s-%s' % (upload_date[:2], upload_date[2:4], upload_date[4:])) if upload_date else None
return {
'id': video_id,
'title': title,
'formats': formats,
'description': clean_html(get_element_by_class('wysiwyg', webpage)),
'upload_date': upload_date,
'thumbnail': thumbnail,
'duration': int_or_none(self._og_search_property('video:duration', webpage) if webpage else None),
'view_count': int_or_none(info.get('nb_vues')),
}
class Alsace20TVIE(Alsace20TVBaseIE):
_VALID_URL = r'https?://(?:www\.)?alsace20\.tv/(?:[\w-]+/)+[\w-]+-(?P<id>[\w]+)'
_TESTS = [{
'url': 'https://www.alsace20.tv/VOD/Actu/JT/Votre-JT-jeudi-3-fevrier-lyNHCXpYJh.html',
'info_dict': {
'id': 'lyNHCXpYJh',
'ext': 'mp4',
'description': 'md5:fc0bc4a0692d3d2dba4524053de4c7b7',
'title': 'Votre JT du jeudi 3 février',
'upload_date': '20220203',
'thumbnail': r're:https?://.+\.jpg',
'duration': 1073,
'view_count': int,
},
}]
def _real_extract(self, url):
video_id = self._match_id(url)
return self._extract_video(video_id, url)
class Alsace20TVEmbedIE(Alsace20TVBaseIE):
_VALID_URL = r'https?://(?:www\.)?alsace20\.tv/emb/(?P<id>[\w]+)'
_TESTS = [{
'url': 'https://www.alsace20.tv/emb/lyNHCXpYJh',
# 'md5': 'd91851bf9af73c0ad9b2cdf76c127fbb',
'info_dict': {
'id': 'lyNHCXpYJh',
'ext': 'mp4',
'title': 'Votre JT du jeudi 3 février',
'upload_date': '20220203',
'thumbnail': r're:https?://.+\.jpg',
'view_count': int,
},
'params': {
'format': 'bestvideo',
},
}]
def _real_extract(self, url):
video_id = self._match_id(url)
return self._extract_video(video_id)
yt_dlp/extractor/alura.py
+167
View File
@@ -0,0 +1,167 @@
import re
from .common import InfoExtractor
from ..compat import (
compat_urlparse,
)
from ..utils import (
urlencode_postdata,
urljoin,
int_or_none,
clean_html,
ExtractorError
)
class AluraIE(InfoExtractor):
_VALID_URL = r'https?://(?:cursos\.)?alura\.com\.br/course/(?P<course_name>[^/]+)/task/(?P<id>\d+)'
_LOGIN_URL = 'https://cursos.alura.com.br/loginForm?urlAfterLogin=/loginForm'
_VIDEO_URL = 'https://cursos.alura.com.br/course/%s/task/%s/video'
_NETRC_MACHINE = 'alura'
_TESTS = [{
'url': 'https://cursos.alura.com.br/course/clojure-mutabilidade-com-atoms-e-refs/task/60095',
'info_dict': {
'id': '60095',
'ext': 'mp4',
'title': 'Referências, ref-set e alter'
},
'skip': 'Requires alura account credentials'},
{
# URL without video
'url': 'https://cursos.alura.com.br/course/clojure-mutabilidade-com-atoms-e-refs/task/60098',
'only_matching': True},
{
'url': 'https://cursos.alura.com.br/course/fundamentos-market-digital/task/55219',
'only_matching': True}
]
def _real_extract(self, url):
course, video_id = self._match_valid_url(url)
video_url = self._VIDEO_URL % (course, video_id)
video_dict = self._download_json(video_url, video_id, 'Searching for videos')
if video_dict:
webpage = self._download_webpage(url, video_id)
video_title = clean_html(self._search_regex(
r'<span[^>]+class=(["\'])task-body-header-title-text\1[^>]*>(?P<title>[^<]+)',
webpage, 'title', group='title'))
formats = []
for video_obj in video_dict:
video_url_m3u8 = video_obj.get('link')
video_format = self._extract_m3u8_formats(
video_url_m3u8, None, 'mp4', entry_protocol='m3u8_native',
m3u8_id='hls', fatal=False)
for f in video_format:
m = re.search(r'^[\w \W]*-(?P<res>\w*).mp4[\W \w]*', f['url'])
if m:
if not f.get('height'):
f['height'] = int('720' if m.group('res') == 'hd' else '480')
formats.extend(video_format)
return {
'id': video_id,
'title': video_title,
"formats": formats
}
def _perform_login(self, username, password):
login_page = self._download_webpage(
self._LOGIN_URL, None, 'Downloading login popup')
def is_logged(webpage):
return any(re.search(p, webpage) for p in (
r'href=[\"|\']?/signout[\"|\']',
r'>Logout<'))
# already logged in
if is_logged(login_page):
return
login_form = self._hidden_inputs(login_page)
login_form.update({
'username': username,
'password': password,
})
post_url = self._search_regex(
r'<form[^>]+class=["|\']signin-form["|\'] action=["|\'](?P<url>.+?)["|\']', login_page,
'post url', default=self._LOGIN_URL, group='url')
if not post_url.startswith('http'):
post_url = compat_urlparse.urljoin(self._LOGIN_URL, post_url)
response = self._download_webpage(
post_url, None, 'Logging in',
data=urlencode_postdata(login_form),
headers={'Content-Type': 'application/x-www-form-urlencoded'})
if not is_logged(response):
error = self._html_search_regex(
r'(?s)<p[^>]+class="alert-message[^"]*">(.+?)</p>',
response, 'error message', default=None)
if error:
raise ExtractorError('Unable to login: %s' % error, expected=True)
raise ExtractorError('Unable to log in')
class AluraCourseIE(AluraIE): # XXX: Do not subclass from concrete IE
_VALID_URL = r'https?://(?:cursos\.)?alura\.com\.br/course/(?P<id>[^/]+)'
_LOGIN_URL = 'https://cursos.alura.com.br/loginForm?urlAfterLogin=/loginForm'
_NETRC_MACHINE = 'aluracourse'
_TESTS = [{
'url': 'https://cursos.alura.com.br/course/clojure-mutabilidade-com-atoms-e-refs',
'only_matching': True,
}]
@classmethod
def suitable(cls, url):
return False if AluraIE.suitable(url) else super(AluraCourseIE, cls).suitable(url)
def _real_extract(self, url):
course_path = self._match_id(url)
webpage = self._download_webpage(url, course_path)
course_title = self._search_regex(
r'<h1.*?>(.*?)<strong>(?P<course_title>.*?)</strong></h[0-9]>', webpage,
'course title', default=course_path, group='course_title')
entries = []
if webpage:
for path in re.findall(r'<a\b(?=[^>]* class="[^"]*(?<=[" ])courseSectionList-section[" ])(?=[^>]* href="([^"]*))', webpage):
page_url = urljoin(url, path)
section_path = self._download_webpage(page_url, course_path)
for path_video in re.findall(r'<a\b(?=[^>]* class="[^"]*(?<=[" ])task-menu-nav-item-link-VIDEO[" ])(?=[^>]* href="([^"]*))', section_path):
chapter = clean_html(
self._search_regex(
r'<h3[^>]+class=(["\'])task-menu-section-title-text\1[^>]*>(?P<chapter>[^<]+)',
section_path,
'chapter',
group='chapter'))
chapter_number = int_or_none(
self._search_regex(
r'<span[^>]+class=(["\'])task-menu-section-title-number[^>]*>(.*?)<strong>(?P<chapter_number>[^<]+)</strong>',
section_path,
'chapter number',
group='chapter_number'))
video_url = urljoin(url, path_video)
entry = {
'_type': 'url_transparent',
'id': self._match_id(video_url),
'url': video_url,
'id_key': self.ie_key(),
'chapter': chapter,
'chapter_number': chapter_number
}
entries.append(entry)
return self.playlist_result(entries, course_path, course_title)
yt_dlp/extractor/amara.py
+100
View File
@@ -0,0 +1,100 @@
from .common import InfoExtractor
from .youtube import YoutubeIE
from .vimeo import VimeoIE
from ..utils import (
int_or_none,
parse_iso8601,
update_url_query,
)
class AmaraIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?amara\.org/(?:\w+/)?videos/(?P<id>\w+)'
_TESTS = [{
# Youtube
'url': 'https://amara.org/en/videos/jVx79ZKGK1ky/info/why-jury-trials-are-becoming-less-common/?tab=video',
'md5': 'ea10daf2b6154b8c1ecf9922aca5e8ae',
'info_dict': {
'id': 'h6ZuVdvYnfE',
'ext': 'mp4',
'title': 'Why jury trials are becoming less common',
'description': 'md5:a61811c319943960b6ab1c23e0cbc2c1',
'thumbnail': r're:^https?://.*\.jpg$',
'subtitles': dict,
'upload_date': '20160813',
'uploader': 'PBS NewsHour',
'uploader_id': 'PBSNewsHour',
'timestamp': 1549639570,
}
}, {
# Vimeo
'url': 'https://amara.org/en/videos/kYkK1VUTWW5I/info/vimeo-at-ces-2011',
'md5': '99392c75fa05d432a8f11df03612195e',
'info_dict': {
'id': '18622084',
'ext': 'mov',
'title': 'Vimeo at CES 2011!',
'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
'thumbnail': r're:^https?://.*\.jpg$',
'subtitles': dict,
'timestamp': 1294763658,
'upload_date': '20110111',
'uploader': 'Sam Morrill',
'uploader_id': 'sammorrill'
}
}, {
# Direct Link
'url': 'https://amara.org/en/videos/s8KL7I3jLmh6/info/the-danger-of-a-single-story/',
'md5': 'd3970f08512738ee60c5807311ff5d3f',
'info_dict': {
'id': 's8KL7I3jLmh6',
'ext': 'mp4',
'title': 'The danger of a single story',
'description': 'md5:d769b31139c3b8bb5be9177f62ea3f23',
'thumbnail': r're:^https?://.*\.jpg$',
'subtitles': dict,
'upload_date': '20091007',
'timestamp': 1254942511,
}
}]
def _real_extract(self, url):
video_id = self._match_id(url)
meta = self._download_json(
'https://amara.org/api/videos/%s/' % video_id,
video_id, query={'format': 'json'})
title = meta['title']
video_url = meta['all_urls'][0]
subtitles = {}
for language in (meta.get('languages') or []):
subtitles_uri = language.get('subtitles_uri')
if not (subtitles_uri and language.get('published')):
continue
subtitle = subtitles.setdefault(language.get('code') or 'en', [])
for f in ('json', 'srt', 'vtt'):
subtitle.append({
'ext': f,
'url': update_url_query(subtitles_uri, {'format': f}),
})
info = {
'url': video_url,
'id': video_id,
'subtitles': subtitles,
'title': title,
'description': meta.get('description'),
'thumbnail': meta.get('thumbnail'),
'duration': int_or_none(meta.get('duration')),
'timestamp': parse_iso8601(meta.get('created')),
}
for ie in (YoutubeIE, VimeoIE):
if ie.suitable(video_url):
info.update({
'_type': 'url_transparent',
'ie_key': ie.ie_key(),
})
break
return info
yt_dlp/extractor/amazon.py
+170
View File
@@ -0,0 +1,170 @@
import re
from .common import InfoExtractor
from ..utils import (
ExtractorError,
clean_html,
float_or_none,
get_element_by_attribute,
get_element_by_class,
int_or_none,
js_to_json,
traverse_obj,
url_or_none,
)
class AmazonStoreIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?amazon\.(?:[a-z]{2,3})(?:\.[a-z]{2})?/(?:[^/]+/)?(?:dp|gp/product)/(?P<id>[^/&#$?]+)'
_TESTS = [{
'url': 'https://www.amazon.co.uk/dp/B098XNCHLD/',
'info_dict': {
'id': 'B098XNCHLD',
'title': str,
},
'playlist_mincount': 1,
'playlist': [{
'info_dict': {
'id': 'A1F83G8C2ARO7P',
'ext': 'mp4',
'title': 'mcdodo usb c cable 100W 5a',
'thumbnail': r're:^https?://.*\.jpg$',
'duration': 34,
},
}],
'expected_warnings': ['Unable to extract data'],
}, {
'url': 'https://www.amazon.in/Sony-WH-1000XM4-Cancelling-Headphones-Bluetooth/dp/B0863TXGM3',
'info_dict': {
'id': 'B0863TXGM3',
'title': str,
},
'playlist_mincount': 4,
'expected_warnings': ['Unable to extract data'],
}, {
'url': 'https://www.amazon.com/dp/B0845NXCXF/',
'info_dict': {
'id': 'B0845NXCXF',
'title': str,
},
'playlist-mincount': 1,
'expected_warnings': ['Unable to extract data'],
}, {
'url': 'https://www.amazon.es/Samsung-Smartphone-s-AMOLED-Quad-c%C3%A1mara-espa%C3%B1ola/dp/B08WX337PQ',
'info_dict': {
'id': 'B08WX337PQ',
'title': str,
},
'playlist_mincount': 1,
'expected_warnings': ['Unable to extract data'],
}]
def _real_extract(self, url):
id = self._match_id(url)
for retry in self.RetryManager():
webpage = self._download_webpage(url, id)
try:
data_json = self._search_json(
r'var\s?obj\s?=\s?jQuery\.parseJSON\(\'', webpage, 'data', id,
transform_source=js_to_json)
except ExtractorError as e:
retry.error = e
entries = [{
'id': video['marketPlaceID'],
'url': video['url'],
'title': video.get('title'),
'thumbnail': video.get('thumbUrl') or video.get('thumb'),
'duration': video.get('durationSeconds'),
'height': int_or_none(video.get('videoHeight')),
'width': int_or_none(video.get('videoWidth')),
} for video in (data_json.get('videos') or []) if video.get('isVideo') and video.get('url')]
return self.playlist_result(entries, playlist_id=id, playlist_title=data_json.get('title'))
class AmazonReviewsIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?amazon\.(?:[a-z]{2,3})(?:\.[a-z]{2})?/gp/customer-reviews/(?P<id>[^/&#$?]+)'
_TESTS = [{
'url': 'https://www.amazon.com/gp/customer-reviews/R10VE9VUSY19L3/ref=cm_cr_arp_d_rvw_ttl',
'info_dict': {
'id': 'R10VE9VUSY19L3',
'ext': 'mp4',
'title': 'Get squad #Suspicious',
'description': 'md5:7012695052f440a1e064e402d87e0afb',
'uploader': 'Kimberly Cronkright',
'average_rating': 1.0,
'thumbnail': r're:^https?://.*\.jpg$',
},
'expected_warnings': ['Review body was not found in webpage'],
}, {
'url': 'https://www.amazon.com/gp/customer-reviews/R10VE9VUSY19L3/ref=cm_cr_arp_d_rvw_ttl?language=es_US',
'info_dict': {
'id': 'R10VE9VUSY19L3',
'ext': 'mp4',
'title': 'Get squad #Suspicious',
'description': 'md5:7012695052f440a1e064e402d87e0afb',
'uploader': 'Kimberly Cronkright',
'average_rating': 1.0,
'thumbnail': r're:^https?://.*\.jpg$',
},
'expected_warnings': ['Review body was not found in webpage'],
}, {
'url': 'https://www.amazon.in/gp/customer-reviews/RV1CO8JN5VGXV/',
'info_dict': {
'id': 'RV1CO8JN5VGXV',
'ext': 'mp4',
'title': 'Not sure about its durability',
'description': 'md5:1a252c106357f0a3109ebf37d2e87494',
'uploader': 'Shoaib Gulzar',
'average_rating': 2.0,
'thumbnail': r're:^https?://.*\.jpg$',
},
'expected_warnings': ['Review body was not found in webpage'],
}]
def _real_extract(self, url):
video_id = self._match_id(url)
for retry in self.RetryManager():
webpage = self._download_webpage(url, video_id)
review_body = get_element_by_attribute('data-hook', 'review-body', webpage)
if not review_body:
retry.error = ExtractorError('Review body was not found in webpage', expected=True)
formats, subtitles = [], {}
manifest_url = self._search_regex(
r'data-video-url="([^"]+)"', review_body, 'm3u8 url', default=None)
if url_or_none(manifest_url):
fmts, subtitles = self._extract_m3u8_formats_and_subtitles(
manifest_url, video_id, 'mp4', fatal=False)
formats.extend(fmts)
video_url = self._search_regex(
r'<input[^>]+\bvalue="([^"]+)"[^>]+\bclass="video-url"', review_body, 'mp4 url', default=None)
if url_or_none(video_url):
formats.append({
'url': video_url,
'ext': 'mp4',
'format_id': 'http-mp4',
})
if not formats:
self.raise_no_formats('No video found for this customer review', expected=True)
return {
'id': video_id,
'title': (clean_html(get_element_by_attribute('data-hook', 'review-title', webpage))
or self._html_extract_title(webpage)),
'description': clean_html(traverse_obj(re.findall(
r'<span(?:\s+class="cr-original-review-content")?>(.+?)</span>', review_body), -1)),
'uploader': clean_html(get_element_by_class('a-profile-name', webpage)),
'average_rating': float_or_none(clean_html(get_element_by_attribute(
'data-hook', 'review-star-rating', webpage) or '').partition(' ')[0]),
'thumbnail': self._search_regex(
r'data-thumbnail-url="([^"]+)"', review_body, 'thumbnail', default=None),
'formats': formats,
'subtitles': subtitles,
}
yt_dlp/extractor/amazonminitv.py
+291
View File
@@ -0,0 +1,291 @@
import json
from .common import InfoExtractor
from ..utils import ExtractorError, int_or_none, traverse_obj, try_get
class AmazonMiniTVBaseIE(InfoExtractor):
def _real_initialize(self):
self._download_webpage(
'https://www.amazon.in/minitv', None,
note='Fetching guest session cookies')
AmazonMiniTVBaseIE.session_id = self._get_cookies('https://www.amazon.in')['session-id'].value
def _call_api(self, asin, data=None, note=None):
device = {'clientId': 'ATVIN', 'deviceLocale': 'en_GB'}
if data:
data['variables'].update({
'contentType': 'VOD',
'sessionIdToken': self.session_id,
**device,
})
resp = self._download_json(
f'https://www.amazon.in/minitv/api/web/{"graphql" if data else "prs"}',
asin, note=note, headers={'Content-Type': 'application/json'},
data=json.dumps(data).encode() if data else None,
query=None if data else {
'deviceType': 'A1WMMUXPCUJL4N',
'contentId': asin,
**device,
})
if resp.get('errors'):
raise ExtractorError(f'MiniTV said: {resp["errors"][0]["message"]}')
elif not data:
return resp
return resp['data'][data['operationName']]
class AmazonMiniTVIE(AmazonMiniTVBaseIE):
_VALID_URL = r'(?:https?://(?:www\.)?amazon\.in/minitv/tp/|amazonminitv:(?:amzn1\.dv\.gti\.)?)(?P<id>[a-f0-9-]+)'
_TESTS = [{
'url': 'https://www.amazon.in/minitv/tp/75fe3a75-b8fe-4499-8100-5c9424344840?referrer=https%3A%2F%2Fwww.amazon.in%2Fminitv',
'info_dict': {
'id': 'amzn1.dv.gti.75fe3a75-b8fe-4499-8100-5c9424344840',
'ext': 'mp4',
'title': 'May I Kiss You?',
'language': 'Hindi',
'thumbnail': r're:^https?://.*\.jpg$',
'description': 'md5:a549bfc747973e04feb707833474e59d',
'release_timestamp': 1644710400,
'release_date': '20220213',
'duration': 846,
'chapters': 'count:2',
'series': 'Couple Goals',
'series_id': 'amzn1.dv.gti.56521d46-b040-4fd5-872e-3e70476a04b0',
'season': 'Season 3',
'season_number': 3,
'season_id': 'amzn1.dv.gti.20331016-d9b9-4968-b991-c89fa4927a36',
'episode': 'May I Kiss You?',
'episode_number': 2,
'episode_id': 'amzn1.dv.gti.75fe3a75-b8fe-4499-8100-5c9424344840',
},
}, {
'url': 'https://www.amazon.in/minitv/tp/280d2564-584f-452f-9c98-7baf906e01ab?referrer=https%3A%2F%2Fwww.amazon.in%2Fminitv',
'info_dict': {
'id': 'amzn1.dv.gti.280d2564-584f-452f-9c98-7baf906e01ab',
'ext': 'mp4',
'title': 'Jahaan',
'language': 'Hindi',
'thumbnail': r're:^https?://.*\.jpg',
'description': 'md5:05eb765a77bf703f322f120ec6867339',
'release_timestamp': 1647475200,
'release_date': '20220317',
'duration': 783,
'chapters': [],
},
}, {
'url': 'https://www.amazon.in/minitv/tp/280d2564-584f-452f-9c98-7baf906e01ab',
'only_matching': True,
}, {
'url': 'amazonminitv:amzn1.dv.gti.280d2564-584f-452f-9c98-7baf906e01ab',
'only_matching': True,
}, {
'url': 'amazonminitv:280d2564-584f-452f-9c98-7baf906e01ab',
'only_matching': True,
}]
_GRAPHQL_QUERY_CONTENT = '''
query content($sessionIdToken: String!, $deviceLocale: String, $contentId: ID!, $contentType: ContentType!, $clientId: String) {
content(
applicationContextInput: {deviceLocale: $deviceLocale, sessionIdToken: $sessionIdToken, clientId: $clientId}
contentId: $contentId
contentType: $contentType
) {
contentId
name
... on Episode {
contentId
vodType
name
images
description {
synopsis
contentLengthInSeconds
}
publicReleaseDateUTC
audioTracks
seasonId
seriesId
seriesName
seasonNumber
episodeNumber
timecode {
endCreditsTime
}
}
... on MovieContent {
contentId
vodType
name
description {
synopsis
contentLengthInSeconds
}
images
publicReleaseDateUTC
audioTracks
}
}
}'''
def _real_extract(self, url):
asin = f'amzn1.dv.gti.{self._match_id(url)}'
prs = self._call_api(asin, note='Downloading playback info')
formats, subtitles = [], {}
for type_, asset in prs['playbackAssets'].items():
if not traverse_obj(asset, 'manifestUrl'):
continue
if type_ == 'hls':
m3u8_fmts, m3u8_subs = self._extract_m3u8_formats_and_subtitles(
asset['manifestUrl'], asin, ext='mp4', entry_protocol='m3u8_native',
m3u8_id=type_, fatal=False)
formats.extend(m3u8_fmts)
subtitles = self._merge_subtitles(subtitles, m3u8_subs)
elif type_ == 'dash':
mpd_fmts, mpd_subs = self._extract_mpd_formats_and_subtitles(
asset['manifestUrl'], asin, mpd_id=type_, fatal=False)
formats.extend(mpd_fmts)
subtitles = self._merge_subtitles(subtitles, mpd_subs)
else:
self.report_warning(f'Unknown asset type: {type_}')
title_info = self._call_api(
asin, note='Downloading title info', data={
'operationName': 'content',
'variables': {'contentId': asin},
'query': self._GRAPHQL_QUERY_CONTENT,
})
credits_time = try_get(title_info, lambda x: x['timecode']['endCreditsTime'] / 1000)
is_episode = title_info.get('vodType') == 'EPISODE'
return {
'id': asin,
'title': title_info.get('name'),
'formats': formats,
'subtitles': subtitles,
'language': traverse_obj(title_info, ('audioTracks', 0)),
'thumbnails': [{
'id': type_,
'url': url,
} for type_, url in (title_info.get('images') or {}).items()],
'description': traverse_obj(title_info, ('description', 'synopsis')),
'release_timestamp': int_or_none(try_get(title_info, lambda x: x['publicReleaseDateUTC'] / 1000)),
'duration': traverse_obj(title_info, ('description', 'contentLengthInSeconds')),
'chapters': [{
'start_time': credits_time,
'title': 'End Credits',
}] if credits_time else [],
'series': title_info.get('seriesName'),
'series_id': title_info.get('seriesId'),
'season_number': title_info.get('seasonNumber'),
'season_id': title_info.get('seasonId'),
'episode': title_info.get('name') if is_episode else None,
'episode_number': title_info.get('episodeNumber'),
'episode_id': asin if is_episode else None,
}
class AmazonMiniTVSeasonIE(AmazonMiniTVBaseIE):
IE_NAME = 'amazonminitv:season'
_VALID_URL = r'amazonminitv:season:(?:amzn1\.dv\.gti\.)?(?P<id>[a-f0-9-]+)'
IE_DESC = 'Amazon MiniTV Season, "minitv:season:" prefix'
_TESTS = [{
'url': 'amazonminitv:season:amzn1.dv.gti.0aa996eb-6a1b-4886-a342-387fbd2f1db0',
'playlist_mincount': 6,
'info_dict': {
'id': 'amzn1.dv.gti.0aa996eb-6a1b-4886-a342-387fbd2f1db0',
},
}, {
'url': 'amazonminitv:season:0aa996eb-6a1b-4886-a342-387fbd2f1db0',
'only_matching': True,
}]
_GRAPHQL_QUERY = '''
query getEpisodes($sessionIdToken: String!, $clientId: String, $episodeOrSeasonId: ID!, $deviceLocale: String) {
getEpisodes(
applicationContextInput: {sessionIdToken: $sessionIdToken, deviceLocale: $deviceLocale, clientId: $clientId}
episodeOrSeasonId: $episodeOrSeasonId
) {
episodes {
... on Episode {
contentId
name
images
seriesName
seasonId
seriesId
seasonNumber
episodeNumber
description {
synopsis
contentLengthInSeconds
}
publicReleaseDateUTC
}
}
}
}
'''
def _entries(self, asin):
season_info = self._call_api(
asin, note='Downloading season info', data={
'operationName': 'getEpisodes',
'variables': {'episodeOrSeasonId': asin},
'query': self._GRAPHQL_QUERY,
})
for episode in season_info['episodes']:
yield self.url_result(
f'amazonminitv:{episode["contentId"]}', AmazonMiniTVIE, episode['contentId'])
def _real_extract(self, url):
asin = f'amzn1.dv.gti.{self._match_id(url)}'
return self.playlist_result(self._entries(asin), asin)
class AmazonMiniTVSeriesIE(AmazonMiniTVBaseIE):
IE_NAME = 'amazonminitv:series'
_VALID_URL = r'amazonminitv:series:(?:amzn1\.dv\.gti\.)?(?P<id>[a-f0-9-]+)'
IE_DESC = 'Amazon MiniTV Series, "minitv:series:" prefix'
_TESTS = [{
'url': 'amazonminitv:series:amzn1.dv.gti.56521d46-b040-4fd5-872e-3e70476a04b0',
'playlist_mincount': 3,
'info_dict': {
'id': 'amzn1.dv.gti.56521d46-b040-4fd5-872e-3e70476a04b0',
},
}, {
'url': 'amazonminitv:series:56521d46-b040-4fd5-872e-3e70476a04b0',
'only_matching': True,
}]
_GRAPHQL_QUERY = '''
query getSeasons($sessionIdToken: String!, $deviceLocale: String, $episodeOrSeasonOrSeriesId: ID!, $clientId: String) {
getSeasons(
applicationContextInput: {deviceLocale: $deviceLocale, sessionIdToken: $sessionIdToken, clientId: $clientId}
episodeOrSeasonOrSeriesId: $episodeOrSeasonOrSeriesId
) {
seasons {
seasonId
}
}
}
'''
def _entries(self, asin):
season_info = self._call_api(
asin, note='Downloading series info', data={
'operationName': 'getSeasons',
'variables': {'episodeOrSeasonOrSeriesId': asin},
'query': self._GRAPHQL_QUERY,
})
for season in season_info['seasons']:
yield self.url_result(f'amazonminitv:season:{season["seasonId"]}', AmazonMiniTVSeasonIE, season['seasonId'])
def _real_extract(self, url):
asin = f'amzn1.dv.gti.{self._match_id(url)}'
return self.playlist_result(self._entries(asin), asin)
yt_dlp/extractor/amcnetworks.py
+146
View File
@@ -0,0 +1,146 @@
import re
from .theplatform import ThePlatformIE
from ..utils import (
int_or_none,
parse_age_limit,
try_get,
update_url_query,
)
class AMCNetworksIE(ThePlatformIE): # XXX: Do not subclass from concrete IE
_VALID_URL = r'https?://(?:www\.)?(?P<site>amc|bbcamerica|ifc|(?:we|sundance)tv)\.com/(?P<id>(?:movies|shows(?:/[^/]+)+)/[^/?#&]+)'
_TESTS = [{
'url': 'https://www.bbcamerica.com/shows/the-graham-norton-show/videos/tina-feys-adorable-airline-themed-family-dinner--51631',
'info_dict': {
'id': '4Lq1dzOnZGt0',
'ext': 'mp4',
'title': "The Graham Norton Show - Season 28 - Tina Fey's Adorable Airline-Themed Family Dinner",
'description': "It turns out child stewardesses are very generous with the wine! All-new episodes of 'The Graham Norton Show' premiere Fridays at 11/10c on BBC America.",
'upload_date': '20201120',
'timestamp': 1605904350,
'uploader': 'AMCN',
},
'params': {
# m3u8 download
'skip_download': True,
},
}, {
'url': 'http://www.bbcamerica.com/shows/the-hunt/full-episodes/season-1/episode-01-the-hardest-challenge',
'only_matching': True,
}, {
'url': 'http://www.amc.com/shows/preacher/full-episodes/season-01/episode-00/pilot',
'only_matching': True,
}, {
'url': 'http://www.wetv.com/shows/million-dollar-matchmaker/season-01/episode-06-the-dumped-dj-and-shallow-hal',
'only_matching': True,
}, {
'url': 'http://www.ifc.com/movies/chaos',
'only_matching': True,
}, {
'url': 'http://www.bbcamerica.com/shows/doctor-who/full-episodes/the-power-of-the-daleks/episode-01-episode-1-color-version',
'only_matching': True,
}, {
'url': 'http://www.wetv.com/shows/mama-june-from-not-to-hot/full-episode/season-01/thin-tervention',
'only_matching': True,
}, {
'url': 'http://www.wetv.com/shows/la-hair/videos/season-05/episode-09-episode-9-2/episode-9-sneak-peek-3',
'only_matching': True,
}, {
'url': 'https://www.sundancetv.com/shows/riviera/full-episodes/season-1/episode-01-episode-1',
'only_matching': True,
}]
_REQUESTOR_ID_MAP = {
'amc': 'AMC',
'bbcamerica': 'BBCA',
'ifc': 'IFC',
'sundancetv': 'SUNDANCE',
'wetv': 'WETV',
}
def _real_extract(self, url):
site, display_id = self._match_valid_url(url).groups()
requestor_id = self._REQUESTOR_ID_MAP[site]
page_data = self._download_json(
'https://content-delivery-gw.svc.ds.amcn.com/api/v2/content/amcn/%s/url/%s'
% (requestor_id.lower(), display_id), display_id)['data']
properties = page_data.get('properties') or {}
query = {
'mbr': 'true',
'manifest': 'm3u',
}
video_player_count = 0
try:
for v in page_data['children']:
if v.get('type') == 'video-player':
releasePid = v['properties']['currentVideo']['meta']['releasePid']
tp_path = 'M_UwQC/' + releasePid
media_url = 'https://link.theplatform.com/s/' + tp_path
video_player_count += 1
except KeyError:
pass
if video_player_count > 1:
self.report_warning(
'The JSON data has %d video players. Only one will be extracted' % video_player_count)
# Fall back to videoPid if releasePid not found.
# TODO: Fall back to videoPid if releasePid manifest uses DRM.
if not video_player_count:
tp_path = 'M_UwQC/media/' + properties['videoPid']
media_url = 'https://link.theplatform.com/s/' + tp_path
theplatform_metadata = self._download_theplatform_metadata(tp_path, display_id)
info = self._parse_theplatform_metadata(theplatform_metadata)
video_id = theplatform_metadata['pid']
title = theplatform_metadata['title']
rating = try_get(
theplatform_metadata, lambda x: x['ratings'][0]['rating'])
video_category = properties.get('videoCategory')
if video_category and video_category.endswith('-Auth'):
resource = self._get_mvpd_resource(
requestor_id, title, video_id, rating)
query['auth'] = self._extract_mvpd_auth(
url, video_id, requestor_id, resource)
media_url = update_url_query(media_url, query)
formats, subtitles = self._extract_theplatform_smil(
media_url, video_id)
thumbnails = []
thumbnail_urls = [properties.get('imageDesktop')]
if 'thumbnail' in info:
thumbnail_urls.append(info.pop('thumbnail'))
for thumbnail_url in thumbnail_urls:
if not thumbnail_url:
continue
mobj = re.search(r'(\d+)x(\d+)', thumbnail_url)
thumbnails.append({
'url': thumbnail_url,
'width': int(mobj.group(1)) if mobj else None,
'height': int(mobj.group(2)) if mobj else None,
})
info.update({
'age_limit': parse_age_limit(rating),
'formats': formats,
'id': video_id,
'subtitles': subtitles,
'thumbnails': thumbnails,
})
ns_keys = theplatform_metadata.get('$xmlns', {}).keys()
if ns_keys:
ns = list(ns_keys)[0]
episode = theplatform_metadata.get(ns + '$episodeTitle') or None
episode_number = int_or_none(
theplatform_metadata.get(ns + '$episode'))
season_number = int_or_none(
theplatform_metadata.get(ns + '$season'))
series = theplatform_metadata.get(ns + '$show') or None
info.update({
'episode': episode,
'episode_number': episode_number,
'season_number': season_number,
'series': series,
})
return info
yt_dlp/extractor/americastestkitchen.py
+215
View File
@@ -0,0 +1,215 @@
import json
from .common import InfoExtractor
from ..utils import (
clean_html,
int_or_none,
try_get,
unified_strdate,
unified_timestamp,
)
class AmericasTestKitchenIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?(?:americastestkitchen|cooks(?:country|illustrated))\.com/(?:cooks(?:country|illustrated)/)?(?P<resource_type>episode|videos)/(?P<id>\d+)'
_TESTS = [{
'url': 'https://www.americastestkitchen.com/episode/582-weeknight-japanese-suppers',
'md5': 'b861c3e365ac38ad319cfd509c30577f',
'info_dict': {
'id': '5b400b9ee338f922cb06450c',
'title': 'Japanese Suppers',
'ext': 'mp4',
'display_id': 'weeknight-japanese-suppers',
'description': 'md5:64e606bfee910627efc4b5f050de92b3',
'timestamp': 1523304000,
'upload_date': '20180409',
'release_date': '20180409',
'series': 'America\'s Test Kitchen',
'season': 'Season 18',
'episode': 'Japanese Suppers',
'season_number': 18,
'episode_number': 15,
'duration': 1376,
'thumbnail': r're:^https?://',
'average_rating': 0,
'view_count': int,
},
'params': {
'skip_download': True,
},
}, {
# Metadata parsing behaves differently for newer episodes (705) as opposed to older episodes (582 above)
'url': 'https://www.americastestkitchen.com/episode/705-simple-chicken-dinner',
'md5': '06451608c57651e985a498e69cec17e5',
'info_dict': {
'id': '5fbe8c61bda2010001c6763b',
'title': 'Simple Chicken Dinner',
'ext': 'mp4',
'display_id': 'atktv_2103_simple-chicken-dinner_full-episode_web-mp4',
'description': 'md5:eb68737cc2fd4c26ca7db30139d109e7',
'timestamp': 1610737200,
'upload_date': '20210115',
'release_date': '20210115',
'series': 'America\'s Test Kitchen',
'season': 'Season 21',
'episode': 'Simple Chicken Dinner',
'season_number': 21,
'episode_number': 3,
'duration': 1397,
'thumbnail': r're:^https?://',
'view_count': int,
'average_rating': 0,
},
'params': {
'skip_download': True,
},
}, {
'url': 'https://www.americastestkitchen.com/videos/3420-pan-seared-salmon',
'only_matching': True,
}, {
'url': 'https://www.americastestkitchen.com/cookscountry/episode/564-when-only-chocolate-will-do',
'only_matching': True,
}, {
'url': 'https://www.americastestkitchen.com/cooksillustrated/videos/4478-beef-wellington',
'only_matching': True,
}, {
'url': 'https://www.cookscountry.com/episode/564-when-only-chocolate-will-do',
'only_matching': True,
}, {
'url': 'https://www.cooksillustrated.com/videos/4478-beef-wellington',
'only_matching': True,
}]
def _real_extract(self, url):
resource_type, video_id = self._match_valid_url(url).groups()
is_episode = resource_type == 'episode'
if is_episode:
resource_type = 'episodes'
resource = self._download_json(
'https://www.americastestkitchen.com/api/v6/%s/%s' % (resource_type, video_id), video_id)
video = resource['video'] if is_episode else resource
episode = resource if is_episode else resource.get('episode') or {}
return {
'_type': 'url_transparent',
'url': 'https://player.zype.com/embed/%s.js?api_key=jZ9GUhRmxcPvX7M3SlfejB6Hle9jyHTdk2jVxG7wOHPLODgncEKVdPYBhuz9iWXQ' % video['zypeId'],
'ie_key': 'Zype',
'description': clean_html(video.get('description')),
'timestamp': unified_timestamp(video.get('publishDate')),
'release_date': unified_strdate(video.get('publishDate')),
'episode_number': int_or_none(episode.get('number')),
'season_number': int_or_none(episode.get('season')),
'series': try_get(episode, lambda x: x['show']['title']),
'episode': episode.get('title'),
}
class AmericasTestKitchenSeasonIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?(?P<show>americastestkitchen|(?P<cooks>cooks(?:country|illustrated)))\.com(?:(?:/(?P<show2>cooks(?:country|illustrated)))?(?:/?$|(?<!ated)(?<!ated\.com)/episodes/browse/season_(?P<season>\d+)))'
_TESTS = [{
# ATK Season
'url': 'https://www.americastestkitchen.com/episodes/browse/season_1',
'info_dict': {
'id': 'season_1',
'title': 'Season 1',
},
'playlist_count': 13,
}, {
# Cooks Country Season
'url': 'https://www.americastestkitchen.com/cookscountry/episodes/browse/season_12',
'info_dict': {
'id': 'season_12',
'title': 'Season 12',
},
'playlist_count': 13,
}, {
# America's Test Kitchen Series
'url': 'https://www.americastestkitchen.com/',
'info_dict': {
'id': 'americastestkitchen',
'title': 'America\'s Test Kitchen',
},
'playlist_count': 558,
}, {
# Cooks Country Series
'url': 'https://www.americastestkitchen.com/cookscountry',
'info_dict': {
'id': 'cookscountry',
'title': 'Cook\'s Country',
},
'playlist_count': 199,
}, {
'url': 'https://www.americastestkitchen.com/cookscountry/',
'only_matching': True,
}, {
'url': 'https://www.cookscountry.com/episodes/browse/season_12',
'only_matching': True,
}, {
'url': 'https://www.cookscountry.com',
'only_matching': True,
}, {
'url': 'https://www.americastestkitchen.com/cooksillustrated/',
'only_matching': True,
}, {
'url': 'https://www.cooksillustrated.com',
'only_matching': True,
}]
def _real_extract(self, url):
season_number, show1, show = self._match_valid_url(url).group('season', 'show', 'show2')
show_path = ('/' + show) if show else ''
show = show or show1
season_number = int_or_none(season_number)
slug, title = {
'americastestkitchen': ('atk', 'America\'s Test Kitchen'),
'cookscountry': ('cco', 'Cook\'s Country'),
'cooksillustrated': ('cio', 'Cook\'s Illustrated'),
}[show]
facet_filters = [
'search_document_klass:episode',
'search_show_slug:' + slug,
]
if season_number:
playlist_id = 'season_%d' % season_number
playlist_title = 'Season %d' % season_number
facet_filters.append('search_season_list:' + playlist_title)
else:
playlist_id = show
playlist_title = title
season_search = self._download_json(
'https://y1fnzxui30-dsn.algolia.net/1/indexes/everest_search_%s_season_desc_production' % slug,
playlist_id, headers={
'Origin': 'https://www.americastestkitchen.com',
'X-Algolia-API-Key': '8d504d0099ed27c1b73708d22871d805',
'X-Algolia-Application-Id': 'Y1FNZXUI30',
}, query={
'facetFilters': json.dumps(facet_filters),
'attributesToRetrieve': 'description,search_%s_episode_number,search_document_date,search_url,title,search_atk_episode_season' % slug,
'attributesToHighlight': '',
'hitsPerPage': 1000,
})
def entries():
for episode in (season_search.get('hits') or []):
search_url = episode.get('search_url') # always formatted like '/episode/123-title-of-episode'
if not search_url:
continue
yield {
'_type': 'url',
'url': f'https://www.americastestkitchen.com{show_path or ""}{search_url}',
'id': try_get(episode, lambda e: e['objectID'].split('_')[-1]),
'title': episode.get('title'),
'description': episode.get('description'),
'timestamp': unified_timestamp(episode.get('search_document_date')),
'season_number': season_number,
'episode_number': int_or_none(episode.get('search_%s_episode_number' % slug)),
'ie_key': AmericasTestKitchenIE.ie_key(),
}
return self.playlist_result(
entries(), playlist_id, playlist_title)
yt_dlp/extractor/amp.py
+98
View File
@@ -0,0 +1,98 @@
from .common import InfoExtractor
from ..utils import (
determine_ext,
ExtractorError,
int_or_none,
mimetype2ext,
parse_iso8601,
unified_timestamp,
url_or_none,
)
class AMPIE(InfoExtractor): # XXX: Conventionally, base classes should end with BaseIE/InfoExtractor
# parse Akamai Adaptive Media Player feed
def _extract_feed_info(self, url):
feed = self._download_json(
url, None, 'Downloading Akamai AMP feed',
'Unable to download Akamai AMP feed')
item = feed.get('channel', {}).get('item')
if not item:
raise ExtractorError('%s said: %s' % (self.IE_NAME, feed['error']))
video_id = item['guid']
def get_media_node(name, default=None):
media_name = 'media-%s' % name
media_group = item.get('media-group') or item
return media_group.get(media_name) or item.get(media_name) or item.get(name, default)
thumbnails = []
media_thumbnail = get_media_node('thumbnail')
if media_thumbnail:
if isinstance(media_thumbnail, dict):
media_thumbnail = [media_thumbnail]
for thumbnail_data in media_thumbnail:
thumbnail = thumbnail_data.get('@attributes', {})
thumbnail_url = url_or_none(thumbnail.get('url'))
if not thumbnail_url:
continue
thumbnails.append({
'url': self._proto_relative_url(thumbnail_url, 'http:'),
'width': int_or_none(thumbnail.get('width')),
'height': int_or_none(thumbnail.get('height')),
})
subtitles = {}
media_subtitle = get_media_node('subTitle')
if media_subtitle:
if isinstance(media_subtitle, dict):
media_subtitle = [media_subtitle]
for subtitle_data in media_subtitle:
subtitle = subtitle_data.get('@attributes', {})
subtitle_href = url_or_none(subtitle.get('href'))
if not subtitle_href:
continue
subtitles.setdefault(subtitle.get('lang') or 'en', []).append({
'url': subtitle_href,
'ext': mimetype2ext(subtitle.get('type')) or determine_ext(subtitle_href),
})
formats = []
media_content = get_media_node('content')
if isinstance(media_content, dict):
media_content = [media_content]
for media_data in media_content:
media = media_data.get('@attributes', {})
media_url = url_or_none(media.get('url'))
if not media_url:
continue
ext = mimetype2ext(media.get('type')) or determine_ext(media_url)
if ext == 'f4m':
formats.extend(self._extract_f4m_formats(
media_url + '?hdcore=3.4.0&plugin=aasp-3.4.0.132.124',
video_id, f4m_id='hds', fatal=False))
elif ext == 'm3u8':
formats.extend(self._extract_m3u8_formats(
media_url, video_id, 'mp4', m3u8_id='hls', fatal=False))
else:
formats.append({
'format_id': media_data.get('media-category', {}).get('@attributes', {}).get('label'),
'url': media_url,
'tbr': int_or_none(media.get('bitrate')),
'filesize': int_or_none(media.get('fileSize')),
'ext': ext,
})
timestamp = unified_timestamp(item.get('pubDate'), ' ') or parse_iso8601(item.get('dc-date'))
return {
'id': video_id,
'title': get_media_node('title'),
'description': get_media_node('description'),
'thumbnails': thumbnails,
'timestamp': timestamp,
'duration': int_or_none(media_content[0].get('@attributes', {}).get('duration')),
'subtitles': subtitles,
'formats': formats,
}
yt_dlp/extractor/anchorfm.py
+98
View File
@@ -0,0 +1,98 @@
from .common import InfoExtractor
from ..utils import (
clean_html,
float_or_none,
int_or_none,
str_or_none,
traverse_obj,
unified_timestamp
)
class AnchorFMEpisodeIE(InfoExtractor):
_VALID_URL = r'https?://anchor\.fm/(?P<channel_name>\w+)/(?:embed/)?episodes/[\w-]+-(?P<episode_id>\w+)'
_EMBED_REGEX = [rf'<iframe[^>]+\bsrc=[\'"](?P<url>{_VALID_URL})']
_TESTS = [{
'url': 'https://anchor.fm/lovelyti/episodes/Chrisean-Rock-takes-to-twitter-to-announce-shes-pregnant--Blueface-denies-he-is-the-father-e1tpt3d',
'info_dict': {
'id': 'e1tpt3d',
'ext': 'mp3',
'title': ' Chrisean Rock takes to twitter to announce she\'s pregnant, Blueface denies he is the father!',
'description': 'md5:207d167de3e28ceb4ddc1ebf5a30044c',
'thumbnail': 'https://s3-us-west-2.amazonaws.com/anchor-generated-image-bank/production/podcast_uploaded_nologo/1034827/1034827-1658438968460-5f3bfdf3601e8.jpg',
'duration': 624.718,
'uploader': 'Lovelyti ',
'uploader_id': '991541',
'channel': 'lovelyti',
'modified_date': '20230121',
'modified_timestamp': 1674285178,
'release_date': '20230121',
'release_timestamp': 1674285179,
'episode_id': 'e1tpt3d',
}
}, {
# embed url
'url': 'https://anchor.fm/apakatatempo/embed/episodes/S2E75-Perang-Bintang-di-Balik-Kasus-Ferdy-Sambo-dan-Ismail-Bolong-e1shjqd',
'info_dict': {
'id': 'e1shjqd',
'ext': 'mp3',
'title': 'S2E75 Perang Bintang di Balik Kasus Ferdy Sambo dan Ismail Bolong',
'description': 'md5:9e95ad9293bf00178bf8d33e9cb92c41',
'duration': 1042.008,
'thumbnail': 'https://s3-us-west-2.amazonaws.com/anchor-generated-image-bank/production/podcast_uploaded_episode400/2627805/2627805-1671590688729-4db3882ac9e4b.jpg',
'release_date': '20221221',
'release_timestamp': 1671595916,
'modified_date': '20221221',
'modified_timestamp': 1671590834,
'channel': 'apakatatempo',
'uploader': 'Podcast Tempo',
'uploader_id': '2585461',
'season': 'Season 2',
'season_number': 2,
'episode_id': 'e1shjqd',
}
}]
_WEBPAGE_TESTS = [{
'url': 'https://podcast.tempo.co/podcast/192/perang-bintang-di-balik-kasus-ferdy-sambo-dan-ismail-bolong',
'info_dict': {
'id': 'e1shjqd',
'ext': 'mp3',
'release_date': '20221221',
'duration': 1042.008,
'season': 'Season 2',
'modified_timestamp': 1671590834,
'uploader_id': '2585461',
'modified_date': '20221221',
'description': 'md5:9e95ad9293bf00178bf8d33e9cb92c41',
'season_number': 2,
'title': 'S2E75 Perang Bintang di Balik Kasus Ferdy Sambo dan Ismail Bolong',
'release_timestamp': 1671595916,
'episode_id': 'e1shjqd',
'thumbnail': 'https://s3-us-west-2.amazonaws.com/anchor-generated-image-bank/production/podcast_uploaded_episode400/2627805/2627805-1671590688729-4db3882ac9e4b.jpg',
'uploader': 'Podcast Tempo',
'channel': 'apakatatempo',
}
}]
def _real_extract(self, url):
channel_name, episode_id = self._match_valid_url(url).group('channel_name', 'episode_id')
api_data = self._download_json(f'https://anchor.fm/api/v3/episodes/{episode_id}', episode_id)
return {
'id': episode_id,
'title': traverse_obj(api_data, ('episode', 'title')),
'url': traverse_obj(api_data, ('episode', 'episodeEnclosureUrl'), ('episodeAudios', 0, 'url')),
'ext': 'mp3',
'vcodec': 'none',
'thumbnail': traverse_obj(api_data, ('episode', 'episodeImage')),
'description': clean_html(traverse_obj(api_data, ('episode', ('description', 'descriptionPreview')), get_all=False)),
'duration': float_or_none(traverse_obj(api_data, ('episode', 'duration')), 1000),
'modified_timestamp': unified_timestamp(traverse_obj(api_data, ('episode', 'modified'))),
'release_timestamp': int_or_none(traverse_obj(api_data, ('episode', 'publishOnUnixTimestamp'))),
'episode_id': episode_id,
'uploader': traverse_obj(api_data, ('creator', 'name')),
'uploader_id': str_or_none(traverse_obj(api_data, ('creator', 'userId'))),
'season_number': int_or_none(traverse_obj(api_data, ('episode', 'podcastSeasonNumber'))),
'channel': channel_name or traverse_obj(api_data, ('creator', 'vanitySlug')),
}
yt_dlp/extractor/angel.py
+56
View File
@@ -0,0 +1,56 @@
import re
from .common import InfoExtractor
from ..utils import url_or_none, merge_dicts
class AngelIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?angel\.com/watch/(?P<series>[^/?#]+)/episode/(?P<id>[\w-]+)/season-(?P<season_number>\d+)/episode-(?P<episode_number>\d+)/(?P<title>[^/?#]+)'
_TESTS = [{
'url': 'https://www.angel.com/watch/tuttle-twins/episode/2f3d0382-ea82-4cdc-958e-84fbadadc710/season-1/episode-1/when-laws-give-you-lemons',
'md5': '4734e5cfdd64a568e837246aa3eaa524',
'info_dict': {
'id': '2f3d0382-ea82-4cdc-958e-84fbadadc710',
'ext': 'mp4',
'title': 'Tuttle Twins Season 1, Episode 1: When Laws Give You Lemons',
'description': 'md5:73b704897c20ab59c433a9c0a8202d5e',
'thumbnail': r're:^https?://images.angelstudios.com/image/upload/angel-app/.*$',
'duration': 1359.0
}
}, {
'url': 'https://www.angel.com/watch/the-chosen/episode/8dfb714d-bca5-4812-8125-24fb9514cd10/season-1/episode-1/i-have-called-you-by-name',
'md5': 'e4774bad0a5f0ad2e90d175cafdb797d',
'info_dict': {
'id': '8dfb714d-bca5-4812-8125-24fb9514cd10',
'ext': 'mp4',
'title': 'The Chosen Season 1, Episode 1: I Have Called You By Name',
'description': 'md5:aadfb4827a94415de5ff6426e6dee3be',
'thumbnail': r're:^https?://images.angelstudios.com/image/upload/angel-app/.*$',
'duration': 3276.0
}
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
json_ld = self._search_json_ld(webpage, video_id)
formats, subtitles = self._extract_m3u8_formats_and_subtitles(
json_ld.pop('url'), video_id, note='Downloading HD m3u8 information')
info_dict = {
'id': video_id,
'title': self._og_search_title(webpage),
'description': self._og_search_description(webpage),
'formats': formats,
'subtitles': subtitles
}
# Angel uses cloudinary in the background and supports image transformations.
# We remove these transformations and return the source file
base_thumbnail_url = url_or_none(self._og_search_thumbnail(webpage)) or json_ld.pop('thumbnails')
if base_thumbnail_url:
info_dict['thumbnail'] = re.sub(r'(/upload)/.+(/angel-app/.+)$', r'\1\2', base_thumbnail_url)
return merge_dicts(info_dict, json_ld)
yt_dlp/extractor/ant1newsgr.py
+128
View File
@@ -0,0 +1,128 @@
import urllib.parse
from .common import InfoExtractor
from ..utils import (
HEADRequest,
ExtractorError,
determine_ext,
scale_thumbnails_to_max_format_width,
)
class Ant1NewsGrBaseIE(InfoExtractor):
def _download_and_extract_api_data(self, video_id, netloc, cid=None):
url = f'{self.http_scheme()}//{netloc}{self._API_PATH}'
info = self._download_json(url, video_id, query={'cid': cid or video_id})
try:
source = info['url']
except KeyError:
raise ExtractorError('no source found for %s' % video_id)
formats, subs = (self._extract_m3u8_formats_and_subtitles(source, video_id, 'mp4')
if determine_ext(source) == 'm3u8' else ([{'url': source}], {}))
thumbnails = scale_thumbnails_to_max_format_width(
formats, [{'url': info['thumb']}], r'(?<=/imgHandler/)\d+')
return {
'id': video_id,
'title': info.get('title'),
'thumbnails': thumbnails,
'formats': formats,
'subtitles': subs,
}
class Ant1NewsGrWatchIE(Ant1NewsGrBaseIE):
IE_NAME = 'ant1newsgr:watch'
IE_DESC = 'ant1news.gr videos'
_VALID_URL = r'https?://(?P<netloc>(?:www\.)?ant1news\.gr)/watch/(?P<id>\d+)/'
_API_PATH = '/templates/data/player'
_TESTS = [{
'url': 'https://www.ant1news.gr/watch/1506168/ant1-news-09112021-stis-18-45',
'md5': '95925e6b32106754235f2417e0d2dfab',
'info_dict': {
'id': '1506168',
'ext': 'mp4',
'title': 'md5:0ad00fa66ecf8aa233d26ab0dba7514a',
'description': 'md5:18665af715a6dcfeac1d6153a44f16b0',
'thumbnail': 'https://ant1media.azureedge.net/imgHandler/640/26d46bf6-8158-4f02-b197-7096c714b2de.jpg',
},
}]
def _real_extract(self, url):
video_id, netloc = self._match_valid_url(url).group('id', 'netloc')
webpage = self._download_webpage(url, video_id)
info = self._download_and_extract_api_data(video_id, netloc)
info['description'] = self._og_search_description(webpage)
return info
class Ant1NewsGrArticleIE(Ant1NewsGrBaseIE):
IE_NAME = 'ant1newsgr:article'
IE_DESC = 'ant1news.gr articles'
_VALID_URL = r'https?://(?:www\.)?ant1news\.gr/[^/]+/article/(?P<id>\d+)/'
_TESTS = [{
'url': 'https://www.ant1news.gr/afieromata/article/549468/o-tzeims-mpont-sta-meteora-oi-apeiles-kai-o-xesikomos-ton-kalogeron',
'md5': '294f18331bb516539d72d85a82887dcc',
'info_dict': {
'id': '_xvg/m_cmbatw=',
'ext': 'mp4',
'title': 'md5:a93e8ecf2e4073bfdffcb38f59945411',
'timestamp': 1603092840,
'upload_date': '20201019',
'thumbnail': 'https://ant1media.azureedge.net/imgHandler/640/756206d2-d640-40e2-b201-3555abdfc0db.jpg',
},
}, {
'url': 'https://ant1news.gr/Society/article/620286/symmoria-anilikon-dikigoros-thymaton-ithelan-na-toys-apoteleiosoyn',
'info_dict': {
'id': '620286',
'title': 'md5:91fe569e952e4d146485740ae927662b',
},
'playlist_mincount': 2,
'params': {
'skip_download': True,
},
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
info = self._search_json_ld(webpage, video_id, expected_type='NewsArticle')
embed_urls = list(Ant1NewsGrEmbedIE._extract_embed_urls(url, webpage))
if not embed_urls:
raise ExtractorError('no videos found for %s' % video_id, expected=True)
return self.playlist_from_matches(
embed_urls, video_id, info.get('title'), ie=Ant1NewsGrEmbedIE.ie_key(),
video_kwargs={'url_transparent': True, 'timestamp': info.get('timestamp')})
class Ant1NewsGrEmbedIE(Ant1NewsGrBaseIE):
IE_NAME = 'ant1newsgr:embed'
IE_DESC = 'ant1news.gr embedded videos'
_BASE_PLAYER_URL_RE = r'(?:https?:)?//(?:[a-zA-Z0-9\-]+\.)?(?:antenna|ant1news)\.gr/templates/pages/player'
_VALID_URL = rf'{_BASE_PLAYER_URL_RE}\?([^#]+&)?cid=(?P<id>[^#&]+)'
_EMBED_REGEX = [rf'<iframe[^>]+?src=(?P<_q1>["\'])(?P<url>{_BASE_PLAYER_URL_RE}\?(?:(?!(?P=_q1)).)+)(?P=_q1)']
_API_PATH = '/news/templates/data/jsonPlayer'
_TESTS = [{
'url': 'https://www.antenna.gr/templates/pages/player?cid=3f_li_c_az_jw_y_u=&w=670&h=377',
'md5': 'dfc58c3a11a5a9aad2ba316ed447def3',
'info_dict': {
'id': '3f_li_c_az_jw_y_u=',
'ext': 'mp4',
'title': 'md5:a30c93332455f53e1e84ae0724f0adf7',
'thumbnail': 'https://ant1media.azureedge.net/imgHandler/640/bbe31201-3f09-4a4e-87f5-8ad2159fffe2.jpg',
},
}]
def _real_extract(self, url):
video_id = self._match_id(url)
canonical_url = self._request_webpage(
HEADRequest(url), video_id,
note='Resolve canonical player URL',
errnote='Could not resolve canonical player URL').geturl()
_, netloc, _, _, query, _ = urllib.parse.urlparse(canonical_url)
cid = urllib.parse.parse_qs(query)['cid'][0]
return self._download_and_extract_api_data(video_id, netloc, cid=cid)
yt_dlp/extractor/anvato.py
+412
View File
@@ -0,0 +1,412 @@
import base64
import hashlib
import json
import random
import re
import time
from .common import InfoExtractor
from ..aes import aes_encrypt
from ..utils import (
bytes_to_intlist,
determine_ext,
int_or_none,
intlist_to_bytes,
join_nonempty,
smuggle_url,
strip_jsonp,
traverse_obj,
unescapeHTML,
unsmuggle_url,
)
def md5_text(s):
return hashlib.md5(str(s).encode()).hexdigest()
class AnvatoIE(InfoExtractor):
_VALID_URL = r'anvato:(?P<access_key_or_mcp>[^:]+):(?P<id>\d+)'
_API_BASE_URL = 'https://tkx.mp.lura.live/rest/v2'
_ANVP_RE = r'<script[^>]+\bdata-anvp\s*=\s*(["\'])(?P<anvp>(?:(?!\1).)+)\1'
_AUTH_KEY = b'\x31\xc2\x42\x84\x9e\x73\xa0\xce' # from anvplayer.min.js
_TESTS = [{
# from https://www.nfl.com/videos/baker-mayfield-s-game-changing-plays-from-3-td-game-week-14
'url': 'anvato:GXvEgwyJeWem8KCYXfeoHWknwP48Mboj:899441',
'md5': '921919dab3cd0b849ff3d624831ae3e2',
'info_dict': {
'id': '899441',
'ext': 'mp4',
'title': 'Baker Mayfield\'s game-changing plays from 3-TD game Week 14',
'description': 'md5:85e05a3cc163f8c344340f220521136d',
'upload_date': '20201215',
'timestamp': 1608009755,
'thumbnail': r're:^https?://.*\.jpg',
'uploader': 'NFL',
'tags': ['Baltimore Ravens at Cleveland Browns (2020-REG-14)', 'Baker Mayfield', 'Game Highlights',
'Player Highlights', 'Cleveland Browns', 'league'],
'duration': 157,
'categories': ['Entertainment', 'Game', 'Highlights'],
},
}, {
# from https://ktla.com/news/99-year-old-woman-learns-to-fly-in-torrance-checks-off-bucket-list-dream/
'url': 'anvato:X8POa4zpGZMmeiq0wqiO8IP5rMqQM9VN:8032455',
'md5': '837718bcfb3a7778d022f857f7a9b19e',
'info_dict': {
'id': '8032455',
'ext': 'mp4',
'title': '99-year-old woman learns to fly plane in Torrance, checks off bucket list dream',
'description': 'md5:0a12bab8159445e78f52a297a35c6609',
'upload_date': '20220928',
'timestamp': 1664408881,
'thumbnail': r're:^https?://.*\.jpg',
'uploader': 'LIN',
'tags': ['video', 'news', '5live'],
'duration': 155,
'categories': ['News'],
},
}]
# Copied from anvplayer.min.js
_ANVACK_TABLE = {
'nbcu_nbcd_desktop_web_prod_93d8ead38ce2024f8f544b78306fbd15895ae5e6': 'NNemUkySjxLyPTKvZRiGntBIjEyK8uqicjMakIaQ',
'nbcu_nbcd_desktop_web_qa_1a6f01bdd0dc45a439043b694c8a031d': 'eSxJUbA2UUKBTXryyQ2d6NuM8oEqaPySvaPzfKNA',
'nbcu_nbcd_desktop_web_acc_eb2ff240a5d4ae9a63d4c297c32716b6c523a129': '89JR3RtUGbvKuuJIiKOMK0SoarLb5MUx8v89RcbP',
'nbcu_nbcd_watchvod_web_prod_e61107507180976724ec8e8319fe24ba5b4b60e1': 'Uc7dFt7MJ9GsBWB5T7iPvLaMSOt8BBxv4hAXk5vv',
'nbcu_nbcd_watchvod_web_qa_42afedba88a36203db5a4c09a5ba29d045302232': 'T12oDYVFP2IaFvxkmYMy5dKxswpLHtGZa4ZAXEi7',
'nbcu_nbcd_watchvod_web_acc_9193214448e2e636b0ffb78abacfd9c4f937c6ca': 'MmobcxUxMedUpohNWwXaOnMjlbiyTOBLL6d46ZpR',
'nbcu_local_monitor_web_acc_f998ad54eaf26acd8ee033eb36f39a7b791c6335': 'QvfIoPYrwsjUCcASiw3AIkVtQob2LtJHfidp9iWg',
'nbcu_cable_monitor_web_acc_a413759603e8bedfcd3c61b14767796e17834077': 'uwVPJLShvJWSs6sWEIuVem7MTF8A4IknMMzIlFto',
'nbcu_nbcd_mcpstage_web_qa_4c43a8f6e95a88dbb40276c0630ba9f693a63a4e': 'PxVYZVwjhgd5TeoPRxL3whssb5OUPnM3zyAzq8GY',
'nbcu_comcast_comcast_web_prod_074080762ad4ce956b26b43fb22abf153443a8c4': 'afnaRZfDyg1Z3WZHdupKfy6xrbAG2MHqe3VfuSwh',
'nbcu_comcast_comcast_web_qa_706103bb93ead3ef70b1de12a0e95e3c4481ade0': 'DcjsVbX9b3uoPlhdriIiovgFQZVxpISZwz0cx1ZK',
'nbcu_comcast_comcastcable_web_prod_669f04817536743563d7331c9293e59fbdbe3d07': '0RwMN2cWy10qhAhOscq3eK7aEe0wqnKt3vJ0WS4D',
'nbcu_comcast_comcastcable_web_qa_3d9d2d66219094127f0f6b09cc3c7bb076e3e1ca': '2r8G9DEya7PCqBceKZgrn2XkXgASjwLMuaFE1Aad',
'hearst_hearst_demo_web_stage_960726dfef3337059a01a78816e43b29ec04dfc7': 'cuZBPXTR6kSdoTCVXwk5KGA8rk3NrgGn4H6e9Dsp',
'anvato_mcpqa_demo_web_stage_18b55e00db5a13faa8d03ae6e41f6f5bcb15b922': 'IOaaLQ8ymqVyem14QuAvE5SndQynTcH5CrLkU2Ih',
'anvato_nextmedia_demo_web_stage_9787d56a02ff6b9f43e9a2b0920d8ca88beb5818': 'Pqu9zVzI1ApiIzbVA3VkGBEQHvdKSUuKpD6s2uaR',
'anvato_scripps_app_web_prod_0837996dbe373629133857ae9eb72e740424d80a': 'du1ccmn7RxzgizwbWU7hyUaGodNlJn7HtXI0WgXW',
'anvato_scripps_app_web_stage_360797e00fe2826be142155c4618cc52fce6c26c': '2PMrQ0BRoqCWl7nzphj0GouIMEh2mZYivAT0S1Su',
'fs2go_fs2go_go_all_prod_21934911ccfafc03a075894ead2260d11e2ddd24': 'RcuHlKikW2IJw6HvVoEkqq2UsuEJlbEl11pWXs4Q',
'fs2go_fs2go_go_web_prod_ead4b0eec7460c1a07783808db21b49cf1f2f9a7': '4K0HTT2u1zkQA2MaGaZmkLa1BthGSBdr7jllrhk5',
'fs2go_fs2go_go_web_stage_407585454a4400355d4391691c67f361': 'ftnc37VKRJBmHfoGGi3kT05bHyeJzilEzhKJCyl3',
'fs2go_fs2go_go_android_stage_44b714db6f8477f29afcba15a41e1d30': 'CtxpPvVpo6AbZGomYUhkKs7juHZwNml9b9J0J2gI',
'anvato_cbslocal_app_web_prod_547f3e49241ef0e5d30c79b2efbca5d92c698f67': 'Pw0XX5KBDsyRnPS0R2JrSrXftsy8Jnz5pAjaYC8s',
'anvato_cbslocal_app_web_stage_547a5f096594cd3e00620c6f825cad1096d28c80': '37OBUhX2uwNyKhhrNzSSNHSRPZpApC3trdqDBpuz',
'fs2go_att_att_web_prod_1042dddd089a05438b6a08f972941176f699ffd8': 'JLcF20JwYvpv6uAGcLWIaV12jKwaL1R8us4b6Zkg',
'fs2go_att_att_web_stage_807c5001955fc114a3331fe027ddc76e': 'gbu1oO1y0JiOFh4SUipt86P288JHpyjSqolrrT1x',
'fs2go_fs2go_tudor_web_prod_a7dd8e5a7cdc830cae55eae6f3e9fee5ee49eb9b': 'ipcp87VCEZXPPe868j3orLqzc03oTy7DXsGkAXXH',
'anvato_mhz_app_web_prod_b808218b30de7fdf60340cbd9831512bc1bf6d37': 'Stlm5Gs6BEhJLRTZHcNquyzxGqr23EuFmE5DCgjX',
'fs2go_charter_charter_web_stage_c2c6e5a68375a1bf00fff213d3ff8f61a835a54c': 'Lz4hbJp1fwL6jlcz4M2PMzghM4jp4aAmybtT5dPc',
'fs2go_charter_charter_web_prod_ebfe3b10f1af215a7321cd3d629e0b81dfa6fa8c': 'vUJsK345A1bVmyYDRhZX0lqFIgVXuqhmuyp1EtPK',
'anvato_epfox_app_web_prod_b3373168e12f423f41504f207000188daf88251b': 'GDKq1ixvX3MoBNdU5IOYmYa2DTUXYOozPjrCJnW7',
'anvato_epfox_app_web_stage_a3c2ce60f8f83ef374a88b68ee73a950f8ab87ce': '2jz2NH4BsXMaDsoJ5qkHMbcczAfIReo2eFYuVC1C',
'fs2go_verizon_verizon_web_stage_08e6df0354a4803f1b1f2428b5a9a382e8dbcd62': 'rKTVapNaAcmnUbGL4ZcuOoY4SE7VmZSQsblPFr7e',
'fs2go_verizon_verizon_web_prod_f909564cb606eff1f731b5e22e0928676732c445': 'qLSUuHerM3u9eNPzaHyUK52obai5MvE4XDJfqYe1',
'fs2go_foxcom_synd_web_stage_f7b9091f00ea25a4fdaaae77fca5b54cdc7e7043': '96VKF2vLd24fFiDfwPFpzM5llFN4TiIGAlodE0Re',
'fs2go_foxcom_synd_web_prod_0f2cdd64d87e4ab6a1d54aada0ff7a7c8387a064': 'agiPjbXEyEZUkbuhcnmVPhe9NNVbDjCFq2xkcx51',
'anvato_own_app_web_stage_1214ade5d28422c4dae9d03c1243aba0563c4dba': 'mzhamNac3swG4WsJAiUTacnGIODi6SWeVWk5D7ho',
'anvato_own_app_web_prod_944e162ed927ec3e9ed13eb68ed2f1008ee7565e': '9TSxh6G2TXOLBoYm9ro3LdNjjvnXpKb8UR8KoIP9',
'anvato_scripps_app_ftv_prod_a10a10468edd5afb16fb48171c03b956176afad1': 'COJ2i2UIPK7xZqIWswxe7FaVBOVgRkP1F6O6qGoH',
'anvato_scripps_app_ftv_stage_77d3ad2bdb021ec37ca2e35eb09acd396a974c9a': 'Q7nnopNLe2PPfGLOTYBqxSaRpl209IhqaEuDZi1F',
'anvato_univision_app_web_stage_551236ef07a0e17718c3995c35586b5ed8cb5031': 'D92PoLS6UitwxDRA191HUGT9OYcOjV6mPMa5wNyo',
'anvato_univision_app_web_prod_039a5c0a6009e637ae8ac906718a79911e0e65e1': '5mVS5u4SQjtw6NGw2uhMbKEIONIiLqRKck5RwQLR',
'nbcu_cnbc_springfield_ios_prod_670207fae43d6e9a94c351688851a2ce': 'M7fqCCIP9lW53oJbHs19OlJlpDrVyc2OL8gNeuTa',
'nbcu_cnbc_springfieldvod_ios_prod_7a5f04b1ceceb0e9c9e2264a44aa236e08e034c2': 'Yia6QbJahW0S7K1I0drksimhZb4UFq92xLBmmMvk',
'anvato_cox_app_web_prod_ce45cda237969f93e7130f50ee8bb6280c1484ab': 'cc0miZexpFtdoqZGvdhfXsLy7FXjRAOgb9V0f5fZ',
'anvato_cox_app_web_stage_c23dbe016a8e9d8c7101d10172b92434f6088bf9': 'yivU3MYHd2eDZcOfmLbINVtqxyecKTOp8OjOuoGJ',
'anvato_chnzero_app_web_stage_b1164d1352b579e792e542fddf13ee34c0eeb46b': 'A76QkXMmVH8lTCfU15xva1mZnSVcqeY4Xb22Kp7m',
'anvato_chnzero_app_web_prod_253d358928dc08ec161eda2389d53707288a730c': 'OA5QI3ZWZZkdtUEDqh28AH8GedsF6FqzJI32596b',
'anvato_discovery_vodpoc_web_stage_9fa7077b5e8af1f8355f65d4fb8d2e0e9d54e2b7': 'q3oT191tTQ5g3JCP67PkjLASI9s16DuWZ6fYmry3',
'anvato_discovery_vodpoc_web_prod_688614983167a1af6cdf6d76343fda10a65223c1': 'qRvRQCTVHd0VVOHsMvvfidyWmlYVrTbjby7WqIuK',
'nbcu_cnbc_springfieldvod_ftv_stage_826040aad1925a46ac5dfb4b3c5143e648c6a30d': 'JQaSb5a8Tz0PT4ti329DNmzDO30TnngTHmvX8Vua',
'nbcu_cnbc_springfield_ftv_stage_826040aad1925a46ac5dfb4b3c5143e648c6a30d': 'JQaSb5a8Tz0PT4ti329DNmzDO30TnngTHmvX8Vua',
'nbcu_nbcd_capture_web_stage_4dd9d585bfb984ebf856dee35db027b2465cc4ae': '0j1Ov4Vopyi2HpBZJYdL2m8ERJVGYh3nNpzPiO8F',
'nbcu_nbcd_watch3_android_prod_7712ca5fcf1c22f19ec1870a9650f9c37db22dcf': '3LN2UB3rPUAMu7ZriWkHky9vpLMXYha8JbSnxBlx',
'nbcu_nbcd_watchvod3_android_prod_0910a3a4692d57c0b5ff4316075bc5d096be45b9': 'mJagcQ2II30vUOAauOXne7ERwbf5S9nlB3IP17lQ',
'anvato_scripps_app_atv_prod_790deda22e16e71e83df58f880cd389908a45d52': 'CB6trI1mpoDIM5o54DNTsji90NDBQPZ4z4RqBNSH',
'nbcu_nbcd_watchv4_android_prod_ff67cef9cb409158c6f8c3533edddadd0b750507': 'j8CHQCUWjlYERj4NFRmUYOND85QNbHViH09UwuKm',
'nbcu_nbcd_watchvodv4_android_prod_a814d781609989dea6a629d50ae4c7ad8cc8e907': 'rkVnUXxdA9rawVLUlDQtMue9Y4Q7lFEaIotcUhjt',
'rvVKpA50qlOPLFxMjrCGf5pdkdQDm7qn': '1J7ZkY5Qz5lMLi93QOH9IveE7EYB3rLl',
'nbcu_dtv_local_web_prod_b266cf49defe255fd4426a97e27c09e513e9f82f': 'HuLnJDqzLa4saCzYMJ79zDRSQpEduw1TzjMNQu2b',
'nbcu_att_local_web_prod_4cef038b2d969a6b7d700a56a599040b6a619f67': 'Q0Em5VDc2KpydUrVwzWRXAwoNBulWUxCq2faK0AV',
'nbcu_dish_local_web_prod_c56dcaf2da2e9157a4266c82a78195f1dd570f6b': 'bC1LWmRz9ayj2AlzizeJ1HuhTfIaJGsDBnZNgoRg',
'nbcu_verizon_local_web_prod_88bebd2ce006d4ed980de8133496f9a74cb9b3e1': 'wzhDKJZpgvUSS1EQvpCQP8Q59qVzcPixqDGJefSk',
'nbcu_charter_local_web_prod_9ad90f7fc4023643bb718f0fe0fd5beea2382a50': 'PyNbxNhEWLzy1ZvWEQelRuIQY88Eub7xbSVRMdfT',
'nbcu_suddenlink_local_web_prod_20fb711725cac224baa1c1cb0b1c324d25e97178': '0Rph41lPXZbb3fqeXtHjjbxfSrNbtZp1Ygq7Jypa',
'nbcu_wow_local_web_prod_652d9ce4f552d9c2e7b5b1ed37b8cb48155174ad': 'qayIBZ70w1dItm2zS42AptXnxW15mkjRrwnBjMPv',
'nbcu_centurylink_local_web_prod_2034402b029bf3e837ad46814d9e4b1d1345ccd5': 'StePcPMkjsX51PcizLdLRMzxMEl5k2FlsMLUNV4k',
'nbcu_atlanticbrd_local_web_prod_8d5f5ecbf7f7b2f5e6d908dd75d90ae3565f682e': 'NtYLb4TFUS0pRs3XTkyO5sbVGYjVf17bVbjaGscI',
'nbcu_nbcd_watchvod_web_dev_08bc05699be47c4f31d5080263a8cfadc16d0f7c': 'hwxi2dgDoSWgfmVVXOYZm14uuvku4QfopstXckhr',
'anvato_nextmedia_app_web_prod_a4fa8c7204aa65e71044b57aaf63711980cfe5a0': 'tQN1oGPYY1nM85rJYePWGcIb92TG0gSqoVpQTWOw',
'anvato_mcp_lin_web_prod_4c36fbfd4d8d8ecae6488656e21ac6d1ac972749': 'GUXNf5ZDX2jFUpu4WT2Go4DJ5nhUCzpnwDRRUx1K',
'anvato_mcp_univision_web_prod_37fe34850c99a3b5cdb71dab10a417dd5cdecafa': 'bLDYF8JqfG42b7bwKEgQiU9E2LTIAtnKzSgYpFUH',
'anvato_mcp_fs2go_web_prod_c7b90a93e171469cdca00a931211a2f556370d0a': 'icgGoYGipQMMSEvhplZX1pwbN69srwKYWksz3xWK',
'anvato_mcp_sps_web_prod_54bdc90dd6ba21710e9f7074338365bba28da336': 'fA2iQdI7RDpynqzQYIpXALVS83NTPr8LLFK4LFsu',
'anvato_mcp_anv_web_prod_791407490f4c1ef2a4bcb21103e0cb1bcb3352b3': 'rMOUZqe9lwcGq2mNgG3EDusm6lKgsUnczoOX3mbg',
'anvato_mcp_gray_web_prod_4c10f067c393ed8fc453d3930f8ab2b159973900': 'rMOUZqe9lwcGq2mNgG3EDusm6lKgsUnczoOX3mbg',
'anvato_mcp_hearst_web_prod_5356c3de0fc7c90a3727b4863ca7fec3a4524a99': 'P3uXJ0fXXditBPCGkfvlnVScpPEfKmc64Zv7ZgbK',
'anvato_mcp_cbs_web_prod_02f26581ff80e5bda7aad28226a8d369037f2cbe': 'mGPvo5ZA5SgjOFAPEPXv7AnOpFUICX8hvFQVz69n',
'anvato_mcp_telemundo_web_prod_c5278d51ad46fda4b6ca3d0ea44a7846a054f582': 'qyT6PXXLjVNCrHaRVj0ugAhalNRS7Ee9BP7LUokD',
'nbcu_nbcd_watchvodv4_web_stage_4108362fba2d4ede21f262fea3c4162cbafd66c7': 'DhaU5lj0W2gEdcSSsnxURq8t7KIWtJfD966crVDk',
'anvato_scripps_app_ios_prod_409c41960c60b308db43c3cc1da79cab9f1c3d93': 'WPxj5GraLTkYCyj3M7RozLqIycjrXOEcDGFMIJPn',
'EZqvRyKBJLrgpClDPDF8I7Xpdp40Vx73': '4OxGd2dEakylntVKjKF0UK9PDPYB6A9W',
'M2v78QkpleXm9hPp9jUXI63x5vA6BogR': 'ka6K32k7ZALmpINkjJUGUo0OE42Md1BQ',
'nbcu_nbcd_desktop_web_prod_93d8ead38ce2024f8f544b78306fbd15895ae5e6_secure': 'NNemUkySjxLyPTKvZRiGntBIjEyK8uqicjMakIaQ',
'X8POa4zPPaKVZHqmWjuEzfP31b1QM9VN': 'Dn5vOY9ooDw7VSl9qztjZI5o0g08mA0z',
'M2v78QkBMpNJlSPp9diX5F2PBmBy6Bog': 'ka6K32kyo7nDZfNkjQCGWf1lpApXMd1B',
'bvJ0dQpav07l0hG5JgfVLF2dv1vARwpP': 'BzoQW24GrJZoJfmNodiJKSPeB9B8NOxj',
'lxQMLg2XZKuEZaWgsqubBxV9INZ6bryY': 'Vm2Mx6noKds9jB71h6urazwlTG3m9x8l',
'04EnjvXeoSmkbJ9ckPs7oY0mcxv7PlyN': 'aXERQP9LMfQVlEDsgGs6eEA1SWznAQ8P',
'mQbO2ge6BFRWVPYCYpU06YvNt80XLvAX': 'E2BV1NGmasN5v7eujECVPJgwflnLPm2A',
'g43oeBzJrCml7o6fa5fRL1ErCdeD8z4K': 'RX34mZ6zVH4Nr6whbxIGLv9WSbxEKo8V',
'VQrDJoP7mtdBzkxhXbSPwGB1coeElk4x': 'j2VejQx0VFKQepAF7dI0mJLKtOVJE18z',
'WxA5NzLRjCrmq0NUgaU5pdMDuZO7RJ4w': 'lyY5ADLKaIOLEgAsGQCveEMAcqnx3rY9',
'M4lpMXB71ie0PjMCjdFzVXq0SeRVqz49': 'n2zVkOqaLIv3GbLfBjcwW51LcveWOZ2e',
'dyDZGEqN8u8nkJZcJns0oxYmtP7KbGAn': 'VXOEqQW9BtEVLajfZQSLEqxgS5B7qn2D',
'E7QNjrVY5u5mGvgu67IoDgV1CjEND8QR': 'rz8AaDmdKIkLmPNhB5ILPJnjS5PnlL8d',
'a4zrqjoKlfzg0dwHEWtP31VqcLBpjm4g': 'LY9J16gwETdGWa3hjBu5o0RzuoQDjqXQ',
'dQP5BZroMsMVLO1hbmT5r2Enu86GjxA6': '7XR3oOdbPF6x3PRFLDCq9RkgsRjAo48V',
'M4lKNBO1NFe0PjMCj1tzVXq0SeRVqzA9': 'n2zoRqGLRUv3GbLfBmTwW51LcveWOZYe',
'nAZ7MZdpGCGg1pqFEbsoJOz2C60mv143': 'dYJgdqA9aT4yojETqGi7yNgoFADxqmXP',
'3y1MERYgOuE9NzbFgwhV6Wv2F0YKvbyz': '081xpZDQgC4VadLTavhWQxrku56DAgXV',
'bmQvmEXr5HWklBMCZOcpE2Z3HBYwqGyl': 'zxXPbVNyMiMAZldhr9FkOmA0fl4aKr2v',
'wA7oDNYldfr6050Hwxi52lPZiVlB86Ap': 'ZYK16aA7ni0d3l3c34uwpxD7CbReMm8Q',
'g43MbKMWmFml7o7sJoSRkXxZiXRvJ3QK': 'RX3oBJonvs4Nr6rUWBCGn3matRGqJPXV',
'mA9VdlqpLS0raGaSDvtoqNrBTzb8XY4q': '0XN4OjBD3fnW7r7IbmtJB4AyfOmlrE2r',
'mAajOwgkGt17oGoFmEuklMP9H0GnW54d': 'lXbBLPGyzikNGeGujAuAJGjZiwLRxyXR',
'vy8vjJ9kbUwrRqRu59Cj5dWZfzYErlAb': 'K8l7gpwaGcBpnAnCLNCmPZRdin3eaQX0',
'xQMWBpR8oHEZaWaSMGUb0avOHjLVYn4Y': 'm2MrN4vEaf9jB7BFy5Srb40jTrN67AYl',
'xyKEmVO3miRr6D6UVkt7oB8jtD6aJEAv': 'g2ddDebqDfqdgKgswyUKwGjbTWwzq923',
'7Qk0wa2D9FjKapacoJF27aLvUDKkLGA0': 'b2kgBEkephJaMkMTL7s1PLe4Ua6WyP2P',
'3QLg6nqmNTJ5VvVTo7f508LPidz1xwyY': 'g2L1GgpraipmAOAUqmIbBnPxHOmw4MYa',
'3y1B7zZjXTE9NZNSzZSVNPZaTNLjo6Qz': '081b5G6wzH4VagaURmcWbN5mT4JGEe2V',
'lAqnwvkw6SG6D8DSqmUg6DRLUp0w3G4x': 'O2pbP0xPDFNJjpjIEvcdryOJtpkVM4X5',
'awA7xd1N0Hr6050Hw2c52lPZiVlB864p': 'GZYKpn4aoT0d3l3c3PiwpxD7CbReMmXQ',
'jQVqPLl9YHL1WGWtR1HDgWBGT63qRNyV': '6X03ne6vrU4oWyWUN7tQVoajikxJR3Ye',
'GQRMR8mL7uZK797t7xH3eNzPIP5dOny1': 'm2vqPWGd4U31zWzSyasDRAoMT1PKRp8o',
'zydq9RdmRhXLkNkfNoTJlMzaF0lWekQB': '3X7LnvE7vH5nkEkSqLiey793Un7dLB8e',
'VQrDzwkB2IdBzjzu9MHPbEYkSB50gR4x': 'j2VebLzoKUKQeEesmVh0gM1eIp9jKz8z',
'mAa2wMamBs17oGoFmktklMP9H0GnW54d': 'lXbgP74xZTkNGeGujVUAJGjZiwLRxy8R',
'7yjB6ZLG6sW8R6RF2xcan1KGfJ5dNoyd': 'wXQkPorvPHZ45N5t4Jf6qwg5Tp4xvw29',
'a4zPpNeWGuzg0m0iX3tPeanGSkRKWXQg': 'LY9oa3QAyHdGW9Wu3Ri5JGeEik7l1N8Q',
'k2rneA2M38k25cXDwwSknTJlxPxQLZ6M': '61lyA2aEVDzklfdwmmh31saPxQx2VRjp',
'bK9Zk4OvPnvxduLgxvi8VUeojnjA02eV': 'o5jANYjbeMb4nfBaQvcLAt1jzLzYx6ze',
'5VD6EydM3R9orHmNMGInGCJwbxbQvGRw': 'w3zjmX7g4vnxzCxElvUEOiewkokXprkZ',
'70X35QbVYVYNPUmP9YfbzI06YqYQk2R1': 'vG4Aj2BMjMjoztB7zeFOnCVPJpJ8lMOa',
'26qYwQVG9p1Bks2GgBckjfDJOXOAMgG1': 'r4ev9X0mv5zqJc0yk5IBDcQOwZw8mnwQ',
'rvVKpA56MBXWlSxMw3cobT5pdkd4Dm7q': '1J7ZkY53pZ645c93owcLZuveE7E8B3rL',
'qN1zdy1zlYL23IWZGWtDvfV6WeWQWkJo': 'qN1zdy1zlYL23IWZGWtDvfV6WeWQWkJo',
'jdKqRGF16dKsBviMDae7IGDl7oTjEbVV': 'Q09l7vhlNxPFErIOK6BVCe7KnwUW5DVV',
'3QLkogW1OUJ5VvPsrDH56DY2u7lgZWyY': 'g2LRE1V9espmAOPhE4ubj4ZdUA57yDXa',
'wyJvWbXGBSdbkEzhv0CW8meou82aqRy8': 'M2wolPvyBIpQGkbT4juedD4ruzQGdK2y',
'7QkdZrzEkFjKap6IYDU2PB0oCNZORmA0': 'b2kN1l96qhJaMkPs9dt1lpjBfwqZoA8P',
'pvA05113MHG1w3JTYxc6DVlRCjErVz4O': 'gQXeAbblBUnDJ7vujbHvbRd1cxlz3AXO',
'mA9blJDZwT0raG1cvkuoeVjLC7ZWd54q': '0XN9jRPwMHnW7rvumgfJZOD9CJgVkWYr',
'5QwRN5qKJTvGKlDTmnf7xwNZcjRmvEy9': 'R2GP6LWBJU1QlnytwGt0B9pytWwAdDYy',
'eyn5rPPbkfw2KYxH32fG1q58CbLJzM40': 'p2gyqooZnS56JWeiDgfmOy1VugOQEBXn',
'3BABn3b5RfPJGDwilbHe7l82uBoR05Am': '7OYZG7KMVhbPdKJS3xcWEN3AuDlLNmXj',
'xA5zNGXD3HrmqMlF6OS5pdMDuZO7RJ4w': 'yY5DAm6r1IOLE3BCVMFveEMAcqnx3r29',
'g43PgW3JZfml7o6fDEURL1ErCdeD8zyK': 'RX3aQn1zrS4Nr6whDgCGLv9WSbxEKo2V',
'lAqp8WbGgiG6D8LTKJcg3O72CDdre1Qx': 'O2pnm6473HNJjpKuVosd3vVeh975yrX5',
'wyJbYEDxKSdbkJ6S6RhW8meou82aqRy8': 'M2wPm7EgRSpQGlAh70CedD4ruzQGdKYy',
'M4lgW28nLCe0PVdtaXszVXq0SeRVqzA9': 'n2zmJvg4jHv3G0ETNgiwW51LcveWOZ8e',
'5Qw3OVvp9FvGKlDTmOC7xwNZcjRmvEQ9': 'R2GzDdml9F1Qlnytw9s0B9pytWwAdD8y',
'vy8a98X7zCwrRqbHrLUjYzwDiK2b70Qb': 'K8lVwzyjZiBpnAaSGeUmnAgxuGOBxmY0',
'g4eGjJLLoiqRD3Pf9oT5O03LuNbLRDQp': '6XqD59zzpfN4EwQuaGt67qNpSyRBlnYy',
'g43OPp9boIml7o6fDOIRL1ErCdeD8z4K': 'RX33alNB4s4Nr6whDPUGLv9WSbxEKoXV',
'xA2ng9OkBcGKzDbTkKsJlx7dUK8R3dA5': 'z2aPnJvzBfObkwGC3vFaPxeBhxoMqZ8K',
'xyKEgBajZuRr6DEC0Kt7XpD1cnNW9gAv': 'g2ddlEBvRsqdgKaI4jUK9PrgfMexGZ23',
'BAogww51jIMa2JnH1BcYpXM5F658RNAL': 'rYWDmm0KptlkGv4FGJFMdZmjs9RDE6XR',
'BAokpg62VtMa2JnH1mHYpXM5F658RNAL': 'rYWryDnlNslkGv4FG4HMdZmjs9RDE62R',
'a4z1Px5e2hzg0m0iMMCPeanGSkRKWXAg': 'LY9eorNQGUdGW9WuKKf5JGeEik7l1NYQ',
'kAx69R58kF9nY5YcdecJdl2pFXP53WyX': 'gXyRxELpbfPvLeLSaRil0mp6UEzbZJ8L',
'BAoY13nwViMa2J2uo2cY6BlETgmdwryL': 'rYWwKzJmNFlkGvGtNoUM9bzwIJVzB1YR',
}
_MCP_TO_ACCESS_KEY_TABLE = {
'qa': 'anvato_mcpqa_demo_web_stage_18b55e00db5a13faa8d03ae6e41f6f5bcb15b922',
'lin': 'anvato_mcp_lin_web_prod_4c36fbfd4d8d8ecae6488656e21ac6d1ac972749',
'univison': 'anvato_mcp_univision_web_prod_37fe34850c99a3b5cdb71dab10a417dd5cdecafa',
'uni': 'anvato_mcp_univision_web_prod_37fe34850c99a3b5cdb71dab10a417dd5cdecafa',
'dev': 'anvato_mcp_fs2go_web_prod_c7b90a93e171469cdca00a931211a2f556370d0a',
'sps': 'anvato_mcp_sps_web_prod_54bdc90dd6ba21710e9f7074338365bba28da336',
'spsstg': 'anvato_mcp_sps_web_prod_54bdc90dd6ba21710e9f7074338365bba28da336',
'anv': 'anvato_mcp_anv_web_prod_791407490f4c1ef2a4bcb21103e0cb1bcb3352b3',
'gray': 'anvato_mcp_gray_web_prod_4c10f067c393ed8fc453d3930f8ab2b159973900',
'hearst': 'anvato_mcp_hearst_web_prod_5356c3de0fc7c90a3727b4863ca7fec3a4524a99',
'cbs': 'anvato_mcp_cbs_web_prod_02f26581ff80e5bda7aad28226a8d369037f2cbe',
'telemundo': 'anvato_mcp_telemundo_web_prod_c5278d51ad46fda4b6ca3d0ea44a7846a054f582'
}
def _generate_nfl_token(self, anvack, mcp_id):
reroute = self._download_json(
'https://api.nfl.com/v1/reroute', mcp_id, data=b'grant_type=client_credentials',
headers={'X-Domain-Id': 100}, note='Fetching token info')
token_type = reroute.get('token_type') or 'Bearer'
auth_token = f'{token_type} {reroute["access_token"]}'
response = self._download_json(
'https://api.nfl.com/v3/shield/', mcp_id, data=json.dumps({
'query': '''{
viewer {
mediaToken(anvack: "%s", id: %s) {
token
}
}
}''' % (anvack, mcp_id),
}).encode(), headers={
'Authorization': auth_token,
'Content-Type': 'application/json',
}, note='Fetching NFL API token')
return traverse_obj(response, ('data', 'viewer', 'mediaToken', 'token'))
_TOKEN_GENERATORS = {
'GXvEgwyJeWem8KCYXfeoHWknwP48Mboj': _generate_nfl_token,
}
def _server_time(self, access_key, video_id):
return int_or_none(traverse_obj(self._download_json(
f'{self._API_BASE_URL}/server_time', video_id, query={'anvack': access_key},
note='Fetching server time', fatal=False), 'server_time')) or int(time.time())
def _get_video_json(self, access_key, video_id, extracted_token):
# See et() in anvplayer.min.js, which is an alias of getVideoJSON()
video_data_url = f'{self._API_BASE_URL}/mcp/video/{video_id}?anvack={access_key}'
server_time = self._server_time(access_key, video_id)
input_data = f'{server_time}~{md5_text(video_data_url)}~{md5_text(server_time)}'
auth_secret = intlist_to_bytes(aes_encrypt(
bytes_to_intlist(input_data[:64]), bytes_to_intlist(self._AUTH_KEY)))
query = {
'X-Anvato-Adst-Auth': base64.b64encode(auth_secret).decode('ascii'),
'rtyp': 'fp',
}
anvrid = md5_text(time.time() * 1000 * random.random())[:30]
api = {
'anvrid': anvrid,
'anvts': server_time,
}
if extracted_token is not None:
api['anvstk2'] = extracted_token
elif self._TOKEN_GENERATORS.get(access_key) is not None:
api['anvstk2'] = self._TOKEN_GENERATORS[access_key](self, access_key, video_id)
elif self._ANVACK_TABLE.get(access_key) is not None:
api['anvstk'] = md5_text(f'{access_key}|{anvrid}|{server_time}|{self._ANVACK_TABLE[access_key]}')
else:
api['anvstk2'] = 'default'
return self._download_json(
video_data_url, video_id, transform_source=strip_jsonp, query=query,
data=json.dumps({'api': api}, separators=(',', ':')).encode('utf-8'))
def _get_anvato_videos(self, access_key, video_id, token):
video_data = self._get_video_json(access_key, video_id, token)
formats = []
for published_url in video_data['published_urls']:
video_url = published_url.get('embed_url')
if not video_url:
continue
media_format = published_url.get('format')
ext = determine_ext(video_url)
if ext == 'smil' or media_format == 'smil':
formats.extend(self._extract_smil_formats(video_url, video_id))
continue
tbr = int_or_none(published_url.get('kbps'))
a_format = {
'url': video_url,
'format_id': join_nonempty('http', published_url.get('cdn_name')).lower(),
'tbr': tbr or None,
}
vtt_subs, hls_subs = {}, {}
if media_format == 'vtt':
_, vtt_subs = self._extract_m3u8_formats_and_subtitles(
video_url, video_id, m3u8_id='vtt', fatal=False)
continue
elif media_format == 'm3u8' and tbr is not None:
a_format.update({
'format_id': join_nonempty('hls', tbr),
'ext': 'mp4',
})
elif media_format == 'm3u8-variant' or ext == 'm3u8':
# For some videos the initial m3u8 URL returns JSON instead
manifest_json = self._download_json(
video_url, video_id, note='Downloading manifest JSON', errnote=False)
if manifest_json:
video_url = manifest_json.get('master_m3u8')
if not video_url:
continue
hls_fmts, hls_subs = self._extract_m3u8_formats_and_subtitles(
video_url, video_id, ext='mp4', m3u8_id='hls', fatal=False)
formats.extend(hls_fmts)
continue
elif ext == 'mp3' or media_format == 'mp3':
a_format['vcodec'] = 'none'
else:
a_format.update({
'width': int_or_none(published_url.get('width')),
'height': int_or_none(published_url.get('height')),
})
formats.append(a_format)
subtitles = {}
for caption in video_data.get('captions', []):
a_caption = {
'url': caption['url'],
'ext': 'tt' if caption.get('format') == 'SMPTE-TT' else None
}
subtitles.setdefault(caption['language'], []).append(a_caption)
subtitles = self._merge_subtitles(subtitles, hls_subs, vtt_subs)
return {
'id': video_id,
'formats': formats,
'title': video_data.get('def_title'),
'description': video_data.get('def_description'),
'tags': video_data.get('def_tags', '').split(','),
'categories': video_data.get('categories'),
'thumbnail': video_data.get('src_image_url') or video_data.get('thumbnail'),
'timestamp': int_or_none(video_data.get(
'ts_published') or video_data.get('ts_added')),
'uploader': video_data.get('mcp_id'),
'duration': int_or_none(video_data.get('duration')),
'subtitles': subtitles,
}
@classmethod
def _extract_from_webpage(cls, url, webpage):
for mobj in re.finditer(cls._ANVP_RE, webpage):
anvplayer_data = unescapeHTML(json.loads(mobj.group('anvp'))) or {}
video_id, access_key = anvplayer_data.get('video'), anvplayer_data.get('accessKey')
if not access_key:
access_key = cls._MCP_TO_ACCESS_KEY_TABLE.get((anvplayer_data.get('mcp') or '').lower())
if not (video_id or '').isdigit() or not access_key:
continue
url = f'anvato:{access_key}:{video_id}'
if anvplayer_data.get('token'):
url = smuggle_url(url, {'token': anvplayer_data['token']})
yield cls.url_result(url, AnvatoIE, video_id)
def _extract_anvato_videos(self, webpage, video_id):
anvplayer_data = self._parse_json(
self._html_search_regex(
self._ANVP_RE, webpage, 'Anvato player data', group='anvp'),
video_id)
return self._get_anvato_videos(
anvplayer_data['accessKey'], anvplayer_data['video'], 'default') # cbslocal token = 'default'
def _real_extract(self, url):
url, smuggled_data = unsmuggle_url(url, {})
self._initialize_geo_bypass({
'countries': smuggled_data.get('geo_countries'),
})
access_key, video_id = self._match_valid_url(url).group('access_key_or_mcp', 'id')
if access_key not in self._ANVACK_TABLE:
access_key = self._MCP_TO_ACCESS_KEY_TABLE.get(access_key) or access_key
return self._get_anvato_videos(access_key, video_id, smuggled_data.get('token'))
yt_dlp/extractor/aol.py
+132
View File
@@ -0,0 +1,132 @@
import re
from .yahoo import YahooIE
from ..utils import (
ExtractorError,
int_or_none,
parse_qs,
url_or_none,
)
class AolIE(YahooIE): # XXX: Do not subclass from concrete IE
IE_NAME = 'aol.com'
_VALID_URL = r'(?:aol-video:|https?://(?:www\.)?aol\.(?:com|ca|co\.uk|de|jp)/video/(?:[^/]+/)*)(?P<id>\d{9}|[0-9a-f]{24}|[0-9a-f]{8}-(?:[0-9a-f]{4}-){3}[0-9a-f]{12})'
_TESTS = [{
# video with 5min ID
'url': 'https://www.aol.com/video/view/u-s--official-warns-of-largest-ever-irs-phone-scam/518167793/',
'md5': '18ef68f48740e86ae94b98da815eec42',
'info_dict': {
'id': '518167793',
'ext': 'mp4',
'title': 'U.S. Official Warns Of \'Largest Ever\' IRS Phone Scam',
'description': 'A major phone scam has cost thousands of taxpayers more than $1 million, with less than a month until income tax returns are due to the IRS.',
'timestamp': 1395405060,
'upload_date': '20140321',
'uploader': 'Newsy Studio',
},
'params': {
# m3u8 download
'skip_download': True,
}
}, {
# video with vidible ID
'url': 'https://www.aol.com/video/view/netflix-is-raising-rates/5707d6b8e4b090497b04f706/',
'info_dict': {
'id': '5707d6b8e4b090497b04f706',
'ext': 'mp4',
'title': 'Netflix is Raising Rates',
'description': 'Netflix is rewarding millions of it’s long-standing members with an increase in cost. Veuer’s Carly Figueroa has more.',
'upload_date': '20160408',
'timestamp': 1460123280,
'uploader': 'Veuer',
},
'params': {
# m3u8 download
'skip_download': True,
}
}, {
'url': 'https://www.aol.com/video/view/park-bench-season-2-trailer/559a1b9be4b0c3bfad3357a7/',
'only_matching': True,
}, {
'url': 'https://www.aol.com/video/view/donald-trump-spokeswoman-tones-down-megyn-kelly-attacks/519442220/',
'only_matching': True,
}, {
'url': 'aol-video:5707d6b8e4b090497b04f706',
'only_matching': True,
}, {
'url': 'https://www.aol.com/video/playlist/PL8245/5ca79d19d21f1a04035db606/',
'only_matching': True,
}, {
'url': 'https://www.aol.ca/video/view/u-s-woman-s-family-arrested-for-murder-first-pinned-on-panhandler-police/5c7ccf45bc03931fa04b2fe1/',
'only_matching': True,
}, {
'url': 'https://www.aol.co.uk/video/view/-one-dead-and-22-hurt-in-bus-crash-/5cb3a6f3d21f1a072b457347/',
'only_matching': True,
}, {
'url': 'https://www.aol.de/video/view/eva-braun-privataufnahmen-von-hitlers-geliebter-werden-digitalisiert/5cb2d49de98ab54c113d3d5d/',
'only_matching': True,
}, {
'url': 'https://www.aol.jp/video/playlist/5a28e936a1334d000137da0c/5a28f3151e642219fde19831/',
'only_matching': True,
}, {
# Yahoo video
'url': 'https://www.aol.com/video/play/991e6700-ac02-11ea-99ff-357400036f61/24bbc846-3e30-3c46-915e-fe8ccd7fcc46/',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
if '-' in video_id:
return self._extract_yahoo_video(video_id, 'us')
response = self._download_json(
'https://feedapi.b2c.on.aol.com/v1.0/app/videos/aolon/%s/details' % video_id,
video_id)['response']
if response['statusText'] != 'Ok':
raise ExtractorError('%s said: %s' % (self.IE_NAME, response['statusText']), expected=True)
video_data = response['data']
formats = []
m3u8_url = url_or_none(video_data.get('videoMasterPlaylist'))
if m3u8_url:
formats.extend(self._extract_m3u8_formats(
m3u8_url, video_id, 'mp4', m3u8_id='hls', fatal=False))
for rendition in video_data.get('renditions', []):
video_url = url_or_none(rendition.get('url'))
if not video_url:
continue
ext = rendition.get('format')
if ext == 'm3u8':
formats.extend(self._extract_m3u8_formats(
video_url, video_id, 'mp4', m3u8_id='hls', fatal=False))
else:
f = {
'url': video_url,
'format_id': rendition.get('quality'),
}
mobj = re.search(r'(\d+)x(\d+)', video_url)
if mobj:
f.update({
'width': int(mobj.group(1)),
'height': int(mobj.group(2)),
})
else:
qs = parse_qs(video_url)
f.update({
'width': int_or_none(qs.get('w', [None])[0]),
'height': int_or_none(qs.get('h', [None])[0]),
})
formats.append(f)
return {
'id': video_id,
'title': video_data['title'],
'duration': int_or_none(video_data.get('duration')),
'timestamp': int_or_none(video_data.get('publishDate')),
'view_count': int_or_none(video_data.get('views')),
'description': video_data.get('description'),
'uploader': video_data.get('videoOwner'),
'formats': formats,
}
yt_dlp/extractor/apa.py
+82
View File
@@ -0,0 +1,82 @@
from .common import InfoExtractor
from ..utils import (
determine_ext,
int_or_none,
url_or_none,
)
class APAIE(InfoExtractor):
_VALID_URL = r'(?P<base_url>https?://[^/]+\.apa\.at)/embed/(?P<id>[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})'
_EMBED_REGEX = [r'<iframe[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//[^/]+\.apa\.at/embed/[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12}.*?)\1']
_TESTS = [{
'url': 'http://uvp.apa.at/embed/293f6d17-692a-44e3-9fd5-7b178f3a1029',
'md5': '2b12292faeb0a7d930c778c7a5b4759b',
'info_dict': {
'id': '293f6d17-692a-44e3-9fd5-7b178f3a1029',
'ext': 'mp4',
'title': '293f6d17-692a-44e3-9fd5-7b178f3a1029',
'thumbnail': r're:^https?://.*\.jpg$',
},
}, {
'url': 'https://uvp-apapublisher.sf.apa.at/embed/2f94e9e6-d945-4db2-9548-f9a41ebf7b78',
'only_matching': True,
}, {
'url': 'http://uvp-rma.sf.apa.at/embed/70404cca-2f47-4855-bbb8-20b1fae58f76',
'only_matching': True,
}, {
'url': 'http://uvp-kleinezeitung.sf.apa.at/embed/f1c44979-dba2-4ebf-b021-e4cf2cac3c81',
'only_matching': True,
}]
def _real_extract(self, url):
mobj = self._match_valid_url(url)
video_id, base_url = mobj.group('id', 'base_url')
webpage = self._download_webpage(
'%s/player/%s' % (base_url, video_id), video_id)
jwplatform_id = self._search_regex(
r'media[iI]d\s*:\s*["\'](?P<id>[a-zA-Z0-9]{8})', webpage,
'jwplatform id', default=None)
if jwplatform_id:
return self.url_result(
'jwplatform:' + jwplatform_id, ie='JWPlatform',
video_id=video_id)
def extract(field, name=None):
return self._search_regex(
r'\b%s["\']\s*:\s*(["\'])(?P<value>(?:(?!\1).)+)\1' % field,
webpage, name or field, default=None, group='value')
title = extract('title') or video_id
description = extract('description')
thumbnail = extract('poster', 'thumbnail')
formats = []
for format_id in ('hls', 'progressive'):
source_url = url_or_none(extract(format_id))
if not source_url:
continue
ext = determine_ext(source_url)
if ext == 'm3u8':
formats.extend(self._extract_m3u8_formats(
source_url, video_id, 'mp4', entry_protocol='m3u8_native',
m3u8_id='hls', fatal=False))
else:
height = int_or_none(self._search_regex(
r'(\d+)\.mp4', source_url, 'height', default=None))
formats.append({
'url': source_url,
'format_id': format_id,
'height': height,
})
return {
'id': video_id,
'title': title,
'description': description,
'thumbnail': thumbnail,
'formats': formats,
}
yt_dlp/extractor/aparat.py
+88
View File
@@ -0,0 +1,88 @@
from .common import InfoExtractor
from ..utils import (
get_element_by_id,
int_or_none,
merge_dicts,
mimetype2ext,
url_or_none,
)
class AparatIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?aparat\.com/(?:v/|video/video/embed/videohash/)(?P<id>[a-zA-Z0-9]+)'
_EMBED_REGEX = [r'<iframe .*?src="(?P<url>http://www\.aparat\.com/video/[^"]+)"']
_TESTS = [{
'url': 'http://www.aparat.com/v/wP8On',
'md5': '131aca2e14fe7c4dcb3c4877ba300c89',
'info_dict': {
'id': 'wP8On',
'ext': 'mp4',
'title': 'تیم گلکسی 11 - زومیت',
'description': 'md5:096bdabcdcc4569f2b8a5e903a3b3028',
'duration': 231,
'timestamp': 1387394859,
'upload_date': '20131218',
'view_count': int,
},
}, {
# multiple formats
'url': 'https://www.aparat.com/v/8dflw/',
'only_matching': True,
}]
def _parse_options(self, webpage, video_id, fatal=True):
return self._parse_json(self._search_regex(
r'options\s*=\s*({.+?})\s*;', webpage, 'options', default='{}'), video_id)
def _real_extract(self, url):
video_id = self._match_id(url)
# If available, provides more metadata
webpage = self._download_webpage(url, video_id, fatal=False)
options = self._parse_options(webpage, video_id, fatal=False)
if not options:
webpage = self._download_webpage(
'http://www.aparat.com/video/video/embed/vt/frame/showvideo/yes/videohash/' + video_id,
video_id, 'Downloading embed webpage')
options = self._parse_options(webpage, video_id)
formats = []
for sources in (options.get('multiSRC') or []):
for item in sources:
if not isinstance(item, dict):
continue
file_url = url_or_none(item.get('src'))
if not file_url:
continue
item_type = item.get('type')
if item_type == 'application/vnd.apple.mpegurl':
formats.extend(self._extract_m3u8_formats(
file_url, video_id, 'mp4',
entry_protocol='m3u8_native', m3u8_id='hls',
fatal=False))
else:
ext = mimetype2ext(item.get('type'))
label = item.get('label')
formats.append({
'url': file_url,
'ext': ext,
'format_id': 'http-%s' % (label or ext),
'height': int_or_none(self._search_regex(
r'(\d+)[pP]', label or '', 'height',
default=None)),
})
info = self._search_json_ld(webpage, video_id, default={})
if not info.get('title'):
info['title'] = get_element_by_id('videoTitle', webpage) or \
self._html_search_meta(['og:title', 'twitter:title', 'DC.Title', 'title'], webpage, fatal=True)
return merge_dicts(info, {
'id': video_id,
'thumbnail': url_or_none(options.get('poster')),
'duration': int_or_none(options.get('duration')),
'formats': formats,
})
yt_dlp/extractor/appleconnect.py
+50
View File
@@ -0,0 +1,50 @@
from .common import InfoExtractor
from ..utils import (
str_to_int,
ExtractorError
)
class AppleConnectIE(InfoExtractor):
_VALID_URL = r'https?://itunes\.apple\.com/\w{0,2}/?post/(?:id)?sa\.(?P<id>[\w-]+)'
_TESTS = [{
'url': 'https://itunes.apple.com/us/post/idsa.4ab17a39-2720-11e5-96c5-a5b38f6c42d3',
'md5': 'c1d41f72c8bcaf222e089434619316e4',
'info_dict': {
'id': '4ab17a39-2720-11e5-96c5-a5b38f6c42d3',
'ext': 'm4v',
'title': 'Energy',
'uploader': 'Drake',
'thumbnail': r're:^https?://.*\.jpg$',
'upload_date': '20150710',
'timestamp': 1436545535,
},
}, {
'url': 'https://itunes.apple.com/us/post/sa.0fe0229f-2457-11e5-9f40-1bb645f2d5d9',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
try:
video_json = self._html_search_regex(
r'class="auc-video-data">(\{.*?\})', webpage, 'json')
except ExtractorError:
raise ExtractorError('This post doesn\'t contain a video', expected=True)
video_data = self._parse_json(video_json, video_id)
timestamp = str_to_int(self._html_search_regex(r'data-timestamp="(\d+)"', webpage, 'timestamp'))
like_count = str_to_int(self._html_search_regex(r'(\d+) Loves', webpage, 'like count', default=None))
return {
'id': video_id,
'url': video_data['sslSrc'],
'title': video_data['title'],
'description': video_data['description'],
'uploader': video_data['artistName'],
'thumbnail': video_data['artworkUrl'],
'timestamp': timestamp,
'like_count': like_count,
}
yt_dlp/extractor/applepodcasts.py
+85
View File
@@ -0,0 +1,85 @@
from .common import InfoExtractor
from ..utils import (
clean_html,
clean_podcast_url,
get_element_by_class,
int_or_none,
parse_iso8601,
try_get,
)
class ApplePodcastsIE(InfoExtractor):
_VALID_URL = r'https?://podcasts\.apple\.com/(?:[^/]+/)?podcast(?:/[^/]+){1,2}.*?\bi=(?P<id>\d+)'
_TESTS = [{
'url': 'https://podcasts.apple.com/us/podcast/207-whitney-webb-returns/id1135137367?i=1000482637777',
'md5': '41dc31cd650143e530d9423b6b5a344f',
'info_dict': {
'id': '1000482637777',
'ext': 'mp3',
'title': '207 - Whitney Webb Returns',
'description': 'md5:75ef4316031df7b41ced4e7b987f79c6',
'upload_date': '20200705',
'timestamp': 1593932400,
'duration': 6454,
'series': 'The Tim Dillon Show',
'thumbnail': 're:.+[.](png|jpe?g|webp)',
}
}, {
'url': 'https://podcasts.apple.com/podcast/207-whitney-webb-returns/id1135137367?i=1000482637777',
'only_matching': True,
}, {
'url': 'https://podcasts.apple.com/podcast/207-whitney-webb-returns?i=1000482637777',
'only_matching': True,
}, {
'url': 'https://podcasts.apple.com/podcast/id1135137367?i=1000482637777',
'only_matching': True,
}]
def _real_extract(self, url):
episode_id = self._match_id(url)
webpage = self._download_webpage(url, episode_id)
episode_data = {}
ember_data = {}
# new page type 2021-11
amp_data = self._parse_json(self._search_regex(
r'(?s)id="shoebox-media-api-cache-amp-podcasts"[^>]*>\s*({.+?})\s*<',
webpage, 'AMP data', default='{}'), episode_id, fatal=False) or {}
amp_data = try_get(amp_data,
lambda a: self._parse_json(
next(a[x] for x in iter(a) if episode_id in x),
episode_id),
dict) or {}
amp_data = amp_data.get('d') or []
episode_data = try_get(
amp_data,
lambda a: next(x for x in a
if x['type'] == 'podcast-episodes' and x['id'] == episode_id),
dict)
if not episode_data:
# try pre 2021-11 page type: TODO: consider deleting if no longer used
ember_data = self._parse_json(self._search_regex(
r'(?s)id="shoebox-ember-data-store"[^>]*>\s*({.+?})\s*<',
webpage, 'ember data'), episode_id) or {}
ember_data = ember_data.get(episode_id) or ember_data
episode_data = try_get(ember_data, lambda x: x['data'], dict)
episode = episode_data['attributes']
description = episode.get('description') or {}
series = None
for inc in (amp_data or ember_data.get('included') or []):
if inc.get('type') == 'media/podcast':
series = try_get(inc, lambda x: x['attributes']['name'])
series = series or clean_html(get_element_by_class('podcast-header__identity', webpage))
return {
'id': episode_id,
'title': episode.get('name'),
'url': clean_podcast_url(episode['assetUrl']),
'description': description.get('standard') or description.get('short'),
'timestamp': parse_iso8601(episode.get('releaseDateTime')),
'duration': int_or_none(episode.get('durationInMilliseconds'), 1000),
'series': series,
'thumbnail': self._og_search_thumbnail(webpage),
'vcodec': 'none',
}
yt_dlp/extractor/appletrailers.py
+278
View File
@@ -0,0 +1,278 @@
import re
import json
from .common import InfoExtractor
from ..compat import compat_urlparse
from ..utils import (
int_or_none,
parse_duration,
unified_strdate,
)
class AppleTrailersIE(InfoExtractor):
IE_NAME = 'appletrailers'
_VALID_URL = r'https?://(?:www\.|movie)?trailers\.apple\.com/(?:trailers|ca)/(?P<company>[^/]+)/(?P<movie>[^/]+)'
_TESTS = [{
'url': 'http://trailers.apple.com/trailers/wb/manofsteel/',
'info_dict': {
'id': '5111',
'title': 'Man of Steel',
},
'playlist': [
{
'md5': 'd97a8e575432dbcb81b7c3acb741f8a8',
'info_dict': {
'id': 'manofsteel-trailer4',
'ext': 'mov',
'duration': 111,
'title': 'Trailer 4',
'upload_date': '20130523',
'uploader_id': 'wb',
},
},
{
'md5': 'b8017b7131b721fb4e8d6f49e1df908c',
'info_dict': {
'id': 'manofsteel-trailer3',
'ext': 'mov',
'duration': 182,
'title': 'Trailer 3',
'upload_date': '20130417',
'uploader_id': 'wb',
},
},
{
'md5': 'd0f1e1150989b9924679b441f3404d48',
'info_dict': {
'id': 'manofsteel-trailer',
'ext': 'mov',
'duration': 148,
'title': 'Trailer',
'upload_date': '20121212',
'uploader_id': 'wb',
},
},
{
'md5': '5fe08795b943eb2e757fa95cb6def1cb',
'info_dict': {
'id': 'manofsteel-teaser',
'ext': 'mov',
'duration': 93,
'title': 'Teaser',
'upload_date': '20120721',
'uploader_id': 'wb',
},
},
]
}, {
'url': 'http://trailers.apple.com/trailers/magnolia/blackthorn/',
'info_dict': {
'id': '4489',
'title': 'Blackthorn',
},
'playlist_mincount': 2,
'expected_warnings': ['Unable to download JSON metadata'],
}, {
# json data only available from http://trailers.apple.com/trailers/feeds/data/15881.json
'url': 'http://trailers.apple.com/trailers/fox/kungfupanda3/',
'info_dict': {
'id': '15881',
'title': 'Kung Fu Panda 3',
},
'playlist_mincount': 4,
}, {
'url': 'http://trailers.apple.com/ca/metropole/autrui/',
'only_matching': True,
}, {
'url': 'http://movietrailers.apple.com/trailers/focus_features/kuboandthetwostrings/',
'only_matching': True,
}]
_JSON_RE = r'iTunes.playURL\((.*?)\);'
def _real_extract(self, url):
mobj = self._match_valid_url(url)
movie = mobj.group('movie')
uploader_id = mobj.group('company')
webpage = self._download_webpage(url, movie)
film_id = self._search_regex(r"FilmId\s*=\s*'(\d+)'", webpage, 'film id')
film_data = self._download_json(
'http://trailers.apple.com/trailers/feeds/data/%s.json' % film_id,
film_id, fatal=False)
if film_data:
entries = []
for clip in film_data.get('clips', []):
clip_title = clip['title']
formats = []
for version, version_data in clip.get('versions', {}).items():
for size, size_data in version_data.get('sizes', {}).items():
src = size_data.get('src')
if not src:
continue
formats.append({
'format_id': '%s-%s' % (version, size),
'url': re.sub(r'_(\d+p\.mov)', r'_h\1', src),
'width': int_or_none(size_data.get('width')),
'height': int_or_none(size_data.get('height')),
'language': version[:2],
})
entries.append({
'id': movie + '-' + re.sub(r'[^a-zA-Z0-9]', '', clip_title).lower(),
'formats': formats,
'title': clip_title,
'thumbnail': clip.get('screen') or clip.get('thumb'),
'duration': parse_duration(clip.get('runtime') or clip.get('faded')),
'upload_date': unified_strdate(clip.get('posted')),
'uploader_id': uploader_id,
})
page_data = film_data.get('page', {})
return self.playlist_result(entries, film_id, page_data.get('movie_title'))
playlist_url = compat_urlparse.urljoin(url, 'includes/playlists/itunes.inc')
def fix_html(s):
s = re.sub(r'(?s)<script[^<]*?>.*?</script>', '', s)
s = re.sub(r'<img ([^<]*?)/?>', r'<img \1/>', s)
# The ' in the onClick attributes are not escaped, it couldn't be parsed
# like: http://trailers.apple.com/trailers/wb/gravity/
def _clean_json(m):
return 'iTunes.playURL(%s);' % m.group(1).replace('\'', '&#39;')
s = re.sub(self._JSON_RE, _clean_json, s)
s = '<html>%s</html>' % s
return s
doc = self._download_xml(playlist_url, movie, transform_source=fix_html)
playlist = []
for li in doc.findall('./div/ul/li'):
on_click = li.find('.//a').attrib['onClick']
trailer_info_json = self._search_regex(self._JSON_RE,
on_click, 'trailer info')
trailer_info = json.loads(trailer_info_json)
first_url = trailer_info.get('url')
if not first_url:
continue
title = trailer_info['title']
video_id = movie + '-' + re.sub(r'[^a-zA-Z0-9]', '', title).lower()
thumbnail = li.find('.//img').attrib['src']
upload_date = trailer_info['posted'].replace('-', '')
runtime = trailer_info['runtime']
m = re.search(r'(?P<minutes>[0-9]+):(?P<seconds>[0-9]{1,2})', runtime)
duration = None
if m:
duration = 60 * int(m.group('minutes')) + int(m.group('seconds'))
trailer_id = first_url.split('/')[-1].rpartition('_')[0].lower()
settings_json_url = compat_urlparse.urljoin(url, 'includes/settings/%s.json' % trailer_id)
settings = self._download_json(settings_json_url, trailer_id, 'Downloading settings json')
formats = []
for format in settings['metadata']['sizes']:
# The src is a file pointing to the real video file
format_url = re.sub(r'_(\d*p\.mov)', r'_h\1', format['src'])
formats.append({
'url': format_url,
'format': format['type'],
'width': int_or_none(format['width']),
'height': int_or_none(format['height']),
})
playlist.append({
'_type': 'video',
'id': video_id,
'formats': formats,
'title': title,
'duration': duration,
'thumbnail': thumbnail,
'upload_date': upload_date,
'uploader_id': uploader_id,
'http_headers': {
'User-Agent': 'QuickTime compatible (yt-dlp)',
},
})
return {
'_type': 'playlist',
'id': movie,
'entries': playlist,
}
class AppleTrailersSectionIE(InfoExtractor):
IE_NAME = 'appletrailers:section'
_SECTIONS = {
'justadded': {
'feed_path': 'just_added',
'title': 'Just Added',
},
'exclusive': {
'feed_path': 'exclusive',
'title': 'Exclusive',
},
'justhd': {
'feed_path': 'just_hd',
'title': 'Just HD',
},
'mostpopular': {
'feed_path': 'most_pop',
'title': 'Most Popular',
},
'moviestudios': {
'feed_path': 'studios',
'title': 'Movie Studios',
},
}
_VALID_URL = r'https?://(?:www\.)?trailers\.apple\.com/#section=(?P<id>%s)' % '|'.join(_SECTIONS)
_TESTS = [{
'url': 'http://trailers.apple.com/#section=justadded',
'info_dict': {
'title': 'Just Added',
'id': 'justadded',
},
'playlist_mincount': 80,
}, {
'url': 'http://trailers.apple.com/#section=exclusive',
'info_dict': {
'title': 'Exclusive',
'id': 'exclusive',
},
'playlist_mincount': 80,
}, {
'url': 'http://trailers.apple.com/#section=justhd',
'info_dict': {
'title': 'Just HD',
'id': 'justhd',
},
'playlist_mincount': 80,
}, {
'url': 'http://trailers.apple.com/#section=mostpopular',
'info_dict': {
'title': 'Most Popular',
'id': 'mostpopular',
},
'playlist_mincount': 30,
}, {
'url': 'http://trailers.apple.com/#section=moviestudios',
'info_dict': {
'title': 'Movie Studios',
'id': 'moviestudios',
},
'playlist_mincount': 80,
}]
def _real_extract(self, url):
section = self._match_id(url)
section_data = self._download_json(
'http://trailers.apple.com/trailers/home/feeds/%s.json' % self._SECTIONS[section]['feed_path'],
section)
entries = [
self.url_result('http://trailers.apple.com' + e['location'])
for e in section_data]
return self.playlist_result(entries, section, self._SECTIONS[section]['title'])
yt_dlp/extractor/archiveorg.py
+1183
View File
File diff suppressed because it is too large Load Diff
yt_dlp/extractor/arcpublishing.py
+164
View File
@@ -0,0 +1,164 @@
import re
from .common import InfoExtractor
from ..utils import (
extract_attributes,
int_or_none,
parse_iso8601,
try_get,
)
class ArcPublishingIE(InfoExtractor):
_UUID_REGEX = r'[\da-f]{8}-(?:[\da-f]{4}-){3}[\da-f]{12}'
_VALID_URL = r'arcpublishing:(?P<org>[a-z]+):(?P<id>%s)' % _UUID_REGEX
_TESTS = [{
# https://www.adn.com/politics/2020/11/02/video-senate-candidates-campaign-in-anchorage-on-eve-of-election-day/
'url': 'arcpublishing:adn:8c99cb6e-b29c-4bc9-9173-7bf9979225ab',
'only_matching': True,
}, {
# https://www.bostonglobe.com/video/2020/12/30/metro/footage-released-showing-officer-talking-about-striking-protesters-with-car/
'url': 'arcpublishing:bostonglobe:232b7ae6-7d73-432d-bc0a-85dbf0119ab1',
'only_matching': True,
}, {
# https://www.actionnewsjax.com/video/live-stream/
'url': 'arcpublishing:cmg:cfb1cf1b-3ab5-4d1b-86c5-a5515d311f2a',
'only_matching': True,
}, {
# https://elcomercio.pe/videos/deportes/deporte-total-futbol-peruano-seleccion-peruana-la-valorizacion-de-los-peruanos-en-el-exterior-tras-un-2020-atipico-nnav-vr-video-noticia/
'url': 'arcpublishing:elcomercio:27a7e1f8-2ec7-4177-874f-a4feed2885b3',
'only_matching': True,
}, {
# https://www.clickondetroit.com/video/community/2020/05/15/events-surrounding-woodward-dream-cruise-being-canceled/
'url': 'arcpublishing:gmg:c8793fb2-8d44-4242-881e-2db31da2d9fe',
'only_matching': True,
}, {
# https://www.wabi.tv/video/2020/12/30/trenton-company-making-equipment-pfizer-covid-vaccine/
'url': 'arcpublishing:gray:0b0ba30e-032a-4598-8810-901d70e6033e',
'only_matching': True,
}, {
# https://www.lateja.cr/el-mundo/video-china-aprueba-con-condiciones-su-primera/dfcbfa57-527f-45ff-a69b-35fe71054143/video/
'url': 'arcpublishing:gruponacion:dfcbfa57-527f-45ff-a69b-35fe71054143',
'only_matching': True,
}, {
# https://www.fifthdomain.com/video/2018/03/09/is-america-vulnerable-to-a-cyber-attack/
'url': 'arcpublishing:mco:aa0ca6fe-1127-46d4-b32c-be0d6fdb8055',
'only_matching': True,
}, {
# https://www.vl.no/kultur/2020/12/09/en-melding-fra-en-lytter-endret-julelista-til-lewi-bergrud/
'url': 'arcpublishing:mentormedier:47a12084-650b-4011-bfd0-3699b6947b2d',
'only_matching': True,
}, {
# https://www.14news.com/2020/12/30/whiskey-theft-caught-camera-henderson-liquor-store/
'url': 'arcpublishing:raycom:b89f61f8-79fa-4c09-8255-e64237119bf7',
'only_matching': True,
}, {
# https://www.theglobeandmail.com/world/video-ethiopian-woman-who-became-symbol-of-integration-in-italy-killed-on/
'url': 'arcpublishing:tgam:411b34c1-8701-4036-9831-26964711664b',
'only_matching': True,
}, {
# https://www.pilotonline.com/460f2931-8130-4719-8ea1-ffcb2d7cb685-132.html
'url': 'arcpublishing:tronc:460f2931-8130-4719-8ea1-ffcb2d7cb685',
'only_matching': True,
}]
_POWA_DEFAULTS = [
(['cmg', 'prisa'], '%s-config-prod.api.cdn.arcpublishing.com/video'),
([
'adn', 'advancelocal', 'answers', 'bonnier', 'bostonglobe', 'demo',
'gmg', 'gruponacion', 'infobae', 'mco', 'nzme', 'pmn', 'raycom',
'spectator', 'tbt', 'tgam', 'tronc', 'wapo', 'wweek',
], 'video-api-cdn.%s.arcpublishing.com/api'),
]
@classmethod
def _extract_embed_urls(cls, url, webpage):
entries = []
# https://arcpublishing.atlassian.net/wiki/spaces/POWA/overview
for powa_el in re.findall(r'(<div[^>]+class="[^"]*\bpowa\b[^"]*"[^>]+data-uuid="%s"[^>]*>)' % ArcPublishingIE._UUID_REGEX, webpage):
powa = extract_attributes(powa_el) or {}
org = powa.get('data-org')
uuid = powa.get('data-uuid')
if org and uuid:
entries.append('arcpublishing:%s:%s' % (org, uuid))
return entries
def _real_extract(self, url):
org, uuid = self._match_valid_url(url).groups()
for orgs, tmpl in self._POWA_DEFAULTS:
if org in orgs:
base_api_tmpl = tmpl
break
else:
base_api_tmpl = '%s-prod-cdn.video-api.arcpublishing.com/api'
if org == 'wapo':
org = 'washpost'
video = self._download_json(
'https://%s/v1/ansvideos/findByUuid' % (base_api_tmpl % org),
uuid, query={'uuid': uuid})[0]
title = video['headlines']['basic']
is_live = video.get('status') == 'live'
urls = []
formats = []
for s in video.get('streams', []):
s_url = s.get('url')
if not s_url or s_url in urls:
continue
urls.append(s_url)
stream_type = s.get('stream_type')
if stream_type == 'smil':
smil_formats = self._extract_smil_formats(
s_url, uuid, fatal=False)
for f in smil_formats:
if f['url'].endswith('/cfx/st'):
f['app'] = 'cfx/st'
if not f['play_path'].startswith('mp4:'):
f['play_path'] = 'mp4:' + f['play_path']
if isinstance(f['tbr'], float):
f['vbr'] = f['tbr'] * 1000
del f['tbr']
f['format_id'] = 'rtmp-%d' % f['vbr']
formats.extend(smil_formats)
elif stream_type in ('ts', 'hls'):
m3u8_formats = self._extract_m3u8_formats(
s_url, uuid, 'mp4', live=is_live, m3u8_id='hls', fatal=False)
if all([f.get('acodec') == 'none' for f in m3u8_formats]):
continue
for f in m3u8_formats:
height = f.get('height')
if not height:
continue
vbr = self._search_regex(
r'[_x]%d[_-](\d+)' % height, f['url'], 'vbr', default=None)
if vbr:
f['vbr'] = int(vbr)
formats.extend(m3u8_formats)
else:
vbr = int_or_none(s.get('bitrate'))
formats.append({
'format_id': '%s-%d' % (stream_type, vbr) if vbr else stream_type,
'vbr': vbr,
'width': int_or_none(s.get('width')),
'height': int_or_none(s.get('height')),
'filesize': int_or_none(s.get('filesize')),
'url': s_url,
'quality': -10,
})
subtitles = {}
for subtitle in (try_get(video, lambda x: x['subtitles']['urls'], list) or []):
subtitle_url = subtitle.get('url')
if subtitle_url:
subtitles.setdefault('en', []).append({'url': subtitle_url})
return {
'id': uuid,
'title': title,
'thumbnail': try_get(video, lambda x: x['promo_image']['url']),
'description': try_get(video, lambda x: x['subheadlines']['basic']),
'formats': formats,
'duration': int_or_none(video.get('duration'), 100),
'timestamp': parse_iso8601(video.get('created_date')),
'subtitles': subtitles,
'is_live': is_live,
}
yt_dlp/extractor/ard.py
+645
View File
@@ -0,0 +1,645 @@
import json
import re
from .common import InfoExtractor
from .generic import GenericIE
from ..utils import (
determine_ext,
ExtractorError,
int_or_none,
parse_duration,
qualities,
str_or_none,
try_get,
unified_strdate,
unified_timestamp,
update_url_query,
url_or_none,
xpath_text,
)
from ..compat import compat_etree_fromstring
class ARDMediathekBaseIE(InfoExtractor):
_GEO_COUNTRIES = ['DE']
def _extract_media_info(self, media_info_url, webpage, video_id):
media_info = self._download_json(
media_info_url, video_id, 'Downloading media JSON')
return self._parse_media_info(media_info, video_id, '"fsk"' in webpage)
def _parse_media_info(self, media_info, video_id, fsk):
formats = self._extract_formats(media_info, video_id)
if not formats:
if fsk:
self.raise_no_formats(
'This video is only available after 20:00', expected=True)
elif media_info.get('_geoblocked'):
self.raise_geo_restricted(
'This video is not available due to geoblocking',
countries=self._GEO_COUNTRIES, metadata_available=True)
subtitles = {}
subtitle_url = media_info.get('_subtitleUrl')
if subtitle_url:
subtitles['de'] = [{
'ext': 'ttml',
'url': subtitle_url,
}, {
'ext': 'vtt',
'url': subtitle_url.replace('/ebutt/', '/webvtt/') + '.vtt',
}]
return {
'id': video_id,
'duration': int_or_none(media_info.get('_duration')),
'thumbnail': media_info.get('_previewImage'),
'is_live': media_info.get('_isLive') is True,
'formats': formats,
'subtitles': subtitles,
}
def _ARD_extract_episode_info(self, title):
"""Try to extract season/episode data from the title."""
res = {}
if not title:
return res
for pattern in [
# Pattern for title like "Homo sapiens (S06/E07) - Originalversion"
# from: https://www.ardmediathek.de/one/sendung/doctor-who/Y3JpZDovL3dkci5kZS9vbmUvZG9jdG9yIHdobw
r'.*(?P<ep_info> \(S(?P<season_number>\d+)/E(?P<episode_number>\d+)\)).*',
# E.g.: title="Fritjof aus Norwegen (2) (AD)"
# from: https://www.ardmediathek.de/ard/sammlung/der-krieg-und-ich/68cMkqJdllm639Skj4c7sS/
r'.*(?P<ep_info> \((?:Folge |Teil )?(?P<episode_number>\d+)(?:/\d+)?\)).*',
r'.*(?P<ep_info>Folge (?P<episode_number>\d+)(?:\:| -|) )\"(?P<episode>.+)\".*',
# E.g.: title="Folge 25/42: Symmetrie"
# from: https://www.ardmediathek.de/ard/video/grips-mathe/folge-25-42-symmetrie/ard-alpha/Y3JpZDovL2JyLmRlL3ZpZGVvLzMyYzI0ZjczLWQ1N2MtNDAxNC05ZmZhLTFjYzRkZDA5NDU5OQ/
# E.g.: title="Folge 1063 - Vertrauen"
# from: https://www.ardmediathek.de/ard/sendung/die-fallers/Y3JpZDovL3N3ci5kZS8yMzAyMDQ4/
r'.*(?P<ep_info>Folge (?P<episode_number>\d+)(?:/\d+)?(?:\:| -|) ).*',
]:
m = re.match(pattern, title)
if m:
groupdict = m.groupdict()
res['season_number'] = int_or_none(groupdict.get('season_number'))
res['episode_number'] = int_or_none(groupdict.get('episode_number'))
res['episode'] = str_or_none(groupdict.get('episode'))
# Build the episode title by removing numeric episode information:
if groupdict.get('ep_info') and not res['episode']:
res['episode'] = str_or_none(
title.replace(groupdict.get('ep_info'), ''))
if res['episode']:
res['episode'] = res['episode'].strip()
break
# As a fallback use the whole title as the episode name:
if not res.get('episode'):
res['episode'] = title.strip()
return res
def _extract_formats(self, media_info, video_id):
type_ = media_info.get('_type')
media_array = media_info.get('_mediaArray', [])
formats = []
for num, media in enumerate(media_array):
for stream in media.get('_mediaStreamArray', []):
stream_urls = stream.get('_stream')
if not stream_urls:
continue
if not isinstance(stream_urls, list):
stream_urls = [stream_urls]
quality = stream.get('_quality')
server = stream.get('_server')
for stream_url in stream_urls:
if not url_or_none(stream_url):
continue
ext = determine_ext(stream_url)
if quality != 'auto' and ext in ('f4m', 'm3u8'):
continue
if ext == 'f4m':
formats.extend(self._extract_f4m_formats(
update_url_query(stream_url, {
'hdcore': '3.1.1',
'plugin': 'aasp-3.1.1.69.124'
}), video_id, f4m_id='hds', fatal=False))
elif ext == 'm3u8':
formats.extend(self._extract_m3u8_formats(
stream_url, video_id, 'mp4', 'm3u8_native',
m3u8_id='hls', fatal=False))
else:
if server and server.startswith('rtmp'):
f = {
'url': server,
'play_path': stream_url,
'format_id': 'a%s-rtmp-%s' % (num, quality),
}
else:
f = {
'url': stream_url,
'format_id': 'a%s-%s-%s' % (num, ext, quality)
}
m = re.search(
r'_(?P<width>\d+)x(?P<height>\d+)\.mp4$',
stream_url)
if m:
f.update({
'width': int(m.group('width')),
'height': int(m.group('height')),
})
if type_ == 'audio':
f['vcodec'] = 'none'
formats.append(f)
return formats
class ARDMediathekIE(ARDMediathekBaseIE):
IE_NAME = 'ARD:mediathek'
_VALID_URL = r'^https?://(?:(?:(?:www|classic)\.)?ardmediathek\.de|mediathek\.(?:daserste|rbb-online)\.de|one\.ard\.de)/(?:.*/)(?P<video_id>[0-9]+|[^0-9][^/\?]+)[^/\?]*(?:\?.*)?'
_TESTS = [{
# available till 26.07.2022
'url': 'http://www.ardmediathek.de/tv/S%C3%9CDLICHT/Was-ist-die-Kunst-der-Zukunft-liebe-Ann/BR-Fernsehen/Video?bcastId=34633636&documentId=44726822',
'info_dict': {
'id': '44726822',
'ext': 'mp4',
'title': 'Was ist die Kunst der Zukunft, liebe Anna McCarthy?',
'description': 'md5:4ada28b3e3b5df01647310e41f3a62f5',
'duration': 1740,
},
'params': {
# m3u8 download
'skip_download': True,
}
}, {
'url': 'https://one.ard.de/tv/Mord-mit-Aussicht/Mord-mit-Aussicht-6-39-T%C3%B6dliche-Nach/ONE/Video?bcastId=46384294&documentId=55586872',
'only_matching': True,
}, {
# audio
'url': 'http://www.ardmediathek.de/tv/WDR-H%C3%B6rspiel-Speicher/Tod-eines-Fu%C3%9Fballers/WDR-3/Audio-Podcast?documentId=28488308&bcastId=23074086',
'only_matching': True,
}, {
'url': 'http://mediathek.daserste.de/sendungen_a-z/328454_anne-will/22429276_vertrauen-ist-gut-spionieren-ist-besser-geht',
'only_matching': True,
}, {
# audio
'url': 'http://mediathek.rbb-online.de/radio/Hörspiel/Vor-dem-Fest/kulturradio/Audio?documentId=30796318&topRessort=radio&bcastId=9839158',
'only_matching': True,
}, {
'url': 'https://classic.ardmediathek.de/tv/Panda-Gorilla-Co/Panda-Gorilla-Co-Folge-274/Das-Erste/Video?bcastId=16355486&documentId=58234698',
'only_matching': True,
}]
@classmethod
def suitable(cls, url):
return False if ARDBetaMediathekIE.suitable(url) else super(ARDMediathekIE, cls).suitable(url)
def _real_extract(self, url):
# determine video id from url
m = self._match_valid_url(url)
document_id = None
numid = re.search(r'documentId=([0-9]+)', url)
if numid:
document_id = video_id = numid.group(1)
else:
video_id = m.group('video_id')
webpage = self._download_webpage(url, video_id)
ERRORS = (
('>Leider liegt eine Störung vor.', 'Video %s is unavailable'),
('>Der gewünschte Beitrag ist nicht mehr verfügbar.<',
'Video %s is no longer available'),
)
for pattern, message in ERRORS:
if pattern in webpage:
raise ExtractorError(message % video_id, expected=True)
if re.search(r'[\?&]rss($|[=&])', url):
doc = compat_etree_fromstring(webpage.encode('utf-8'))
if doc.tag == 'rss':
return GenericIE()._extract_rss(url, video_id, doc)
title = self._og_search_title(webpage, default=None) or self._html_search_regex(
[r'<h1(?:\s+class="boxTopHeadline")?>(.*?)</h1>',
r'<meta name="dcterms\.title" content="(.*?)"/>',
r'<h4 class="headline">(.*?)</h4>',
r'<title[^>]*>(.*?)</title>'],
webpage, 'title')
description = self._og_search_description(webpage, default=None) or self._html_search_meta(
'dcterms.abstract', webpage, 'description', default=None)
if description is None:
description = self._html_search_meta(
'description', webpage, 'meta description', default=None)
if description is None:
description = self._html_search_regex(
r'<p\s+class="teasertext">(.+?)</p>',
webpage, 'teaser text', default=None)
# Thumbnail is sometimes not present.
# It is in the mobile version, but that seems to use a different URL
# structure altogether.
thumbnail = self._og_search_thumbnail(webpage, default=None)
media_streams = re.findall(r'''(?x)
mediaCollection\.addMediaStream\([0-9]+,\s*[0-9]+,\s*"[^"]*",\s*
"([^"]+)"''', webpage)
if media_streams:
QUALITIES = qualities(['lo', 'hi', 'hq'])
formats = []
for furl in set(media_streams):
if furl.endswith('.f4m'):
fid = 'f4m'
else:
fid_m = re.match(r'.*\.([^.]+)\.[^.]+$', furl)
fid = fid_m.group(1) if fid_m else None
formats.append({
'quality': QUALITIES(fid),
'format_id': fid,
'url': furl,
})
info = {
'formats': formats,
}
else: # request JSON file
if not document_id:
video_id = self._search_regex(
(r'/play/(?:config|media|sola)/(\d+)', r'contentId["\']\s*:\s*(\d+)'),
webpage, 'media id', default=None)
info = self._extract_media_info(
'http://www.ardmediathek.de/play/media/%s' % video_id,
webpage, video_id)
info.update({
'id': video_id,
'title': title,
'description': description,
'thumbnail': thumbnail,
})
info.update(self._ARD_extract_episode_info(info['title']))
return info
class ARDIE(InfoExtractor):
_VALID_URL = r'(?P<mainurl>https?://(?:www\.)?daserste\.de/(?:[^/?#&]+/)+(?P<id>[^/?#&]+))\.html'
_TESTS = [{
# available till 7.12.2023
'url': 'https://www.daserste.de/information/talk/maischberger/videos/maischberger-video-424.html',
'md5': 'a438f671e87a7eba04000336a119ccc4',
'info_dict': {
'id': 'maischberger-video-424',
'display_id': 'maischberger-video-424',
'ext': 'mp4',
'duration': 4452.0,
'title': 'maischberger am 07.12.2022',
'upload_date': '20221207',
'thumbnail': r're:^https?://.*\.jpg$',
},
}, {
'url': 'https://www.daserste.de/information/politik-weltgeschehen/morgenmagazin/videosextern/dominik-kahun-aus-der-nhl-direkt-zur-weltmeisterschaft-100.html',
'only_matching': True,
}, {
'url': 'https://www.daserste.de/information/nachrichten-wetter/tagesthemen/videosextern/tagesthemen-17736.html',
'only_matching': True,
}, {
'url': 'https://www.daserste.de/unterhaltung/serie/in-aller-freundschaft-die-jungen-aerzte/videos/diversity-tag-sanam-afrashteh100.html',
'only_matching': True,
}, {
'url': 'http://www.daserste.de/information/reportage-dokumentation/dokus/videos/die-story-im-ersten-mission-unter-falscher-flagge-100.html',
'only_matching': True,
}, {
'url': 'https://www.daserste.de/unterhaltung/serie/in-aller-freundschaft-die-jungen-aerzte/Drehpause-100.html',
'only_matching': True,
}, {
'url': 'https://www.daserste.de/unterhaltung/film/filmmittwoch-im-ersten/videos/making-ofwendezeit-video-100.html',
'only_matching': True,
}]
def _real_extract(self, url):
mobj = self._match_valid_url(url)
display_id = mobj.group('id')
player_url = mobj.group('mainurl') + '~playerXml.xml'
doc = self._download_xml(player_url, display_id)
video_node = doc.find('./video')
upload_date = unified_strdate(xpath_text(
video_node, './broadcastDate'))
thumbnail = xpath_text(video_node, './/teaserImage//variant/url')
formats = []
for a in video_node.findall('.//asset'):
file_name = xpath_text(a, './fileName', default=None)
if not file_name:
continue
format_type = a.attrib.get('type')
format_url = url_or_none(file_name)
if format_url:
ext = determine_ext(file_name)
if ext == 'm3u8':
formats.extend(self._extract_m3u8_formats(
format_url, display_id, 'mp4', entry_protocol='m3u8_native',
m3u8_id=format_type or 'hls', fatal=False))
continue
elif ext == 'f4m':
formats.extend(self._extract_f4m_formats(
update_url_query(format_url, {'hdcore': '3.7.0'}),
display_id, f4m_id=format_type or 'hds', fatal=False))
continue
f = {
'format_id': format_type,
'width': int_or_none(xpath_text(a, './frameWidth')),
'height': int_or_none(xpath_text(a, './frameHeight')),
'vbr': int_or_none(xpath_text(a, './bitrateVideo')),
'abr': int_or_none(xpath_text(a, './bitrateAudio')),
'vcodec': xpath_text(a, './codecVideo'),
'tbr': int_or_none(xpath_text(a, './totalBitrate')),
}
server_prefix = xpath_text(a, './serverPrefix', default=None)
if server_prefix:
f.update({
'url': server_prefix,
'playpath': file_name,
})
else:
if not format_url:
continue
f['url'] = format_url
formats.append(f)
_SUB_FORMATS = (
('./dataTimedText', 'ttml'),
('./dataTimedTextNoOffset', 'ttml'),
('./dataTimedTextVtt', 'vtt'),
)
subtitles = {}
for subsel, subext in _SUB_FORMATS:
for node in video_node.findall(subsel):
subtitles.setdefault('de', []).append({
'url': node.attrib['url'],
'ext': subext,
})
return {
'id': xpath_text(video_node, './videoId', default=display_id),
'formats': formats,
'subtitles': subtitles,
'display_id': display_id,
'title': video_node.find('./title').text,
'duration': parse_duration(video_node.find('./duration').text),
'upload_date': upload_date,
'thumbnail': thumbnail,
}
class ARDBetaMediathekIE(ARDMediathekBaseIE):
_VALID_URL = r'''(?x)https://
(?:(?:beta|www)\.)?ardmediathek\.de/
(?:(?P<client>[^/]+)/)?
(?:player|live|video|(?P<playlist>sendung|sammlung))/
(?:(?P<display_id>(?(playlist)[^?#]+?|[^?#]+))/)?
(?P<id>(?(playlist)|Y3JpZDovL)[a-zA-Z0-9]+)
(?(playlist)/(?P<season>\d+)?/?(?:[?#]|$))'''
_TESTS = [{
'url': 'https://www.ardmediathek.de/mdr/video/die-robuste-roswita/Y3JpZDovL21kci5kZS9iZWl0cmFnL2Ntcy84MWMxN2MzZC0wMjkxLTRmMzUtODk4ZS0wYzhlOWQxODE2NGI/',
'md5': 'a1dc75a39c61601b980648f7c9f9f71d',
'info_dict': {
'display_id': 'die-robuste-roswita',
'id': '78566716',
'title': 'Die robuste Roswita',
'description': r're:^Der Mord.*totgeglaubte Ehefrau Roswita',
'duration': 5316,
'thumbnail': 'https://img.ardmediathek.de/standard/00/78/56/67/84/575672121/16x9/960?mandant=ard',
'timestamp': 1596658200,
'upload_date': '20200805',
'ext': 'mp4',
},
'skip': 'Error',
}, {
'url': 'https://www.ardmediathek.de/video/tagesschau-oder-tagesschau-20-00-uhr/das-erste/Y3JpZDovL2Rhc2Vyc3RlLmRlL3RhZ2Vzc2NoYXUvZmM4ZDUxMjgtOTE0ZC00Y2MzLTgzNzAtNDZkNGNiZWJkOTll',
'md5': 'f1837e563323b8a642a8ddeff0131f51',
'info_dict': {
'id': '10049223',
'ext': 'mp4',
'title': 'tagesschau, 20:00 Uhr',
'timestamp': 1636398000,
'description': 'md5:39578c7b96c9fe50afdf5674ad985e6b',
'upload_date': '20211108',
},
}, {
'url': 'https://www.ardmediathek.de/sendung/beforeigners/beforeigners/staffel-1/Y3JpZDovL2Rhc2Vyc3RlLmRlL2JlZm9yZWlnbmVycw/1',
'playlist_count': 6,
'info_dict': {
'id': 'Y3JpZDovL2Rhc2Vyc3RlLmRlL2JlZm9yZWlnbmVycw',
'title': 'beforeigners/beforeigners/staffel-1',
},
}, {
'url': 'https://beta.ardmediathek.de/ard/video/Y3JpZDovL2Rhc2Vyc3RlLmRlL3RhdG9ydC9mYmM4NGM1NC0xNzU4LTRmZGYtYWFhZS0wYzcyZTIxNGEyMDE',
'only_matching': True,
}, {
'url': 'https://ardmediathek.de/ard/video/saartalk/saartalk-gesellschaftsgift-haltung-gegen-hass/sr-fernsehen/Y3JpZDovL3NyLW9ubGluZS5kZS9TVF84MTY4MA/',
'only_matching': True,
}, {
'url': 'https://www.ardmediathek.de/ard/video/trailer/private-eyes-s01-e01/one/Y3JpZDovL3dkci5kZS9CZWl0cmFnLTE1MTgwYzczLWNiMTEtNGNkMS1iMjUyLTg5MGYzOWQxZmQ1YQ/',
'only_matching': True,
}, {
'url': 'https://www.ardmediathek.de/ard/player/Y3JpZDovL3N3ci5kZS9hZXgvbzEwNzE5MTU/',
'only_matching': True,
}, {
'url': 'https://www.ardmediathek.de/swr/live/Y3JpZDovL3N3ci5kZS8xMzQ4MTA0Mg',
'only_matching': True,
}, {
# playlist of type 'sendung'
'url': 'https://www.ardmediathek.de/ard/sendung/doctor-who/Y3JpZDovL3dkci5kZS9vbmUvZG9jdG9yIHdobw/',
'only_matching': True,
}, {
# playlist of type 'sammlung'
'url': 'https://www.ardmediathek.de/ard/sammlung/team-muenster/5JpTzLSbWUAK8184IOvEir/',
'only_matching': True,
}, {
'url': 'https://www.ardmediathek.de/video/coronavirus-update-ndr-info/astrazeneca-kurz-lockdown-und-pims-syndrom-81/ndr/Y3JpZDovL25kci5kZS84NzE0M2FjNi0wMWEwLTQ5ODEtOTE5NS1mOGZhNzdhOTFmOTI/',
'only_matching': True,
}, {
'url': 'https://www.ardmediathek.de/ard/player/Y3JpZDovL3dkci5kZS9CZWl0cmFnLWQ2NDJjYWEzLTMwZWYtNGI4NS1iMTI2LTU1N2UxYTcxOGIzOQ/tatort-duo-koeln-leipzig-ihr-kinderlein-kommet',
'only_matching': True,
}]
def _ARD_load_playlist_snipped(self, playlist_id, display_id, client, mode, pageNumber):
""" Query the ARD server for playlist information
and returns the data in "raw" format """
if mode == 'sendung':
graphQL = json.dumps({
'query': '''{
showPage(
client: "%s"
showId: "%s"
pageNumber: %d
) {
pagination {
pageSize
totalElements
}
teasers { # Array
mediumTitle
links { target { id href title } }
type
}
}}''' % (client, playlist_id, pageNumber),
}).encode()
else: # mode == 'sammlung'
graphQL = json.dumps({
'query': '''{
morePage(
client: "%s"
compilationId: "%s"
pageNumber: %d
) {
widget {
pagination {
pageSize
totalElements
}
teasers { # Array
mediumTitle
links { target { id href title } }
type
}
}
}}''' % (client, playlist_id, pageNumber),
}).encode()
# Ressources for ARD graphQL debugging:
# https://api-test.ardmediathek.de/public-gateway
show_page = self._download_json(
'https://api.ardmediathek.de/public-gateway',
'[Playlist] %s' % display_id,
data=graphQL,
headers={'Content-Type': 'application/json'})['data']
# align the structure of the returned data:
if mode == 'sendung':
show_page = show_page['showPage']
else: # mode == 'sammlung'
show_page = show_page['morePage']['widget']
return show_page
def _ARD_extract_playlist(self, url, playlist_id, display_id, client, mode):
""" Collects all playlist entries and returns them as info dict.
Supports playlists of mode 'sendung' and 'sammlung', and also nested
playlists. """
entries = []
pageNumber = 0
while True: # iterate by pageNumber
show_page = self._ARD_load_playlist_snipped(
playlist_id, display_id, client, mode, pageNumber)
for teaser in show_page['teasers']: # process playlist items
if '/compilation/' in teaser['links']['target']['href']:
# alternativ cond.: teaser['type'] == "compilation"
# => This is an nested compilation, e.g. like:
# https://www.ardmediathek.de/ard/sammlung/die-kirche-bleibt-im-dorf/5eOHzt8XB2sqeFXbIoJlg2/
link_mode = 'sammlung'
else:
link_mode = 'video'
item_url = 'https://www.ardmediathek.de/%s/%s/%s/%s/%s' % (
client, link_mode, display_id,
# perform HTLM quoting of episode title similar to ARD:
re.sub('^-|-$', '', # remove '-' from begin/end
re.sub('[^a-zA-Z0-9]+', '-', # replace special chars by -
teaser['links']['target']['title'].lower()
.replace('ä', 'ae').replace('ö', 'oe')
.replace('ü', 'ue').replace('ß', 'ss'))),
teaser['links']['target']['id'])
entries.append(self.url_result(
item_url,
ie=ARDBetaMediathekIE.ie_key()))
if (show_page['pagination']['pageSize'] * (pageNumber + 1)
>= show_page['pagination']['totalElements']):
# we've processed enough pages to get all playlist entries
break
pageNumber = pageNumber + 1
return self.playlist_result(entries, playlist_id, playlist_title=display_id)
def _real_extract(self, url):
video_id, display_id, playlist_type, client, season_number = self._match_valid_url(url).group(
'id', 'display_id', 'playlist', 'client', 'season')
display_id, client = display_id or video_id, client or 'ard'
if playlist_type:
# TODO: Extract only specified season
return self._ARD_extract_playlist(url, video_id, display_id, client, playlist_type)
player_page = self._download_json(
'https://api.ardmediathek.de/public-gateway',
display_id, data=json.dumps({
'query': '''{
playerPage(client:"%s", clipId: "%s") {
blockedByFsk
broadcastedOn
maturityContentRating
mediaCollection {
_duration
_geoblocked
_isLive
_mediaArray {
_mediaStreamArray {
_quality
_server
_stream
}
}
_previewImage
_subtitleUrl
_type
}
show {
title
}
synopsis
title
tracking {
atiCustomVars {
contentId
}
}
}
}''' % (client, video_id),
}).encode(), headers={
'Content-Type': 'application/json'
})['data']['playerPage']
title = player_page['title']
content_id = str_or_none(try_get(
player_page, lambda x: x['tracking']['atiCustomVars']['contentId']))
media_collection = player_page.get('mediaCollection') or {}
if not media_collection and content_id:
media_collection = self._download_json(
'https://www.ardmediathek.de/play/media/' + content_id,
content_id, fatal=False) or {}
info = self._parse_media_info(
media_collection, content_id or video_id,
player_page.get('blockedByFsk'))
age_limit = None
description = player_page.get('synopsis')
maturity_content_rating = player_page.get('maturityContentRating')
if maturity_content_rating:
age_limit = int_or_none(maturity_content_rating.lstrip('FSK'))
if not age_limit and description:
age_limit = int_or_none(self._search_regex(
r'\(FSK\s*(\d+)\)\s*$', description, 'age limit', default=None))
info.update({
'age_limit': age_limit,
'display_id': display_id,
'title': title,
'description': description,
'timestamp': unified_timestamp(player_page.get('broadcastedOn')),
'series': try_get(player_page, lambda x: x['show']['title']),
})
info.update(self._ARD_extract_episode_info(info['title']))
return info
yt_dlp/extractor/arkena.py
+150
View File
@@ -0,0 +1,150 @@
from .common import InfoExtractor
from ..utils import (
ExtractorError,
float_or_none,
int_or_none,
parse_iso8601,
parse_qs,
try_get,
)
class ArkenaIE(InfoExtractor):
_VALID_URL = r'''(?x)
https?://
(?:
video\.(?:arkena|qbrick)\.com/play2/embed/player\?|
play\.arkena\.com/(?:config|embed)/avp/v\d/player/media/(?P<id>[^/]+)/[^/]+/(?P<account_id>\d+)
)
'''
# See https://support.arkena.com/display/PLAY/Ways+to+embed+your+video
_EMBED_REGEX = [r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//play\.arkena\.com/embed/avp/.+?)\1']
_TESTS = [{
'url': 'https://video.qbrick.com/play2/embed/player?accountId=1034090&mediaId=d8ab4607-00090107-aab86310',
'md5': '97f117754e5f3c020f5f26da4a44ebaf',
'info_dict': {
'id': 'd8ab4607-00090107-aab86310',
'ext': 'mp4',
'title': 'EM_HT20_117_roslund_v2.mp4',
'timestamp': 1608285912,
'upload_date': '20201218',
'duration': 1429.162667,
'subtitles': {
'sv': 'count:3',
},
},
}, {
'url': 'https://play.arkena.com/embed/avp/v2/player/media/b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe/1/129411',
'only_matching': True,
}, {
'url': 'https://play.arkena.com/config/avp/v2/player/media/b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe/1/129411/?callbackMethod=jQuery1111023664739129262213_1469227693893',
'only_matching': True,
}, {
'url': 'http://play.arkena.com/config/avp/v1/player/media/327336/darkmatter/131064/?callbackMethod=jQuery1111002221189684892677_1469227595972',
'only_matching': True,
}, {
'url': 'http://play.arkena.com/embed/avp/v1/player/media/327336/darkmatter/131064/',
'only_matching': True,
}, {
'url': 'http://video.arkena.com/play2/embed/player?accountId=472718&mediaId=35763b3b-00090078-bf604299&pageStyling=styled',
'only_matching': True,
}]
def _real_extract(self, url):
mobj = self._match_valid_url(url)
video_id = mobj.group('id')
account_id = mobj.group('account_id')
# Handle http://video.arkena.com/play2/embed/player URL
if not video_id:
qs = parse_qs(url)
video_id = qs.get('mediaId', [None])[0]
account_id = qs.get('accountId', [None])[0]
if not video_id or not account_id:
raise ExtractorError('Invalid URL', expected=True)
media = self._download_json(
'https://video.qbrick.com/api/v1/public/accounts/%s/medias/%s' % (account_id, video_id),
video_id, query={
# https://video.qbrick.com/docs/api/examples/library-api.html
'fields': 'asset/resources/*/renditions/*(height,id,language,links/*(href,mimeType),type,size,videos/*(audios/*(codec,sampleRate),bitrate,codec,duration,height,width),width),created,metadata/*(title,description),tags',
})
metadata = media.get('metadata') or {}
title = metadata['title']
duration = None
formats = []
thumbnails = []
subtitles = {}
for resource in media['asset']['resources']:
for rendition in (resource.get('renditions') or []):
rendition_type = rendition.get('type')
for i, link in enumerate(rendition.get('links') or []):
href = link.get('href')
if not href:
continue
if rendition_type == 'image':
thumbnails.append({
'filesize': int_or_none(rendition.get('size')),
'height': int_or_none(rendition.get('height')),
'id': rendition.get('id'),
'url': href,
'width': int_or_none(rendition.get('width')),
})
elif rendition_type == 'subtitle':
subtitles.setdefault(rendition.get('language') or 'en', []).append({
'url': href,
})
elif rendition_type == 'video':
f = {
'filesize': int_or_none(rendition.get('size')),
'format_id': rendition.get('id'),
'url': href,
}
video = try_get(rendition, lambda x: x['videos'][i], dict)
if video:
if not duration:
duration = float_or_none(video.get('duration'))
f.update({
'height': int_or_none(video.get('height')),
'tbr': int_or_none(video.get('bitrate'), 1000),
'vcodec': video.get('codec'),
'width': int_or_none(video.get('width')),
})
audio = try_get(video, lambda x: x['audios'][0], dict)
if audio:
f.update({
'acodec': audio.get('codec'),
'asr': int_or_none(audio.get('sampleRate')),
})
formats.append(f)
elif rendition_type == 'index':
mime_type = link.get('mimeType')
if mime_type == 'application/smil+xml':
formats.extend(self._extract_smil_formats(
href, video_id, fatal=False))
elif mime_type == 'application/x-mpegURL':
formats.extend(self._extract_m3u8_formats(
href, video_id, 'mp4', 'm3u8_native',
m3u8_id='hls', fatal=False))
elif mime_type == 'application/hds+xml':
formats.extend(self._extract_f4m_formats(
href, video_id, f4m_id='hds', fatal=False))
elif mime_type == 'application/dash+xml':
formats.extend(self._extract_f4m_formats(
href, video_id, f4m_id='hds', fatal=False))
elif mime_type == 'application/vnd.ms-sstr+xml':
formats.extend(self._extract_ism_formats(
href, video_id, ism_id='mss', fatal=False))
return {
'id': video_id,
'title': title,
'description': metadata.get('description'),
'timestamp': parse_iso8601(media.get('created')),
'thumbnails': thumbnails,
'subtitles': subtitles,
'duration': duration,
'tags': media.get('tags'),
'formats': formats,
}
yt_dlp/extractor/arnes.py
+98
View File
@@ -0,0 +1,98 @@
from .common import InfoExtractor
from ..compat import (
compat_parse_qs,
compat_urllib_parse_urlparse,
)
from ..utils import (
format_field,
float_or_none,
int_or_none,
parse_iso8601,
remove_start,
)
class ArnesIE(InfoExtractor):
IE_NAME = 'video.arnes.si'
IE_DESC = 'Arnes Video'
_VALID_URL = r'https?://video\.arnes\.si/(?:[a-z]{2}/)?(?:watch|embed|api/(?:asset|public/video))/(?P<id>[0-9a-zA-Z]{12})'
_TESTS = [{
'url': 'https://video.arnes.si/watch/a1qrWTOQfVoU?t=10',
'md5': '4d0f4d0a03571b33e1efac25fd4a065d',
'info_dict': {
'id': 'a1qrWTOQfVoU',
'ext': 'mp4',
'title': 'Linearna neodvisnost, definicija',
'description': 'Linearna neodvisnost, definicija',
'license': 'PRIVATE',
'creator': 'Polona Oblak',
'timestamp': 1585063725,
'upload_date': '20200324',
'channel': 'Polona Oblak',
'channel_id': 'q6pc04hw24cj',
'channel_url': 'https://video.arnes.si/?channel=q6pc04hw24cj',
'duration': 596.75,
'view_count': int,
'tags': ['linearna_algebra'],
'start_time': 10,
}
}, {
'url': 'https://video.arnes.si/api/asset/s1YjnV7hadlC/play.mp4',
'only_matching': True,
}, {
'url': 'https://video.arnes.si/embed/s1YjnV7hadlC',
'only_matching': True,
}, {
'url': 'https://video.arnes.si/en/watch/s1YjnV7hadlC',
'only_matching': True,
}, {
'url': 'https://video.arnes.si/embed/s1YjnV7hadlC?t=123&hideRelated=1',
'only_matching': True,
}, {
'url': 'https://video.arnes.si/api/public/video/s1YjnV7hadlC',
'only_matching': True,
}]
_BASE_URL = 'https://video.arnes.si'
def _real_extract(self, url):
video_id = self._match_id(url)
video = self._download_json(
self._BASE_URL + '/api/public/video/' + video_id, video_id)['data']
title = video['title']
formats = []
for media in (video.get('media') or []):
media_url = media.get('url')
if not media_url:
continue
formats.append({
'url': self._BASE_URL + media_url,
'format_id': remove_start(media.get('format'), 'FORMAT_'),
'format_note': media.get('formatTranslation'),
'width': int_or_none(media.get('width')),
'height': int_or_none(media.get('height')),
})
channel = video.get('channel') or {}
channel_id = channel.get('url')
thumbnail = video.get('thumbnailUrl')
return {
'id': video_id,
'title': title,
'formats': formats,
'thumbnail': self._BASE_URL + thumbnail,
'description': video.get('description'),
'license': video.get('license'),
'creator': video.get('author'),
'timestamp': parse_iso8601(video.get('creationTime')),
'channel': channel.get('name'),
'channel_id': channel_id,
'channel_url': format_field(channel_id, None, f'{self._BASE_URL}/?channel=%s'),
'duration': float_or_none(video.get('duration'), 1000),
'view_count': int_or_none(video.get('views')),
'tags': video.get('hashtags'),
'start_time': int_or_none(compat_parse_qs(
compat_urllib_parse_urlparse(url).query).get('t', [None])[0]),
}
yt_dlp/extractor/arte.py
+324
View File
@@ -0,0 +1,324 @@
import re
from .common import InfoExtractor
from ..utils import (
ExtractorError,
GeoRestrictedError,
int_or_none,
parse_iso8601,
parse_qs,
strip_or_none,
traverse_obj,
url_or_none,
)
class ArteTVBaseIE(InfoExtractor):
_ARTE_LANGUAGES = 'fr|de|en|es|it|pl'
_API_BASE = 'https://api.arte.tv/api/player/v2'
class ArteTVIE(ArteTVBaseIE):
_VALID_URL = r'''(?x)
(?:https?://
(?:
(?:www\.)?arte\.tv/(?P<lang>%(langs)s)/videos|
api\.arte\.tv/api/player/v\d+/config/(?P<lang_2>%(langs)s)
)
|arte://program)
/(?P<id>\d{6}-\d{3}-[AF]|LIVE)
''' % {'langs': ArteTVBaseIE._ARTE_LANGUAGES}
_TESTS = [{
'url': 'https://www.arte.tv/en/videos/088501-000-A/mexico-stealing-petrol-to-survive/',
'only_matching': True,
}, {
'url': 'https://www.arte.tv/pl/videos/100103-000-A/usa-dyskryminacja-na-porodowce/',
'info_dict': {
'id': '100103-000-A',
'title': 'USA: Dyskryminacja na porodówce',
'description': 'md5:242017b7cce59ffae340a54baefcafb1',
'alt_title': 'ARTE Reportage',
'upload_date': '20201103',
'duration': 554,
'thumbnail': r're:https://api-cdn\.arte\.tv/.+940x530',
'timestamp': 1604417980,
'ext': 'mp4',
},
'params': {'skip_download': 'm3u8'}
}, {
'note': 'No alt_title',
'url': 'https://www.arte.tv/fr/videos/110371-000-A/la-chaleur-supplice-des-arbres-de-rue/',
'info_dict': {
'id': '110371-000-A',
'ext': 'mp4',
'upload_date': '20220718',
'duration': 154,
'timestamp': 1658162460,
'description': 'md5:5890f36fe7dccfadb8b7c0891de54786',
'title': 'La chaleur, supplice des arbres de rue',
'thumbnail': 'https://api-cdn.arte.tv/img/v2/image/CPE2sQDtD8GLQgt8DuYHLf/940x530',
},
'params': {'skip_download': 'm3u8'}
}, {
'url': 'https://api.arte.tv/api/player/v2/config/de/100605-013-A',
'only_matching': True,
}, {
'url': 'https://api.arte.tv/api/player/v2/config/de/LIVE',
'only_matching': True,
}, {
'url': 'https://www.arte.tv/de/videos/110203-006-A/zaz/',
'info_dict': {
'id': '110203-006-A',
'chapters': 'count:16',
'description': 'md5:cf592f1df52fe52007e3f8eac813c084',
'alt_title': 'Zaz',
'title': 'Baloise Session 2022',
'timestamp': 1668445200,
'duration': 4054,
'thumbnail': 'https://api-cdn.arte.tv/img/v2/image/ubQjmVCGyRx3hmBuZEK9QZ/940x530',
'upload_date': '20221114',
'ext': 'mp4',
},
'expected_warnings': ['geo restricted']
}]
_GEO_BYPASS = True
_LANG_MAP = { # ISO639 -> French abbreviations
'fr': 'F',
'de': 'A',
'en': 'E[ANG]',
'es': 'E[ESP]',
'it': 'E[ITA]',
'pl': 'E[POL]',
# XXX: probably means mixed; <https://www.arte.tv/en/videos/107710-029-A/dispatches-from-ukraine-local-journalists-report/>
# uses this code for audio that happens to be in Ukrainian, but the manifest uses the ISO code 'mul' (mixed)
'mul': 'EU',
}
_VERSION_CODE_RE = re.compile(r'''(?x)
V
(?P<original_voice>O?)
(?P<vlang>[FA]|E\[[A-Z]+\]|EU)?
(?P<audio_desc>AUD|)
(?:
(?P<has_sub>-ST)
(?P<sdh_sub>M?)
(?P<sub_lang>[FA]|E\[[A-Z]+\]|EU)
)?
''')
# all obtained by exhaustive testing
_COUNTRIES_MAP = {
'DE_FR': (
'BL', 'DE', 'FR', 'GF', 'GP', 'MF', 'MQ', 'NC',
'PF', 'PM', 'RE', 'WF', 'YT',
),
# with both of the below 'BE' sometimes works, sometimes doesn't
'EUR_DE_FR': (
'AT', 'BL', 'CH', 'DE', 'FR', 'GF', 'GP', 'LI',
'MC', 'MF', 'MQ', 'NC', 'PF', 'PM', 'RE', 'WF',
'YT',
),
'SAT': (
'AD', 'AT', 'AX', 'BG', 'BL', 'CH', 'CY', 'CZ',
'DE', 'DK', 'EE', 'ES', 'FI', 'FR', 'GB', 'GF',
'GR', 'HR', 'HU', 'IE', 'IS', 'IT', 'KN', 'LI',
'LT', 'LU', 'LV', 'MC', 'MF', 'MQ', 'MT', 'NC',
'NL', 'NO', 'PF', 'PL', 'PM', 'PT', 'RE', 'RO',
'SE', 'SI', 'SK', 'SM', 'VA', 'WF', 'YT',
),
}
def _real_extract(self, url):
mobj = self._match_valid_url(url)
video_id = mobj.group('id')
lang = mobj.group('lang') or mobj.group('lang_2')
langauge_code = self._LANG_MAP.get(lang)
config = self._download_json(f'{self._API_BASE}/config/{lang}/{video_id}', video_id)
geoblocking = traverse_obj(config, ('data', 'attributes', 'restriction', 'geoblocking')) or {}
if geoblocking.get('restrictedArea'):
raise GeoRestrictedError(f'Video restricted to {geoblocking["code"]!r}',
countries=self._COUNTRIES_MAP.get(geoblocking['code'], ('DE', 'FR')))
if not traverse_obj(config, ('data', 'attributes', 'rights')):
# Eg: https://www.arte.tv/de/videos/097407-215-A/28-minuten
# Eg: https://www.arte.tv/es/videos/104351-002-A/serviteur-du-peuple-1-23
raise ExtractorError(
'Video is not available in this language edition of Arte or broadcast rights expired', expected=True)
formats, subtitles = [], {}
secondary_formats = []
for stream in config['data']['attributes']['streams']:
# official player contains code like `e.get("versions")[0].eStat.ml5`
stream_version = stream['versions'][0]
stream_version_code = stream_version['eStat']['ml5']
lang_pref = -1
m = self._VERSION_CODE_RE.match(stream_version_code)
if m:
lang_pref = int(''.join('01'[x] for x in (
m.group('vlang') == langauge_code, # we prefer voice in the requested language
not m.group('audio_desc'), # and not the audio description version
bool(m.group('original_voice')), # but if voice is not in the requested language, at least choose the original voice
m.group('sub_lang') == langauge_code, # if subtitles are present, we prefer them in the requested language
not m.group('has_sub'), # but we prefer no subtitles otherwise
not m.group('sdh_sub'), # and we prefer not the hard-of-hearing subtitles if there are subtitles
)))
short_label = traverse_obj(stream_version, 'shortLabel', expected_type=str, default='?')
if stream['protocol'].startswith('HLS'):
fmts, subs = self._extract_m3u8_formats_and_subtitles(
stream['url'], video_id=video_id, ext='mp4', m3u8_id=stream_version_code, fatal=False)
for fmt in fmts:
fmt.update({
'format_note': f'{stream_version.get("label", "unknown")} [{short_label}]',
'language_preference': lang_pref,
})
if any(map(short_label.startswith, ('cc', 'OGsub'))):
secondary_formats.extend(fmts)
else:
formats.extend(fmts)
self._merge_subtitles(subs, target=subtitles)
elif stream['protocol'] in ('HTTPS', 'RTMP'):
formats.append({
'format_id': f'{stream["protocol"]}-{stream_version_code}',
'url': stream['url'],
'format_note': f'{stream_version.get("label", "unknown")} [{short_label}]',
'language_preference': lang_pref,
# 'ext': 'mp4', # XXX: may or may not be necessary, at least for HTTPS
})
else:
self.report_warning(f'Skipping stream with unknown protocol {stream["protocol"]}')
formats.extend(secondary_formats)
self._remove_duplicate_formats(formats)
metadata = config['data']['attributes']['metadata']
return {
'id': metadata['providerId'],
'webpage_url': traverse_obj(metadata, ('link', 'url')),
'title': traverse_obj(metadata, 'subtitle', 'title'),
'alt_title': metadata.get('subtitle') and metadata.get('title'),
'description': metadata.get('description'),
'duration': traverse_obj(metadata, ('duration', 'seconds')),
'language': metadata.get('language'),
'timestamp': traverse_obj(config, ('data', 'attributes', 'rights', 'begin'), expected_type=parse_iso8601),
'is_live': config['data']['attributes'].get('live', False),
'formats': formats,
'subtitles': subtitles,
'thumbnails': [
{'url': image['url'], 'id': image.get('caption')}
for image in metadata.get('images') or [] if url_or_none(image.get('url'))
],
# TODO: chapters may also be in stream['segments']?
'chapters': traverse_obj(config, ('data', 'attributes', 'chapters', 'elements', ..., {
'start_time': 'startTime',
'title': 'title',
})) or None,
}
class ArteTVEmbedIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?arte\.tv/player/v\d+/index\.php\?.*?\bjson_url=.+'
_EMBED_REGEX = [r'<(?:iframe|script)[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?arte\.tv/player/v\d+/index\.php\?.*?\bjson_url=.+?)\1']
_TESTS = [{
'url': 'https://www.arte.tv/player/v5/index.php?json_url=https%3A%2F%2Fapi.arte.tv%2Fapi%2Fplayer%2Fv2%2Fconfig%2Fde%2F100605-013-A&lang=de&autoplay=true&mute=0100605-013-A',
'info_dict': {
'id': '100605-013-A',
'ext': 'mp4',
'title': 'United we Stream November Lockdown Edition #13',
'description': 'md5:be40b667f45189632b78c1425c7c2ce1',
'upload_date': '20201116',
},
'skip': 'No video available'
}, {
'url': 'https://www.arte.tv/player/v3/index.php?json_url=https://api.arte.tv/api/player/v2/config/de/100605-013-A',
'only_matching': True,
}]
def _real_extract(self, url):
qs = parse_qs(url)
json_url = qs['json_url'][0]
video_id = ArteTVIE._match_id(json_url)
return self.url_result(
json_url, ie=ArteTVIE.ie_key(), video_id=video_id)
class ArteTVPlaylistIE(ArteTVBaseIE):
_VALID_URL = r'https?://(?:www\.)?arte\.tv/(?P<lang>%s)/videos/(?P<id>RC-\d{6})' % ArteTVBaseIE._ARTE_LANGUAGES
_TESTS = [{
'url': 'https://www.arte.tv/en/videos/RC-016954/earn-a-living/',
'only_matching': True,
}, {
'url': 'https://www.arte.tv/pl/videos/RC-014123/arte-reportage/',
'playlist_mincount': 100,
'info_dict': {
'description': 'md5:84e7bf1feda248bc325ebfac818c476e',
'id': 'RC-014123',
'title': 'ARTE Reportage - najlepsze reportaże',
},
}]
def _real_extract(self, url):
lang, playlist_id = self._match_valid_url(url).group('lang', 'id')
playlist = self._download_json(
f'{self._API_BASE}/playlist/{lang}/{playlist_id}', playlist_id)['data']['attributes']
entries = [{
'_type': 'url_transparent',
'url': video['config']['url'],
'ie_key': ArteTVIE.ie_key(),
'id': video.get('providerId'),
'title': video.get('title'),
'alt_title': video.get('subtitle'),
'thumbnail': url_or_none(traverse_obj(video, ('mainImage', 'url'))),
'duration': int_or_none(traverse_obj(video, ('duration', 'seconds'))),
} for video in traverse_obj(playlist, ('items', lambda _, v: v['config']['url']))]
return self.playlist_result(entries, playlist_id,
traverse_obj(playlist, ('metadata', 'title')),
traverse_obj(playlist, ('metadata', 'description')))
class ArteTVCategoryIE(ArteTVBaseIE):
_VALID_URL = r'https?://(?:www\.)?arte\.tv/(?P<lang>%s)/videos/(?P<id>[\w-]+(?:/[\w-]+)*)/?\s*$' % ArteTVBaseIE._ARTE_LANGUAGES
_TESTS = [{
'url': 'https://www.arte.tv/en/videos/politics-and-society/',
'info_dict': {
'id': 'politics-and-society',
'title': 'Politics and society',
'description': 'Investigative documentary series, geopolitical analysis, and international commentary',
},
'playlist_mincount': 13,
}]
@classmethod
def suitable(cls, url):
return (
not any(ie.suitable(url) for ie in (ArteTVIE, ArteTVPlaylistIE, ))
and super().suitable(url))
def _real_extract(self, url):
lang, playlist_id = self._match_valid_url(url).groups()
webpage = self._download_webpage(url, playlist_id)
items = []
for video in re.finditer(
r'<a\b[^>]*?href\s*=\s*(?P<q>"|\'|\b)(?P<url>https?://www\.arte\.tv/%s/videos/[\w/-]+)(?P=q)' % lang,
webpage):
video = video.group('url')
if video == url:
continue
if any(ie.suitable(video) for ie in (ArteTVIE, ArteTVPlaylistIE, )):
items.append(video)
title = strip_or_none(self._generic_title('', webpage, default='').rsplit('|', 1)[0]) or None
return self.playlist_from_matches(items, playlist_id=playlist_id, playlist_title=title,
description=self._og_search_description(webpage, default=None))
yt_dlp/extractor/asiancrush.py
+196
View File
@@ -0,0 +1,196 @@
import functools
import re
from .common import InfoExtractor
from .kaltura import KalturaIE
from ..utils import (
extract_attributes,
int_or_none,
OnDemandPagedList,
parse_age_limit,
strip_or_none,
try_get,
)
class AsianCrushBaseIE(InfoExtractor):
_VALID_URL_BASE = r'https?://(?:www\.)?(?P<host>(?:(?:asiancrush|yuyutv|midnightpulp)\.com|(?:cocoro|retrocrush)\.tv))'
_KALTURA_KEYS = [
'video_url', 'progressive_url', 'download_url', 'thumbnail_url',
'widescreen_thumbnail_url', 'screencap_widescreen',
]
_API_SUFFIX = {'retrocrush.tv': '-ott'}
def _call_api(self, host, endpoint, video_id, query, resource):
return self._download_json(
'https://api%s.%s/%s' % (self._API_SUFFIX.get(host, ''), host, endpoint), video_id,
'Downloading %s JSON metadata' % resource, query=query,
headers=self.geo_verification_headers())['objects']
def _download_object_data(self, host, object_id, resource):
return self._call_api(
host, 'search', object_id, {'id': object_id}, resource)[0]
def _get_object_description(self, obj):
return strip_or_none(obj.get('long_description') or obj.get('short_description'))
def _parse_video_data(self, video):
title = video['name']
entry_id, partner_id = [None] * 2
for k in self._KALTURA_KEYS:
k_url = video.get(k)
if k_url:
mobj = re.search(r'/p/(\d+)/.+?/entryId/([^/]+)/', k_url)
if mobj:
partner_id, entry_id = mobj.groups()
break
meta_categories = try_get(video, lambda x: x['meta']['categories'], list) or []
categories = list(filter(None, [c.get('name') for c in meta_categories]))
show_info = video.get('show_info') or {}
return {
'_type': 'url_transparent',
'url': 'kaltura:%s:%s' % (partner_id, entry_id),
'ie_key': KalturaIE.ie_key(),
'id': entry_id,
'title': title,
'description': self._get_object_description(video),
'age_limit': parse_age_limit(video.get('mpaa_rating') or video.get('tv_rating')),
'categories': categories,
'series': show_info.get('show_name'),
'season_number': int_or_none(show_info.get('season_num')),
'season_id': show_info.get('season_id'),
'episode_number': int_or_none(show_info.get('episode_num')),
}
class AsianCrushIE(AsianCrushBaseIE):
_VALID_URL = r'%s/video/(?:[^/]+/)?0+(?P<id>\d+)v\b' % AsianCrushBaseIE._VALID_URL_BASE
_TESTS = [{
'url': 'https://www.asiancrush.com/video/004289v/women-who-flirt',
'md5': 'c3b740e48d0ba002a42c0b72857beae6',
'info_dict': {
'id': '1_y4tmjm5r',
'ext': 'mp4',
'title': 'Women Who Flirt',
'description': 'md5:b65c7e0ae03a85585476a62a186f924c',
'timestamp': 1496936429,
'upload_date': '20170608',
'uploader_id': 'craig@crifkin.com',
'age_limit': 13,
'categories': 'count:5',
'duration': 5812,
},
}, {
'url': 'https://www.asiancrush.com/video/she-was-pretty/011886v-pretty-episode-3/',
'only_matching': True,
}, {
'url': 'https://www.yuyutv.com/video/013886v/the-act-of-killing/',
'only_matching': True,
}, {
'url': 'https://www.yuyutv.com/video/peep-show/013922v-warring-factions/',
'only_matching': True,
}, {
'url': 'https://www.midnightpulp.com/video/010400v/drifters/',
'only_matching': True,
}, {
'url': 'https://www.midnightpulp.com/video/mononoke/016378v-zashikiwarashi-part-1/',
'only_matching': True,
}, {
'url': 'https://www.cocoro.tv/video/the-wonderful-wizard-of-oz/008878v-the-wonderful-wizard-of-oz-ep01/',
'only_matching': True,
}, {
'url': 'https://www.retrocrush.tv/video/true-tears/012328v-i...gave-away-my-tears',
'only_matching': True,
}]
def _real_extract(self, url):
host, video_id = self._match_valid_url(url).groups()
if host == 'cocoro.tv':
webpage = self._download_webpage(url, video_id)
embed_vars = self._parse_json(self._search_regex(
r'iEmbedVars\s*=\s*({.+?})', webpage, 'embed vars',
default='{}'), video_id, fatal=False) or {}
video_id = embed_vars.get('entry_id') or video_id
video = self._download_object_data(host, video_id, 'video')
return self._parse_video_data(video)
class AsianCrushPlaylistIE(AsianCrushBaseIE):
_VALID_URL = r'%s/series/0+(?P<id>\d+)s\b' % AsianCrushBaseIE._VALID_URL_BASE
_TESTS = [{
'url': 'https://www.asiancrush.com/series/006447s/fruity-samurai',
'info_dict': {
'id': '6447',
'title': 'Fruity Samurai',
'description': 'md5:7535174487e4a202d3872a7fc8f2f154',
},
'playlist_count': 13,
}, {
'url': 'https://www.yuyutv.com/series/013920s/peep-show/',
'only_matching': True,
}, {
'url': 'https://www.midnightpulp.com/series/016375s/mononoke/',
'only_matching': True,
}, {
'url': 'https://www.cocoro.tv/series/008549s/the-wonderful-wizard-of-oz/',
'only_matching': True,
}, {
'url': 'https://www.retrocrush.tv/series/012355s/true-tears',
'only_matching': True,
}]
_PAGE_SIZE = 1000000000
def _fetch_page(self, domain, parent_id, page):
videos = self._call_api(
domain, 'getreferencedobjects', parent_id, {
'max': self._PAGE_SIZE,
'object_type': 'video',
'parent_id': parent_id,
'start': page * self._PAGE_SIZE,
}, 'page %d' % (page + 1))
for video in videos:
yield self._parse_video_data(video)
def _real_extract(self, url):
host, playlist_id = self._match_valid_url(url).groups()
if host == 'cocoro.tv':
webpage = self._download_webpage(url, playlist_id)
entries = []
for mobj in re.finditer(
r'<a[^>]+href=(["\'])(?P<url>%s.*?)\1[^>]*>' % AsianCrushIE._VALID_URL,
webpage):
attrs = extract_attributes(mobj.group(0))
if attrs.get('class') == 'clearfix':
entries.append(self.url_result(
mobj.group('url'), ie=AsianCrushIE.ie_key()))
title = self._html_search_regex(
r'(?s)<h1\b[^>]\bid=["\']movieTitle[^>]+>(.+?)</h1>', webpage,
'title', default=None) or self._og_search_title(
webpage, default=None) or self._html_search_meta(
'twitter:title', webpage, 'title',
default=None) or self._html_extract_title(webpage)
if title:
title = re.sub(r'\s*\|\s*.+?$', '', title)
description = self._og_search_description(
webpage, default=None) or self._html_search_meta(
'twitter:description', webpage, 'description', fatal=False)
else:
show = self._download_object_data(host, playlist_id, 'show')
title = show.get('name')
description = self._get_object_description(show)
entries = OnDemandPagedList(
functools.partial(self._fetch_page, host, playlist_id),
self._PAGE_SIZE)
return self.playlist_result(entries, playlist_id, title, description)
yt_dlp/extractor/atresplayer.py
+104
View File
@@ -0,0 +1,104 @@
from .common import InfoExtractor
from ..compat import compat_HTTPError
from ..utils import (
ExtractorError,
int_or_none,
urlencode_postdata,
)
class AtresPlayerIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?atresplayer\.com/[^/]+/[^/]+/[^/]+/[^/]+/(?P<display_id>.+?)_(?P<id>[0-9a-f]{24})'
_NETRC_MACHINE = 'atresplayer'
_TESTS = [
{
'url': 'https://www.atresplayer.com/antena3/series/pequenas-coincidencias/temporada-1/capitulo-7-asuntos-pendientes_5d4aa2c57ed1a88fc715a615/',
'info_dict': {
'id': '5d4aa2c57ed1a88fc715a615',
'ext': 'mp4',
'title': 'Capítulo 7: Asuntos pendientes',
'description': 'md5:7634cdcb4d50d5381bedf93efb537fbc',
'duration': 3413,
},
'skip': 'This video is only available for registered users'
},
{
'url': 'https://www.atresplayer.com/lasexta/programas/el-club-de-la-comedia/temporada-4/capitulo-10-especial-solidario-nochebuena_5ad08edf986b2855ed47adc4/',
'only_matching': True,
},
{
'url': 'https://www.atresplayer.com/antena3/series/el-secreto-de-puente-viejo/el-chico-de-los-tres-lunares/capitulo-977-29-12-14_5ad51046986b2886722ccdea/',
'only_matching': True,
},
]
_API_BASE = 'https://api.atresplayer.com/'
def _handle_error(self, e, code):
if isinstance(e.cause, compat_HTTPError) and e.cause.code == code:
error = self._parse_json(e.cause.read(), None)
if error.get('error') == 'required_registered':
self.raise_login_required()
raise ExtractorError(error['error_description'], expected=True)
raise
def _perform_login(self, username, password):
self._request_webpage(
self._API_BASE + 'login', None, 'Downloading login page')
try:
target_url = self._download_json(
'https://account.atresmedia.com/api/login', None,
'Logging in', headers={
'Content-Type': 'application/x-www-form-urlencoded'
}, data=urlencode_postdata({
'username': username,
'password': password,
}))['targetUrl']
except ExtractorError as e:
self._handle_error(e, 400)
self._request_webpage(target_url, None, 'Following Target URL')
def _real_extract(self, url):
display_id, video_id = self._match_valid_url(url).groups()
try:
episode = self._download_json(
self._API_BASE + 'client/v1/player/episode/' + video_id, video_id)
except ExtractorError as e:
self._handle_error(e, 403)
title = episode['titulo']
formats = []
subtitles = {}
for source in episode.get('sources', []):
src = source.get('src')
if not src:
continue
src_type = source.get('type')
if src_type == 'application/vnd.apple.mpegurl':
formats, subtitles = self._extract_m3u8_formats(
src, video_id, 'mp4', 'm3u8_native',
m3u8_id='hls', fatal=False)
elif src_type == 'application/dash+xml':
formats, subtitles = self._extract_mpd_formats(
src, video_id, mpd_id='dash', fatal=False)
heartbeat = episode.get('heartbeat') or {}
omniture = episode.get('omniture') or {}
get_meta = lambda x: heartbeat.get(x) or omniture.get(x)
return {
'display_id': display_id,
'id': video_id,
'title': title,
'description': episode.get('descripcion'),
'thumbnail': episode.get('imgPoster'),
'duration': int_or_none(episode.get('duration')),
'formats': formats,
'channel': get_meta('channel'),
'season': get_meta('season'),
'episode_number': int_or_none(get_meta('episodeNumber')),
'subtitles': subtitles,
}
yt_dlp/extractor/atscaleconf.py
+34
View File
@@ -0,0 +1,34 @@
import re
from .common import InfoExtractor
class AtScaleConfEventIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?atscaleconference\.com/events/(?P<id>[^/&$?]+)'
_TESTS = [{
'url': 'https://atscaleconference.com/events/data-scale-spring-2022/',
'playlist_mincount': 13,
'info_dict': {
'id': 'data-scale-spring-2022',
'title': 'Data @Scale Spring 2022',
'description': 'md5:7d7ca1c42ac9c6d8a785092a1aea4b55'
},
}, {
'url': 'https://atscaleconference.com/events/video-scale-2021/',
'playlist_mincount': 14,
'info_dict': {
'id': 'video-scale-2021',
'title': 'Video @Scale 2021',
'description': 'md5:7d7ca1c42ac9c6d8a785092a1aea4b55'
},
}]
def _real_extract(self, url):
id = self._match_id(url)
webpage = self._download_webpage(url, id)
return self.playlist_from_matches(
re.findall(r'data-url\s*=\s*"(https?://(?:www\.)?atscaleconference\.com/videos/[^"]+)"', webpage),
ie='Generic', playlist_id=id,
title=self._og_search_title(webpage), description=self._og_search_description(webpage))
yt_dlp/extractor/atttechchannel.py
+53
View File
@@ -0,0 +1,53 @@
from .common import InfoExtractor
from ..utils import unified_strdate
class ATTTechChannelIE(InfoExtractor):
_VALID_URL = r'https?://techchannel\.att\.com/play-video\.cfm/([^/]+/)*(?P<id>.+)'
_TEST = {
'url': 'http://techchannel.att.com/play-video.cfm/2014/1/27/ATT-Archives-The-UNIX-System-Making-Computers-Easier-to-Use',
'info_dict': {
'id': '11316',
'display_id': 'ATT-Archives-The-UNIX-System-Making-Computers-Easier-to-Use',
'ext': 'flv',
'title': 'AT&T Archives : The UNIX System: Making Computers Easier to Use',
'description': 'A 1982 film about UNIX is the foundation for software in use around Bell Labs and AT&T.',
'thumbnail': r're:^https?://.*\.jpg$',
'upload_date': '20140127',
},
'params': {
# rtmp download
'skip_download': True,
},
}
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
video_url = self._search_regex(
r"url\s*:\s*'(rtmp://[^']+)'",
webpage, 'video URL')
video_id = self._search_regex(
r'mediaid\s*=\s*(\d+)',
webpage, 'video id', fatal=False)
title = self._og_search_title(webpage)
description = self._og_search_description(webpage)
thumbnail = self._og_search_thumbnail(webpage)
upload_date = unified_strdate(self._search_regex(
r'[Rr]elease\s+date:\s*(\d{1,2}/\d{1,2}/\d{4})',
webpage, 'upload date', fatal=False), False)
return {
'id': video_id,
'display_id': display_id,
'url': video_url,
'ext': 'flv',
'title': title,
'description': description,
'thumbnail': thumbnail,
'upload_date': upload_date,
}
yt_dlp/extractor/atvat.py
+108
View File
@@ -0,0 +1,108 @@
import datetime
from .common import InfoExtractor
from ..utils import (
float_or_none,
jwt_encode_hs256,
try_get,
ExtractorError,
)
class ATVAtIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?atv\.at/tv/(?:[^/]+/){2,3}(?P<id>.*)'
_TESTS = [{
'url': 'https://www.atv.at/tv/bauer-sucht-frau/staffel-18/bauer-sucht-frau/bauer-sucht-frau-staffel-18-folge-3-die-hofwochen',
'md5': '3c3b4aaca9f63e32b35e04a9c2515903',
'info_dict': {
'id': 'v-ce9cgn1e70n5-1',
'ext': 'mp4',
'title': 'Bauer sucht Frau - Staffel 18 Folge 3 - Die Hofwochen',
}
}, {
'url': 'https://www.atv.at/tv/bauer-sucht-frau/staffel-18/episode-01/bauer-sucht-frau-staffel-18-vorstellungsfolge-1',
'only_matching': True,
}]
# extracted from bootstrap.js function (search for e.encryption_key and use your browser's debugger)
_ACCESS_ID = 'x_atv'
_ENCRYPTION_KEY = 'Hohnaekeishoogh2omaeghooquooshia'
def _extract_video_info(self, url, content, video):
clip_id = content.get('splitId', content['id'])
formats = []
clip_urls = video['urls']
for protocol, variant in clip_urls.items():
source_url = try_get(variant, lambda x: x['clear']['url'])
if not source_url:
continue
if protocol == 'dash':
formats.extend(self._extract_mpd_formats(
source_url, clip_id, mpd_id=protocol, fatal=False))
elif protocol == 'hls':
formats.extend(self._extract_m3u8_formats(
source_url, clip_id, 'mp4', 'm3u8_native',
m3u8_id=protocol, fatal=False))
else:
formats.append({
'url': source_url,
'format_id': protocol,
})
return {
'id': clip_id,
'title': content.get('title'),
'duration': float_or_none(content.get('duration')),
'series': content.get('tvShowTitle'),
'formats': formats,
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
json_data = self._parse_json(
self._search_regex(r'<script id="state" type="text/plain">(.*)</script>', webpage, 'json_data'),
video_id=video_id)
video_title = json_data['views']['default']['page']['title']
contentResource = json_data['views']['default']['page']['contentResource']
content_id = contentResource[0]['id']
content_ids = [{'id': id, 'subclip_start': content['start'], 'subclip_end': content['end']}
for id, content in enumerate(contentResource)]
time_of_request = datetime.datetime.now()
not_before = time_of_request - datetime.timedelta(minutes=5)
expire = time_of_request + datetime.timedelta(minutes=5)
payload = {
'content_ids': {
content_id: content_ids,
},
'secure_delivery': True,
'iat': int(time_of_request.timestamp()),
'nbf': int(not_before.timestamp()),
'exp': int(expire.timestamp()),
}
jwt_token = jwt_encode_hs256(payload, self._ENCRYPTION_KEY, headers={'kid': self._ACCESS_ID})
videos = self._download_json(
'https://vas-v4.p7s1video.net/4.0/getsources',
content_id, 'Downloading videos JSON', query={
'token': jwt_token.decode('utf-8')
})
video_id, videos_data = list(videos['data'].items())[0]
error_msg = try_get(videos_data, lambda x: x['error']['title'])
if error_msg == 'Geo check failed':
self.raise_geo_restricted(error_msg)
elif error_msg:
raise ExtractorError(error_msg)
entries = [
self._extract_video_info(url, contentResource[video['id']], video)
for video in videos_data]
return {
'_type': 'multi_video',
'id': video_id,
'title': video_title,
'entries': entries,
}
yt_dlp/extractor/audimedia.py
+89
View File
@@ -0,0 +1,89 @@
from .common import InfoExtractor
from ..utils import (
int_or_none,
parse_iso8601,
)
class AudiMediaIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?audi-mediacenter\.com/(?:en|de)/audimediatv/(?:video/)?(?P<id>[^/?#]+)'
_TESTS = [{
'url': 'https://www.audi-mediacenter.com/en/audimediatv/60-seconds-of-audi-sport-104-2015-wec-bahrain-rookie-test-1467',
'md5': '79a8b71c46d49042609795ab59779b66',
'info_dict': {
'id': '1565',
'ext': 'mp4',
'title': '60 Seconds of Audi Sport 104/2015 - WEC Bahrain, Rookie Test',
'description': 'md5:60e5d30a78ced725f7b8d34370762941',
'upload_date': '20151124',
'timestamp': 1448354940,
'duration': 74022,
'view_count': int,
}
}, {
'url': 'https://www.audi-mediacenter.com/en/audimediatv/video/60-seconds-of-audi-sport-104-2015-wec-bahrain-rookie-test-2991',
'only_matching': True,
}]
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
raw_payload = self._search_regex([
r'class="amtv-embed"[^>]+id="([0-9a-z-]+)"',
r'id="([0-9a-z-]+)"[^>]+class="amtv-embed"',
r'class=\\"amtv-embed\\"[^>]+id=\\"([0-9a-z-]+)\\"',
r'id=\\"([0-9a-z-]+)\\"[^>]+class=\\"amtv-embed\\"',
r'id=(?:\\)?"(amtve-[a-z]-\d+-[a-z]{2})',
], webpage, 'raw payload')
_, stage_mode, video_id, _ = raw_payload.split('-')
# TODO: handle s and e stage_mode (live streams and ended live streams)
if stage_mode not in ('s', 'e'):
video_data = self._download_json(
'https://www.audimedia.tv/api/video/v1/videos/' + video_id,
video_id, query={
'embed[]': ['video_versions', 'thumbnail_image'],
})['results']
formats = []
stream_url_hls = video_data.get('stream_url_hls')
if stream_url_hls:
formats.extend(self._extract_m3u8_formats(
stream_url_hls, video_id, 'mp4',
entry_protocol='m3u8_native', m3u8_id='hls', fatal=False))
stream_url_hds = video_data.get('stream_url_hds')
if stream_url_hds:
formats.extend(self._extract_f4m_formats(
stream_url_hds + '?hdcore=3.4.0',
video_id, f4m_id='hds', fatal=False))
for video_version in video_data.get('video_versions', []):
video_version_url = video_version.get('download_url') or video_version.get('stream_url')
if not video_version_url:
continue
f = {
'url': video_version_url,
'width': int_or_none(video_version.get('width')),
'height': int_or_none(video_version.get('height')),
'abr': int_or_none(video_version.get('audio_bitrate')),
'vbr': int_or_none(video_version.get('video_bitrate')),
}
bitrate = self._search_regex(r'(\d+)k', video_version_url, 'bitrate', default=None)
if bitrate:
f.update({
'format_id': 'http-%s' % bitrate,
})
formats.append(f)
return {
'id': video_id,
'title': video_data['title'],
'description': video_data.get('subtitle'),
'thumbnail': video_data.get('thumbnail_image', {}).get('file'),
'timestamp': parse_iso8601(video_data.get('publication_date')),
'duration': int_or_none(video_data.get('duration')),
'view_count': int_or_none(video_data.get('view_count')),
'formats': formats,
}
yt_dlp/extractor/audioboom.py
+57
View File
@@ -0,0 +1,57 @@
from .common import InfoExtractor
from ..utils import clean_html, float_or_none, traverse_obj, unescapeHTML
class AudioBoomIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?audioboom\.com/(?:boos|posts)/(?P<id>[0-9]+)'
_TESTS = [{
'url': 'https://audioboom.com/posts/7398103-asim-chaudhry',
'md5': '4d68be11c9f9daf3dab0778ad1e010c3',
'info_dict': {
'id': '7398103',
'ext': 'mp3',
'title': 'Asim Chaudhry',
'description': 'md5:0ed714ae0e81e5d9119cac2f618ad679',
'duration': 4000.99,
'uploader': 'Sue Perkins: An hour or so with...',
'uploader_url': r're:https?://(?:www\.)?audioboom\.com/channel/perkins',
}
}, { # Direct mp3-file link
'url': 'https://audioboom.com/posts/8128496.mp3',
'md5': 'e329edf304d450def95c7f86a9165ee1',
'info_dict': {
'id': '8128496',
'ext': 'mp3',
'title': 'TCRNo8 / DAILY 03 - In Control',
'description': 'md5:44665f142db74858dfa21c5b34787948',
'duration': 1689.7,
'uploader': 'Lost Dot Podcast: The Trans Pyrenees and Transcontinental Race',
'uploader_url': r're:https?://(?:www\.)?audioboom\.com/channels/5003904',
}
}, {
'url': 'https://audioboom.com/posts/4279833-3-09-2016-czaban-hour-3?t=0',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(f'https://audioboom.com/posts/{video_id}', video_id)
clip_store = self._search_json(
r'data-react-class="V5DetailPagePlayer"\s*data-react-props=["\']',
webpage, 'clip store', video_id, fatal=False, transform_source=unescapeHTML)
clip = traverse_obj(clip_store, ('clips', 0), expected_type=dict) or {}
return {
'id': video_id,
'url': clip.get('clipURLPriorToLoading') or self._og_search_property('audio', webpage, 'audio url'),
'title': clip.get('title') or self._html_search_meta(['og:title', 'og:audio:title', 'audio_title'], webpage),
'description': (clip.get('description') or clean_html(clip.get('formattedDescription'))
or self._og_search_description(webpage)),
'duration': float_or_none(clip.get('duration') or self._html_search_meta('weibo:audio:duration', webpage)),
'uploader': clip.get('author') or self._html_search_meta(
['og:audio:artist', 'twitter:audio:artist_name', 'audio_artist'], webpage, 'uploader'),
'uploader_url': clip.get('author_url') or self._html_search_regex(
r'<div class="avatar flex-shrink-0">\s*<a href="(?P<uploader_url>http[^"]+)"',
webpage, 'uploader url', fatal=False),
}
yt_dlp/extractor/audiodraft.py
+93
View File
@@ -0,0 +1,93 @@
from .common import InfoExtractor
from ..utils import int_or_none
class AudiodraftBaseIE(InfoExtractor):
def _audiodraft_extract_from_id(self, player_entry_id):
data_json = self._download_json(
'https://www.audiodraft.com/scripts/general/player/getPlayerInfoNew.php', player_entry_id,
headers={
'Content-type': 'application/x-www-form-urlencoded; charset=UTF-8',
'X-Requested-With': 'XMLHttpRequest',
}, data=f'id={player_entry_id}'.encode('utf-8'))
return {
'id': str(data_json['entry_id']),
'title': data_json.get('entry_title'),
'url': data_json['path'],
'vcodec': 'none',
'ext': 'mp3',
'uploader': data_json.get('designer_name'),
'uploader_id': data_json.get('designer_id'),
'webpage_url': data_json.get('entry_url'),
'like_count': int_or_none(data_json.get('entry_likes')),
'average_rating': int_or_none(data_json.get('entry_rating')),
}
class AudiodraftCustomIE(AudiodraftBaseIE):
IE_NAME = 'Audiodraft:custom'
_VALID_URL = r'https?://(?:[-\w]+)\.audiodraft\.com/entry/(?P<id>\d+)'
_TESTS = [{
'url': 'http://nokiatune.audiodraft.com/entry/5874',
'info_dict': {
'id': '9485',
'ext': 'mp3',
'title': 'Hula Hula Calls',
'uploader': 'unclemaki',
'uploader_id': '13512',
'average_rating': 5,
'like_count': int,
},
}, {
'url': 'http://vikinggrace.audiodraft.com/entry/501',
'info_dict': {
'id': '22241',
'ext': 'mp3',
'title': 'MVG Happy',
'uploader': 'frog',
'uploader_id': '19142',
'average_rating': 5,
'like_count': int,
},
}, {
'url': 'http://timferriss.audiodraft.com/entry/765',
'info_dict': {
'id': '19710',
'ext': 'mp3',
'title': 'ferris03',
'uploader': 'malex',
'uploader_id': '17335',
'average_rating': 5,
'like_count': int,
},
}]
def _real_extract(self, url):
id = self._match_id(url)
webpage = self._download_webpage(url, id)
player_entry_id = self._search_regex(r'playAudio\(\'(player_entry_\d+)\'\);', webpage, id, 'play entry id')
return self._audiodraft_extract_from_id(player_entry_id)
class AudiodraftGenericIE(AudiodraftBaseIE):
IE_NAME = 'Audiodraft:generic'
_VALID_URL = r'https?://www\.audiodraft\.com/contests/[^/#]+#entries&eid=(?P<id>\d+)'
_TESTS = [{
'url': 'https://www.audiodraft.com/contests/570-Score-A-Video-Surprise-Us#entries&eid=30138',
'info_dict': {
'id': '30138',
'ext': 'mp3',
'title': 'DROP in sound_V2',
'uploader': 'TiagoSilva',
'uploader_id': '19452',
'average_rating': 4,
'like_count': int,
},
}]
def _real_extract(self, url):
id = self._match_id(url)
return self._audiodraft_extract_from_id(f'player_entry_{id}')
yt_dlp/extractor/audiomack.py
+147
View File
@@ -0,0 +1,147 @@
import itertools
import time
from .common import InfoExtractor
from .soundcloud import SoundcloudIE
from ..compat import compat_str
from ..utils import (
ExtractorError,
url_basename,
)
class AudiomackIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?audiomack\.com/(?:song/|(?=.+/song/))(?P<id>[\w/-]+)'
IE_NAME = 'audiomack'
_TESTS = [
# hosted on audiomack
{
'url': 'http://www.audiomack.com/song/roosh-williams/extraordinary',
'info_dict':
{
'id': '310086',
'ext': 'mp3',
'uploader': 'Roosh Williams',
'title': 'Extraordinary'
}
},
# audiomack wrapper around soundcloud song
# Needs new test URL.
{
'add_ie': ['Soundcloud'],
'url': 'http://www.audiomack.com/song/hip-hop-daily/black-mamba-freestyle',
'info_dict': {
'id': '258901379',
'ext': 'mp3',
'description': 'mamba day freestyle for the legend Kobe Bryant ',
'title': 'Black Mamba Freestyle [Prod. By Danny Wolf]',
'uploader': 'ILOVEMAKONNEN',
'upload_date': '20160414',
},
'skip': 'Song has been removed from the site',
},
]
def _real_extract(self, url):
# URLs end with [uploader name]/song/[uploader title]
# this title is whatever the user types in, and is rarely
# the proper song title. Real metadata is in the api response
album_url_tag = self._match_id(url).replace('/song/', '/')
# Request the extended version of the api for extra fields like artist and title
api_response = self._download_json(
'http://www.audiomack.com/api/music/url/song/%s?extended=1&_=%d' % (
album_url_tag, time.time()),
album_url_tag)
# API is inconsistent with errors
if 'url' not in api_response or not api_response['url'] or 'error' in api_response:
raise ExtractorError('Invalid url %s' % url)
# Audiomack wraps a lot of soundcloud tracks in their branded wrapper
# if so, pass the work off to the soundcloud extractor
if SoundcloudIE.suitable(api_response['url']):
return self.url_result(api_response['url'], SoundcloudIE.ie_key())
return {
'id': compat_str(api_response.get('id', album_url_tag)),
'uploader': api_response.get('artist'),
'title': api_response.get('title'),
'url': api_response['url'],
}
class AudiomackAlbumIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?audiomack\.com/(?:album/|(?=.+/album/))(?P<id>[\w/-]+)'
IE_NAME = 'audiomack:album'
_TESTS = [
# Standard album playlist
{
'url': 'http://www.audiomack.com/album/flytunezcom/tha-tour-part-2-mixtape',
'playlist_count': 11,
'info_dict':
{
'id': '812251',
'title': 'Tha Tour: Part 2 (Official Mixtape)'
}
},
# Album playlist ripped from fakeshoredrive with no metadata
{
'url': 'http://www.audiomack.com/album/fakeshoredrive/ppp-pistol-p-project',
'info_dict': {
'title': 'PPP (Pistol P Project)',
'id': '837572',
},
'playlist': [{
'info_dict': {
'title': 'PPP (Pistol P Project) - 8. Real (prod by SYK SENSE )',
'id': '837576',
'ext': 'mp3',
'uploader': 'Lil Herb a.k.a. G Herbo',
}
}, {
'info_dict': {
'title': 'PPP (Pistol P Project) - 10. 4 Minutes Of Hell Part 4 (prod by DY OF 808 MAFIA)',
'id': '837580',
'ext': 'mp3',
'uploader': 'Lil Herb a.k.a. G Herbo',
}
}],
}
]
def _real_extract(self, url):
# URLs end with [uploader name]/album/[uploader title]
# this title is whatever the user types in, and is rarely
# the proper song title. Real metadata is in the api response
album_url_tag = self._match_id(url).replace('/album/', '/')
result = {'_type': 'playlist', 'entries': []}
# There is no one endpoint for album metadata - instead it is included/repeated in each song's metadata
# Therefore we don't know how many songs the album has and must infi-loop until failure
for track_no in itertools.count():
# Get song's metadata
api_response = self._download_json(
'http://www.audiomack.com/api/music/url/album/%s/%d?extended=1&_=%d'
% (album_url_tag, track_no, time.time()), album_url_tag,
note='Querying song information (%d)' % (track_no + 1))
# Total failure, only occurs when url is totally wrong
# Won't happen in middle of valid playlist (next case)
if 'url' not in api_response or 'error' in api_response:
raise ExtractorError('Invalid url for track %d of album url %s' % (track_no, url))
# URL is good but song id doesn't exist - usually means end of playlist
elif not api_response['url']:
break
else:
# Pull out the album metadata and add to result (if it exists)
for resultkey, apikey in [('id', 'album_id'), ('title', 'album_title')]:
if apikey in api_response and resultkey not in result:
result[resultkey] = compat_str(api_response[apikey])
song_id = url_basename(api_response['url']).rpartition('.')[0]
result['entries'].append({
'id': compat_str(api_response.get('id', song_id)),
'uploader': api_response.get('artist'),
'title': api_response.get('title', song_id),
'url': api_response['url'],
})
return result
yt_dlp/extractor/audius.py
+271
View File
@@ -0,0 +1,271 @@
import random
from .common import InfoExtractor
from ..compat import compat_str, compat_urllib_parse_unquote
from ..utils import ExtractorError, str_or_none, try_get
class AudiusBaseIE(InfoExtractor):
_API_BASE = None
_API_V = '/v1'
def _get_response_data(self, response):
if isinstance(response, dict):
response_data = response.get('data')
if response_data is not None:
return response_data
if len(response) == 1 and 'message' in response:
raise ExtractorError('API error: %s' % response['message'],
expected=True)
raise ExtractorError('Unexpected API response')
def _select_api_base(self):
"""Selecting one of the currently available API hosts"""
response = super(AudiusBaseIE, self)._download_json(
'https://api.audius.co/', None,
note='Requesting available API hosts',
errnote='Unable to request available API hosts')
hosts = self._get_response_data(response)
if isinstance(hosts, list):
self._API_BASE = random.choice(hosts)
return
raise ExtractorError('Unable to get available API hosts')
@staticmethod
def _prepare_url(url, title):
"""
Audius removes forward slashes from the uri, but leaves backslashes.
The problem is that the current version of Chrome replaces backslashes
in the address bar with a forward slashes, so if you copy the link from
there and paste it into youtube-dl, you won't be able to download
anything from this link, since the Audius API won't be able to resolve
this url
"""
url = compat_urllib_parse_unquote(url)
title = compat_urllib_parse_unquote(title)
if '/' in title or '%2F' in title:
fixed_title = title.replace('/', '%5C').replace('%2F', '%5C')
return url.replace(title, fixed_title)
return url
def _api_request(self, path, item_id=None, note='Downloading JSON metadata',
errnote='Unable to download JSON metadata',
expected_status=None):
if self._API_BASE is None:
self._select_api_base()
try:
response = super(AudiusBaseIE, self)._download_json(
'%s%s%s' % (self._API_BASE, self._API_V, path), item_id, note=note,
errnote=errnote, expected_status=expected_status)
except ExtractorError as exc:
# some of Audius API hosts may not work as expected and return HTML
if 'Failed to parse JSON' in compat_str(exc):
raise ExtractorError('An error occurred while receiving data. Try again',
expected=True)
raise exc
return self._get_response_data(response)
def _resolve_url(self, url, item_id):
return self._api_request('/resolve?url=%s' % url, item_id,
expected_status=404)
class AudiusIE(AudiusBaseIE):
_VALID_URL = r'''(?x)https?://(?:www\.)?(?:audius\.co/(?P<uploader>[\w\d-]+)(?!/album|/playlist)/(?P<title>\S+))'''
IE_DESC = 'Audius.co'
_TESTS = [
{
# URL from Chrome address bar which replace backslash to forward slash
'url': 'https://audius.co/test_acc/t%D0%B5%D0%B5%D0%B5est-1.%5E_%7B%7D/%22%3C%3E.%E2%84%96~%60-198631',
'md5': '92c35d3e754d5a0f17eef396b0d33582',
'info_dict': {
'id': 'xd8gY',
'title': '''Tеееest/ 1.!@#$%^&*()_+=[]{};'\\\":<>,.?/№~`''',
'ext': 'mp3',
'description': 'Description',
'duration': 30,
'track': '''Tеееest/ 1.!@#$%^&*()_+=[]{};'\\\":<>,.?/№~`''',
'artist': 'test',
'genre': 'Electronic',
'thumbnail': r're:https?://.*\.jpg',
'view_count': int,
'like_count': int,
'repost_count': int,
}
},
{
# Regular track
'url': 'https://audius.co/voltra/radar-103692',
'md5': '491898a0a8de39f20c5d6a8a80ab5132',
'info_dict': {
'id': 'KKdy2',
'title': 'RADAR',
'ext': 'mp3',
'duration': 318,
'track': 'RADAR',
'artist': 'voltra',
'genre': 'Trance',
'thumbnail': r're:https?://.*\.jpg',
'view_count': int,
'like_count': int,
'repost_count': int,
}
},
]
_ARTWORK_MAP = {
"150x150": 150,
"480x480": 480,
"1000x1000": 1000
}
def _real_extract(self, url):
mobj = self._match_valid_url(url)
track_id = try_get(mobj, lambda x: x.group('track_id'))
if track_id is None:
title = mobj.group('title')
# uploader = mobj.group('uploader')
url = self._prepare_url(url, title)
track_data = self._resolve_url(url, title)
else: # API link
title = None
# uploader = None
track_data = self._api_request('/tracks/%s' % track_id, track_id)
if not isinstance(track_data, dict):
raise ExtractorError('Unexpected API response')
track_id = track_data.get('id')
if track_id is None:
raise ExtractorError('Unable to get ID of the track')
artworks_data = track_data.get('artwork')
thumbnails = []
if isinstance(artworks_data, dict):
for quality_key, thumbnail_url in artworks_data.items():
thumbnail = {
"url": thumbnail_url
}
quality_code = self._ARTWORK_MAP.get(quality_key)
if quality_code is not None:
thumbnail['preference'] = quality_code
thumbnails.append(thumbnail)
return {
'id': track_id,
'title': track_data.get('title', title),
'url': '%s/v1/tracks/%s/stream' % (self._API_BASE, track_id),
'ext': 'mp3',
'description': track_data.get('description'),
'duration': track_data.get('duration'),
'track': track_data.get('title'),
'artist': try_get(track_data, lambda x: x['user']['name'], compat_str),
'genre': track_data.get('genre'),
'thumbnails': thumbnails,
'view_count': track_data.get('play_count'),
'like_count': track_data.get('favorite_count'),
'repost_count': track_data.get('repost_count'),
}
class AudiusTrackIE(AudiusIE): # XXX: Do not subclass from concrete IE
_VALID_URL = r'''(?x)(?:audius:)(?:https?://(?:www\.)?.+/v1/tracks/)?(?P<track_id>\w+)'''
IE_NAME = 'audius:track'
IE_DESC = 'Audius track ID or API link. Prepend with "audius:"'
_TESTS = [
{
'url': 'audius:9RWlo',
'only_matching': True
},
{
'url': 'audius:http://discoveryprovider.audius.prod-us-west-2.staked.cloud/v1/tracks/9RWlo',
'only_matching': True
},
]
class AudiusPlaylistIE(AudiusBaseIE):
_VALID_URL = r'https?://(?:www\.)?audius\.co/(?P<uploader>[\w\d-]+)/(?:album|playlist)/(?P<title>\S+)'
IE_NAME = 'audius:playlist'
IE_DESC = 'Audius.co playlists'
_TEST = {
'url': 'https://audius.co/test_acc/playlist/test-playlist-22910',
'info_dict': {
'id': 'DNvjN',
'title': 'test playlist',
'description': 'Test description\n\nlol',
},
'playlist_count': 175,
}
def _build_playlist(self, tracks):
entries = []
for track in tracks:
if not isinstance(track, dict):
raise ExtractorError('Unexpected API response')
track_id = str_or_none(track.get('id'))
if not track_id:
raise ExtractorError('Unable to get track ID from playlist')
entries.append(self.url_result(
'audius:%s' % track_id,
ie=AudiusTrackIE.ie_key(), video_id=track_id))
return entries
def _real_extract(self, url):
self._select_api_base()
mobj = self._match_valid_url(url)
title = mobj.group('title')
# uploader = mobj.group('uploader')
url = self._prepare_url(url, title)
playlist_response = self._resolve_url(url, title)
if not isinstance(playlist_response, list) or len(playlist_response) != 1:
raise ExtractorError('Unexpected API response')
playlist_data = playlist_response[0]
if not isinstance(playlist_data, dict):
raise ExtractorError('Unexpected API response')
playlist_id = playlist_data.get('id')
if playlist_id is None:
raise ExtractorError('Unable to get playlist ID')
playlist_tracks = self._api_request(
'/playlists/%s/tracks' % playlist_id,
title, note='Downloading playlist tracks metadata',
errnote='Unable to download playlist tracks metadata')
if not isinstance(playlist_tracks, list):
raise ExtractorError('Unexpected API response')
entries = self._build_playlist(playlist_tracks)
return self.playlist_result(entries, playlist_id,
playlist_data.get('playlist_name', title),
playlist_data.get('description'))
class AudiusProfileIE(AudiusPlaylistIE): # XXX: Do not subclass from concrete IE
IE_NAME = 'audius:artist'
IE_DESC = 'Audius.co profile/artist pages'
_VALID_URL = r'https?://(?:www)?audius\.co/(?P<id>[^\/]+)/?(?:[?#]|$)'
_TEST = {
'url': 'https://audius.co/pzl/',
'info_dict': {
'id': 'ezRo7',
'description': 'TAMALE\n\nContact: officialpzl@gmail.com',
'title': 'pzl',
},
'playlist_count': 24,
}
def _real_extract(self, url):
self._select_api_base()
profile_id = self._match_id(url)
try:
_profile_data = self._api_request('/full/users/handle/' + profile_id, profile_id)
except ExtractorError as e:
raise ExtractorError('Could not download profile info; ' + str(e))
profile_audius_id = _profile_data[0]['id']
profile_bio = _profile_data[0].get('bio')
api_call = self._api_request('/full/users/handle/%s/tracks' % profile_id, profile_id)
return self.playlist_result(self._build_playlist(api_call), profile_audius_id, profile_id, profile_bio)
yt_dlp/extractor/awaan.py
+184
View File
@@ -0,0 +1,184 @@
import base64
from .common import InfoExtractor
from ..compat import (
compat_urllib_parse_urlencode,
compat_str,
)
from ..utils import (
format_field,
int_or_none,
parse_iso8601,
smuggle_url,
unsmuggle_url,
urlencode_postdata,
)
class AWAANIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?(?:awaan|dcndigital)\.ae/(?:#/)?show/(?P<show_id>\d+)/[^/]+(?:/(?P<id>\d+)/(?P<season_id>\d+))?'
def _real_extract(self, url):
show_id, video_id, season_id = self._match_valid_url(url).groups()
if video_id and int(video_id) > 0:
return self.url_result(
'http://awaan.ae/media/%s' % video_id, 'AWAANVideo')
elif season_id and int(season_id) > 0:
return self.url_result(smuggle_url(
'http://awaan.ae/program/season/%s' % season_id,
{'show_id': show_id}), 'AWAANSeason')
else:
return self.url_result(
'http://awaan.ae/program/%s' % show_id, 'AWAANSeason')
class AWAANBaseIE(InfoExtractor):
def _parse_video_data(self, video_data, video_id, is_live):
title = video_data.get('title_en') or video_data['title_ar']
img = video_data.get('img')
return {
'id': video_id,
'title': title,
'description': video_data.get('description_en') or video_data.get('description_ar'),
'thumbnail': format_field(img, None, 'http://admin.mangomolo.com/analytics/%s'),
'duration': int_or_none(video_data.get('duration')),
'timestamp': parse_iso8601(video_data.get('create_time'), ' '),
'is_live': is_live,
'uploader_id': video_data.get('user_id'),
}
class AWAANVideoIE(AWAANBaseIE):
IE_NAME = 'awaan:video'
_VALID_URL = r'https?://(?:www\.)?(?:awaan|dcndigital)\.ae/(?:#/)?(?:video(?:/[^/]+)?|media|catchup/[^/]+/[^/]+)/(?P<id>\d+)'
_TESTS = [{
'url': 'http://www.dcndigital.ae/#/video/%D8%B1%D8%AD%D9%84%D8%A9-%D8%A7%D9%84%D8%B9%D9%85%D8%B1-%D8%A7%D9%84%D8%AD%D9%84%D9%82%D8%A9-1/17375',
'md5': '5f61c33bfc7794315c671a62d43116aa',
'info_dict':
{
'id': '17375',
'ext': 'mp4',
'title': 'رحلة العمر : الحلقة 1',
'description': 'md5:0156e935d870acb8ef0a66d24070c6d6',
'duration': 2041,
'timestamp': 1227504126,
'upload_date': '20081124',
'uploader_id': '71',
},
}, {
'url': 'http://awaan.ae/video/26723981/%D8%AF%D8%A7%D8%B1-%D8%A7%D9%84%D8%B3%D9%84%D8%A7%D9%85:-%D8%AE%D9%8A%D8%B1-%D8%AF%D9%88%D8%B1-%D8%A7%D9%84%D8%A3%D9%86%D8%B5%D8%A7%D8%B1',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
video_data = self._download_json(
'http://admin.mangomolo.com/analytics/index.php/plus/video?id=%s' % video_id,
video_id, headers={'Origin': 'http://awaan.ae'})
info = self._parse_video_data(video_data, video_id, False)
embed_url = 'http://admin.mangomolo.com/analytics/index.php/customers/embed/video?' + compat_urllib_parse_urlencode({
'id': video_data['id'],
'user_id': video_data['user_id'],
'signature': video_data['signature'],
'countries': 'Q0M=',
'filter': 'DENY',
})
info.update({
'_type': 'url_transparent',
'url': embed_url,
'ie_key': 'MangomoloVideo',
})
return info
class AWAANLiveIE(AWAANBaseIE):
IE_NAME = 'awaan:live'
_VALID_URL = r'https?://(?:www\.)?(?:awaan|dcndigital)\.ae/(?:#/)?live/(?P<id>\d+)'
_TEST = {
'url': 'http://awaan.ae/live/6/dubai-tv',
'info_dict': {
'id': '6',
'ext': 'mp4',
'title': 're:Dubai Al Oula [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
'upload_date': '20150107',
'timestamp': 1420588800,
'uploader_id': '71',
},
'params': {
# m3u8 download
'skip_download': True,
},
}
def _real_extract(self, url):
channel_id = self._match_id(url)
channel_data = self._download_json(
'http://admin.mangomolo.com/analytics/index.php/plus/getchanneldetails?channel_id=%s' % channel_id,
channel_id, headers={'Origin': 'http://awaan.ae'})
info = self._parse_video_data(channel_data, channel_id, True)
embed_url = 'http://admin.mangomolo.com/analytics/index.php/customers/embed/index?' + compat_urllib_parse_urlencode({
'id': base64.b64encode(channel_data['user_id'].encode()).decode(),
'channelid': base64.b64encode(channel_data['id'].encode()).decode(),
'signature': channel_data['signature'],
'countries': 'Q0M=',
'filter': 'DENY',
})
info.update({
'_type': 'url_transparent',
'url': embed_url,
'ie_key': 'MangomoloLive',
})
return info
class AWAANSeasonIE(InfoExtractor):
IE_NAME = 'awaan:season'
_VALID_URL = r'https?://(?:www\.)?(?:awaan|dcndigital)\.ae/(?:#/)?program/(?:(?P<show_id>\d+)|season/(?P<season_id>\d+))'
_TEST = {
'url': 'http://dcndigital.ae/#/program/205024/%D9%85%D8%AD%D8%A7%D8%B6%D8%B1%D8%A7%D8%AA-%D8%A7%D9%84%D8%B4%D9%8A%D8%AE-%D8%A7%D9%84%D8%B4%D8%B9%D8%B1%D8%A7%D9%88%D9%8A',
'info_dict':
{
'id': '7910',
'title': 'محاضرات الشيخ الشعراوي',
},
'playlist_mincount': 27,
}
def _real_extract(self, url):
url, smuggled_data = unsmuggle_url(url, {})
show_id, season_id = self._match_valid_url(url).groups()
data = {}
if season_id:
data['season'] = season_id
show_id = smuggled_data.get('show_id')
if show_id is None:
season = self._download_json(
'http://admin.mangomolo.com/analytics/index.php/plus/season_info?id=%s' % season_id,
season_id, headers={'Origin': 'http://awaan.ae'})
show_id = season['id']
data['show_id'] = show_id
show = self._download_json(
'http://admin.mangomolo.com/analytics/index.php/plus/show',
show_id, data=urlencode_postdata(data), headers={
'Origin': 'http://awaan.ae',
'Content-Type': 'application/x-www-form-urlencoded'
})
if not season_id:
season_id = show['default_season']
for season in show['seasons']:
if season['id'] == season_id:
title = season.get('title_en') or season['title_ar']
entries = []
for video in show['videos']:
video_id = compat_str(video['id'])
entries.append(self.url_result(
'http://awaan.ae/media/%s' % video_id, 'AWAANVideo', video_id))
return self.playlist_result(entries, season_id, title)
yt_dlp/extractor/aws.py
+75
View File
@@ -0,0 +1,75 @@
import datetime
import hashlib
import hmac
from .common import InfoExtractor
from ..compat import compat_urllib_parse_urlencode
class AWSIE(InfoExtractor): # XXX: Conventionally, base classes should end with BaseIE/InfoExtractor
_AWS_ALGORITHM = 'AWS4-HMAC-SHA256'
_AWS_REGION = 'us-east-1'
def _aws_execute_api(self, aws_dict, video_id, query=None):
query = query or {}
amz_date = datetime.datetime.utcnow().strftime('%Y%m%dT%H%M%SZ')
date = amz_date[:8]
headers = {
'Accept': 'application/json',
'Host': self._AWS_PROXY_HOST,
'X-Amz-Date': amz_date,
'X-Api-Key': self._AWS_API_KEY
}
session_token = aws_dict.get('session_token')
if session_token:
headers['X-Amz-Security-Token'] = session_token
def aws_hash(s):
return hashlib.sha256(s.encode('utf-8')).hexdigest()
# Task 1: http://docs.aws.amazon.com/general/latest/gr/sigv4-create-canonical-request.html
canonical_querystring = compat_urllib_parse_urlencode(query)
canonical_headers = ''
for header_name, header_value in sorted(headers.items()):
canonical_headers += '%s:%s\n' % (header_name.lower(), header_value)
signed_headers = ';'.join([header.lower() for header in sorted(headers.keys())])
canonical_request = '\n'.join([
'GET',
aws_dict['uri'],
canonical_querystring,
canonical_headers,
signed_headers,
aws_hash('')
])
# Task 2: http://docs.aws.amazon.com/general/latest/gr/sigv4-create-string-to-sign.html
credential_scope_list = [date, self._AWS_REGION, 'execute-api', 'aws4_request']
credential_scope = '/'.join(credential_scope_list)
string_to_sign = '\n'.join([self._AWS_ALGORITHM, amz_date, credential_scope, aws_hash(canonical_request)])
# Task 3: http://docs.aws.amazon.com/general/latest/gr/sigv4-calculate-signature.html
def aws_hmac(key, msg):
return hmac.new(key, msg.encode('utf-8'), hashlib.sha256)
def aws_hmac_digest(key, msg):
return aws_hmac(key, msg).digest()
def aws_hmac_hexdigest(key, msg):
return aws_hmac(key, msg).hexdigest()
k_signing = ('AWS4' + aws_dict['secret_key']).encode('utf-8')
for value in credential_scope_list:
k_signing = aws_hmac_digest(k_signing, value)
signature = aws_hmac_hexdigest(k_signing, string_to_sign)
# Task 4: http://docs.aws.amazon.com/general/latest/gr/sigv4-add-signature-to-request.html
headers['Authorization'] = ', '.join([
'%s Credential=%s/%s' % (self._AWS_ALGORITHM, aws_dict['access_key'], credential_scope),
'SignedHeaders=%s' % signed_headers,
'Signature=%s' % signature,
])
return self._download_json(
'https://%s%s%s' % (self._AWS_PROXY_HOST, aws_dict['uri'], '?' + canonical_querystring if canonical_querystring else ''),
video_id, headers=headers)
yt_dlp/extractor/azmedien.py
+66
View File
@@ -0,0 +1,66 @@
import json
from .common import InfoExtractor
from .kaltura import KalturaIE
class AZMedienIE(InfoExtractor):
IE_DESC = 'AZ Medien videos'
_VALID_URL = r'''(?x)
https?://
(?:www\.|tv\.)?
(?P<host>
telezueri\.ch|
telebaern\.tv|
telem1\.ch|
tvo-online\.ch
)/
[^/]+/
(?P<id>
[^/]+-(?P<article_id>\d+)
)
(?:
\#video=
(?P<kaltura_id>
[_0-9a-z]+
)
)?
'''
_TESTS = [{
'url': 'https://tv.telezueri.ch/sonntalk/bundesrats-vakanzen-eu-rahmenabkommen-133214569',
'info_dict': {
'id': '1_anruz3wy',
'ext': 'mp4',
'title': 'Bundesrats-Vakanzen / EU-Rahmenabkommen',
'uploader_id': 'TVOnline',
'upload_date': '20180930',
'timestamp': 1538328802,
'view_count': int,
'thumbnail': 'http://cfvod.kaltura.com/p/1719221/sp/171922100/thumbnail/entry_id/1_anruz3wy/version/100031',
'duration': 1930
},
'params': {
'skip_download': True,
},
}, {
'url': 'https://www.telebaern.tv/telebaern-news/montag-1-oktober-2018-ganze-sendung-133531189#video=0_7xjo9lf1',
'only_matching': True
}]
_API_TEMPL = 'https://www.%s/api/pub/gql/%s/NewsArticleTeaser/a4016f65fe62b81dc6664dd9f4910e4ab40383be'
_PARTNER_ID = '1719221'
def _real_extract(self, url):
host, display_id, article_id, entry_id = self._match_valid_url(url).groups()
if not entry_id:
entry_id = self._download_json(
self._API_TEMPL % (host, host.split('.')[0]), display_id, query={
'variables': json.dumps({
'contextId': 'NewsArticle:' + article_id,
}),
})['data']['context']['mainAsset']['video']['kaltura']['kalturaId']
return self.url_result(
'kaltura:%s:%s' % (self._PARTNER_ID, entry_id),
ie=KalturaIE.ie_key(), video_id=entry_id)
yt_dlp/extractor/baidu.py
+51
View File
@@ -0,0 +1,51 @@
from .common import InfoExtractor
from ..utils import unescapeHTML
class BaiduVideoIE(InfoExtractor):
IE_DESC = '百度视频'
_VALID_URL = r'https?://v\.baidu\.com/(?P<type>[a-z]+)/(?P<id>\d+)\.htm'
_TESTS = [{
'url': 'http://v.baidu.com/comic/1069.htm?frp=bdbrand&q=%E4%B8%AD%E5%8D%8E%E5%B0%8F%E5%BD%93%E5%AE%B6',
'info_dict': {
'id': '1069',
'title': '中华小当家 TV版国语',
'description': 'md5:51be07afe461cf99fa61231421b5397c',
},
'playlist_count': 52,
}, {
'url': 'http://v.baidu.com/show/11595.htm?frp=bdbrand',
'info_dict': {
'id': '11595',
'title': 're:^奔跑吧兄弟',
'description': 'md5:1bf88bad6d850930f542d51547c089b8',
},
'playlist_mincount': 12,
}]
def _call_api(self, path, category, playlist_id, note):
return self._download_json('http://app.video.baidu.com/%s/?worktype=adnative%s&id=%s' % (
path, category, playlist_id), playlist_id, note)
def _real_extract(self, url):
category, playlist_id = self._match_valid_url(url).groups()
if category == 'show':
category = 'tvshow'
if category == 'tv':
category = 'tvplay'
playlist_detail = self._call_api(
'xqinfo', category, playlist_id, 'Download playlist JSON metadata')
playlist_title = playlist_detail['title']
playlist_description = unescapeHTML(playlist_detail.get('intro'))
episodes_detail = self._call_api(
'xqsingle', category, playlist_id, 'Download episodes JSON metadata')
entries = [self.url_result(
episode['url'], video_title=episode['title']
) for episode in episodes_detail['videos']]
return self.playlist_result(
entries, playlist_id, playlist_title, playlist_description)
yt_dlp/extractor/banbye.py
+148
View File
@@ -0,0 +1,148 @@
import math
from .common import InfoExtractor
from ..compat import (
compat_urllib_parse_urlparse,
compat_parse_qs,
)
from ..utils import (
format_field,
InAdvancePagedList,
traverse_obj,
unified_timestamp,
)
class BanByeBaseIE(InfoExtractor):
_API_BASE = 'https://api.banbye.com'
_CDN_BASE = 'https://cdn.banbye.com'
_VIDEO_BASE = 'https://banbye.com/watch'
@staticmethod
def _extract_playlist_id(url, param='playlist'):
return compat_parse_qs(
compat_urllib_parse_urlparse(url).query).get(param, [None])[0]
def _extract_playlist(self, playlist_id):
data = self._download_json(f'{self._API_BASE}/playlists/{playlist_id}', playlist_id)
return self.playlist_result([
self.url_result(f'{self._VIDEO_BASE}/{video_id}', BanByeIE)
for video_id in data['videoIds']], playlist_id, data.get('name'))
class BanByeIE(BanByeBaseIE):
_VALID_URL = r'https?://(?:www\.)?banbye.com/(?:en/)?watch/(?P<id>\w+)'
_TESTS = [{
'url': 'https://banbye.com/watch/v_ytfmvkVYLE8T',
'md5': '2f4ea15c5ca259a73d909b2cfd558eb5',
'info_dict': {
'id': 'v_ytfmvkVYLE8T',
'ext': 'mp4',
'title': 'md5:5ec098f88a0d796f987648de6322ba0f',
'description': 'md5:4d94836e73396bc18ef1fa0f43e5a63a',
'uploader': 'wRealu24',
'channel_id': 'ch_wrealu24',
'channel_url': 'https://banbye.com/channel/ch_wrealu24',
'timestamp': 1647604800,
'upload_date': '20220318',
'duration': 1931,
'thumbnail': r're:https?://.*\.webp',
'tags': 'count:5',
'like_count': int,
'dislike_count': int,
'view_count': int,
'comment_count': int,
},
}, {
'url': 'https://banbye.com/watch/v_2JjQtqjKUE_F?playlistId=p_Ld82N6gBw_OJ',
'info_dict': {
'title': 'Krzysztof Karoń',
'id': 'p_Ld82N6gBw_OJ',
},
'playlist_count': 9,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
playlist_id = self._extract_playlist_id(url, 'playlistId')
if self._yes_playlist(playlist_id, video_id):
return self._extract_playlist(playlist_id)
data = self._download_json(f'{self._API_BASE}/videos/{video_id}', video_id)
thumbnails = [{
'id': f'{quality}p',
'url': f'{self._CDN_BASE}/video/{video_id}/{quality}.webp',
} for quality in [48, 96, 144, 240, 512, 1080]]
formats = [{
'format_id': f'http-{quality}p',
'quality': quality,
'url': f'{self._CDN_BASE}/video/{video_id}/{quality}.mp4',
} for quality in data['quality']]
return {
'id': video_id,
'title': data.get('title'),
'description': data.get('desc'),
'uploader': traverse_obj(data, ('channel', 'name')),
'channel_id': data.get('channelId'),
'channel_url': format_field(data, 'channelId', 'https://banbye.com/channel/%s'),
'timestamp': unified_timestamp(data.get('publishedAt')),
'duration': data.get('duration'),
'tags': data.get('tags'),
'formats': formats,
'thumbnails': thumbnails,
'like_count': data.get('likes'),
'dislike_count': data.get('dislikes'),
'view_count': data.get('views'),
'comment_count': data.get('commentCount'),
}
class BanByeChannelIE(BanByeBaseIE):
_VALID_URL = r'https?://(?:www\.)?banbye.com/(?:en/)?channel/(?P<id>\w+)'
_TESTS = [{
'url': 'https://banbye.com/channel/ch_wrealu24',
'info_dict': {
'title': 'wRealu24',
'id': 'ch_wrealu24',
'description': 'md5:da54e48416b74dfdde20a04867c0c2f6',
},
'playlist_mincount': 791,
}, {
'url': 'https://banbye.com/channel/ch_wrealu24?playlist=p_Ld82N6gBw_OJ',
'info_dict': {
'title': 'Krzysztof Karoń',
'id': 'p_Ld82N6gBw_OJ',
},
'playlist_count': 9,
}]
_PAGE_SIZE = 100
def _real_extract(self, url):
channel_id = self._match_id(url)
playlist_id = self._extract_playlist_id(url)
if playlist_id:
return self._extract_playlist(playlist_id)
def page_func(page_num):
data = self._download_json(f'{self._API_BASE}/videos', channel_id, query={
'channelId': channel_id,
'sort': 'new',
'limit': self._PAGE_SIZE,
'offset': page_num * self._PAGE_SIZE,
}, note=f'Downloading page {page_num+1}')
return [
self.url_result(f"{self._VIDEO_BASE}/{video['_id']}", BanByeIE)
for video in data['items']
]
channel_data = self._download_json(f'{self._API_BASE}/channels/{channel_id}', channel_id)
entries = InAdvancePagedList(
page_func,
math.ceil(channel_data['videoCount'] / self._PAGE_SIZE),
self._PAGE_SIZE)
return self.playlist_result(
entries, channel_id, channel_data.get('name'), channel_data.get('description'))
yt_dlp/extractor/bandaichannel.py
+33
View File
@@ -0,0 +1,33 @@
from .brightcove import BrightcoveNewBaseIE
from ..utils import extract_attributes
class BandaiChannelIE(BrightcoveNewBaseIE):
IE_NAME = 'bandaichannel'
_VALID_URL = r'https?://(?:www\.)?b-ch\.com/titles/(?P<id>\d+/\d+)'
_TESTS = [{
'url': 'https://www.b-ch.com/titles/514/001',
'md5': 'a0f2d787baa5729bed71108257f613a4',
'info_dict': {
'id': '6128044564001',
'ext': 'mp4',
'title': 'メタルファイターMIKU 第1話',
'timestamp': 1580354056,
'uploader_id': '5797077852001',
'upload_date': '20200130',
'duration': 1387.733,
},
'params': {
'skip_download': True,
},
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
attrs = extract_attributes(self._search_regex(
r'(<video-js[^>]+\bid="bcplayer"[^>]*>)', webpage, 'player'))
bc = self._download_json(
'https://pbifcd.b-ch.com/v1/playbackinfo/ST/70/' + attrs['data-info'],
video_id, headers={'X-API-KEY': attrs['data-auth'].strip()})['bc']
return self._parse_brightcove_metadata(bc, bc['id'])
yt_dlp/extractor/bandcamp.py
+485
View File
@@ -0,0 +1,485 @@
import random
import re
import time
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
KNOWN_EXTENSIONS,
ExtractorError,
float_or_none,
int_or_none,
parse_filesize,
str_or_none,
try_get,
unified_strdate,
unified_timestamp,
update_url_query,
url_or_none,
urljoin,
)
class BandcampIE(InfoExtractor):
_VALID_URL = r'https?://(?P<uploader>[^/]+)\.bandcamp\.com/track/(?P<id>[^/?#&]+)'
_EMBED_REGEX = [r'<meta property="og:url"[^>]*?content="(?P<url>.*?bandcamp\.com.*?)"']
_TESTS = [{
'url': 'http://youtube-dl.bandcamp.com/track/youtube-dl-test-song',
'md5': 'c557841d5e50261777a6585648adf439',
'info_dict': {
'id': '1812978515',
'ext': 'mp3',
'title': 'youtube-dl "\'/\\ä↭ - youtube-dl "\'/\\ä↭ - youtube-dl test song "\'/\\ä↭',
'duration': 9.8485,
'uploader': 'youtube-dl "\'/\\ä↭',
'upload_date': '20121129',
'timestamp': 1354224127,
'track': 'youtube-dl "\'/\\ä↭ - youtube-dl test song "\'/\\ä↭',
'album_artist': 'youtube-dl "\'/\\ä↭',
'track_id': '1812978515',
'artist': 'youtube-dl "\'/\\ä↭',
'uploader_url': 'https://youtube-dl.bandcamp.com',
'uploader_id': 'youtube-dl',
'thumbnail': 'https://f4.bcbits.com/img/a3216802731_5.jpg',
},
'_skip': 'There is a limit of 200 free downloads / month for the test song'
}, {
# free download
'url': 'http://benprunty.bandcamp.com/track/lanius-battle',
'info_dict': {
'id': '2650410135',
'ext': 'm4a',
'acodec': r're:[fa]lac',
'title': 'Ben Prunty - Lanius (Battle)',
'thumbnail': r're:^https?://.*\.jpg$',
'uploader': 'Ben Prunty',
'timestamp': 1396508491,
'upload_date': '20140403',
'release_timestamp': 1396483200,
'release_date': '20140403',
'duration': 260.877,
'track': 'Lanius (Battle)',
'track_number': 1,
'track_id': '2650410135',
'artist': 'Ben Prunty',
'album_artist': 'Ben Prunty',
'album': 'FTL: Advanced Edition Soundtrack',
'uploader_url': 'https://benprunty.bandcamp.com',
'uploader_id': 'benprunty',
},
}, {
# no free download, mp3 128
'url': 'https://relapsealumni.bandcamp.com/track/hail-to-fire',
'md5': 'fec12ff55e804bb7f7ebeb77a800c8b7',
'info_dict': {
'id': '2584466013',
'ext': 'mp3',
'title': 'Mastodon - Hail to Fire',
'thumbnail': r're:^https?://.*\.jpg$',
'uploader': 'Mastodon',
'timestamp': 1322005399,
'upload_date': '20111122',
'release_timestamp': 1076112000,
'release_date': '20040207',
'duration': 120.79,
'track': 'Hail to Fire',
'track_number': 5,
'track_id': '2584466013',
'artist': 'Mastodon',
'album_artist': 'Mastodon',
'album': 'Call of the Mastodon',
'uploader_url': 'https://relapsealumni.bandcamp.com',
'uploader_id': 'relapsealumni',
},
}, {
# track from compilation album (artist/album_artist difference)
'url': 'https://diskotopia.bandcamp.com/track/safehouse',
'md5': '19c5337bca1428afa54129f86a2f6a69',
'info_dict': {
'id': '1978174799',
'ext': 'mp3',
'title': 'submerse - submerse - Safehouse',
'thumbnail': r're:^https?://.*\.jpg$',
'uploader': 'submerse',
'timestamp': 1480779297,
'upload_date': '20161203',
'release_timestamp': 1481068800,
'release_date': '20161207',
'duration': 154.066,
'track': 'submerse - Safehouse',
'track_number': 3,
'track_id': '1978174799',
'artist': 'submerse',
'album_artist': 'Diskotopia',
'album': 'DSK F/W 2016-2017 Free Compilation',
'uploader_url': 'https://diskotopia.bandcamp.com',
'uploader_id': 'diskotopia',
},
}]
def _extract_data_attr(self, webpage, video_id, attr='tralbum', fatal=True):
return self._parse_json(self._html_search_regex(
r'data-%s=(["\'])({.+?})\1' % attr, webpage,
attr + ' data', group=2), video_id, fatal=fatal)
def _real_extract(self, url):
title, uploader = self._match_valid_url(url).group('id', 'uploader')
webpage = self._download_webpage(url, title)
tralbum = self._extract_data_attr(webpage, title)
thumbnail = self._og_search_thumbnail(webpage)
track_id = None
track = None
track_number = None
duration = None
formats = []
track_info = try_get(tralbum, lambda x: x['trackinfo'][0], dict)
if track_info:
file_ = track_info.get('file')
if isinstance(file_, dict):
for format_id, format_url in file_.items():
if not url_or_none(format_url):
continue
ext, abr_str = format_id.split('-', 1)
formats.append({
'format_id': format_id,
'url': self._proto_relative_url(format_url, 'http:'),
'ext': ext,
'vcodec': 'none',
'acodec': ext,
'abr': int_or_none(abr_str),
})
track = track_info.get('title')
track_id = str_or_none(
track_info.get('track_id') or track_info.get('id'))
track_number = int_or_none(track_info.get('track_num'))
duration = float_or_none(track_info.get('duration'))
embed = self._extract_data_attr(webpage, title, 'embed', False)
current = tralbum.get('current') or {}
artist = embed.get('artist') or current.get('artist') or tralbum.get('artist')
album_artist = self._html_search_regex(
r'<h3 class="albumTitle">[\S\s]*?by\s*<span>\s*<a href="[^>]+">\s*([^>]+?)\s*</a>',
webpage, 'album artist', fatal=False)
timestamp = unified_timestamp(
current.get('publish_date') or tralbum.get('album_publish_date'))
download_link = tralbum.get('freeDownloadPage')
if download_link:
track_id = compat_str(tralbum['id'])
download_webpage = self._download_webpage(
download_link, track_id, 'Downloading free downloads page')
blob = self._extract_data_attr(download_webpage, track_id, 'blob')
info = try_get(
blob, (lambda x: x['digital_items'][0],
lambda x: x['download_items'][0]), dict)
if info:
downloads = info.get('downloads')
if isinstance(downloads, dict):
if not track:
track = info.get('title')
if not artist:
artist = info.get('artist')
if not thumbnail:
thumbnail = info.get('thumb_url')
download_formats = {}
download_formats_list = blob.get('download_formats')
if isinstance(download_formats_list, list):
for f in blob['download_formats']:
name, ext = f.get('name'), f.get('file_extension')
if all(isinstance(x, compat_str) for x in (name, ext)):
download_formats[name] = ext.strip('.')
for format_id, f in downloads.items():
format_url = f.get('url')
if not format_url:
continue
# Stat URL generation algorithm is reverse engineered from
# download_*_bundle_*.js
stat_url = update_url_query(
format_url.replace('/download/', '/statdownload/'), {
'.rand': int(time.time() * 1000 * random.random()),
})
format_id = f.get('encoding_name') or format_id
stat = self._download_json(
stat_url, track_id, 'Downloading %s JSON' % format_id,
transform_source=lambda s: s[s.index('{'):s.rindex('}') + 1],
fatal=False)
if not stat:
continue
retry_url = url_or_none(stat.get('retry_url'))
if not retry_url:
continue
formats.append({
'url': self._proto_relative_url(retry_url, 'http:'),
'ext': download_formats.get(format_id),
'format_id': format_id,
'format_note': f.get('description'),
'filesize': parse_filesize(f.get('size_mb')),
'vcodec': 'none',
'acodec': format_id.split('-')[0],
})
title = '%s - %s' % (artist, track) if artist else track
if not duration:
duration = float_or_none(self._html_search_meta(
'duration', webpage, default=None))
return {
'id': track_id,
'title': title,
'thumbnail': thumbnail,
'uploader': artist,
'uploader_id': uploader,
'uploader_url': f'https://{uploader}.bandcamp.com',
'timestamp': timestamp,
'release_timestamp': unified_timestamp(tralbum.get('album_release_date')),
'duration': duration,
'track': track,
'track_number': track_number,
'track_id': track_id,
'artist': artist,
'album': embed.get('album_title'),
'album_artist': album_artist,
'formats': formats,
}
class BandcampAlbumIE(BandcampIE): # XXX: Do not subclass from concrete IE
IE_NAME = 'Bandcamp:album'
_VALID_URL = r'https?://(?:(?P<subdomain>[^.]+)\.)?bandcamp\.com/album/(?P<id>[^/?#&]+)'
_TESTS = [{
'url': 'http://blazo.bandcamp.com/album/jazz-format-mixtape-vol-1',
'playlist': [
{
'md5': '39bc1eded3476e927c724321ddf116cf',
'info_dict': {
'id': '1353101989',
'ext': 'mp3',
'title': 'Blazo - Intro',
'timestamp': 1311756226,
'upload_date': '20110727',
'uploader': 'Blazo',
}
},
{
'md5': '1a2c32e2691474643e912cc6cd4bffaa',
'info_dict': {
'id': '38097443',
'ext': 'mp3',
'title': 'Blazo - Kero One - Keep It Alive (Blazo remix)',
'timestamp': 1311757238,
'upload_date': '20110727',
'uploader': 'Blazo',
}
},
],
'info_dict': {
'title': 'Jazz Format Mixtape vol.1',
'id': 'jazz-format-mixtape-vol-1',
'uploader_id': 'blazo',
},
'params': {
'playlistend': 2
},
'skip': 'Bandcamp imposes download limits.'
}, {
'url': 'http://nightbringer.bandcamp.com/album/hierophany-of-the-open-grave',
'info_dict': {
'title': 'Hierophany of the Open Grave',
'uploader_id': 'nightbringer',
'id': 'hierophany-of-the-open-grave',
},
'playlist_mincount': 9,
}, {
# with escaped quote in title
'url': 'https://jstrecords.bandcamp.com/album/entropy-ep',
'info_dict': {
'title': '"Entropy" EP',
'uploader_id': 'jstrecords',
'id': 'entropy-ep',
'description': 'md5:0ff22959c943622972596062f2f366a5',
},
'playlist_mincount': 3,
}, {
# not all tracks have songs
'url': 'https://insulters.bandcamp.com/album/we-are-the-plague',
'info_dict': {
'id': 'we-are-the-plague',
'title': 'WE ARE THE PLAGUE',
'uploader_id': 'insulters',
'description': 'md5:b3cf845ee41b2b1141dc7bde9237255f',
},
'playlist_count': 2,
}]
@classmethod
def suitable(cls, url):
return (False
if BandcampWeeklyIE.suitable(url) or BandcampIE.suitable(url)
else super(BandcampAlbumIE, cls).suitable(url))
def _real_extract(self, url):
uploader_id, album_id = self._match_valid_url(url).groups()
playlist_id = album_id or uploader_id
webpage = self._download_webpage(url, playlist_id)
tralbum = self._extract_data_attr(webpage, playlist_id)
track_info = tralbum.get('trackinfo')
if not track_info:
raise ExtractorError('The page doesn\'t contain any tracks')
# Only tracks with duration info have songs
entries = [
self.url_result(
urljoin(url, t['title_link']), BandcampIE.ie_key(),
str_or_none(t.get('track_id') or t.get('id')), t.get('title'))
for t in track_info
if t.get('duration')]
current = tralbum.get('current') or {}
return {
'_type': 'playlist',
'uploader_id': uploader_id,
'id': playlist_id,
'title': current.get('title'),
'description': current.get('about'),
'entries': entries,
}
class BandcampWeeklyIE(BandcampIE): # XXX: Do not subclass from concrete IE
IE_NAME = 'Bandcamp:weekly'
_VALID_URL = r'https?://(?:www\.)?bandcamp\.com/?\?(?:.*?&)?show=(?P<id>\d+)'
_TESTS = [{
'url': 'https://bandcamp.com/?show=224',
'md5': 'b00df799c733cf7e0c567ed187dea0fd',
'info_dict': {
'id': '224',
'ext': 'opus',
'title': 'BC Weekly April 4th 2017 - Magic Moments',
'description': 'md5:5d48150916e8e02d030623a48512c874',
'duration': 5829.77,
'release_date': '20170404',
'series': 'Bandcamp Weekly',
'episode': 'Magic Moments',
'episode_id': '224',
},
'params': {
'format': 'opus-lo',
},
}, {
'url': 'https://bandcamp.com/?blah/blah@&show=228',
'only_matching': True
}]
def _real_extract(self, url):
show_id = self._match_id(url)
webpage = self._download_webpage(url, show_id)
blob = self._extract_data_attr(webpage, show_id, 'blob')
show = blob['bcw_data'][show_id]
formats = []
for format_id, format_url in show['audio_stream'].items():
if not url_or_none(format_url):
continue
for known_ext in KNOWN_EXTENSIONS:
if known_ext in format_id:
ext = known_ext
break
else:
ext = None
formats.append({
'format_id': format_id,
'url': format_url,
'ext': ext,
'vcodec': 'none',
})
title = show.get('audio_title') or 'Bandcamp Weekly'
subtitle = show.get('subtitle')
if subtitle:
title += ' - %s' % subtitle
return {
'id': show_id,
'title': title,
'description': show.get('desc') or show.get('short_desc'),
'duration': float_or_none(show.get('audio_duration')),
'is_live': False,
'release_date': unified_strdate(show.get('published_date')),
'series': 'Bandcamp Weekly',
'episode': show.get('subtitle'),
'episode_id': show_id,
'formats': formats
}
class BandcampUserIE(InfoExtractor):
IE_NAME = 'Bandcamp:user'
_VALID_URL = r'https?://(?!www\.)(?P<id>[^.]+)\.bandcamp\.com(?:/music)?/?(?:[#?]|$)'
_TESTS = [{
# Type 1 Bandcamp user page.
'url': 'https://adrianvonziegler.bandcamp.com',
'info_dict': {
'id': 'adrianvonziegler',
'title': 'Discography of adrianvonziegler',
},
'playlist_mincount': 23,
}, {
# Bandcamp user page with only one album
'url': 'http://dotscale.bandcamp.com',
'info_dict': {
'id': 'dotscale',
'title': 'Discography of dotscale'
},
'playlist_count': 1,
}, {
# Type 2 Bandcamp user page.
'url': 'https://nightcallofficial.bandcamp.com',
'info_dict': {
'id': 'nightcallofficial',
'title': 'Discography of nightcallofficial',
},
'playlist_count': 4,
}, {
'url': 'https://steviasphere.bandcamp.com/music',
'playlist_mincount': 47,
'info_dict': {
'id': 'steviasphere',
'title': 'Discography of steviasphere',
},
}, {
'url': 'https://coldworldofficial.bandcamp.com/music',
'playlist_mincount': 10,
'info_dict': {
'id': 'coldworldofficial',
'title': 'Discography of coldworldofficial',
},
}, {
'url': 'https://nuclearwarnowproductions.bandcamp.com/music',
'playlist_mincount': 399,
'info_dict': {
'id': 'nuclearwarnowproductions',
'title': 'Discography of nuclearwarnowproductions',
},
}]
def _real_extract(self, url):
uploader = self._match_id(url)
webpage = self._download_webpage(url, uploader)
discography_data = (re.findall(r'<li data-item-id=["\'][^>]+>\s*<a href=["\'](?![^"\'/]*?/merch)([^"\']+)', webpage)
or re.findall(r'<div[^>]+trackTitle["\'][^"\']+["\']([^"\']+)', webpage))
return self.playlist_from_matches(
discography_data, uploader, f'Discography of {uploader}', getter=lambda x: urljoin(url, x))
yt_dlp/extractor/bannedvideo.py
+155
View File
@@ -0,0 +1,155 @@
import json
from .common import InfoExtractor
from ..utils import (
try_get,
int_or_none,
url_or_none,
float_or_none,
unified_timestamp,
)
class BannedVideoIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?banned\.video/watch\?id=(?P<id>[0-f]{24})'
_TESTS = [{
'url': 'https://banned.video/watch?id=5e7a859644e02200c6ef5f11',
'md5': '14b6e81d41beaaee2215cd75c6ed56e4',
'info_dict': {
'id': '5e7a859644e02200c6ef5f11',
'ext': 'mp4',
'title': 'China Discovers Origin of Corona Virus: Issues Emergency Statement',
'thumbnail': r're:^https?://(?:www\.)?assets\.infowarsmedia.com/images/',
'description': 'md5:560d96f02abbebe6c6b78b47465f6b28',
'upload_date': '20200324',
'timestamp': 1585087895,
}
}]
_GRAPHQL_GETMETADATA_QUERY = '''
query GetVideoAndComments($id: String!) {
getVideo(id: $id) {
streamUrl
directUrl
unlisted
live
tags {
name
}
title
summary
playCount
largeImage
videoDuration
channel {
_id
title
}
createdAt
}
getVideoComments(id: $id, limit: 999999, offset: 0) {
_id
content
user {
_id
username
}
voteCount {
positive
}
createdAt
replyCount
}
}'''
_GRAPHQL_GETCOMMENTSREPLIES_QUERY = '''
query GetCommentReplies($id: String!) {
getCommentReplies(id: $id, limit: 999999, offset: 0) {
_id
content
user {
_id
username
}
voteCount {
positive
}
createdAt
replyCount
}
}'''
_GRAPHQL_QUERIES = {
'GetVideoAndComments': _GRAPHQL_GETMETADATA_QUERY,
'GetCommentReplies': _GRAPHQL_GETCOMMENTSREPLIES_QUERY,
}
def _call_api(self, video_id, id, operation, note):
return self._download_json(
'https://api.infowarsmedia.com/graphql', video_id, note=note,
headers={
'Content-Type': 'application/json; charset=utf-8'
}, data=json.dumps({
'variables': {'id': id},
'operationName': operation,
'query': self._GRAPHQL_QUERIES[operation]
}).encode('utf8')).get('data')
def _get_comments(self, video_id, comments, comment_data):
yield from comments
for comment in comment_data.copy():
comment_id = comment.get('_id')
if comment.get('replyCount') > 0:
reply_json = self._call_api(
video_id, comment_id, 'GetCommentReplies',
f'Downloading replies for comment {comment_id}')
for reply in reply_json.get('getCommentReplies'):
yield self._parse_comment(reply, comment_id)
@staticmethod
def _parse_comment(comment_data, parent):
return {
'id': comment_data.get('_id'),
'text': comment_data.get('content'),
'author': try_get(comment_data, lambda x: x['user']['username']),
'author_id': try_get(comment_data, lambda x: x['user']['_id']),
'timestamp': unified_timestamp(comment_data.get('createdAt')),
'parent': parent,
'like_count': try_get(comment_data, lambda x: x['voteCount']['positive']),
}
def _real_extract(self, url):
video_id = self._match_id(url)
video_json = self._call_api(video_id, video_id, 'GetVideoAndComments', 'Downloading video metadata')
video_info = video_json['getVideo']
is_live = video_info.get('live')
comments = [self._parse_comment(comment, 'root') for comment in video_json.get('getVideoComments')]
formats = [{
'format_id': 'direct',
'quality': 1,
'url': video_info.get('directUrl'),
'ext': 'mp4',
}] if url_or_none(video_info.get('directUrl')) else []
if video_info.get('streamUrl'):
formats.extend(self._extract_m3u8_formats(
video_info.get('streamUrl'), video_id, 'mp4',
entry_protocol='m3u8_native', m3u8_id='hls', live=True))
return {
'id': video_id,
'title': video_info.get('title')[:-1],
'formats': formats,
'is_live': is_live,
'description': video_info.get('summary'),
'channel': try_get(video_info, lambda x: x['channel']['title']),
'channel_id': try_get(video_info, lambda x: x['channel']['_id']),
'view_count': int_or_none(video_info.get('playCount')),
'thumbnail': url_or_none(video_info.get('largeImage')),
'duration': float_or_none(video_info.get('videoDuration')),
'timestamp': unified_timestamp(video_info.get('createdAt')),
'tags': [tag.get('name') for tag in video_info.get('tags')],
'availability': self._availability(is_unlisted=video_info.get('unlisted')),
'comments': comments,
'__post_extractor': self.extract_comments(video_id, comments, video_json.get('getVideoComments'))
}
yt_dlp/extractor/bbc.py
+1643
View File
File diff suppressed because it is too large Load Diff
yt_dlp/extractor/beatbump.py
+101
View File
@@ -0,0 +1,101 @@
from .common import InfoExtractor
from .youtube import YoutubeIE, YoutubeTabIE
class BeatBumpVideoIE(InfoExtractor):
_VALID_URL = r'https://beatbump\.ml/listen\?id=(?P<id>[\w-]+)'
_TESTS = [{
'url': 'https://beatbump.ml/listen?id=MgNrAu2pzNs',
'md5': '5ff3fff41d3935b9810a9731e485fe66',
'info_dict': {
'id': 'MgNrAu2pzNs',
'ext': 'mp4',
'uploader_url': 'http://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA',
'artist': 'Stephen',
'thumbnail': 'https://i.ytimg.com/vi_webp/MgNrAu2pzNs/maxresdefault.webp',
'channel_url': 'https://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA',
'upload_date': '20190312',
'categories': ['Music'],
'playable_in_embed': True,
'duration': 169,
'like_count': int,
'alt_title': 'Voyeur Girl',
'view_count': int,
'track': 'Voyeur Girl',
'uploader': 'Stephen - Topic',
'title': 'Voyeur Girl',
'channel_follower_count': int,
'uploader_id': 'UC-pWHpBjdGG69N9mM2auIAA',
'age_limit': 0,
'availability': 'public',
'live_status': 'not_live',
'album': 'it\'s too much love to know my dear',
'channel': 'Stephen',
'comment_count': int,
'description': 'md5:7ae382a65843d6df2685993e90a8628f',
'tags': 'count:11',
'creator': 'Stephen',
'channel_id': 'UC-pWHpBjdGG69N9mM2auIAA',
}
}]
def _real_extract(self, url):
id_ = self._match_id(url)
return self.url_result(f'https://music.youtube.com/watch?v={id_}', YoutubeIE, id_)
class BeatBumpPlaylistIE(InfoExtractor):
_VALID_URL = r'https://beatbump\.ml/(?:release\?id=|artist/|playlist/)(?P<id>[\w-]+)'
_TESTS = [{
'url': 'https://beatbump.ml/release?id=MPREb_gTAcphH99wE',
'playlist_count': 50,
'info_dict': {
'id': 'OLAK5uy_l1m0thk3g31NmIIz_vMIbWtyv7eZixlH0',
'availability': 'unlisted',
'view_count': int,
'title': 'Album - Royalty Free Music Library V2 (50 Songs)',
'description': '',
'tags': [],
'modified_date': '20221223',
}
}, {
'url': 'https://beatbump.ml/artist/UC_aEa8K-EOJ3D6gOs7HcyNg',
'playlist_mincount': 1,
'params': {'flatplaylist': True},
'info_dict': {
'id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
'uploader_url': 'https://www.youtube.com/channel/UC_aEa8K-EOJ3D6gOs7HcyNg',
'channel_url': 'https://www.youtube.com/channel/UC_aEa8K-EOJ3D6gOs7HcyNg',
'uploader_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
'channel_follower_count': int,
'title': 'NoCopyrightSounds - Videos',
'uploader': 'NoCopyrightSounds',
'description': 'md5:cd4fd53d81d363d05eee6c1b478b491a',
'channel': 'NoCopyrightSounds',
'tags': 'count:12',
'channel_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
},
}, {
'url': 'https://beatbump.ml/playlist/VLPLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
'playlist_mincount': 1,
'params': {'flatplaylist': True},
'info_dict': {
'id': 'PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
'uploader_url': 'https://www.youtube.com/@NoCopyrightSounds',
'description': 'Providing you with copyright free / safe music for gaming, live streaming, studying and more!',
'view_count': int,
'channel_url': 'https://www.youtube.com/@NoCopyrightSounds',
'uploader_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
'title': 'NCS : All Releases 💿',
'uploader': 'NoCopyrightSounds',
'availability': 'public',
'channel': 'NoCopyrightSounds',
'tags': [],
'modified_date': '20221225',
'channel_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
}
}]
def _real_extract(self, url):
id_ = self._match_id(url)
return self.url_result(f'https://music.youtube.com/browse/{id_}', YoutubeTabIE, id_)
yt_dlp/extractor/beatport.py
+97
View File
@@ -0,0 +1,97 @@
import re
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import int_or_none
class BeatportIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.|pro\.)?beatport\.com/track/(?P<display_id>[^/]+)/(?P<id>[0-9]+)'
_TESTS = [{
'url': 'https://beatport.com/track/synesthesia-original-mix/5379371',
'md5': 'b3c34d8639a2f6a7f734382358478887',
'info_dict': {
'id': '5379371',
'display_id': 'synesthesia-original-mix',
'ext': 'mp4',
'title': 'Froxic - Synesthesia (Original Mix)',
},
}, {
'url': 'https://beatport.com/track/love-and-war-original-mix/3756896',
'md5': 'e44c3025dfa38c6577fbaeb43da43514',
'info_dict': {
'id': '3756896',
'display_id': 'love-and-war-original-mix',
'ext': 'mp3',
'title': 'Wolfgang Gartner - Love & War (Original Mix)',
},
}, {
'url': 'https://beatport.com/track/birds-original-mix/4991738',
'md5': 'a1fd8e8046de3950fd039304c186c05f',
'info_dict': {
'id': '4991738',
'display_id': 'birds-original-mix',
'ext': 'mp4',
'title': "Tos, Middle Milk, Mumblin' Johnsson - Birds (Original Mix)",
}
}]
def _real_extract(self, url):
mobj = self._match_valid_url(url)
track_id = mobj.group('id')
display_id = mobj.group('display_id')
webpage = self._download_webpage(url, display_id)
playables = self._parse_json(
self._search_regex(
r'window\.Playables\s*=\s*({.+?});', webpage,
'playables info', flags=re.DOTALL),
track_id)
track = next(t for t in playables['tracks'] if t['id'] == int(track_id))
title = ', '.join((a['name'] for a in track['artists'])) + ' - ' + track['name']
if track['mix']:
title += ' (' + track['mix'] + ')'
formats = []
for ext, info in track['preview'].items():
if not info['url']:
continue
fmt = {
'url': info['url'],
'ext': ext,
'format_id': ext,
'vcodec': 'none',
}
if ext == 'mp3':
fmt['acodec'] = 'mp3'
fmt['abr'] = 96
fmt['asr'] = 44100
elif ext == 'mp4':
fmt['acodec'] = 'aac'
fmt['abr'] = 96
fmt['asr'] = 44100
formats.append(fmt)
images = []
for name, info in track['images'].items():
image_url = info.get('url')
if name == 'dynamic' or not image_url:
continue
image = {
'id': name,
'url': image_url,
'height': int_or_none(info.get('height')),
'width': int_or_none(info.get('width')),
}
images.append(image)
return {
'id': compat_str(track.get('id')) or track_id,
'display_id': track.get('slug') or display_id,
'title': title,
'formats': formats,
'thumbnails': images,
}
yt_dlp/extractor/beeg.py
+89
View File
@@ -0,0 +1,89 @@
from .common import InfoExtractor
from ..utils import (
int_or_none,
traverse_obj,
try_get,
unified_timestamp,
)
class BeegIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?beeg\.(?:com(?:/video)?)/-?(?P<id>\d+)'
_TESTS = [{
'url': 'https://beeg.com/-0983946056129650',
'md5': '51d235147c4627cfce884f844293ff88',
'info_dict': {
'id': '0983946056129650',
'ext': 'mp4',
'title': 'sucked cock and fucked in a private plane',
'duration': 927,
'tags': list,
'age_limit': 18,
'upload_date': '20220131',
'timestamp': 1643656455,
'display_id': 2540839,
}
}, {
'url': 'https://beeg.com/-0599050563103750?t=4-861',
'md5': 'bd8b5ea75134f7f07fad63008db2060e',
'info_dict': {
'id': '0599050563103750',
'ext': 'mp4',
'title': 'Bad Relatives',
'duration': 2060,
'tags': list,
'age_limit': 18,
'description': 'md5:b4fc879a58ae6c604f8f259155b7e3b9',
'timestamp': 1643623200,
'display_id': 2569965,
'upload_date': '20220131',
}
}, {
# api/v6 v2
'url': 'https://beeg.com/1941093077?t=911-1391',
'only_matching': True,
}, {
# api/v6 v2 w/o t
'url': 'https://beeg.com/1277207756',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
video = self._download_json(
'https://store.externulls.com/facts/file/%s' % video_id,
video_id, 'Downloading JSON for %s' % video_id)
fc_facts = video.get('fc_facts')
first_fact = {}
for fact in fc_facts:
if not first_fact or try_get(fact, lambda x: x['id'] < first_fact['id']):
first_fact = fact
resources = traverse_obj(video, ('file', 'hls_resources')) or first_fact.get('hls_resources')
formats = []
for format_id, video_uri in resources.items():
if not video_uri:
continue
height = int_or_none(self._search_regex(r'fl_cdn_(\d+)', format_id, 'height', default=None))
current_formats = self._extract_m3u8_formats(f'https://video.beeg.com/{video_uri}', video_id, ext='mp4', m3u8_id=str(height))
for f in current_formats:
f['height'] = height
formats.extend(current_formats)
return {
'id': video_id,
'display_id': first_fact.get('id'),
'title': traverse_obj(video, ('file', 'stuff', 'sf_name')),
'description': traverse_obj(video, ('file', 'stuff', 'sf_story')),
'timestamp': unified_timestamp(first_fact.get('fc_created')),
'duration': int_or_none(traverse_obj(video, ('file', 'fl_duration'))),
'tags': traverse_obj(video, ('tags', ..., 'tg_name')),
'formats': formats,
'age_limit': self._rta_search(webpage),
}
yt_dlp/extractor/behindkink.py
+41
View File
@@ -0,0 +1,41 @@
from .common import InfoExtractor
from ..utils import url_basename
class BehindKinkIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?behindkink\.com/(?P<year>[0-9]{4})/(?P<month>[0-9]{2})/(?P<day>[0-9]{2})/(?P<id>[^/#?_]+)'
_TEST = {
'url': 'http://www.behindkink.com/2014/12/05/what-are-you-passionate-about-marley-blaze/',
'md5': '507b57d8fdcd75a41a9a7bdb7989c762',
'info_dict': {
'id': '37127',
'ext': 'mp4',
'title': 'What are you passionate about – Marley Blaze',
'description': 'md5:aee8e9611b4ff70186f752975d9b94b4',
'upload_date': '20141205',
'thumbnail': 'http://www.behindkink.com/wp-content/uploads/2014/12/blaze-1.jpg',
'age_limit': 18,
}
}
def _real_extract(self, url):
mobj = self._match_valid_url(url)
display_id = mobj.group('id')
webpage = self._download_webpage(url, display_id)
video_url = self._search_regex(
r'<source src="([^"]+)"', webpage, 'video URL')
video_id = url_basename(video_url).split('_')[0]
upload_date = mobj.group('year') + mobj.group('month') + mobj.group('day')
return {
'id': video_id,
'display_id': display_id,
'url': video_url,
'title': self._og_search_title(webpage),
'thumbnail': self._og_search_thumbnail(webpage),
'description': self._og_search_description(webpage),
'upload_date': upload_date,
'age_limit': 18,
}
yt_dlp/extractor/bellmedia.py
+91
View File
@@ -0,0 +1,91 @@
from .common import InfoExtractor
class BellMediaIE(InfoExtractor):
_VALID_URL = r'''(?x)https?://(?:www\.)?
(?P<domain>
(?:
ctv|
tsn|
bnn(?:bloomberg)?|
thecomedynetwork|
discovery|
discoveryvelocity|
sciencechannel|
investigationdiscovery|
animalplanet|
bravo|
mtv|
space|
etalk|
marilyn
)\.ca|
(?:much|cp24)\.com
)/.*?(?:\b(?:vid(?:eoid)?|clipId)=|-vid|~|%7E|/(?:episode)?)(?P<id>[0-9]{6,})'''
_TESTS = [{
'url': 'https://www.bnnbloomberg.ca/video/david-cockfield-s-top-picks~1403070',
'md5': '3e5b8e38370741d5089da79161646635',
'info_dict': {
'id': '1403070',
'ext': 'flv',
'title': 'David Cockfield\'s Top Picks',
'description': 'md5:810f7f8c6a83ad5b48677c3f8e5bb2c3',
'upload_date': '20180525',
'timestamp': 1527288600,
'season_id': 73997,
'season': '2018',
'thumbnail': 'http://images2.9c9media.com/image_asset/2018_5_25_baf30cbd-b28d-4a18-9903-4bb8713b00f5_PNG_956x536.jpg',
'tags': [],
'categories': ['ETFs'],
'season_number': 8,
'duration': 272.038,
'series': 'Market Call Tonight',
},
}, {
'url': 'http://www.thecomedynetwork.ca/video/player?vid=923582',
'only_matching': True,
}, {
'url': 'http://www.tsn.ca/video/expectations-high-for-milos-raonic-at-us-open~939549',
'only_matching': True,
}, {
'url': 'http://www.bnn.ca/video/berman-s-call-part-two-viewer-questions~939654',
'only_matching': True,
}, {
'url': 'http://www.ctv.ca/YourMorning/Video/S1E6-Monday-August-29-2016-vid938009',
'only_matching': True,
}, {
'url': 'http://www.much.com/shows/atmidnight/episode948007/tuesday-september-13-2016',
'only_matching': True,
}, {
'url': 'http://www.much.com/shows/the-almost-impossible-gameshow/928979/episode-6',
'only_matching': True,
}, {
'url': 'http://www.ctv.ca/DCs-Legends-of-Tomorrow/Video/S2E11-Turncoat-vid1051430',
'only_matching': True,
}, {
'url': 'http://www.etalk.ca/video?videoid=663455',
'only_matching': True,
}, {
'url': 'https://www.cp24.com/video?clipId=1982548',
'only_matching': True,
}]
_DOMAINS = {
'thecomedynetwork': 'comedy',
'discoveryvelocity': 'discvel',
'sciencechannel': 'discsci',
'investigationdiscovery': 'invdisc',
'animalplanet': 'aniplan',
'etalk': 'ctv',
'bnnbloomberg': 'bnn',
'marilyn': 'ctv_marilyn',
}
def _real_extract(self, url):
domain, video_id = self._match_valid_url(url).groups()
domain = domain.split('.')[0]
return {
'_type': 'url_transparent',
'id': video_id,
'url': '9c9media:%s_web:%s' % (self._DOMAINS.get(domain, domain), video_id),
'ie_key': 'NineCNineMedia',
}
yt_dlp/extractor/berufetv.py
+70
View File
@@ -0,0 +1,70 @@
from .common import InfoExtractor
from ..utils import float_or_none, mimetype2ext, traverse_obj
class BerufeTVIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?web\.arbeitsagentur\.de/berufetv/[^?#]+/film;filmId=(?P<id>[\w-]+)'
_TESTS = [{
'url': 'https://web.arbeitsagentur.de/berufetv/studienberufe/wirtschaftswissenschaften/wirtschaftswissenschaften-volkswirtschaft/film;filmId=DvKC3DUpMKvUZ_6fEnfg3u',
'md5': '041b6432ec8e6838f84a5c30f31cc795',
'info_dict': {
'id': 'DvKC3DUpMKvUZ_6fEnfg3u',
'ext': 'mp4',
'title': 'Volkswirtschaftslehre',
'description': 'md5:6bd87d0c63163480a6489a37526ee1c1',
'categories': ['Studien&shy;beruf'],
'tags': ['Studienfilm'],
'duration': 602.440,
'thumbnail': r're:^https://asset-out-cdn\.video-cdn\.net/private/videos/DvKC3DUpMKvUZ_6fEnfg3u/thumbnails/793063\?quality=thumbnail&__token__=[^\s]+$',
}
}]
def _real_extract(self, url):
video_id = self._match_id(url)
movie_metadata = self._download_json(
'https://rest.arbeitsagentur.de/infosysbub/berufetv/pc/v1/film-metadata',
video_id, 'Downloading JSON metadata',
headers={'X-API-Key': '79089773-4892-4386-86e6-e8503669f426'}, fatal=False)
meta = traverse_obj(
movie_metadata, ('metadaten', lambda _, i: video_id == i['miId']),
get_all=False, default={})
video = self._download_json(
f'https://d.video-cdn.net/play/player/8YRzUk6pTzmBdrsLe9Y88W/video/{video_id}',
video_id, 'Downloading video JSON')
formats, subtitles = [], {}
for key, source in video['videoSources']['html'].items():
if key == 'auto':
fmts, subs = self._extract_m3u8_formats_and_subtitles(source[0]['source'], video_id)
formats += fmts
subtitles = subs
else:
formats.append({
'url': source[0]['source'],
'ext': mimetype2ext(source[0]['mimeType']),
'format_id': key,
})
for track in video.get('videoTracks') or []:
if track.get('type') != 'SUBTITLES':
continue
subtitles.setdefault(track['language'], []).append({
'url': track['source'],
'name': track.get('label'),
'ext': 'vtt'
})
return {
'id': video_id,
'title': meta.get('titel') or traverse_obj(video, ('videoMetaData', 'title')),
'description': meta.get('beschreibung'),
'thumbnail': meta.get('thumbnail') or f'https://asset-out-cdn.video-cdn.net/private/videos/{video_id}/thumbnails/active',
'duration': float_or_none(video.get('duration'), scale=1000),
'categories': [meta['kategorie']] if meta.get('kategorie') else None,
'tags': meta.get('themengebiete'),
'subtitles': subtitles,
'formats': formats,
}
yt_dlp/extractor/bet.py
+80
View File
@@ -0,0 +1,80 @@
from .mtv import MTVServicesInfoExtractor
from ..utils import unified_strdate
# TODO Remove - Reason: Outdated Site
class BetIE(MTVServicesInfoExtractor):
_VALID_URL = r'https?://(?:www\.)?bet\.com/(?:[^/]+/)+(?P<id>.+?)\.html'
_TESTS = [
{
'url': 'http://www.bet.com/news/politics/2014/12/08/in-bet-exclusive-obama-talks-race-and-racism.html',
'info_dict': {
'id': '07e96bd3-8850-3051-b856-271b457f0ab8',
'display_id': 'in-bet-exclusive-obama-talks-race-and-racism',
'ext': 'flv',
'title': 'A Conversation With President Obama',
'description': 'President Obama urges persistence in confronting racism and bias.',
'duration': 1534,
'upload_date': '20141208',
'thumbnail': r're:(?i)^https?://.*\.jpg$',
'subtitles': {
'en': 'mincount:2',
}
},
'params': {
# rtmp download
'skip_download': True,
},
},
{
'url': 'http://www.bet.com/video/news/national/2014/justice-for-ferguson-a-community-reacts.html',
'info_dict': {
'id': '9f516bf1-7543-39c4-8076-dd441b459ba9',
'display_id': 'justice-for-ferguson-a-community-reacts',
'ext': 'flv',
'title': 'Justice for Ferguson: A Community Reacts',
'description': 'A BET News special.',
'duration': 1696,
'upload_date': '20141125',
'thumbnail': r're:(?i)^https?://.*\.jpg$',
'subtitles': {
'en': 'mincount:2',
}
},
'params': {
# rtmp download
'skip_download': True,
},
}
]
_FEED_URL = "http://feeds.mtvnservices.com/od/feed/bet-mrss-player"
def _get_feed_query(self, uri):
return {
'uuid': uri,
}
def _extract_mgid(self, webpage):
return self._search_regex(r'data-uri="([^"]+)', webpage, 'mgid')
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
mgid = self._extract_mgid(webpage)
videos_info = self._get_videos_info(mgid)
info_dict = videos_info['entries'][0]
upload_date = unified_strdate(self._html_search_meta('date', webpage))
description = self._html_search_meta('description', webpage)
info_dict.update({
'display_id': display_id,
'description': description,
'upload_date': upload_date,
})
return info_dict
yt_dlp/extractor/bfi.py
+34
View File
@@ -0,0 +1,34 @@
import re
from .common import InfoExtractor
from ..utils import extract_attributes
class BFIPlayerIE(InfoExtractor):
IE_NAME = 'bfi:player'
_VALID_URL = r'https?://player\.bfi\.org\.uk/[^/]+/film/watch-(?P<id>[\w-]+)-online'
_TEST = {
'url': 'https://player.bfi.org.uk/free/film/watch-computer-doctor-1974-online',
'md5': 'e8783ebd8e061ec4bc6e9501ed547de8',
'info_dict': {
'id': 'htNnhlZjE60C9VySkQEIBtU-cNV1Xx63',
'ext': 'mp4',
'title': 'Computer Doctor',
'description': 'md5:fb6c240d40c4dbe40428bdd62f78203b',
},
'skip': 'BFI Player films cannot be played outside of the UK',
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
entries = []
for player_el in re.findall(r'(?s)<[^>]+class="player"[^>]*>', webpage):
player_attr = extract_attributes(player_el)
ooyala_id = player_attr.get('data-video-id')
if not ooyala_id:
continue
entries.append(self.url_result(
'ooyala:' + ooyala_id, 'Ooyala',
ooyala_id, player_attr.get('data-label')))
return self.playlist_result(entries)
yt_dlp/extractor/bfmtv.py
+117
View File
@@ -0,0 +1,117 @@
import re
from .common import InfoExtractor
from ..utils import extract_attributes
class BFMTVBaseIE(InfoExtractor):
_VALID_URL_BASE = r'https?://(?:www\.|rmc\.)?bfmtv\.com/'
_VALID_URL_TMPL = _VALID_URL_BASE + r'(?:[^/]+/)*[^/?&#]+_%s[A-Z]-(?P<id>\d{12})\.html'
_VIDEO_BLOCK_REGEX = r'(<div[^>]+class="video_block"[^>]*>)'
BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/%s/%s_default/index.html?videoId=%s'
def _brightcove_url_result(self, video_id, video_block):
account_id = video_block.get('accountid') or '876450612001'
player_id = video_block.get('playerid') or 'I2qBTln4u'
return self.url_result(
self.BRIGHTCOVE_URL_TEMPLATE % (account_id, player_id, video_id),
'BrightcoveNew', video_id)
class BFMTVIE(BFMTVBaseIE):
IE_NAME = 'bfmtv'
_VALID_URL = BFMTVBaseIE._VALID_URL_TMPL % 'V'
_TESTS = [{
'url': 'https://www.bfmtv.com/politique/emmanuel-macron-l-islam-est-une-religion-qui-vit-une-crise-aujourd-hui-partout-dans-le-monde_VN-202010020146.html',
'info_dict': {
'id': '6196747868001',
'ext': 'mp4',
'title': 'Emmanuel Macron: "L\'Islam est une religion qui vit une crise aujourd’hui, partout dans le monde"',
'description': 'Le Président s\'exprime sur la question du séparatisme depuis les Mureaux, dans les Yvelines.',
'uploader_id': '876450610001',
'upload_date': '20201002',
'timestamp': 1601629620,
'duration': 44.757,
'tags': ['bfmactu', 'politique'],
'thumbnail': 'https://cf-images.eu-west-1.prod.boltdns.net/v1/static/876450610001/5041f4c1-bc48-4af8-a256-1b8300ad8ef0/cf2f9114-e8e2-4494-82b4-ab794ea4bc7d/1920x1080/match/image.jpg',
},
}]
def _real_extract(self, url):
bfmtv_id = self._match_id(url)
webpage = self._download_webpage(url, bfmtv_id)
video_block = extract_attributes(self._search_regex(
self._VIDEO_BLOCK_REGEX, webpage, 'video block'))
return self._brightcove_url_result(video_block['videoid'], video_block)
class BFMTVLiveIE(BFMTVIE): # XXX: Do not subclass from concrete IE
IE_NAME = 'bfmtv:live'
_VALID_URL = BFMTVBaseIE._VALID_URL_BASE + '(?P<id>(?:[^/]+/)?en-direct)'
_TESTS = [{
'url': 'https://www.bfmtv.com/en-direct/',
'info_dict': {
'id': '5615950982001',
'ext': 'mp4',
'title': r're:^le direct BFMTV WEB \d{4}-\d{2}-\d{2} \d{2}:\d{2}$',
'uploader_id': '876450610001',
'upload_date': '20171018',
'timestamp': 1508329950,
},
'params': {
'skip_download': True,
},
}, {
'url': 'https://www.bfmtv.com/economie/en-direct/',
'only_matching': True,
}]
class BFMTVArticleIE(BFMTVBaseIE):
IE_NAME = 'bfmtv:article'
_VALID_URL = BFMTVBaseIE._VALID_URL_TMPL % 'A'
_TESTS = [{
'url': 'https://www.bfmtv.com/sante/covid-19-un-responsable-de-l-institut-pasteur-se-demande-quand-la-france-va-se-reconfiner_AV-202101060198.html',
'info_dict': {
'id': '202101060198',
'title': 'Covid-19: un responsable de l\'Institut Pasteur se demande "quand la France va se reconfiner"',
'description': 'md5:947974089c303d3ac6196670ae262843',
},
'playlist_count': 2,
}, {
'url': 'https://www.bfmtv.com/international/pour-bolsonaro-le-bresil-est-en-faillite-mais-il-ne-peut-rien-faire_AD-202101060232.html',
'only_matching': True,
}, {
'url': 'https://www.bfmtv.com/sante/covid-19-oui-le-vaccin-de-pfizer-distribue-en-france-a-bien-ete-teste-sur-des-personnes-agees_AN-202101060275.html',
'only_matching': True,
}, {
'url': 'https://rmc.bfmtv.com/actualites/societe/transports/ce-n-est-plus-tout-rentable-le-bioethanol-e85-depasse-1eu-le-litre-des-automobilistes-regrettent_AV-202301100268.html',
'info_dict': {
'id': '6318445464112',
'ext': 'mp4',
'title': 'Le plein de bioéthanol fait de plus en plus mal à la pompe',
'description': None,
'uploader_id': '876630703001',
'upload_date': '20230110',
'timestamp': 1673341692,
'duration': 109.269,
'tags': ['rmc', 'show', 'apolline de malherbe', 'info', 'talk', 'matinale', 'radio'],
'thumbnail': 'https://cf-images.eu-west-1.prod.boltdns.net/v1/static/876630703001/5bef74b8-9d5e-4480-a21f-60c2e2480c46/96c88b74-f9db-45e1-8040-e199c5da216c/1920x1080/match/image.jpg'
}
}]
def _real_extract(self, url):
bfmtv_id = self._match_id(url)
webpage = self._download_webpage(url, bfmtv_id)
entries = []
for video_block_el in re.findall(self._VIDEO_BLOCK_REGEX, webpage):
video_block = extract_attributes(video_block_el)
video_id = video_block.get('videoid')
if not video_id:
continue
entries.append(self._brightcove_url_result(video_id, video_block))
return self.playlist_result(
entries, bfmtv_id, self._og_search_title(webpage, fatal=False),
self._html_search_meta(['og:description', 'description'], webpage))
yt_dlp/extractor/bibeltv.py
+27
View File
@@ -0,0 +1,27 @@
from .common import InfoExtractor
class BibelTVIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?bibeltv\.de/mediathek/videos/(?:crn/)?(?P<id>\d+)'
_TESTS = [{
'url': 'https://www.bibeltv.de/mediathek/videos/329703-sprachkurs-in-malaiisch',
'md5': '252f908192d611de038b8504b08bf97f',
'info_dict': {
'id': 'ref:329703',
'ext': 'mp4',
'title': 'Sprachkurs in Malaiisch',
'description': 'md5:3e9f197d29ee164714e67351cf737dfe',
'timestamp': 1608316701,
'uploader_id': '5840105145001',
'upload_date': '20201218',
}
}, {
'url': 'https://www.bibeltv.de/mediathek/videos/crn/326374',
'only_matching': True,
}]
BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/5840105145001/default_default/index.html?videoId=ref:%s'
def _real_extract(self, url):
crn_id = self._match_id(url)
return self.url_result(
self.BRIGHTCOVE_URL_TEMPLATE % crn_id, 'BrightcoveNew')
yt_dlp/extractor/bigflix.py
+73
View File
@@ -0,0 +1,73 @@
import re
from .common import InfoExtractor
from ..compat import (
compat_b64decode,
compat_urllib_parse_unquote,
)
class BigflixIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?bigflix\.com/.+/(?P<id>[0-9]+)'
_TESTS = [{
# 2 formats
'url': 'http://www.bigflix.com/Tamil-movies/Drama-movies/Madarasapatinam/16070',
'info_dict': {
'id': '16070',
'ext': 'mp4',
'title': 'Madarasapatinam',
'description': 'md5:9f0470b26a4ba8e824c823b5d95c2f6b',
'formats': 'mincount:2',
},
'params': {
'skip_download': True,
}
}, {
# multiple formats
'url': 'http://www.bigflix.com/Malayalam-movies/Drama-movies/Indian-Rupee/15967',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
title = self._html_search_regex(
r'<div[^>]+class=["\']pagetitle["\'][^>]*>(.+?)</div>',
webpage, 'title')
def decode_url(quoted_b64_url):
return compat_b64decode(compat_urllib_parse_unquote(
quoted_b64_url)).decode('utf-8')
formats = []
for height, encoded_url in re.findall(
r'ContentURL_(\d{3,4})[pP][^=]+=([^&]+)', webpage):
video_url = decode_url(encoded_url)
f = {
'url': video_url,
'format_id': '%sp' % height,
'height': int(height),
}
if video_url.startswith('rtmp'):
f['ext'] = 'flv'
formats.append(f)
file_url = self._search_regex(
r'file=([^&]+)', webpage, 'video url', default=None)
if file_url:
video_url = decode_url(file_url)
if all(f['url'] != video_url for f in formats):
formats.append({
'url': decode_url(file_url),
})
description = self._html_search_meta('description', webpage)
return {
'id': video_id,
'title': title,
'description': description,
'formats': formats
}
yt_dlp/extractor/bigo.py
+56
View File
@@ -0,0 +1,56 @@
from .common import InfoExtractor
from ..utils import ExtractorError, urlencode_postdata
class BigoIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?bigo\.tv/(?:[a-z]{2,}/)?(?P<id>[^/]+)'
_TESTS = [{
'url': 'https://www.bigo.tv/ja/221338632',
'info_dict': {
'id': '6576287577575737440',
'title': '土よ〜💁‍♂️ 休憩室/REST room',
'thumbnail': r're:https?://.+',
'uploader': '✨Shin💫',
'uploader_id': '221338632',
'is_live': True,
},
'skip': 'livestream',
}, {
'url': 'https://www.bigo.tv/th/Tarlerm1304',
'only_matching': True,
}, {
'url': 'https://bigo.tv/115976881',
'only_matching': True,
}]
def _real_extract(self, url):
user_id = self._match_id(url)
info_raw = self._download_json(
'https://ta.bigo.tv/official_website/studio/getInternalStudioInfo',
user_id, data=urlencode_postdata({'siteId': user_id}))
if not isinstance(info_raw, dict):
raise ExtractorError('Received invalid JSON data')
if info_raw.get('code'):
raise ExtractorError(
'Bigo says: %s (code %s)' % (info_raw.get('msg'), info_raw.get('code')), expected=True)
info = info_raw.get('data') or {}
if not info.get('alive'):
raise ExtractorError('This user is offline.', expected=True)
formats, subs = self._extract_m3u8_formats_and_subtitles(
info.get('hls_src'), user_id, 'mp4', 'm3u8')
return {
'id': info.get('roomId') or user_id,
'title': info.get('roomTopic') or info.get('nick_name') or user_id,
'formats': formats,
'subtitles': subs,
'thumbnail': info.get('snapshot'),
'uploader': info.get('nick_name'),
'uploader_id': user_id,
'is_live': True,
}
yt_dlp/extractor/bild.py
+37
View File
@@ -0,0 +1,37 @@
from .common import InfoExtractor
from ..utils import (
int_or_none,
unescapeHTML,
)
class BildIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?bild\.de/(?:[^/]+/)+(?P<display_id>[^/]+)-(?P<id>\d+)(?:,auto=true)?\.bild\.html'
IE_DESC = 'Bild.de'
_TEST = {
'url': 'http://www.bild.de/video/clip/apple-ipad-air/das-koennen-die-neuen-ipads-38184146.bild.html',
'md5': 'dd495cbd99f2413502a1713a1156ac8a',
'info_dict': {
'id': '38184146',
'ext': 'mp4',
'title': 'Das können die neuen iPads',
'description': 'md5:a4058c4fa2a804ab59c00d7244bbf62f',
'thumbnail': r're:^https?://.*\.jpg$',
'duration': 196,
}
}
def _real_extract(self, url):
video_id = self._match_id(url)
video_data = self._download_json(
url.split('.bild.html')[0] + ',view=json.bild.html', video_id)
return {
'id': video_id,
'title': unescapeHTML(video_data['title']).strip(),
'description': unescapeHTML(video_data.get('description')),
'url': video_data['clipList'][0]['srces'][0]['src'],
'thumbnail': video_data.get('poster'),
'duration': int_or_none(video_data.get('durationSec')),
}
yt_dlp/extractor/bilibili.py
+1233
View File
File diff suppressed because it is too large Load Diff
yt_dlp/extractor/biobiochiletv.py
+83
View File
@@ -0,0 +1,83 @@
from .common import InfoExtractor
from ..utils import (
ExtractorError,
remove_end,
)
class BioBioChileTVIE(InfoExtractor):
_VALID_URL = r'https?://(?:tv|www)\.biobiochile\.cl/(?:notas|noticias)/(?:[^/]+/)+(?P<id>[^/]+)\.shtml'
_TESTS = [{
'url': 'http://tv.biobiochile.cl/notas/2015/10/21/sobre-camaras-y-camarillas-parlamentarias.shtml',
'md5': '26f51f03cf580265defefb4518faec09',
'info_dict': {
'id': 'sobre-camaras-y-camarillas-parlamentarias',
'ext': 'mp4',
'title': 'Sobre Cámaras y camarillas parlamentarias',
'thumbnail': r're:^https?://.*\.jpg$',
'uploader': 'Fernando Atria',
},
'skip': 'URL expired and redirected to http://www.biobiochile.cl/portada/bbtv/index.html',
}, {
# different uploader layout
'url': 'http://tv.biobiochile.cl/notas/2016/03/18/natalia-valdebenito-repasa-a-diputado-hasbun-paso-a-la-categoria-de-hablar-brutalidades.shtml',
'md5': 'edc2e6b58974c46d5b047dea3c539ff3',
'info_dict': {
'id': 'natalia-valdebenito-repasa-a-diputado-hasbun-paso-a-la-categoria-de-hablar-brutalidades',
'ext': 'mp4',
'title': 'Natalia Valdebenito repasa a diputado Hasbún: Pasó a la categoría de hablar brutalidades',
'thumbnail': r're:^https?://.*\.jpg$',
'uploader': 'Piangella Obrador',
},
'params': {
'skip_download': True,
},
'skip': 'URL expired and redirected to http://www.biobiochile.cl/portada/bbtv/index.html',
}, {
'url': 'http://www.biobiochile.cl/noticias/bbtv/comentarios-bio-bio/2016/07/08/edecanes-del-congreso-figuras-decorativas-que-le-cuestan-muy-caro-a-los-chilenos.shtml',
'info_dict': {
'id': 'b4xd0LK3SK',
'ext': 'mp4',
# TODO: fix url_transparent information overriding
# 'uploader': 'Juan Pablo Echenique',
'title': 'Comentario Oscar Cáceres',
},
'params': {
# empty m3u8 manifest
'skip_download': True,
},
}, {
'url': 'http://tv.biobiochile.cl/notas/2015/10/22/ninos-transexuales-de-quien-es-la-decision.shtml',
'only_matching': True,
}, {
'url': 'http://tv.biobiochile.cl/notas/2015/10/21/exclusivo-hector-pinto-formador-de-chupete-revela-version-del-ex-delantero-albo.shtml',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
rudo_url = self._search_regex(
r'<iframe[^>]+src=(?P<q1>[\'"])(?P<url>(?:https?:)?//rudo\.video/vod/[0-9a-zA-Z]+)(?P=q1)',
webpage, 'embed URL', None, group='url')
if not rudo_url:
raise ExtractorError('No videos found')
title = remove_end(self._og_search_title(webpage), ' - BioBioChile TV')
thumbnail = self._og_search_thumbnail(webpage)
uploader = self._html_search_regex(
r'<a[^>]+href=["\'](?:https?://(?:busca|www)\.biobiochile\.cl)?/(?:lista/)?(?:author|autor)[^>]+>(.+?)</a>',
webpage, 'uploader', fatal=False)
return {
'_type': 'url_transparent',
'url': rudo_url,
'id': video_id,
'title': title,
'thumbnail': thumbnail,
'uploader': uploader,
}
yt_dlp/extractor/biqle.py
+110
View File
@@ -0,0 +1,110 @@
from .common import InfoExtractor
from .vk import VKIE
from ..compat import compat_b64decode
from ..utils import (
int_or_none,
js_to_json,
traverse_obj,
unified_timestamp,
)
class BIQLEIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?biqle\.(?:com|org|ru)/watch/(?P<id>-?\d+_\d+)'
_TESTS = [{
'url': 'https://biqle.ru/watch/-2000421746_85421746',
'md5': 'ae6ef4f04d19ac84e4658046d02c151c',
'info_dict': {
'id': '-2000421746_85421746',
'ext': 'mp4',
'title': 'Forsaken By Hope Studio Clip',
'description': 'Forsaken By Hope Studio Clip — Смотреть онлайн',
'upload_date': '19700101',
'thumbnail': r're:https://[^/]+/impf/7vN3ACwSTgChP96OdOfzFjUCzFR6ZglDQgWsIw/KPaACiVJJxM\.jpg\?size=800x450&quality=96&keep_aspect_ratio=1&background=000000&sign=b48ea459c4d33dbcba5e26d63574b1cb&type=video_thumb',
'timestamp': 0,
},
}, {
'url': 'http://biqle.org/watch/-44781847_168547604',
'md5': '7f24e72af1db0edf7c1aaba513174f97',
'info_dict': {
'id': '-44781847_168547604',
'ext': 'mp4',
'title': 'Ребенок в шоке от автоматической мойки',
'description': 'Ребенок в шоке от автоматической мойки — Смотреть онлайн',
'timestamp': 1396633454,
'upload_date': '20140404',
'thumbnail': r're:https://[^/]+/c535507/u190034692/video/l_b84df002\.jpg',
},
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
title = self._html_search_meta('name', webpage, 'Title', fatal=False)
timestamp = unified_timestamp(self._html_search_meta('uploadDate', webpage, 'Upload Date', default=None))
description = self._html_search_meta('description', webpage, 'Description', default=None)
global_embed_url = self._search_regex(
r'<script[^<]+?window.globEmbedUrl\s*=\s*\'((?:https?:)?//(?:daxab\.com|dxb\.to|[^/]+/player)/[^\']+)\'',
webpage, 'global Embed url')
hash = self._search_regex(
r'<script id="data-embed-video[^<]+?hash: "([^"]+)"[^<]*</script>', webpage, 'Hash')
embed_url = global_embed_url + hash
if VKIE.suitable(embed_url):
return self.url_result(embed_url, VKIE.ie_key(), video_id)
embed_page = self._download_webpage(
embed_url, video_id, 'Downloading embed webpage', headers={'Referer': url})
glob_params = self._parse_json(self._search_regex(
r'<script id="globParams">[^<]*window.globParams = ([^;]+);[^<]+</script>',
embed_page, 'Global Parameters'), video_id, transform_source=js_to_json)
host_name = compat_b64decode(glob_params['server'][::-1]).decode()
item = self._download_json(
f'https://{host_name}/method/video.get/{video_id}', video_id,
headers={'Referer': url}, query={
'token': glob_params['video']['access_token'],
'videos': video_id,
'ckey': glob_params['c_key'],
'credentials': glob_params['video']['credentials'],
})['response']['items'][0]
formats = []
for f_id, f_url in item.get('files', {}).items():
if f_id == 'external':
return self.url_result(f_url)
ext, height = f_id.split('_')
height_extra_key = traverse_obj(glob_params, ('video', 'partial', 'quality', height))
if height_extra_key:
formats.append({
'format_id': f'{height}p',
'url': f'https://{host_name}/{f_url[8:]}&videos={video_id}&extra_key={height_extra_key}',
'height': int_or_none(height),
'ext': ext,
})
thumbnails = []
for k, v in item.items():
if k.startswith('photo_') and v:
width = k.replace('photo_', '')
thumbnails.append({
'id': width,
'url': v,
'width': int_or_none(width),
})
return {
'id': video_id,
'title': title,
'formats': formats,
'comment_count': int_or_none(item.get('comments')),
'description': description,
'duration': int_or_none(item.get('duration')),
'thumbnails': thumbnails,
'timestamp': timestamp,
'view_count': int_or_none(item.get('views')),
}
yt_dlp/extractor/bitchute.py
+233
View File
@@ -0,0 +1,233 @@
import functools
import re
from .common import InfoExtractor
from ..utils import (
ExtractorError,
HEADRequest,
OnDemandPagedList,
clean_html,
get_element_by_class,
get_element_by_id,
get_elements_html_by_class,
int_or_none,
orderedSet,
parse_count,
parse_duration,
traverse_obj,
unified_strdate,
urlencode_postdata,
)
class BitChuteIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?bitchute\.com/(?:video|embed|torrent/[^/]+)/(?P<id>[^/?#&]+)'
_EMBED_REGEX = [rf'<(?:script|iframe)[^>]+\bsrc=(["\'])(?P<url>{_VALID_URL})']
_TESTS = [{
'url': 'https://www.bitchute.com/video/UGlrF9o9b-Q/',
'md5': '7e427d7ed7af5a75b5855705ec750e2b',
'info_dict': {
'id': 'UGlrF9o9b-Q',
'ext': 'mp4',
'title': 'This is the first video on #BitChute !',
'description': 'md5:a0337e7b1fe39e32336974af8173a034',
'thumbnail': r're:^https?://.*\.jpg$',
'uploader': 'BitChute',
'upload_date': '20170103',
},
}, {
# video not downloadable in browser, but we can recover it
'url': 'https://www.bitchute.com/video/2s6B3nZjAk7R/',
'md5': '05c12397d5354bf24494885b08d24ed1',
'info_dict': {
'id': '2s6B3nZjAk7R',
'ext': 'mp4',
'filesize': 71537926,
'title': 'STYXHEXENHAMMER666 - Election Fraud, Clinton 2020, EU Armies, and Gun Control',
'description': 'md5:228ee93bd840a24938f536aeac9cf749',
'thumbnail': r're:^https?://.*\.jpg$',
'uploader': 'BitChute',
'upload_date': '20181113',
},
'params': {'check_formats': None},
}, {
# restricted video
'url': 'https://www.bitchute.com/video/WEnQU7XGcTdl/',
'info_dict': {
'id': 'WEnQU7XGcTdl',
'ext': 'mp4',
'title': 'Impartial Truth - Ein Letzter Appell an die Vernunft',
},
'params': {'skip_download': True},
'skip': 'Georestricted in DE',
}, {
'url': 'https://www.bitchute.com/embed/lbb5G1hjPhw/',
'only_matching': True,
}, {
'url': 'https://www.bitchute.com/torrent/Zee5BE49045h/szoMrox2JEI.webtorrent',
'only_matching': True,
}]
_GEO_BYPASS = False
_HEADERS = {
'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_14_0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.57 Safari/537.36',
'Referer': 'https://www.bitchute.com/',
}
def _check_format(self, video_url, video_id):
urls = orderedSet(
re.sub(r'(^https?://)(seed\d+)(?=\.bitchute\.com)', fr'\g<1>{host}', video_url)
for host in (r'\g<2>', 'seed150', 'seed151', 'seed152', 'seed153'))
for url in urls:
try:
response = self._request_webpage(
HEADRequest(url), video_id=video_id, note=f'Checking {url}', headers=self._HEADERS)
except ExtractorError as e:
self.to_screen(f'{video_id}: URL is invalid, skipping: {e.cause}')
continue
return {
'url': url,
'filesize': int_or_none(response.headers.get('Content-Length'))
}
def _raise_if_restricted(self, webpage):
page_title = clean_html(get_element_by_class('page-title', webpage)) or ''
if re.fullmatch(r'(?:Channel|Video) Restricted', page_title):
reason = clean_html(get_element_by_id('page-detail', webpage)) or page_title
self.raise_geo_restricted(reason)
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(
f'https://www.bitchute.com/video/{video_id}', video_id, headers=self._HEADERS)
self._raise_if_restricted(webpage)
publish_date = clean_html(get_element_by_class('video-publish-date', webpage))
entries = self._parse_html5_media_entries(url, webpage, video_id)
formats = []
for format_ in traverse_obj(entries, (0, 'formats', ...)):
if self.get_param('check_formats') is not False:
format_.update(self._check_format(format_.pop('url'), video_id) or {})
if 'url' not in format_:
continue
formats.append(format_)
if not formats:
self.raise_no_formats(
'Video is unavailable. Please make sure this video is playable in the browser '
'before reporting this issue.', expected=True, video_id=video_id)
return {
'id': video_id,
'title': self._html_extract_title(webpage) or self._og_search_title(webpage),
'description': self._og_search_description(webpage, default=None),
'thumbnail': self._og_search_thumbnail(webpage),
'uploader': clean_html(get_element_by_class('owner', webpage)),
'upload_date': unified_strdate(self._search_regex(
r'at \d+:\d+ UTC on (.+?)\.', publish_date, 'upload date', fatal=False)),
'formats': formats,
}
class BitChuteChannelIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?bitchute\.com/(?P<type>channel|playlist)/(?P<id>[^/?#&]+)'
_TESTS = [{
'url': 'https://www.bitchute.com/channel/bitchute/',
'info_dict': {
'id': 'bitchute',
'title': 'BitChute',
'description': 'md5:5329fb3866125afa9446835594a9b138',
},
'playlist': [
{
'md5': '7e427d7ed7af5a75b5855705ec750e2b',
'info_dict': {
'id': 'UGlrF9o9b-Q',
'ext': 'mp4',
'filesize': None,
'title': 'This is the first video on #BitChute !',
'description': 'md5:a0337e7b1fe39e32336974af8173a034',
'thumbnail': r're:^https?://.*\.jpg$',
'uploader': 'BitChute',
'upload_date': '20170103',
'duration': 16,
'view_count': int,
},
}
],
'params': {
'skip_download': True,
'playlist_items': '-1',
},
}, {
'url': 'https://www.bitchute.com/playlist/wV9Imujxasw9/',
'playlist_mincount': 20,
'info_dict': {
'id': 'wV9Imujxasw9',
'title': 'Bruce MacDonald and "The Light of Darkness"',
'description': 'md5:04913227d2714af1d36d804aa2ab6b1e',
}
}]
_TOKEN = 'zyG6tQcGPE5swyAEFLqKUwMuMMuF6IO2DZ6ZDQjGfsL0e4dcTLwqkTTul05Jdve7'
PAGE_SIZE = 25
HTML_CLASS_NAMES = {
'channel': {
'container': 'channel-videos-container',
'title': 'channel-videos-title',
'description': 'channel-videos-text',
},
'playlist': {
'container': 'playlist-video',
'title': 'title',
'description': 'description',
}
}
@staticmethod
def _make_url(playlist_id, playlist_type):
return f'https://www.bitchute.com/{playlist_type}/{playlist_id}/'
def _fetch_page(self, playlist_id, playlist_type, page_num):
playlist_url = self._make_url(playlist_id, playlist_type)
data = self._download_json(
f'{playlist_url}extend/', playlist_id, f'Downloading page {page_num}',
data=urlencode_postdata({
'csrfmiddlewaretoken': self._TOKEN,
'name': '',
'offset': page_num * self.PAGE_SIZE,
}), headers={
'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8',
'Referer': playlist_url,
'X-Requested-With': 'XMLHttpRequest',
'Cookie': f'csrftoken={self._TOKEN}',
})
if not data.get('success'):
return
classes = self.HTML_CLASS_NAMES[playlist_type]
for video_html in get_elements_html_by_class(classes['container'], data.get('html')):
video_id = self._search_regex(
r'<a\s[^>]*\bhref=["\']/video/([^"\'/]+)', video_html, 'video id', default=None)
if not video_id:
continue
yield self.url_result(
f'https://www.bitchute.com/video/{video_id}', BitChuteIE, video_id, url_transparent=True,
title=clean_html(get_element_by_class(classes['title'], video_html)),
description=clean_html(get_element_by_class(classes['description'], video_html)),
duration=parse_duration(get_element_by_class('video-duration', video_html)),
view_count=parse_count(clean_html(get_element_by_class('video-views', video_html))))
def _real_extract(self, url):
playlist_type, playlist_id = self._match_valid_url(url).group('type', 'id')
webpage = self._download_webpage(self._make_url(playlist_id, playlist_type), playlist_id)
page_func = functools.partial(self._fetch_page, playlist_id, playlist_type)
return self.playlist_result(
OnDemandPagedList(page_func, self.PAGE_SIZE), playlist_id,
title=self._html_extract_title(webpage, default=None),
description=self._html_search_meta(
('description', 'og:description', 'twitter:description'), webpage, default=None),
playlist_count=int_or_none(self._html_search_regex(
r'<span>(\d+)\s+videos?</span>', webpage, 'playlist count', default=None)))
yt_dlp/extractor/bitwave.py
+58
View File
@@ -0,0 +1,58 @@
from .common import InfoExtractor
class BitwaveReplayIE(InfoExtractor):
IE_NAME = 'bitwave:replay'
_VALID_URL = r'https?://(?:www\.)?bitwave\.tv/(?P<user>\w+)/replay/(?P<id>\w+)/?$'
_TEST = {
'url': 'https://bitwave.tv/RhythmicCarnage/replay/z4P6eq5L7WDrM85UCrVr',
'only_matching': True
}
def _real_extract(self, url):
replay_id = self._match_id(url)
replay = self._download_json(
'https://api.bitwave.tv/v1/replays/' + replay_id,
replay_id
)
return {
'id': replay_id,
'title': replay['data']['title'],
'uploader': replay['data']['name'],
'uploader_id': replay['data']['name'],
'url': replay['data']['url'],
'thumbnails': [
{'url': x} for x in replay['data']['thumbnails']
],
}
class BitwaveStreamIE(InfoExtractor):
IE_NAME = 'bitwave:stream'
_VALID_URL = r'https?://(?:www\.)?bitwave\.tv/(?P<id>\w+)/?$'
_TEST = {
'url': 'https://bitwave.tv/doomtube',
'only_matching': True
}
def _real_extract(self, url):
username = self._match_id(url)
channel = self._download_json(
'https://api.bitwave.tv/v1/channels/' + username,
username)
formats = self._extract_m3u8_formats(
channel['data']['url'], username,
'mp4')
return {
'id': username,
'title': channel['data']['title'],
'uploader': username,
'uploader_id': username,
'formats': formats,
'thumbnail': channel['data']['thumbnail'],
'is_live': True,
'view_count': channel['data']['viewCount']
}
yt_dlp/extractor/blackboardcollaborate.py
+63
View File
@@ -0,0 +1,63 @@
from .common import InfoExtractor
from ..utils import parse_iso8601
class BlackboardCollaborateIE(InfoExtractor):
_VALID_URL = r'''(?x)
https?://
(?P<region>[a-z-]+)\.bbcollab\.com/
(?:
collab/ui/session/playback/load|
recording
)/
(?P<id>[^/]+)'''
_TESTS = [
{
'url': 'https://us-lti.bbcollab.com/collab/ui/session/playback/load/0a633b6a88824deb8c918f470b22b256',
'md5': 'bb7a055682ee4f25fdb5838cdf014541',
'info_dict': {
'id': '0a633b6a88824deb8c918f470b22b256',
'title': 'HESI A2 Information Session - Thursday, May 6, 2021 - recording_1',
'ext': 'mp4',
'duration': 1896000,
'timestamp': 1620331399,
'upload_date': '20210506',
},
},
{
'url': 'https://us.bbcollab.com/collab/ui/session/playback/load/76761522adfe4345a0dee6794bbcabda',
'only_matching': True,
},
{
'url': 'https://ca.bbcollab.com/collab/ui/session/playback/load/b6399dcb44df4f21b29ebe581e22479d',
'only_matching': True,
},
{
'url': 'https://eu.bbcollab.com/recording/51ed7b50810c4444a106e48cefb3e6b5',
'only_matching': True,
},
{
'url': 'https://au.bbcollab.com/collab/ui/session/playback/load/2bccf7165d7c419ab87afc1ec3f3bb15',
'only_matching': True,
},
]
def _real_extract(self, url):
mobj = self._match_valid_url(url)
region = mobj.group('region')
video_id = mobj.group('id')
info = self._download_json(
'https://{}.bbcollab.com/collab/api/csa/recordings/{}/data'.format(region, video_id), video_id)
duration = info.get('duration')
title = info['name']
upload_date = info.get('created')
streams = info['streams']
formats = [{'format_id': k, 'url': url} for k, url in streams.items()]
return {
'duration': duration,
'formats': formats,
'id': video_id,
'timestamp': parse_iso8601(upload_date),
'title': title,
}
yt_dlp/extractor/bleacherreport.py
+109
View File
@@ -0,0 +1,109 @@
from .common import InfoExtractor
from .amp import AMPIE
from ..utils import (
ExtractorError,
int_or_none,
parse_iso8601,
)
class BleacherReportIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?bleacherreport\.com/articles/(?P<id>\d+)'
_TESTS = [{
'url': 'http://bleacherreport.com/articles/2496438-fsu-stat-projections-is-jalen-ramsey-best-defensive-player-in-college-football',
'md5': 'a3ffc3dc73afdbc2010f02d98f990f20',
'info_dict': {
'id': '2496438',
'ext': 'mp4',
'title': 'FSU Stat Projections: Is Jalen Ramsey Best Defensive Player in College Football?',
'uploader_id': 3992341,
'description': 'CFB, ACC, Florida State',
'timestamp': 1434380212,
'upload_date': '20150615',
'uploader': 'Team Stream Now ',
},
'add_ie': ['Ooyala'],
}, {
'url': 'http://bleacherreport.com/articles/2586817-aussie-golfers-get-fright-of-their-lives-after-being-chased-by-angry-kangaroo',
'md5': '6a5cd403418c7b01719248ca97fb0692',
'info_dict': {
'id': '2586817',
'ext': 'webm',
'title': 'Aussie Golfers Get Fright of Their Lives After Being Chased by Angry Kangaroo',
'timestamp': 1446839961,
'uploader': 'Sean Fay',
'description': 'md5:b1601e2314c4d8eec23b6eafe086a757',
'uploader_id': 6466954,
'upload_date': '20151011',
},
'add_ie': ['Youtube'],
}]
def _real_extract(self, url):
article_id = self._match_id(url)
article_data = self._download_json('http://api.bleacherreport.com/api/v1/articles/%s' % article_id, article_id)['article']
thumbnails = []
primary_photo = article_data.get('primaryPhoto')
if primary_photo:
thumbnails = [{
'url': primary_photo['url'],
'width': primary_photo.get('width'),
'height': primary_photo.get('height'),
}]
info = {
'_type': 'url_transparent',
'id': article_id,
'title': article_data['title'],
'uploader': article_data.get('author', {}).get('name'),
'uploader_id': article_data.get('authorId'),
'timestamp': parse_iso8601(article_data.get('createdAt')),
'thumbnails': thumbnails,
'comment_count': int_or_none(article_data.get('commentsCount')),
'view_count': int_or_none(article_data.get('hitCount')),
}
video = article_data.get('video')
if video:
video_type = video['type']
if video_type in ('cms.bleacherreport.com', 'vid.bleacherreport.com'):
info['url'] = 'http://bleacherreport.com/video_embed?id=%s' % video['id']
elif video_type == 'ooyala.com':
info['url'] = 'ooyala:%s' % video['id']
elif video_type == 'youtube.com':
info['url'] = video['id']
elif video_type == 'vine.co':
info['url'] = 'https://vine.co/v/%s' % video['id']
else:
info['url'] = video_type + video['id']
return info
else:
raise ExtractorError('no video in the article', expected=True)
class BleacherReportCMSIE(AMPIE):
_VALID_URL = r'https?://(?:www\.)?bleacherreport\.com/video_embed\?id=(?P<id>[0-9a-f-]{36}|\d{5})'
_TESTS = [{
'url': 'http://bleacherreport.com/video_embed?id=8fd44c2f-3dc5-4821-9118-2c825a98c0e1&library=video-cms',
'md5': '670b2d73f48549da032861130488c681',
'info_dict': {
'id': '8fd44c2f-3dc5-4821-9118-2c825a98c0e1',
'ext': 'mp4',
'title': 'Cena vs. Rollins Would Expose the Heavyweight Division',
'description': 'md5:984afb4ade2f9c0db35f3267ed88b36e',
'upload_date': '20150723',
'timestamp': 1437679032,
},
'expected_warnings': [
'Unable to download f4m manifest'
]
}]
def _real_extract(self, url):
video_id = self._match_id(url)
info = self._extract_feed_info('http://vid.bleacherreport.com/videos/%s.akamai' % video_id)
info['id'] = video_id
return info
yt_dlp/extractor/blerp.py
+167
View File
@@ -0,0 +1,167 @@
import json
from .common import InfoExtractor
from ..utils import strip_or_none, traverse_obj
class BlerpIE(InfoExtractor):
IE_NAME = 'blerp'
_VALID_URL = r'https?://(?:www\.)?blerp\.com/soundbites/(?P<id>[0-9a-zA-Z]+)'
_TESTS = [{
'url': 'https://blerp.com/soundbites/6320fe8745636cb4dd677a5a',
'info_dict': {
'id': '6320fe8745636cb4dd677a5a',
'title': 'Samsung Galaxy S8 Over the Horizon Ringtone 2016',
'uploader': 'luminousaj',
'uploader_id': '5fb81e51aa66ae000c395478',
'ext': 'mp3',
'tags': ['samsung', 'galaxy', 's8', 'over the horizon', '2016', 'ringtone'],
}
}, {
'url': 'https://blerp.com/soundbites/5bc94ef4796001000498429f',
'info_dict': {
'id': '5bc94ef4796001000498429f',
'title': 'Yee',
'uploader': '179617322678353920',
'uploader_id': '5ba99cf71386730004552c42',
'ext': 'mp3',
'tags': ['YEE', 'YEET', 'wo ha haah catchy tune yee', 'yee']
}
}]
_GRAPHQL_OPERATIONNAME = "webBitePageGetBite"
_GRAPHQL_QUERY = (
'''query webBitePageGetBite($_id: MongoID!) {
web {
biteById(_id: $_id) {
...bitePageFrag
__typename
}
__typename
}
}
fragment bitePageFrag on Bite {
_id
title
userKeywords
keywords
color
visibility
isPremium
owned
price
extraReview
isAudioExists
image {
filename
original {
url
__typename
}
__typename
}
userReactions {
_id
reactions
createdAt
__typename
}
topReactions
totalSaveCount
saved
blerpLibraryType
license
licenseMetaData
playCount
totalShareCount
totalFavoriteCount
totalAddedToBoardCount
userCategory
userAudioQuality
audioCreationState
transcription
userTranscription
description
createdAt
updatedAt
author
listingType
ownerObject {
_id
username
profileImage {
filename
original {
url
__typename
}
__typename
}
__typename
}
transcription
favorited
visibility
isCurated
sourceUrl
audienceRating
strictAudienceRating
ownerId
reportObject {
reportedContentStatus
__typename
}
giphy {
mp4
gif
__typename
}
audio {
filename
original {
url
__typename
}
mp3 {
url
__typename
}
__typename
}
__typename
}
''')
def _real_extract(self, url):
audio_id = self._match_id(url)
data = {
'operationName': self._GRAPHQL_OPERATIONNAME,
'query': self._GRAPHQL_QUERY,
'variables': {
'_id': audio_id
}
}
headers = {
'Content-Type': 'application/json'
}
json_result = self._download_json('https://api.blerp.com/graphql',
audio_id, data=json.dumps(data).encode('utf-8'), headers=headers)
bite_json = json_result['data']['web']['biteById']
info_dict = {
'id': bite_json['_id'],
'url': bite_json['audio']['mp3']['url'],
'title': bite_json['title'],
'uploader': traverse_obj(bite_json, ('ownerObject', 'username'), expected_type=strip_or_none),
'uploader_id': traverse_obj(bite_json, ('ownerObject', '_id'), expected_type=strip_or_none),
'ext': 'mp3',
'tags': list(filter(None, map(strip_or_none, (traverse_obj(bite_json, 'userKeywords', expected_type=list) or []))) or None)
}
return info_dict
yt_dlp/extractor/blogger.py
+45
View File
@@ -0,0 +1,45 @@
from ..utils import (
mimetype2ext,
parse_duration,
parse_qs,
str_or_none,
traverse_obj,
)
from .common import InfoExtractor
class BloggerIE(InfoExtractor):
IE_NAME = 'blogger.com'
_VALID_URL = r'https?://(?:www\.)?blogger\.com/video\.g\?token=(?P<id>.+)'
_EMBED_REGEX = [r'''<iframe[^>]+src=["'](?P<url>(?:https?:)?//(?:www\.)?blogger\.com/video\.g\?token=[^"']+)["']''']
_TESTS = [{
'url': 'https://www.blogger.com/video.g?token=AD6v5dzEe9hfcARr5Hlq1WTkYy6t-fXH3BBahVhGvVHe5szdEUBEloSEDSTA8-b111089KbfWuBvTN7fnbxMtymsHhXAXwVvyzHH4Qch2cfLQdGxKQrrEuFpC1amSl_9GuLWODjPgw',
'md5': 'f1bc19b6ea1b0fd1d81e84ca9ec467ac',
'info_dict': {
'id': 'BLOGGER-video-3c740e3a49197e16-796',
'title': 'BLOGGER-video-3c740e3a49197e16-796',
'ext': 'mp4',
'thumbnail': r're:^https?://.*',
'duration': 76.068,
}
}]
def _real_extract(self, url):
token_id = self._match_id(url)
webpage = self._download_webpage(url, token_id)
data_json = self._search_regex(r'var\s+VIDEO_CONFIG\s*=\s*(\{.*)', webpage, 'JSON data')
data = self._parse_json(data_json.encode('utf-8').decode('unicode_escape'), token_id)
streams = data['streams']
formats = [{
'ext': mimetype2ext(traverse_obj(parse_qs(stream['play_url']), ('mime', 0))),
'url': stream['play_url'],
'format_id': str_or_none(stream.get('format_id')),
} for stream in streams]
return {
'id': data.get('iframe_id', token_id),
'title': data.get('iframe_id', token_id),
'formats': formats,
'thumbnail': data.get('thumbnail'),
'duration': parse_duration(traverse_obj(parse_qs(streams[0]['play_url']), ('dur', 0))),
}
yt_dlp/extractor/bloomberg.py
+77
View File
@@ -0,0 +1,77 @@
import re
from .common import InfoExtractor
class BloombergIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?bloomberg\.com/(?:[^/]+/)*(?P<id>[^/?#]+)'
_TESTS = [{
'url': 'https://www.bloomberg.com/news/videos/2021-09-14/apple-unveils-the-new-iphone-13-stock-doesn-t-move-much-video',
'info_dict': {
'id': 'V8cFcYMxTHaMcEiiYVr39A',
'ext': 'flv',
'title': 'Apple Unveils the New IPhone 13, Stock Doesn\'t Move Much',
},
'params': {
'format': 'best[format_id^=hds]',
},
}, {
# video ID in BPlayer(...)
'url': 'http://www.bloomberg.com/features/2016-hello-world-new-zealand/',
'info_dict': {
'id': '938c7e72-3f25-4ddb-8b85-a9be731baa74',
'ext': 'flv',
'title': 'Meet the Real-Life Tech Wizards of Middle Earth',
'description': 'Hello World, Episode 1: New Zealand’s freaky AI babies, robot exoskeletons, and a virtual you.',
},
'params': {
'format': 'best[format_id^=hds]',
},
}, {
# data-bmmrid=
'url': 'https://www.bloomberg.com/politics/articles/2017-02-08/le-pen-aide-briefed-french-central-banker-on-plan-to-print-money',
'only_matching': True,
}, {
'url': 'http://www.bloomberg.com/news/articles/2015-11-12/five-strange-things-that-have-been-happening-in-financial-markets',
'only_matching': True,
}, {
'url': 'http://www.bloomberg.com/politics/videos/2015-11-25/karl-rove-on-jeb-bush-s-struggles-stopping-trump',
'only_matching': True,
}]
def _real_extract(self, url):
name = self._match_id(url)
webpage = self._download_webpage(url, name)
video_id = self._search_regex(
(r'["\']bmmrId["\']\s*:\s*(["\'])(?P<id>(?:(?!\1).)+)\1',
r'videoId\s*:\s*(["\'])(?P<id>(?:(?!\1).)+)\1',
r'data-bmmrid=(["\'])(?P<id>(?:(?!\1).)+)\1'),
webpage, 'id', group='id', default=None)
if not video_id:
bplayer_data = self._parse_json(self._search_regex(
r'BPlayer\(null,\s*({[^;]+})\);', webpage, 'id'), name)
video_id = bplayer_data['id']
title = re.sub(': Video$', '', self._og_search_title(webpage))
embed_info = self._download_json(
'http://www.bloomberg.com/multimedia/api/embed?id=%s' % video_id, video_id)
formats = []
for stream in embed_info['streams']:
stream_url = stream.get('url')
if not stream_url:
continue
if stream['muxing_format'] == 'TS':
formats.extend(self._extract_m3u8_formats(
stream_url, video_id, 'mp4', m3u8_id='hls', fatal=False))
else:
formats.extend(self._extract_f4m_formats(
stream_url, video_id, f4m_id='hds', fatal=False))
return {
'id': video_id,
'title': title,
'formats': formats,
'description': self._og_search_description(webpage),
'thumbnail': self._og_search_thumbnail(webpage),
}
yt_dlp/extractor/bokecc.py
+53
View File
@@ -0,0 +1,53 @@
from .common import InfoExtractor
from ..compat import compat_parse_qs
from ..utils import ExtractorError
class BokeCCBaseIE(InfoExtractor):
def _extract_bokecc_formats(self, webpage, video_id, format_id=None):
player_params_str = self._html_search_regex(
r'<(?:script|embed)[^>]+src=(?P<q>["\'])(?:https?:)?//p\.bokecc\.com/(?:player|flash/player\.swf)\?(?P<query>.+?)(?P=q)',
webpage, 'player params', group='query')
player_params = compat_parse_qs(player_params_str)
info_xml = self._download_xml(
'http://p.bokecc.com/servlet/playinfo?uid=%s&vid=%s&m=1' % (
player_params['siteid'][0], player_params['vid'][0]), video_id)
formats = [{
'format_id': format_id,
'url': quality.find('./copy').attrib['playurl'],
'quality': int(quality.attrib['value']),
} for quality in info_xml.findall('./video/quality')]
return formats
class BokeCCIE(BokeCCBaseIE):
_IE_DESC = 'CC视频'
_VALID_URL = r'https?://union\.bokecc\.com/playvideo\.bo\?(?P<query>.*)'
_TESTS = [{
'url': 'http://union.bokecc.com/playvideo.bo?vid=E0ABAE9D4F509B189C33DC5901307461&uid=FE644790DE9D154A',
'info_dict': {
'id': 'FE644790DE9D154A_E0ABAE9D4F509B189C33DC5901307461',
'ext': 'flv',
'title': 'BokeCC Video',
},
}]
def _real_extract(self, url):
qs = compat_parse_qs(self._match_valid_url(url).group('query'))
if not qs.get('vid') or not qs.get('uid'):
raise ExtractorError('Invalid URL', expected=True)
video_id = '%s_%s' % (qs['uid'][0], qs['vid'][0])
webpage = self._download_webpage(url, video_id)
return {
'id': video_id,
'title': 'BokeCC Video', # no title provided in the webpage
'formats': self._extract_bokecc_formats(webpage, video_id),
}
yt_dlp/extractor/bongacams.py
+70
View File
@@ -0,0 +1,70 @@
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
int_or_none,
try_get,
urlencode_postdata,
)
class BongaCamsIE(InfoExtractor):
_VALID_URL = r'https?://(?P<host>(?:[^/]+\.)?bongacams\d*\.(?:com|net))/(?P<id>[^/?&#]+)'
_TESTS = [{
'url': 'https://de.bongacams.com/azumi-8',
'only_matching': True,
}, {
'url': 'https://cn.bongacams.com/azumi-8',
'only_matching': True,
}, {
'url': 'https://de.bongacams.net/claireashton',
'info_dict': {
'id': 'claireashton',
'ext': 'mp4',
'title': r're:ClaireAshton \d{4}-\d{2}-\d{2} \d{2}:\d{2}',
'age_limit': 18,
'uploader_id': 'ClaireAshton',
'uploader': 'ClaireAshton',
'like_count': int,
'is_live': True,
},
'params': {
'skip_download': True,
},
}]
def _real_extract(self, url):
mobj = self._match_valid_url(url)
host = mobj.group('host')
channel_id = mobj.group('id')
amf = self._download_json(
'https://%s/tools/amf.php' % host, channel_id,
data=urlencode_postdata((
('method', 'getRoomData'),
('args[]', channel_id),
('args[]', 'false'),
)), headers={'X-Requested-With': 'XMLHttpRequest'})
server_url = amf['localData']['videoServerUrl']
uploader_id = try_get(
amf, lambda x: x['performerData']['username'], compat_str) or channel_id
uploader = try_get(
amf, lambda x: x['performerData']['displayName'], compat_str)
like_count = int_or_none(try_get(
amf, lambda x: x['performerData']['loversCount']))
formats = self._extract_m3u8_formats(
'%s/hls/stream_%s/playlist.m3u8' % (server_url, uploader_id),
channel_id, 'mp4', m3u8_id='hls', live=True)
return {
'id': channel_id,
'title': uploader or uploader_id,
'uploader': uploader,
'uploader_id': uploader_id,
'like_count': like_count,
'age_limit': 18,
'is_live': True,
'formats': formats,
}
yt_dlp/extractor/booyah.py
+86
View File
@@ -0,0 +1,86 @@
from .common import InfoExtractor
from ..utils import int_or_none, str_or_none, traverse_obj
class BooyahBaseIE(InfoExtractor):
_BOOYAH_SESSION_KEY = None
def _real_initialize(self):
BooyahBaseIE._BOOYAH_SESSION_KEY = self._request_webpage(
'https://booyah.live/api/v3/auths/sessions', None, data=b'').getheader('booyah-session-key')
def _get_comments(self, video_id):
comment_json = self._download_json(
f'https://booyah.live/api/v3/playbacks/{video_id}/comments/tops', video_id,
headers={'Booyah-Session-Key': self._BOOYAH_SESSION_KEY}, fatal=False) or {}
return [{
'id': comment.get('comment_id'),
'author': comment.get('from_nickname'),
'author_id': comment.get('from_uid'),
'author_thumbnail': comment.get('from_thumbnail'),
'text': comment.get('content'),
'timestamp': comment.get('create_time'),
'like_count': comment.get('like_cnt'),
} for comment in comment_json.get('comment_list') or ()]
class BooyahClipsIE(BooyahBaseIE):
_VALID_URL = r'https?://booyah.live/clips/(?P<id>\d+)'
_TESTS = [{
'url': 'https://booyah.live/clips/13887261322952306617',
'info_dict': {
'id': '13887261322952306617',
'ext': 'mp4',
'view_count': int,
'duration': 30,
'channel_id': 90565760,
'like_count': int,
'title': 'Cayendo con estilo 😎',
'uploader': '♡LɪꜱGΛ​MER​',
'comment_count': int,
'uploader_id': '90565760',
'thumbnail': 'https://resmambet-a.akamaihd.net/mambet-storage/Clip/90565760/90565760-27204374-fba0-409d-9d7b-63a48b5c0e75.jpg',
'upload_date': '20220617',
'timestamp': 1655490556,
'modified_timestamp': 1655490556,
'modified_date': '20220617',
}
}]
def _real_extract(self, url):
video_id = self._match_id(url)
json_data = self._download_json(
f'https://booyah.live/api/v3/playbacks/{video_id}', video_id,
headers={'Booyah-Session-key': self._BOOYAH_SESSION_KEY})
formats = []
for video_data in json_data['playback']['endpoint_list']:
formats.extend(({
'url': video_data.get('stream_url'),
'ext': 'mp4',
'height': video_data.get('resolution'),
}, {
'url': video_data.get('download_url'),
'ext': 'mp4',
'format_note': 'Watermarked',
'height': video_data.get('resolution'),
'preference': -10,
}))
return {
'id': video_id,
'title': traverse_obj(json_data, ('playback', 'name')),
'thumbnail': traverse_obj(json_data, ('playback', 'thumbnail_url')),
'formats': formats,
'view_count': traverse_obj(json_data, ('playback', 'views')),
'like_count': traverse_obj(json_data, ('playback', 'likes')),
'duration': traverse_obj(json_data, ('playback', 'duration')),
'comment_count': traverse_obj(json_data, ('playback', 'comment_cnt')),
'channel_id': traverse_obj(json_data, ('playback', 'channel_id')),
'uploader': traverse_obj(json_data, ('user', 'nickname')),
'uploader_id': str_or_none(traverse_obj(json_data, ('user', 'uid'))),
'modified_timestamp': int_or_none(traverse_obj(json_data, ('playback', 'update_time_ms')), 1000),
'timestamp': int_or_none(traverse_obj(json_data, ('playback', 'create_time_ms')), 1000),
'__post_extractor': self.extract_comments(video_id, self._get_comments(video_id)),
}
yt_dlp/extractor/bostonglobe.py
+69
View File
@@ -0,0 +1,69 @@
import re
from .common import InfoExtractor
from ..utils import (
extract_attributes,
)
class BostonGlobeIE(InfoExtractor):
_VALID_URL = r'(?i)https?://(?:www\.)?bostonglobe\.com/.*/(?P<id>[^/]+)/\w+(?:\.html)?'
_TESTS = [
{
'url': 'http://www.bostonglobe.com/metro/2017/02/11/tree-finally-succumbs-disease-leaving-hole-neighborhood/h1b4lviqzMTIn9sVy8F3gP/story.html',
'md5': '0a62181079c85c2d2b618c9a738aedaf',
'info_dict': {
'title': 'A tree finally succumbs to disease, leaving a hole in a neighborhood',
'id': '5320421710001',
'ext': 'mp4',
'description': 'It arrived as a sapling when the Back Bay was in its infancy, a spindly American elm tamped down into a square of dirt cut into the brick sidewalk of 1880s Marlborough Street, no higher than the first bay window of the new brownstone behind it.',
'timestamp': 1486877593,
'upload_date': '20170212',
'uploader_id': '245991542',
},
},
{
# Embedded youtube video; we hand it off to the Generic extractor.
'url': 'https://www.bostonglobe.com/lifestyle/names/2017/02/17/does-ben-affleck-play-matt-damon-favorite-version-batman/ruqkc9VxKBYmh5txn1XhSI/story.html',
'md5': '582b40327089d5c0c949b3c54b13c24b',
'info_dict': {
'title': "Who Is Matt Damon's Favorite Batman?",
'id': 'ZW1QCnlA6Qc',
'ext': 'mp4',
'upload_date': '20170217',
'description': 'md5:3b3dccb9375867e0b4d527ed87d307cb',
'uploader': 'The Late Late Show with James Corden',
'uploader_id': 'TheLateLateShow',
},
'expected_warnings': ['404'],
},
]
def _real_extract(self, url):
page_id = self._match_id(url)
webpage = self._download_webpage(url, page_id)
page_title = self._og_search_title(webpage, default=None)
# <video data-brightcove-video-id="5320421710001" data-account="245991542" data-player="SJWAiyYWg" data-embed="default" class="video-js" controls itemscope itemtype="http://schema.org/VideoObject">
entries = []
for video in re.findall(r'(?i)(<video[^>]+>)', webpage):
attrs = extract_attributes(video)
video_id = attrs.get('data-brightcove-video-id')
account_id = attrs.get('data-account')
player_id = attrs.get('data-player')
embed = attrs.get('data-embed')
if video_id and account_id and player_id and embed:
entries.append(
'http://players.brightcove.net/%s/%s_%s/index.html?videoId=%s'
% (account_id, player_id, embed, video_id))
if len(entries) == 0:
return self.url_result(url, 'Generic')
elif len(entries) == 1:
return self.url_result(entries[0], 'BrightcoveNew')
else:
return self.playlist_from_matches(entries, page_id, page_title, ie='BrightcoveNew')
yt_dlp/extractor/box.py
+92
View File
@@ -0,0 +1,92 @@
import json
from .common import InfoExtractor
from ..utils import (
determine_ext,
parse_iso8601,
# try_get,
update_url_query,
)
class BoxIE(InfoExtractor):
_VALID_URL = r'https?://(?:[^.]+\.)?app\.box\.com/s/(?P<shared_name>[^/]+)/file/(?P<id>\d+)'
_TEST = {
'url': 'https://mlssoccer.app.box.com/s/0evd2o3e08l60lr4ygukepvnkord1o1x/file/510727257538',
'md5': '1f81b2fd3960f38a40a3b8823e5fcd43',
'info_dict': {
'id': '510727257538',
'ext': 'mp4',
'title': 'Garber St. Louis will be 28th MLS team +scarving.mp4',
'uploader': 'MLS Video',
'timestamp': 1566320259,
'upload_date': '20190820',
'uploader_id': '235196876',
}
}
def _real_extract(self, url):
shared_name, file_id = self._match_valid_url(url).groups()
webpage = self._download_webpage(url, file_id)
request_token = self._parse_json(self._search_regex(
r'Box\.config\s*=\s*({.+?});', webpage,
'Box config'), file_id)['requestToken']
access_token = self._download_json(
'https://app.box.com/app-api/enduserapp/elements/tokens', file_id,
'Downloading token JSON metadata',
data=json.dumps({'fileIDs': [file_id]}).encode(), headers={
'Content-Type': 'application/json',
'X-Request-Token': request_token,
'X-Box-EndUser-API': 'sharedName=' + shared_name,
})[file_id]['read']
shared_link = 'https://app.box.com/s/' + shared_name
f = self._download_json(
'https://api.box.com/2.0/files/' + file_id, file_id,
'Downloading file JSON metadata', headers={
'Authorization': 'Bearer ' + access_token,
'BoxApi': 'shared_link=' + shared_link,
'X-Rep-Hints': '[dash]', # TODO: extract `hls` formats
}, query={
'fields': 'authenticated_download_url,created_at,created_by,description,extension,is_download_available,name,representations,size'
})
title = f['name']
query = {
'access_token': access_token,
'shared_link': shared_link
}
formats = []
# for entry in (try_get(f, lambda x: x['representations']['entries'], list) or []):
# entry_url_template = try_get(
# entry, lambda x: x['content']['url_template'])
# if not entry_url_template:
# continue
# representation = entry.get('representation')
# if representation == 'dash':
# TODO: append query to every fragment URL
# formats.extend(self._extract_mpd_formats(
# entry_url_template.replace('{+asset_path}', 'manifest.mpd'),
# file_id, query=query))
authenticated_download_url = f.get('authenticated_download_url')
if authenticated_download_url and f.get('is_download_available'):
formats.append({
'ext': f.get('extension') or determine_ext(title),
'filesize': f.get('size'),
'format_id': 'download',
'url': update_url_query(authenticated_download_url, query),
})
creator = f.get('created_by') or {}
return {
'id': file_id,
'title': title,
'formats': formats,
'description': f.get('description') or None,
'uploader': creator.get('name'),
'timestamp': parse_iso8601(f.get('created_at')),
'uploader_id': creator.get('id'),
}
yt_dlp/extractor/boxcast.py
+102
View File
@@ -0,0 +1,102 @@
from .common import InfoExtractor
from ..utils import (
js_to_json,
traverse_obj,
unified_timestamp
)
class BoxCastVideoIE(InfoExtractor):
_VALID_URL = r'''(?x)
https?://boxcast\.tv/(?:
view-embed/|
channel/\w+\?(?:[^#]+&)?b=|
video-portal/(?:\w+/){2}
)(?P<id>[\w-]+)'''
_EMBED_REGEX = [r'<iframe[^>]+src=["\'](?P<url>https?://boxcast\.tv/view-embed/[\w-]+)']
_TESTS = [{
'url': 'https://boxcast.tv/view-embed/in-the-midst-of-darkness-light-prevails-an-interdisciplinary-symposium-ozmq5eclj50ujl4bmpwx',
'info_dict': {
'id': 'da1eqqgkacngd5djlqld',
'ext': 'mp4',
'thumbnail': r're:https?://uploads\.boxcast\.com/(?:[\w+-]+/){3}.+\.png$',
'title': 'In the Midst of Darkness Light Prevails: An Interdisciplinary Symposium',
'release_timestamp': 1670686812,
'release_date': '20221210',
'uploader_id': 're8w0v8hohhvpqtbskpe',
'uploader': 'Children\'s Health Defense',
}
}, {
'url': 'https://boxcast.tv/video-portal/vctwevwntun3o0ikq7af/rvyblnn0fxbfjx5nwxhl/otbpltj2kzkveo2qz3ad',
'info_dict': {
'id': 'otbpltj2kzkveo2qz3ad',
'ext': 'mp4',
'uploader_id': 'vctwevwntun3o0ikq7af',
'uploader': 'Legacy Christian Church',
'title': 'The Quest | 1: Beginner\'s Bay | Jamie Schools',
'thumbnail': r're:https?://uploads.boxcast.com/(?:[\w-]+/){3}.+\.jpg'
}
}, {
'url': 'https://boxcast.tv/channel/z03fqwaeaby5lnaawox2?b=ssihlw5gvfij2by8tkev',
'info_dict': {
'id': 'ssihlw5gvfij2by8tkev',
'ext': 'mp4',
'thumbnail': r're:https?://uploads.boxcast.com/(?:[\w-]+/){3}.+\.jpg$',
'release_date': '20230101',
'uploader_id': 'ds25vaazhlu4ygcvffid',
'release_timestamp': 1672543201,
'uploader': 'Lighthouse Ministries International - Beltsville, Maryland',
'description': 'md5:ac23e3d01b0b0be592e8f7fe0ec3a340',
'title': 'New Year\'s Eve CROSSOVER Service at LHMI | December 31, 2022',
}
}]
_WEBPAGE_TESTS = [{
'url': 'https://childrenshealthdefense.eu/live-stream/',
'info_dict': {
'id': 'da1eqqgkacngd5djlqld',
'ext': 'mp4',
'thumbnail': r're:https?://uploads\.boxcast\.com/(?:[\w+-]+/){3}.+\.png$',
'title': 'In the Midst of Darkness Light Prevails: An Interdisciplinary Symposium',
'release_timestamp': 1670686812,
'release_date': '20221210',
'uploader_id': 're8w0v8hohhvpqtbskpe',
'uploader': 'Children\'s Health Defense',
}
}]
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
webpage_json_data = self._search_json(
r'var\s*BOXCAST_PRELOAD\s*=', webpage, 'broadcast data', display_id,
transform_source=js_to_json, default={})
# Ref: https://support.boxcast.com/en/articles/4235158-build-a-custom-viewer-experience-with-boxcast-api
broadcast_json_data = (
traverse_obj(webpage_json_data, ('broadcast', 'data'))
or self._download_json(f'https://api.boxcast.com/broadcasts/{display_id}', display_id))
view_json_data = (
traverse_obj(webpage_json_data, ('view', 'data'))
or self._download_json(f'https://api.boxcast.com/broadcasts/{display_id}/view',
display_id, fatal=False) or {})
formats, subtitles = [], {}
if view_json_data.get('status') == 'recorded':
formats, subtitles = self._extract_m3u8_formats_and_subtitles(
view_json_data['playlist'], display_id)
return {
'id': str(broadcast_json_data['id']),
'title': (broadcast_json_data.get('name')
or self._html_search_meta(['og:title', 'twitter:title'], webpage)),
'description': (broadcast_json_data.get('description')
or self._html_search_meta(['og:description', 'twitter:description'], webpage)
or None),
'thumbnail': (broadcast_json_data.get('preview')
or self._html_search_meta(['og:image', 'twitter:image'], webpage)),
'formats': formats,
'subtitles': subtitles,
'release_timestamp': unified_timestamp(broadcast_json_data.get('streamed_at')),
'uploader': broadcast_json_data.get('account_name'),
'uploader_id': broadcast_json_data.get('account_id'),
}
yt_dlp/extractor/bpb.py
+56
View File
@@ -0,0 +1,56 @@
import re
from .common import InfoExtractor
from ..utils import (
js_to_json,
determine_ext,
)
class BpbIE(InfoExtractor):
IE_DESC = 'Bundeszentrale für politische Bildung'
_VALID_URL = r'https?://(?:www\.)?bpb\.de/mediathek/(?P<id>[0-9]+)/'
_TEST = {
'url': 'http://www.bpb.de/mediathek/297/joachim-gauck-zu-1989-und-die-erinnerung-an-die-ddr',
'md5': 'c4f84c8a8044ca9ff68bb8441d300b3f',
'info_dict': {
'id': '297',
'ext': 'mp4',
'title': 'Joachim Gauck zu 1989 und die Erinnerung an die DDR',
'description': 'Joachim Gauck, erster Beauftragter für die Stasi-Unterlagen, spricht auf dem Geschichtsforum über die friedliche Revolution 1989 und eine "gewisse Traurigkeit" im Umgang mit der DDR-Vergangenheit.'
}
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
title = self._html_search_regex(
r'<h2 class="white">(.*?)</h2>', webpage, 'title')
video_info_dicts = re.findall(
r"({\s*src\s*:\s*'https?://film\.bpb\.de/[^}]+})", webpage)
formats = []
for video_info in video_info_dicts:
video_info = self._parse_json(
video_info, video_id, transform_source=js_to_json, fatal=False)
if not video_info:
continue
video_url = video_info.get('src')
if not video_url:
continue
quality = 'high' if '_high' in video_url else 'low'
formats.append({
'url': video_url,
'quality': 10 if quality == 'high' else 0,
'format_note': quality,
'format_id': '%s-%s' % (quality, determine_ext(video_url)),
})
return {
'id': video_id,
'formats': formats,
'title': title,
'description': self._og_search_description(webpage),
}
yt_dlp/extractor/br.py
+308
View File
@@ -0,0 +1,308 @@
import json
from .common import InfoExtractor
from ..utils import (
determine_ext,
ExtractorError,
int_or_none,
parse_duration,
parse_iso8601,
xpath_element,
xpath_text,
)
class BRIE(InfoExtractor):
IE_DESC = 'Bayerischer Rundfunk'
_VALID_URL = r'(?P<base_url>https?://(?:www\.)?br(?:-klassik)?\.de)/(?:[a-z0-9\-_]+/)+(?P<id>[a-z0-9\-_]+)\.html'
_TESTS = [
{
'url': 'http://www.br.de/mediathek/video/sendungen/abendschau/betriebliche-altersvorsorge-104.html',
'md5': '83a0477cf0b8451027eb566d88b51106',
'info_dict': {
'id': '48f656ef-287e-486f-be86-459122db22cc',
'ext': 'mp4',
'title': 'Die böse Überraschung',
'description': 'md5:ce9ac81b466ce775b8018f6801b48ac9',
'duration': 180,
'uploader': 'Reinhard Weber',
'upload_date': '20150422',
},
'skip': '404 not found',
},
{
'url': 'http://www.br.de/nachrichten/oberbayern/inhalt/muenchner-polizeipraesident-schreiber-gestorben-100.html',
'md5': 'af3a3a4aa43ff0ce6a89504c67f427ef',
'info_dict': {
'id': 'a4b83e34-123d-4b81-9f4e-c0d3121a4e05',
'ext': 'flv',
'title': 'Manfred Schreiber ist tot',
'description': 'md5:b454d867f2a9fc524ebe88c3f5092d97',
'duration': 26,
},
'skip': '404 not found',
},
{
'url': 'https://www.br-klassik.de/audio/peeping-tom-premierenkritik-dance-festival-muenchen-100.html',
'md5': '8b5b27c0b090f3b35eac4ab3f7a73d3d',
'info_dict': {
'id': '74c603c9-26d3-48bb-b85b-079aeed66e0b',
'ext': 'aac',
'title': 'Kurzweilig und sehr bewegend',
'description': 'md5:0351996e3283d64adeb38ede91fac54e',
'duration': 296,
},
'skip': '404 not found',
},
{
'url': 'http://www.br.de/radio/bayern1/service/team/videos/team-video-erdelt100.html',
'md5': 'dbab0aef2e047060ea7a21fc1ce1078a',
'info_dict': {
'id': '6ba73750-d405-45d3-861d-1ce8c524e059',
'ext': 'mp4',
'title': 'Umweltbewusster Häuslebauer',
'description': 'md5:d52dae9792d00226348c1dbb13c9bae2',
'duration': 116,
}
},
{
'url': 'http://www.br.de/fernsehen/br-alpha/sendungen/kant-fuer-anfaenger/kritik-der-reinen-vernunft/kant-kritik-01-metaphysik100.html',
'md5': '23bca295f1650d698f94fc570977dae3',
'info_dict': {
'id': 'd982c9ce-8648-4753-b358-98abb8aec43d',
'ext': 'mp4',
'title': 'Folge 1 - Metaphysik',
'description': 'md5:bb659990e9e59905c3d41e369db1fbe3',
'duration': 893,
'uploader': 'Eva Maria Steimle',
'upload_date': '20170208',
}
},
]
def _real_extract(self, url):
base_url, display_id = self._match_valid_url(url).groups()
page = self._download_webpage(url, display_id)
xml_url = self._search_regex(
r"return BRavFramework\.register\(BRavFramework\('avPlayer_(?:[a-f0-9-]{36})'\)\.setup\({dataURL:'(/(?:[a-z0-9\-]+/)+[a-z0-9/~_.-]+)'}\)\);", page, 'XMLURL')
xml = self._download_xml(base_url + xml_url, display_id)
medias = []
for xml_media in xml.findall('video') + xml.findall('audio'):
media_id = xml_media.get('externalId')
media = {
'id': media_id,
'title': xpath_text(xml_media, 'title', 'title', True),
'duration': parse_duration(xpath_text(xml_media, 'duration')),
'formats': self._extract_formats(xpath_element(
xml_media, 'assets'), media_id),
'thumbnails': self._extract_thumbnails(xpath_element(
xml_media, 'teaserImage/variants'), base_url),
'description': xpath_text(xml_media, 'desc'),
'webpage_url': xpath_text(xml_media, 'permalink'),
'uploader': xpath_text(xml_media, 'author'),
}
broadcast_date = xpath_text(xml_media, 'broadcastDate')
if broadcast_date:
media['upload_date'] = ''.join(reversed(broadcast_date.split('.')))
medias.append(media)
if len(medias) > 1:
self.report_warning(
'found multiple medias; please '
'report this with the video URL to http://yt-dl.org/bug')
if not medias:
raise ExtractorError('No media entries found')
return medias[0]
def _extract_formats(self, assets, media_id):
formats = []
for asset in assets.findall('asset'):
format_url = xpath_text(asset, ['downloadUrl', 'url'])
asset_type = asset.get('type')
if asset_type.startswith('HDS'):
formats.extend(self._extract_f4m_formats(
format_url + '?hdcore=3.2.0', media_id, f4m_id='hds', fatal=False))
elif asset_type.startswith('HLS'):
formats.extend(self._extract_m3u8_formats(
format_url, media_id, 'mp4', 'm3u8_native', m3u8_id='hds', fatal=False))
else:
format_info = {
'ext': xpath_text(asset, 'mediaType'),
'width': int_or_none(xpath_text(asset, 'frameWidth')),
'height': int_or_none(xpath_text(asset, 'frameHeight')),
'tbr': int_or_none(xpath_text(asset, 'bitrateVideo')),
'abr': int_or_none(xpath_text(asset, 'bitrateAudio')),
'vcodec': xpath_text(asset, 'codecVideo'),
'acodec': xpath_text(asset, 'codecAudio'),
'container': xpath_text(asset, 'mediaType'),
'filesize': int_or_none(xpath_text(asset, 'size')),
}
format_url = self._proto_relative_url(format_url)
if format_url:
http_format_info = format_info.copy()
http_format_info.update({
'url': format_url,
'format_id': 'http-%s' % asset_type,
})
formats.append(http_format_info)
server_prefix = xpath_text(asset, 'serverPrefix')
if server_prefix:
rtmp_format_info = format_info.copy()
rtmp_format_info.update({
'url': server_prefix,
'play_path': xpath_text(asset, 'fileName'),
'format_id': 'rtmp-%s' % asset_type,
})
formats.append(rtmp_format_info)
return formats
def _extract_thumbnails(self, variants, base_url):
thumbnails = [{
'url': base_url + xpath_text(variant, 'url'),
'width': int_or_none(xpath_text(variant, 'width')),
'height': int_or_none(xpath_text(variant, 'height')),
} for variant in variants.findall('variant') if xpath_text(variant, 'url')]
thumbnails.sort(key=lambda x: x['width'] * x['height'], reverse=True)
return thumbnails
class BRMediathekIE(InfoExtractor):
IE_DESC = 'Bayerischer Rundfunk Mediathek'
_VALID_URL = r'https?://(?:www\.)?br\.de/mediathek//?video/(?:[^/?&#]+?-)?(?P<id>av:[0-9a-f]{24})'
_TESTS = [{
'url': 'https://www.br.de/mediathek/video/gesundheit-die-sendung-vom-28112017-av:5a1e6a6e8fce6d001871cc8e',
'md5': 'fdc3d485835966d1622587d08ba632ec',
'info_dict': {
'id': 'av:5a1e6a6e8fce6d001871cc8e',
'ext': 'mp4',
'title': 'Die Sendung vom 28.11.2017',
'description': 'md5:6000cdca5912ab2277e5b7339f201ccc',
'timestamp': 1511942766,
'upload_date': '20171129',
}
}, {
'url': 'https://www.br.de/mediathek//video/av:61b0db581aed360007558c12',
'only_matching': True,
}]
def _real_extract(self, url):
clip_id = self._match_id(url)
clip = self._download_json(
'https://proxy-base.master.mango.express/graphql',
clip_id, data=json.dumps({
"query": """{
viewer {
clip(id: "%s") {
title
description
duration
createdAt
ageRestriction
videoFiles {
edges {
node {
publicLocation
fileSize
videoProfile {
width
height
bitrate
encoding
}
}
}
}
captionFiles {
edges {
node {
publicLocation
}
}
}
teaserImages {
edges {
node {
imageFiles {
edges {
node {
publicLocation
width
height
}
}
}
}
}
}
}
}
}""" % clip_id}).encode(), headers={
'Content-Type': 'application/json',
})['data']['viewer']['clip']
title = clip['title']
formats = []
for edge in clip.get('videoFiles', {}).get('edges', []):
node = edge.get('node', {})
n_url = node.get('publicLocation')
if not n_url:
continue
ext = determine_ext(n_url)
if ext == 'm3u8':
formats.extend(self._extract_m3u8_formats(
n_url, clip_id, 'mp4', 'm3u8_native',
m3u8_id='hls', fatal=False))
else:
video_profile = node.get('videoProfile', {})
tbr = int_or_none(video_profile.get('bitrate'))
format_id = 'http'
if tbr:
format_id += '-%d' % tbr
formats.append({
'format_id': format_id,
'url': n_url,
'width': int_or_none(video_profile.get('width')),
'height': int_or_none(video_profile.get('height')),
'tbr': tbr,
'filesize': int_or_none(node.get('fileSize')),
})
subtitles = {}
for edge in clip.get('captionFiles', {}).get('edges', []):
node = edge.get('node', {})
n_url = node.get('publicLocation')
if not n_url:
continue
subtitles.setdefault('de', []).append({
'url': n_url,
})
thumbnails = []
for edge in clip.get('teaserImages', {}).get('edges', []):
for image_edge in edge.get('node', {}).get('imageFiles', {}).get('edges', []):
node = image_edge.get('node', {})
n_url = node.get('publicLocation')
if not n_url:
continue
thumbnails.append({
'url': n_url,
'width': int_or_none(node.get('width')),
'height': int_or_none(node.get('height')),
})
return {
'id': clip_id,
'title': title,
'description': clip.get('description'),
'duration': int_or_none(clip.get('duration')),
'timestamp': parse_iso8601(clip.get('createdAt')),
'age_limit': int_or_none(clip.get('ageRestriction')),
'formats': formats,
'subtitles': subtitles,
'thumbnails': thumbnails,
}
yt_dlp/extractor/bravotv.py
+117
View File
@@ -0,0 +1,117 @@
import re
from .adobepass import AdobePassIE
from ..utils import (
smuggle_url,
update_url_query,
int_or_none,
float_or_none,
try_get,
dict_get,
)
class BravoTVIE(AdobePassIE):
_VALID_URL = r'https?://(?:www\.)?(?P<req_id>bravotv|oxygen)\.com/(?:[^/]+/)+(?P<id>[^/?#]+)'
_TESTS = [{
'url': 'https://www.bravotv.com/top-chef/season-16/episode-15/videos/the-top-chef-season-16-winner-is',
'md5': 'e34684cfea2a96cd2ee1ef3a60909de9',
'info_dict': {
'id': 'epL0pmK1kQlT',
'ext': 'mp4',
'title': 'The Top Chef Season 16 Winner Is...',
'description': 'Find out who takes the title of Top Chef!',
'uploader': 'NBCU-BRAV',
'upload_date': '20190314',
'timestamp': 1552591860,
'season_number': 16,
'episode_number': 15,
'series': 'Top Chef',
'episode': 'The Top Chef Season 16 Winner Is...',
'duration': 190.0,
}
}, {
'url': 'http://www.bravotv.com/below-deck/season-3/ep-14-reunion-part-1',
'only_matching': True,
}, {
'url': 'https://www.oxygen.com/in-ice-cold-blood/season-2/episode-16/videos/handling-the-horwitz-house-after-the-murder-season-2',
'only_matching': True,
}]
def _real_extract(self, url):
site, display_id = self._match_valid_url(url).groups()
webpage = self._download_webpage(url, display_id)
settings = self._parse_json(self._search_regex(
r'<script[^>]+data-drupal-selector="drupal-settings-json"[^>]*>({.+?})</script>', webpage, 'drupal settings'),
display_id)
info = {}
query = {
'mbr': 'true',
}
account_pid, release_pid = [None] * 2
tve = settings.get('ls_tve')
if tve:
query['manifest'] = 'm3u'
mobj = re.search(r'<[^>]+id="pdk-player"[^>]+data-url=["\']?(?:https?:)?//player\.theplatform\.com/p/([^/]+)/(?:[^/]+/)*select/([^?#&"\']+)', webpage)
if mobj:
account_pid, tp_path = mobj.groups()
release_pid = tp_path.strip('/').split('/')[-1]
else:
account_pid = 'HNK2IC'
tp_path = release_pid = tve['release_pid']
if tve.get('entitlement') == 'auth':
adobe_pass = settings.get('tve_adobe_auth', {})
if site == 'bravotv':
site = 'bravo'
resource = self._get_mvpd_resource(
adobe_pass.get('adobePassResourceId') or site,
tve['title'], release_pid, tve.get('rating'))
query['auth'] = self._extract_mvpd_auth(
url, release_pid,
adobe_pass.get('adobePassRequestorId') or site, resource)
else:
shared_playlist = settings['ls_playlist']
account_pid = shared_playlist['account_pid']
metadata = shared_playlist['video_metadata'][shared_playlist['default_clip']]
tp_path = release_pid = metadata.get('release_pid')
if not release_pid:
release_pid = metadata['guid']
tp_path = 'media/guid/2140479951/' + release_pid
info.update({
'title': metadata['title'],
'description': metadata.get('description'),
'season_number': int_or_none(metadata.get('season_num')),
'episode_number': int_or_none(metadata.get('episode_num')),
})
query['switch'] = 'progressive'
tp_url = 'http://link.theplatform.com/s/%s/%s' % (account_pid, tp_path)
tp_metadata = self._download_json(
update_url_query(tp_url, {'format': 'preview'}),
display_id, fatal=False)
if tp_metadata:
info.update({
'title': tp_metadata.get('title'),
'description': tp_metadata.get('description'),
'duration': float_or_none(tp_metadata.get('duration'), 1000),
'season_number': int_or_none(
dict_get(tp_metadata, ('pl1$seasonNumber', 'nbcu$seasonNumber'))),
'episode_number': int_or_none(
dict_get(tp_metadata, ('pl1$episodeNumber', 'nbcu$episodeNumber'))),
# For some reason the series is sometimes wrapped into a single element array.
'series': try_get(
dict_get(tp_metadata, ('pl1$show', 'nbcu$show')),
lambda x: x[0] if isinstance(x, list) else x,
expected_type=str),
'episode': dict_get(
tp_metadata, ('pl1$episodeName', 'nbcu$episodeName', 'title')),
})
info.update({
'_type': 'url_transparent',
'id': release_pid,
'url': smuggle_url(update_url_query(tp_url, query), {'force_smil_url': True}),
'ie_key': 'ThePlatform',
})
return info

Some files were not shown because too many files have changed in this diff Show More