mirror of
https://github.com/migatu/conjurer.git
synced 2026-07-14 13:34:40 +00:00
Bugfixes
asdasdasd :) asa asdasda aa :) asa aa :) :) sa as aa aa aa aaa as 11 aa 11 xxx dd ds aa a1 aa Test Suppress Move Installer aaa Serwis `12` aa xd asasa xd aa asa aaa :) Hejka a xd aa aaas 555 aaa asa aa 11 aaa aaa as sa async asda 00 123 123 aa as ss as a sa aa 1 RES T Hejko aa 11 AA test Test
This commit is contained in:
@@ -0,0 +1,167 @@
|
||||
import re
|
||||
import logging
|
||||
import threading
|
||||
from flask import Flask, jsonify, request
|
||||
import netrc
|
||||
import json
|
||||
from json.decoder import JSONDecodeError
|
||||
from platform import uname
|
||||
from sys import platform
|
||||
from urllib.request import urlopen
|
||||
from habanero import Crossref
|
||||
from waitress import serve
|
||||
|
||||
if platform in ("linux", "linux2"):
|
||||
SEPARATOR_FILE_PATH = "/"
|
||||
if "microsoft-standard" in uname().release:
|
||||
NETRC_FILE = "/home/mtuszowski/.netrc"
|
||||
else:
|
||||
NETRC_FILE = "/home/pi/.netrc"
|
||||
elif platform == "win32":
|
||||
NETRC_FILE = "C:\\Users\\mtusz\\.netrc"
|
||||
|
||||
#HOST_ADDRESS = "192.168.1.191"
|
||||
HOST_ADDRESS = "0.0.0.0"
|
||||
PORT_ADDRESS = 5001
|
||||
|
||||
class Librarian(object):
|
||||
|
||||
def __init__(self) -> None:
|
||||
netrc_mod = netrc.netrc(NETRC_FILE)
|
||||
authTokens = netrc_mod.authenticators("crossref")
|
||||
self.cr = Crossref(mailto=authTokens[0])
|
||||
self.last_search = ""
|
||||
self.limit = 20
|
||||
|
||||
def search_crossref(self, query, uuid):
|
||||
self.last_search = self.cr.works(query = query, limit = self.limit)
|
||||
#add to sql with UUID
|
||||
#sql row - title, doi, author, uuid, last retrieved, is_available
|
||||
with open("results.json", "r+", encoding="UTF-8") as data_file:
|
||||
# First we load existing data into a dict.
|
||||
try:
|
||||
file_data = json.load(data_file)
|
||||
except JSONDecodeError:
|
||||
file_data = []
|
||||
# Join new_data with file_data inside emp_details
|
||||
summarized_results = []
|
||||
for item in self.last_search['message']['items']:
|
||||
container = "NO"
|
||||
if "container-title" in item:
|
||||
container = "YES"
|
||||
print(item['title'])
|
||||
print(item['DOI'])
|
||||
|
||||
summarized_results.append({"DOI" : item['DOI'], "title": item['title'], "type": item['type'], "container": container})
|
||||
result = {"UUID": uuid, "total_results": self.last_search['message']['total-results'], "on_page" : 1, "summary":summarized_results, "results":self.last_search['message']['items'], }
|
||||
file_data.append(result)
|
||||
print("Saving")
|
||||
data_file.seek(0)
|
||||
# convert back to json.
|
||||
json.dump(file_data, data_file, indent=4)
|
||||
|
||||
|
||||
def check_if_exists(self,page_url):
|
||||
in_scihub_db = True
|
||||
if not page_url.startswith(("http:", "https:")):
|
||||
raise ValueError("URL must start with 'http:' or 'https:'")
|
||||
# trunk-ignore(bandit/B310)
|
||||
with urlopen(page_url) as response:
|
||||
info = response.info()
|
||||
print(info.get_content_type())
|
||||
data = response.read()
|
||||
text = data.decode("utf-8")
|
||||
for line in text.splitlines():
|
||||
if re.match(r".*Unfortunately, Sci-Hub doesn't have the requested document.*", line):
|
||||
return None
|
||||
if in_scihub_db:
|
||||
return text
|
||||
return None
|
||||
|
||||
def download(self, page_url):
|
||||
if response := self.check_if_exists(page_url):
|
||||
for line in response.splitlines():
|
||||
if m := re.match(r".*<embed type=\"application.pdf\"\s*src=\"(.*\.pdf)",line):
|
||||
return "https:" + str(m.group(1))
|
||||
return None
|
||||
|
||||
def provide_sci_hub_link(self, page_url):
|
||||
if self.check_if_exists(page_url):
|
||||
return page_url
|
||||
return None
|
||||
|
||||
def answer_query(self, query, uuid):
|
||||
#Search sql for UUID
|
||||
#SQL SELECT * FROM RESULTS WHERE UUID = uuid
|
||||
uuid_found = False
|
||||
database = None
|
||||
with open("results.json", "r", encoding="UTF-8") as new_file:
|
||||
#tu logika komunikacji z SQL i cała logika związana z wyszukaniem
|
||||
#ale tymczasowo plik
|
||||
try:
|
||||
database = json.load(new_file)
|
||||
except JSONDecodeError:
|
||||
pass
|
||||
if database:
|
||||
for item in database:
|
||||
if item["UUID"] == uuid:
|
||||
print (item["UUID"])
|
||||
uuid_found = True
|
||||
self.last_search = item
|
||||
if uuid_found:
|
||||
return self.last_search
|
||||
self.search_crossref(query=query, uuid=uuid)
|
||||
return self.last_search
|
||||
|
||||
#example not exists
|
||||
#sample_non_existing_page_url = "https://sci-hub.se/10.4324/9781003006237"
|
||||
#sample usage to download
|
||||
#sample_existing_page_url = "https://sci-hub.se/10.1057/9781137435026"
|
||||
#print(cl.download(sample_existing_page_url))
|
||||
#cl.search_crossref("BDSM")
|
||||
|
||||
app = Flask(__name__)
|
||||
def flask_debug():
|
||||
"""
|
||||
The `flask_debug` function starts a Flask application in debug mode without using the reloader.
|
||||
Do not use for production for fucks sake.
|
||||
"""
|
||||
# trunk-ignore(bandit/B201)
|
||||
app.run(debug=True, use_reloader=False, host=HOST_ADDRESS, port=PORT_ADDRESS)
|
||||
|
||||
def waitress_run():
|
||||
"""
|
||||
The `waitress_run` function serves the `app` on host "0.0.0.0"
|
||||
and port 5000 using the Waitress WSGI server.
|
||||
"""
|
||||
serve(app, host=HOST_ADDRESS, port=PORT_ADDRESS)
|
||||
|
||||
@app.route("/query", methods=["POST"])
|
||||
def query_database():
|
||||
record = json.loads(request.data)
|
||||
app.logger.info(record)
|
||||
app.logger.info(record["query"])
|
||||
app.logger.info(record["UUID"])
|
||||
cl = Librarian()
|
||||
answer_data = cl.answer_query(record["query"], record["UUID"])
|
||||
return_data = (
|
||||
jsonify(isError=False, message="Success", statusCode=200, data=answer_data),
|
||||
200,
|
||||
)
|
||||
return return_data
|
||||
|
||||
if __name__ == "__main__":
|
||||
logger = logging.getLogger('conjurer_musician')
|
||||
logger.setLevel(logging.DEBUG)
|
||||
threads = []
|
||||
#threads.append(threading.Thread(target=waitress_run))
|
||||
threads.append(threading.Thread(target=flask_debug))
|
||||
|
||||
for worker in threads:
|
||||
worker.start()
|
||||
for worker in threads:
|
||||
worker.join()
|
||||
|
||||
#1. robi liste wyników i ją wyświetla - ale tylko tytuły niezależnych dzieł - jeśli jest coś w containerze to trza pogrupować
|
||||
#2. Tworzy przyciski pozwalające sprawdzić czy jest dostępne - i jeśli jest zwraca link
|
||||
#3. Jest też przycisk "more" - wyszukujemy po 100, wyświetlamy po 20. Po 100 jak jeszcze to dopiero odpytujemy crossref przyciski strzałek przesuwają po obecnej porcji danych
|
||||
@@ -0,0 +1,11 @@
|
||||
#!/bin/bash
|
||||
python3 -m venv /home/pi/Conjurer_librarian/env
|
||||
cp /home/pi/conjurer/conjurer_librarian/conjurer_librarian.py ./Conjurer_librarian/
|
||||
cp /home/pi/conjurer/conjurer_librarian/requirements_librarian.txt ./Conjurer_librarian/
|
||||
cd /home/pi/Conjurer_librarian
|
||||
source /home/pi/Conjurer_librarian/env/bin/activate
|
||||
./env/bin/python3 -m pip install --upgrade pip
|
||||
./env/bin/python3 -m pip install -r requirements_librarian.txt
|
||||
deactivate
|
||||
|
||||
cp /home/pi/conjurer/conjurer_librarian/conjurer_librarian.py ./Conjurer_librarian/
|
||||
@@ -0,0 +1,3 @@
|
||||
habanero
|
||||
waitress
|
||||
flask
|
||||
Reference in New Issue
Block a user