conjurer/conjurer_librarian/conjurer_librarian.py

import re
import logging
import threading
import time
from flask import Flask, jsonify, request
import netrc
import json
import asyncio
from json.decoder import JSONDecodeError
from urllib.request import urlopen
from habanero import Crossref
from waitress import serve
from queue import Queue
import search_bot
import scrape_bot
import requests
NETRC_FILE = r"C:\Users\Activcom.pl\.netrc"

HOST_ADDRESS = "192.168.1.192"
PORT_ADDRESS = 5001
MAIN_BOT_ADDRESS = "http://192.168.1.191:5000"
SEND_RESULTS = "/conjurer"
BDSM_UUID_TEST = '96b7f85a-1142-4908-8986-62a2ea25a147'
MAX_CR_RESULTS = 150000
ENCODING = "utf-8"
app = Flask(__name__)

librarian_queue = Queue()
librarian_list = []

class Librarian(object):

    def __init__(self, app, query, uuid) -> None:
        netrc_mod = netrc.netrc(NETRC_FILE)
        authTokens = netrc_mod.authenticators("crossref")
        self.cr = Crossref(mailto=authTokens[0])
        self.query = query
        self.uuid = str(uuid)
        self.limit = MAX_CR_RESULTS
        self.fetched = 0
        self.hit = 0
        self.total = 0
        self.app = app
        self.logger = app.logger
        self.live_results = []
        self.final_result = []
        self.not_in_db = []
        self.search_result_from_cr = {}
        self.done = False

    async def search_crossref(self, query):
        self.app.logger.info("STARTED SEARCH")
        result = self.cr.works(query = query, limit = 1000)
        self.search_result_from_cr.update(result)
        self.total = result['message']['total-results']
        self.fetched += len(result['message']['items'])
        self.logger.info (self.total)
        self.logger.info(self.fetched)
        while self.total > self.fetched and self.limit > self.fetched:
            result = self.cr.works(query = query, limit = 1000)
            self.search_result_from_cr.update(result)
            self.total = result['message']['total-results']
            self.fetched += len(result['message']['items'])
            self.logger.info (self.total)
            self.logger.info(self.fetched)
            time.sleep(0.1)
        self.app.logger.info("CROSSREF DONE")
        #TODO: add to sql with UUID
        #sql row - title, doi, author, uuid, last retrieved, is_available
        
        with open("rr_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 = {}
            summarized_results = []
            self.app.logger.info("REFINE: Removing all derived works from the list")
            for item in self.search_result_from_cr['message']['items']:
                container = "NO"
                if "container-title" in item:
                    container = "YES"
                else:
                    summarized_results.append({"DOI" : item['DOI'], "title": item['title'] if 'title' in item else None,"type": item['type'] if 'type' in item else None, "container": container})
            result = {self.uuid : {"total_results": self.search_result_from_cr['message']['total-results'], "on_page" : 1, "summary":summarized_results, "results":self.search_result_from_cr['message']['items']}}
            if file_data:
                file_data.update(result)
            else:
                file_data = result
            
            self.app.logger.info("REFINE: Dumping to file")
            data_file.truncate(0)
            data_file.seek(0)
            json.dump(file_data, data_file, indent=4)
            return result

    async def check_dois_in_local_db(self, doi):
        self.app.logger.info("REFINE: Running search in the backend app")
        coro = asyncio.to_thread(search_bot.search_for_doi, doi, self.live_results, self.app.logger)
        result = await coro
        return result

    async def check_if_exists_brute_force(self, page_url):
        self.app.logger.error("REFINE: Brute force search!")
        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:
            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 False
                if m := re.match(r".*<embed type=\"application.pdf\"\s*src=\"(.*\.pdf)",line):
                    direct_download_link = "https:" + str(m.group(1))
                    self.app.logger.info (direct_download_link)
                    return True
        return False

    async def check_if_exists(self, doi, brute_force = False):
        result = {}
        result = await self.check_dois_in_local_db(doi)
        if brute_force and not result:
            for item in doi:
                item_link = "https://sci-hub.se/" + item[0]
                tmp = {"DOI" : item["DOI"], "exists" : await self.check_if_exists_brute_force(item_link), "data": item}
                result.update(tmp)
        return result

    async def refine_query(self, unrefined_reqult, brute_force = False):
        temp = []
        refined_result = []
        for key in unrefined_reqult:
            self.logger.info("KEY:")
            self.logger.info(key)

        for item in unrefined_reqult[self.uuid]["summary"]:
            if item["container"] == "NO" and item["title"]:                
                refined_result.append(item)

        for item in refined_result:
            temp.append([item["DOI"], item])

        refined_result = await self.check_if_exists(temp)

        for item in refined_result:
            if item["exists"]:
                self.final_result.append(item["data"])
            else:
                self.not_in_db.append(item["data"])
        self.hit = len(self.final_result)
        return self.final_result
    #TODO: DOłożyć sprawdzenie czy w rafinowanym pliku już nie mamy częściowego wyniku
    async def answer_query(self):
        #TODO: DOłożyć sprawdzenie czy w rafinowanym pliku już nie mamy częściowego wyniku tutaj bo zanim w ogóle otworzymy nierafinowany
        #Search sql for UUID
        #SQL SELECT * FROM RESULTS WHERE UUID = uuid
        self.logger.info(f"Search started {self.uuid}")
        database = None
        query = self.query
        with open("cr_results.json", "r+", encoding="utf-8") as cr_file:
            #tu logika komunikacji z SQL i cała logika związana z wyszukaniem
            #ale tymczasowo plik
            try:
                database =  json.load(cr_file)
            except JSONDecodeError:
                pass
            #TODO: Zwracać i final_result i not_in_db. Not in db_do pliku - i do ręcznego przeglądania potem.
            if database:
                for item in database.keys():
                    if item in self.uuid:
                        self.result = await self.refine_query(database)
                        temp = {}
                        for item in self.result:
                            temp[item['DOI']] = {"Title" : item['title'], "type": item['type']}
                        self.result = temp
                        temp2 = {}
                        for item in self.not_in_db:
                            temp2[item['DOI']] = {"Title" : item['title'], "type": item['type']}
                        self.not_in_db = temp2
                        return self.result
                answer = await self.search_crossref(query=query)
                database.update(answer)
                cr_file.truncate(0)
                cr_file.seek(0)
                json.dump(database,cr_file)
                self.result = await self.refine_query(answer)
            else:
                answer = await self.search_crossref(query=query)
                database = answer
                cr_file.truncate(0)
                cr_file.seek(0)
                json.dump(database,cr_file)
                self.result = await self.refine_query(answer)
                self.app.logger.info("Refined")
                self.done = True
            temp = {}
            for item in self.result:
                temp[item['DOI']] = {"Title" : item['title'], "type": item['type']}
            self.result = temp
            temp2 = {}
            for item in self.not_in_db:
                temp2[item['DOI']] = {"Title" : item['title'], "type": item['type']}
                self.not_in_db = temp2
            return self.result

#============================= FLASK INTERNALS===============================
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)

class BackgroundTaskSearch(threading.Thread):
    def run(self):
        loop = asyncio.new_event_loop()  # loop = asyncio.get_event_loop()
        loop.run_until_complete(self._run())
        loop.close()

    async def _run(self):
        while True:
            database = None
            ndb_database = None
            librarian = librarian_queue.get()
            self.app.logger.info("STARTED")
            result = await librarian.answer_query()
            result = {librarian.uuid: result}
            self.app.logger.info("Saving to file")
            with open("not_in_db.json", "r+", encoding="utf-8") as ndb_file:
                try:
                    ndb_database =  json.load(ndb_file)
                except JSONDecodeError:
                    pass
                if ndb_database:
                    ndb_database.update(librarian.not_in_db)
                else:
                    ndb_database = librarian.not_in_db
                ndb_file.truncate(0)
                ndb_file.seek(0)
                json.dump(ndb_database, ndb_file)

            with open("s_results.json", "r+", encoding="utf-8") as s_file:
                try:
                    database =  json.load(s_file)
                except JSONDecodeError:
                    pass
                if database:
                    self.app.logger.info(database)
                    self.app.logger.info(result)
                    database.update(result)
                else:
                    database = result
                self.app.logger.info("DUMPING DATA")
                s_file.truncate(0)
                s_file.seek(0)
                json.dump(database, s_file)
            self.app.logger.info("FINISHED")

            self.app.logger.info(result)
            coroutine = asyncio.to_thread(
            requests.post,
            f"{MAIN_BOT_ADDRESS}{SEND_RESULTS}",
            json=result,
            timeout=360,
    )       
            self.app.logger.info("SENT")
            result = await coroutine
            self.app.logger.info(result.status_code)
            self.app.logger.info("SEND CONFIRMED")
            time.sleep(1)
            
#==================================SERVER ROUTES==========================================
@app.route("/query", methods=["POST"])
async def query_database():
    record = json.loads(request.data)
    app.logger.info(record)
    app.logger.info(record["query"])
    app.logger.info(record["UUID"])
    uuid = record["UUID"]
    cl = Librarian(app, record["query"], uuid)
    librarian_queue.put(cl)
    librarian_list.append(cl)
    answer_data = (record["query"], record["UUID"], librarian_queue.qsize())
    return_data = (
        jsonify(isError=False, message="Success", statusCode=200, data=answer_data),
        200,
    )
    return return_data

@app.route("/get_partial_result", methods=["POST"])
async def get_partial():
    record = json.loads(request.data)
    app.logger.info(record)
    app.logger.info(record["UUID"])
    for lib in librarian_list:
        if lib.uuid == record["UUID"]:
            answer_data = lib.live_results
            break
    return_data = (
        jsonify(isError=False, message="Success", statusCode=200, data=answer_data),
        200,
    )
    return return_data

#=======================================MAIN===================================================
if __name__ == "__main__":
    logger = app.logger
    logger.setLevel(logging.DEBUG)
    threads = []
    threads.append(threading.Thread(target=waitress_run))
    #threads.append(threading.Thread(target=flask_debug))
    bgtask = BackgroundTaskSearch()
    bgtask.app = app
    threads.append(bgtask)
    threads.append(threading.Thread(target = scrape_bot.scraper, args=(logger,)))
    i = 0
    for worker in threads:
        try:
            logger.info(f"App number: {i}")
            i+=1
            worker.start()
        except RuntimeError as e:
            logger.error("Exploded")
            print(str(e))
    for worker in threads:
        worker.join()