def sources(self, url, hostDict, hostprDict): try: self._sources = [] if url is None: return self._sources if debrid.status() is False: raise Exception() data = urlparse.parse_qs(url) data = dict([(i, data[i][0]) if data[i] else (i, '') for i in data]) self.title = data[ 'tvshowtitle'] if 'tvshowtitle' in data else data['title'] self.hdlr = 'S%02dE%02d' % ( int(data['season']), int(data['episode']) ) if 'tvshowtitle' in data else data['year'] query = '%s S%02dE%02d' % ( data['tvshowtitle'], int(data['season']), int(data['episode'])) if 'tvshowtitle' in data else '%s %s' % ( data['title'], data['year']) query = re.sub(r'(\\\|/| -|:|;|\*|\?|"|\'|<|>|\|)', ' ', query) if 'tvshowtitle' in data: url = self.search.format('8', urllib.quote(query)) else: url = self.search.format('4', urllib.quote(query)) self.hostDict = hostDict + hostprDict headers = {'User-Agent': client.agent()} _html = client.request(url, headers=headers) threads = [] for i in re.findall(r'<item>(.+?)</item>', _html, re.DOTALL): threads.append(workers.Thread(self._get_items, i)) [i.start() for i in threads] [i.join() for i in threads] return self._sources except BaseException: return self._sources
def sources(self, url, hostDict, hostprDict): try: self._sources = [] self.items = [] if url is None: return self._sources if debrid.status() is False: raise Exception() data = urlparse.parse_qs(url) data = dict([(i, data[i][0]) if data[i] else (i, '') for i in data]) self.title = data[ 'tvshowtitle'] if 'tvshowtitle' in data else data['title'] self.hdlr = 'S%02dE%02d' % ( int(data['season']), int(data['episode']) ) if 'tvshowtitle' in data else data['year'] query = '%s S%02dE%02d' % ( data['tvshowtitle'], int(data['season']), int(data['episode'])) if 'tvshowtitle' in data else '%s %s' % ( data['title'], data['year']) query = re.sub('(\\\|/| -|:|;|\*|\?|"|\'|<|>|\|)', ' ', query) if 'tvshowtitle' in data: url = self.tvsearch.format(urllib.quote(query)) else: url = self.moviesearch.format(urllib.quote(query)) self._get_items(url) self.hostDict = hostDict + hostprDict threads = [] for i in self.items: threads.append(workers.Thread(self._get_sources, i)) [i.start() for i in threads] [i.join() for i in threads] return self._sources except BaseException: return self._sources
def sources(self, url, hostDict, hostprDict): try: self._sources = [] if url is None: return self._sources if debrid.status() is False: raise Exception() self.hostDict = hostDict + hostprDict data = urlparse.parse_qs(url) data = dict([(i, data[i][0]) if data[i] else (i, '') for i in data]) self.title = data[ 'tvshowtitle'] if 'tvshowtitle' in data else data['title'] self.title = self.title.replace('&', 'and').replace( 'Special Victims Unit', 'SVU') self.hdlr = 'S%02dE%02d' % ( int(data['season']), int(data['episode']) ) if 'tvshowtitle' in data else data['year'] self.year = data['year'] query = '%s %s' % (self.title, self.hdlr) query = re.sub('(\\\|/| -|:|;|\*|\?|"|\'|<|>|\|)', '', query) url = self.search_link % urllib.quote_plus(query) url = urlparse.urljoin(self.base_link, url) # log_utils.log('url = %s' % url, log_utils.LOGDEBUG) r = client.request(url) # switch to client.parseDOM() to rid import posts = dom_parser.parse_dom(r, 'div', {'class': 'eTitle'}) posts = [ dom_parser.parse_dom(i.content, 'a', req='href') for i in posts if i ] posts = [(i[0].attrs['href'], re.sub('<.+?>', '', i[0].content)) for i in posts if i] posts = [[i[0], i[1]] for i in posts] threads = [] for i in posts: threads.append(workers.Thread(self._get_sources, i)) [i.start() for i in threads] [i.join() for i in threads] alive = [x for x in threads if x.is_alive() is True] while alive: alive = [x for x in threads if x.is_alive() is True] time.sleep(0.1) return self._sources except: source_utils.scraper_error('ONLINESERIES') return self._sources
def sources(self, url, hostDict, hostprDict): try: self._sources = [] self.items = [] if url is None: return self._sources if debrid.status() is False: return self._sources data = urlparse.parse_qs(url) data = dict([(i, data[i][0]) if data[i] else (i, '') for i in data]) self.title = data[ 'tvshowtitle'] if 'tvshowtitle' in data else data['title'] self.title = self.title.replace('&', 'and').replace( 'Special Victims Unit', 'SVU') self.hdlr = 'S%02dE%02d' % ( int(data['season']), int(data['episode']) ) if 'tvshowtitle' in data else data['year'] self.year = data['year'] query = '%s %s' % (self.title, self.hdlr) query = re.sub('(\\\|/| -|:|;|\*|\?|"|\'|<|>|\|)', '', query) urls = [] if 'tvshowtitle' in data: url = self.search2.format(urllib.quote(query)) else: url = self.search.format(urllib.quote(query)) url = urlparse.urljoin(self.base_link, url) urls.append(url) url2 = url + '/2/' urls.append(url2) # log_utils.log('urls = %s' % urls, log_utils.LOGDEBUG) threads = [] for url in urls: threads.append(workers.Thread(self._get_items, url)) [i.start() for i in threads] [i.join() for i in threads] threads2 = [] for i in self.items: threads2.append(workers.Thread(self._get_sources, i)) [i.start() for i in threads2] [i.join() for i in threads2] return self._sources except: source_utils.scraper_error('KICKASS2') return self._sources
def movie(self, imdb, title, localtitle, aliases, year): if debrid.status(True) is False: return try: url = {'imdb': imdb, 'title': title, 'year': year} url = urllib.urlencode(url) return url except Exception: return
def sources(self, url, hostDict, hostprDict): try: self.sources = [] if url is None: return self.sources if debrid.status() is False: raise Exception() self.hostDict = hostDict + hostprDict data = urlparse.parse_qs(url) data = dict([(i, data[i][0]) if data[i] else (i, '') for i in data]) title = data['tvshowtitle'] if 'tvshowtitle' in data else data[ 'title'] # title = title.replace('&', 'and').replace('Special Victims Unit', 'SVU') hdlr = data['year'] hdlr2 = 'S%02dE%02d' % (int(data['season']), int( data['episode'])) if 'tvshowtitle' in data else '' imdb = data['imdb'] url = self.search(title, hdlr) headers = {'User-Agent': client.agent()} r = self.scraper.get(url, headers=headers).content if hdlr2 == '': r = dom_parser.parse_dom(r, 'ul', {'id': 'releases'})[0] else: r = dom_parser.parse_dom(r, 'ul', {'id': 'episodes'})[0] r = dom_parser.parse_dom(r.content, 'a', req=['href']) r = [(i.content, urlparse.urljoin(self.base_link, i.attrs['href'])) for i in r if i and i.content != 'Watch'] if hdlr2 != '': r = [(i[0], i[1]) for i in r if hdlr2.lower() in i[0].lower()] threads = [] for i in r: threads.append(workers.Thread(self._get_sources, i[0], i[1])) [i.start() for i in threads] # [i.join() for i in threads] alive = [x for x in threads if x.is_alive() is True] while alive: alive = [x for x in threads if x.is_alive() is True] time.sleep(0.1) return self.sources except: source_utils.scraper_error('RAPIDMOVIEZ') return self.sources
def sources(self, url, hostDict, hostprDict): sources = [] try: if url is None: return sources if debrid.status() is False: raise Exception() data = urlparse.parse_qs(url) data = dict([(i, data[i][0]) if data[i] else (i, '') for i in data]) title = data['tvshowtitle'] if 'tvshowtitle' in data else data['title'] hdlr = 'S%02dE%02d' % (int(data['season']), int(data['episode'])) if 'tvshowtitle' in data else data['year'] query = '%s s%02de%02d' % ( data['tvshowtitle'], int(data['season']), int(data['episode'])) if 'tvshowtitle' in data else '%s %s' % ( data['title'], data['year']) query = re.sub('(\\\|/| -|:|;|\*|\?|"|\'|<|>|\|)', ' ', query) url = self.search_link % urllib.quote_plus(query) url = urlparse.urljoin(self.base_link, url) r = client.request(url) try: posts = client.parseDOM(r, 'div', attrs={'class': 'box-info'}) for post in posts: data = client.parseDOM(post, 'a', ret='href') u = [i for i in data if '/torrent/' in i] for u in u: match = '%s %s' % (title, hdlr) match = match.replace('+', '-').replace(' ', '-').replace(':-', '-').replace('---', '-') if not match in u: continue u = self.base_link + u r = client.request(u) r = client.parseDOM(r, 'div', attrs={'class': 'torrent-category-detail clearfix'}) for t in r: link = re.findall('href="magnet:(.+?)" onclick=".+?"', t)[0] link = 'magnet:%s' % link link = str(client.replaceHTMLCodes(link).split('&tr')[0]) seeds = int(re.compile('<span class="seeds">(.+?)</span>').findall(t)[0]) if self.min_seeders > seeds: continue quality, info = source_utils.get_release_quality(link, link) try: size = re.findall('<strong>Total size</strong> <span>(.+?)</span>', t) for size in size: size = '%s' % size info.append(size) except BaseException: pass info = ' | '.join(info) sources.append( {'source': 'Torrent', 'quality': quality, 'language': 'en', 'url': link, 'info': info, 'direct': False, 'debridonly': True}) except: return return sources except: return sources
def tvshow(self, imdb, tvdb, tvshowtitle, localtvshowtitle, aliases, year): if debrid.status() is False: return try: url = {'imdb': imdb, 'tvdb': tvdb, 'tvshowtitle': tvshowtitle, 'year': year} url = urllib.urlencode(url) return url except Exception: failure = traceback.format_exc() log_utils.log('TPB - Exception: \n' + str(failure)) return
def sources(self, url, hostDict, hostprDict): try: sources = [] if url is None: return sources if debrid.status() is False: raise Exception() data = urlparse.parse_qs(url) data = dict([(i, data[i][0]) if data[i] else (i, '') for i in data]) query = '%s %s' % (data['title'], data['year']) url = self.search_link % urllib.quote(query) url = urlparse.urljoin(self.base_link, url).replace('%20', '-') html = client.request(url) try: results = client.parseDOM(html, 'div', attrs={'class': 'ava1'}) except: failure = traceback.format_exc() log_utils.log('YIFYDLL - Exception: \n' + str(failure)) return sources for torrent in results: link = re.findall( 'a data-torrent-id=".+?" href="(magnet:.+?)" class=".+?" title="(.+?)"', torrent, re.DOTALL) for link, name in link: link = str(client.replaceHTMLCodes(link).split('&tr')[0]) quality, info = source_utils.get_release_quality( name, name) try: size = re.findall( '((?:\d+\.\d+|\d+\,\d+|\d+)\s*(?:GB|GiB|MB|MiB))', torrent)[-1] div = 1 if size.endswith(('GB', 'GiB')) else 1024 size = float(re.sub('[^0-9|/.|/,]', '', size)) / div size = '%.2f GB' % size info.append(size) except Exception: pass info = ' | '.join(info) sources.append({ 'source': 'Torrent', 'quality': quality, 'language': 'en', 'url': link, 'info': info, 'direct': False, 'debridonly': True }) return sources except: failure = traceback.format_exc() log_utils.log('YIFYDLL - Exception: \n' + str(failure)) return
def sources(self, url, hostDict, hostprDict): try: self._sources = [] if url is None: return self._sources if debrid.status() is False: raise Exception() data = urlparse.parse_qs(url) data = dict([(i, data[i][0]) if data[i] else (i, '') for i in data]) title = data['tvshowtitle'] if 'tvshowtitle' in data else data[ 'title'] hdlr = 'S%02dE%02d' % (int(data['season']), int( data['episode'])) if 'tvshowtitle' in data else data['year'] query = '%s S%02dE%02d' % ( data['tvshowtitle'], int(data['season']), int(data['episode'])) if 'tvshowtitle' in data else '%s %s' % ( data['title'], data['year']) query = re.sub('(\\\|/| -|:|;|\*|\?|"|\'|<|>|\|)', ' ', query) query = self.search_link % cleantitle.geturl(query) url = urlparse.urljoin(self.base_link, query) r = client.request(url) posts = dom_parser2.parse_dom(r, 'div', {'class': 'eTitle'}) posts = [ dom_parser2.parse_dom(i.content, 'a', req='href') for i in posts if i ] posts = [(i[0].attrs['href'], re.sub('<.+?>', '', i[0].content)) for i in posts if i] posts = [ (i[0], i[1]) for i in posts if (cleantitle.get_simple(i[1].split(hdlr)[0]) == cleantitle.get(title) and hdlr.lower() in i[1].lower()) ] self.hostDict = hostDict + hostprDict threads = [] for i in posts: threads.append(workers.Thread(self._get_sources, i)) [i.start() for i in threads] [i.join() for i in threads] alive = [x for x in threads if x.is_alive() == True] while alive: alive = [x for x in threads if x.is_alive() == True] time.sleep(0.1) return self._sources except Exception: return self._sources
def sources(self, url, hostDict, hostprDict): sources = [] try: if url is None: return sources if debrid.status() is False: raise Exception() data = urlparse.parse_qs(url) data = dict([(i, data[i][0]) if data[i] else (i, '') for i in data]) self.title = data[ 'tvshowtitle'] if 'tvshowtitle' in data else data['title'] self.hdlr = 'S%02dE%02d' % ( int(data['season']), int(data['episode']) ) if 'tvshowtitle' in data else data['year'] query = '%s S%02dE%02d' % ( data['tvshowtitle'], int(data['season']), int(data['episode'])) if 'tvshowtitle' in data else '%s %s' % ( data['title'], data['year']) query = re.sub('(\\\|/| -|:|;|\*|\?|"|\'|<|>|\|)', ' ', query) if 'tvshowtitle' in data: url = self.tvsearch.format(urllib.quote_plus(query)) url = urlparse.urljoin(self.base_link, url) else: url = self.moviesearch.format(urllib.quote_plus(query)) url = urlparse.urljoin(self.base_link, url) items = self._get_items(url) hostDict = hostDict + hostprDict for item in items: try: name = item[0] quality, info = source_utils.get_release_quality( name, name) info.append(item[2]) info = ' | '.join(info) url = item[1] url = url.split('&tr')[0] sources.append({ 'source': 'Torrent', 'quality': quality, 'language': 'en', 'url': url, 'info': info, 'direct': False, 'debridonly': True }) except BaseException: pass return sources except BaseException: return sources
def sources(self, url, hostDict, hostprDict): try: sources = [] if url == None: return sources if debrid.status() == False: raise Exception() data = urlparse.parse_qs(url) data = dict([(i, data[i][0]) if data[i] else (i, '') for i in data]) query = '%s S%02dE%02d' % ( data['tvshowtitle'], int(data['season']), int(data['episode'])) \ if 'tvshowtitle' in data else '%s' % (data['title']) url = self.search_link % urllib.quote_plus(query) url = urlparse.urljoin(self.base_link, url).replace('-', '+') r = self.scraper.get(url).content posts = client.parseDOM(r, "div", attrs={"class": "postpage_movie_download"}) hostDict = hostprDict + hostDict items = [] for post in posts: try: u = client.parseDOM(post, 'a', ret='href') for i in u: items.append(i) except: pass seen_urls = set() for item in items: try: i = str(item) r = client.request(i) u = client.parseDOM(r, "div", attrs={"class": "multilink_lnks"}) for t in u: r = client.parseDOM(t, 'a', ret='href') for url in r: if 'www.share-online.biz' in url: continue if url in seen_urls: continue seen_urls.add(url) quality, info = source_utils.get_release_quality(url) if 'SD' in quality: continue valid, host = source_utils.is_host_valid(url, hostDict) sources.append( {'source': host, 'quality': quality, 'language': 'en', 'url': url, 'info': info, 'direct': False, 'debridonly': True}) except: pass return sources except: return
def sources(self, url, hostDict, hostprDict): sources = [] try: if url is None: return sources if debrid.status() is False: return sources data = urlparse.parse_qs(url) data = dict([(i, data[i][0]) if data[i] else (i, '') for i in data]) q = '%s' % cleantitle.get_gan_url(data['title']) url = self.base_link + self.search_link % q r = self.scraper.get(url).content v = re.compile( '<a href="(.+?)" class="ml-mask jt" title="(.+?)">\r\n\t\t\t\t\t\t\t\t\t\t\t\t<span class=".+?">(.+?)</span>').findall( r) for url, check, quality in v: t = '%s (%s)' % (data['title'], data['year']) if t not in check: raise Exception() key = url.split('-hd')[1] r = self.scraper.get('https://ganool.ws/moviedownload.php?q=' + key).content r = re.compile('<a rel=".+?" href="(.+?)" target=".+?">').findall(r) for url in r: if any(x in url for x in ['.rar']): continue quality = source_utils.check_url(quality) valid, host = source_utils.is_host_valid(url, hostDict) if not valid: continue sources.append({'source': host, 'quality': quality, 'language': 'en', 'url': url, 'direct': False, 'debridonly': True}) return sources except: return sources
def episode(self, url, imdb, tvdb, title, premiered, season, episode): if debrid.status(True) is False: return try: if url is None: return url = urlparse.parse_qs(url) url = dict([(i, url[i][0]) if url[i] else (i, '') for i in url]) url['title'], url['premiered'], url['season'], url[ 'episode'] = title, premiered, season, episode url = urllib.urlencode(url) return url except Exception: return
def episode(self, url, imdb, tvdb, title, premiered, season, episode): if debrid.status() is False: return try: if url is None: return url = urlparse.parse_qs(url) url = dict([(i, url[i][0]) if url[i] else (i, '') for i in url]) url['title'], url['premiered'], url['season'], url['episode'] = title, premiered, season, episode url = urllib.urlencode(url) return url except Exception: failure = traceback.format_exc() log_utils.log('TPB - Exception: \n' + str(failure)) return
def sources(self, url, hostDict, hostprDict): try: sources = [] if url == None: return sources if debrid.status() is False: raise Exception() data = urlparse.parse_qs(url) data = dict([(i, data[i][0]) if data[i] else (i, '') for i in data]) query = '%s S%02dE%02d' % ( data['tvshowtitle'], int(data['season']), int(data['episode'])) if 'tvshowtitle' in data else '%s' % \ data[ 'imdb'] query = re.sub('(\\\|/| -|:|;|\*|\?|"|\'|<|>|\|)', ' ', query) token = client.request(self.token) token = json.loads(token)["token"] if 'tvshowtitle' in data: search_link = self.tvsearch.format(token, urllib.quote_plus(query), 'format=json_extended') else: search_link = self.msearch.format(token, data['imdb'], 'format=json_extended') rjson = client.request(search_link) files = json.loads(rjson)['torrent_results'] for file in files: name = file["title"] quality, info = source_utils.get_release_quality(name, name) size = source_utils.convert_size(file["size"]) info.append(size) info = ' | '.join(info) url = file["download"] url = url.split('&tr')[0] sources.append({ 'source': 'Torrent', 'quality': quality, 'language': 'en', 'url': url, 'info': info, 'direct': False, 'debridonly': True }) return sources except BaseException: return sources
def sources(self, url, hostDict, hostprDict): try: self._sources = [] if url is None: return self._sources if debrid.status() is False: return self._sources data = urlparse.parse_qs(url) data = dict([(i, data[i][0]) if data[i] else (i, '') for i in data]) self.title = data['tvshowtitle'] if 'tvshowtitle' in data else data['title'] self.title = self.title.replace('&', 'and').replace('Special Victims Unit', 'SVU') self.hdlr = 'S%02dE%02d' % (int(data['season']), int(data['episode'])) if 'tvshowtitle' in data else data['year'] self.year = data['year'] query = '%s %s' % (self.title, self.hdlr) query = re.sub('(\\\|/| -|:|;|\*|\?|"|\'|<|>|\|)', '', query) if 'tvshowtitle' in data: url = self.search.format('8', urllib.quote(query)) else: url = self.search.format('4', urllib.quote(query)) # log_utils.log('url = %s' % url, log_utils.LOGDEBUG) headers = {'User-Agent': client.agent()} _html = client.request(url, headers=headers) threads = [] for i in re.findall(r'<item>(.+?)</item>', _html, re.DOTALL): threads.append(workers.Thread(self._get_items, i)) [i.start() for i in threads] [i.join() for i in threads] return self._sources except: source_utils.scraper_error('TORRENTDOWNLOADS') return self._sources
def sources(self, url, hostDict, hostprDict): sources = [] try: if url is None: return sources if debrid.status() is False: raise Exception() data = urlparse.parse_qs(url) data = dict([(i, data[i][0]) if data[i] else (i, '') for i in data]) title = data['tvshowtitle'] if 'tvshowtitle' in data else data['title'] hdlr = 'S%02dE%02d' % (int(data['season']), int(data['episode'])) if 'tvshowtitle' in data else data['year'] query = '%s s%02de%02d' % ( data['tvshowtitle'], int(data['season']), int(data['episode'])) if 'tvshowtitle' in data else '%s %s' % ( data['title'], data['year']) query = re.sub(r'(\\\|/| -|:|;|\*|\?|"|\'|<|>|\|)', ' ', query) url = self.search_link % urllib.quote_plus(query) url = urlparse.urljoin(self.base_link, url) r = client.request(url) try: posts = client.parseDOM(r, 'tbody', attrs={'id': 'results'}) for post in posts: link = re.findall('a href="(magnet:.+?)" title="(.+?)"', post, re.DOTALL) for url, data in link: if not hdlr in data: continue url = url.split('&tr')[0] quality, info = source_utils.get_release_quality(data) if any( x in url for x in ['FRENCH', 'Ita', 'italian', 'TRUEFRENCH', '-lat-', 'Dublado']): continue info = ' | '.join(info) sources.append( {'source': 'Torrent', 'quality': quality, 'language': 'en', 'url': url, 'info': info, 'direct': False, 'debridonly': True}) except: return return sources except: return sources
def sources(self, url, hostDict, hostprDict): try: sources = [] if url is None: return sources if debrid.status() is False: return sources data = urlparse.parse_qs(url) data = dict([(i, data[i][0]) if data[i] else (i, '') for i in data]) title = data['tvshowtitle'] if 'tvshowtitle' in data else data[ 'title'] title = title.replace('&', 'and').replace('Special Victims Unit', 'SVU') hdlr = 'S%02dE%02d' % (int(data['season']), int( data['episode'])) if 'tvshowtitle' in data else data['year'] query = '%s %s' % (title, hdlr) query = re.sub('(\\\|/| -|:|;|\*|\?|"|\'|<|>|\|)', '', query) url = self.search_link % urllib.quote_plus(query) url = urlparse.urljoin(self.base_link, url).replace('%3A+', '+') # log_utils.log('url = %s' % url, log_utils.LOGDEBUG) r = client.request(url) if r is None and 'tvshowtitle' in data: season = re.search('S(.*?)E', hdlr) season = season.group(1) url = title r = client.request(url) for loopCount in range(0, 2): if loopCount == 1 or (r is None and 'tvshowtitle' in data): r = client.request(url) posts = client.parseDOM(r, "h2", attrs={"class": "postTitle"}) hostDict = hostprDict + hostDict items = [] for post in posts: try: u = client.parseDOM(post, 'a', ret='href') for i in u: name = str(i) items.append(name) tit = name.rsplit('/', 1)[0] tit = tit.rsplit('/', 1)[1].upper() t = tit.split(hdlr)[0].replace( data['year'], '').replace('(', '').replace( ')', '').replace('&', 'and') if cleantitle.get(t) != cleantitle.get(title): continue except: source_utils.scraper_error('MAXRLS') pass if len(items) > 0: break for item in items: try: i = str(item) r = client.request(i) u = client.parseDOM(r, "div", attrs={"class": "postContent"}) for t in u: r = client.parseDOM(t, 'a', ret='href') for url in r: quality, info = source_utils.get_release_quality( url) valid, host = source_utils.is_host_valid( url, hostDict) if not valid: continue sources.append({ 'source': host, 'quality': quality, 'language': 'en', 'url': url, 'info': info, 'direct': False, 'debridonly': True }) except: source_utils.scraper_error('MAXRLS') pass return sources except: source_utils.scraper_error('MAXRLS') return sources
def sources(self, url, hostDict, hostprDict): try: sources = [] if url is None: return sources if debrid.status() is False: return sources data = urlparse.parse_qs(url) data = dict([(i, data[i][0]) if data[i] else (i, '') for i in data]) title = data['tvshowtitle'] if 'tvshowtitle' in data else data[ 'title'] title = title.replace('&', 'and').replace('Special Victims Unit', 'SVU') hdlr = 'S%02dE%02d' % (int(data['season']), int( data['episode'])) if 'tvshowtitle' in data else data['year'] query = '%s %s' % (title, hdlr) query = re.sub('(\\\|/| -|:|;|\*|\?|"|\'|<|>|\|)', '', query) url = self.search_link % urllib.quote(query) url = urlparse.urljoin(self.base_link, url) # log_utils.log('url = %s' % url, log_utils.LOGDEBUG) html = client.request(url) html = html.replace(' ', ' ') try: results = client.parseDOM(html, 'table', attrs={'id': 'searchResult'}) except: return sources url2 = url.replace('/1/', '/2/') html2 = client.request(url2) html2 = html2.replace(' ', ' ') try: results += client.parseDOM(html2, 'table', attrs={'id': 'searchResult'}) except: return sources results = ''.join(results) rows = re.findall('<tr(.+?)</tr>', results, re.DOTALL) if rows is None: return sources for entry in rows: try: try: url = 'magnet:%s' % (re.findall( 'a href="magnet:(.+?)"', entry, re.DOTALL)[0]) url = str(client.replaceHTMLCodes(url).split('&tr')[0]) except: continue if any(x in url.lower() for x in [ 'french', 'italian', 'spanish', 'truefrench', 'dublado', 'dubbed' ]): continue try: name = re.findall( 'class="detLink" title=".+?">(.+?)</a>', entry, re.DOTALL)[0] name = client.replaceHTMLCodes(name) t = name.split(hdlr)[0].replace( data['year'], '').replace('(', '').replace(')', '').replace('&', 'and') if cleantitle.get(t) != cleantitle.get(title): continue except: continue if hdlr not in name: continue try: seeders = int( re.findall('<td align="right">(.+?)</td>', entry, re.DOTALL)[0]) except: continue if self.min_seeders > seeders: continue quality, info = source_utils.get_release_quality(name, url) try: size = re.findall( '((?:\d+\.\d+|\d+\,\d+|\d+)\s*(?:GB|GiB|MB|MiB))', entry)[-1] div = 1 if size.endswith(('GB', 'GiB')) else 1024 size = float(re.sub('[^0-9|/.|/,]', '', size)) / div size = '%.2f GB' % size info.append(size) except: pass info = ' | '.join(info) sources.append({ 'source': 'torrent', 'quality': quality, 'language': 'en', 'url': url, 'info': info, 'direct': False, 'debridonly': True }) except: source_utils.scraper_error('PIRATEBAY') continue return sources except: source_utils.scraper_error('PIRATEBAY') return sources
def sources(self, url, hostDict, hostprDict): try: sources = [] if url is None: return sources if debrid.status() is False: return sources hostDict = hostprDict + hostDict data = urlparse.parse_qs(url) data = dict([(i, data[i][0]) if data[i] else (i, '') for i in data]) title = data['tvshowtitle'] if 'tvshowtitle' in data else data[ 'title'] title = title.replace('&', 'and').replace('Special Victims Unit', 'SVU') hdlr = 'S%02dE%02d' % (int(data['season']), int( data['episode'])) if 'tvshowtitle' in data else data['year'] query = '%s %s' % (title, hdlr) query = re.sub('(\\\|/| -|:|;|\*|\?|"|\'|<|>|\|)', '', query) url = self.search_link % urllib.quote_plus(query) url = urlparse.urljoin(self.base_link, url).replace('-', '+') # log_utils.log('url = %s' % url, log_utils.LOGDEBUG) r = client.request(url) # r = self.scraper.get(url).content if r is None and 'tvshowtitle' in data: season = re.search('S(.*?)E', hdlr) season = season.group(1) url = title # r = self.scraper.get(url).content r = client.request(url) for loopCount in range(0, 2): if loopCount == 1 or (r is None and 'tvshowtitle' in data): r = self.scraper.get(url).content # r = client.request(url) posts = client.parseDOM( r, "div", attrs={"class": "postpage_movie_download"}) items = [] for post in posts: try: u = client.parseDOM(post, 'a', ret='href') for i in u: name = str(i) items.append(name) except: pass if len(items) > 0: break for item in items: try: i = str(item) # r = self.scraper.get(i).content r = client.request(i) if r is None: continue tit = client.parseDOM(r, 'meta', attrs={'property': 'og:title'}, ret='content')[0] t = tit.split(hdlr)[0].replace(data['year'], '').replace( '(', '').replace(')', '').replace('&', 'and') if cleantitle.get(t) != cleantitle.get(title): continue if hdlr not in tit: continue u = client.parseDOM(r, "div", attrs={"class": "multilink_lnks"}) for t in u: r = client.parseDOM(t, 'a', ret='href') for url in r: if 'www.share-online.biz' in url: continue if url in str(sources): continue quality, info = source_utils.get_release_quality( url, url) valid, host = source_utils.is_host_valid( url, hostDict) if valid: sources.append({ 'source': host, 'quality': quality, 'language': 'en', 'url': url, 'info': info, 'direct': False, 'debridonly': True }) except: source_utils.scraper_error('2DDL') pass return sources except: source_utils.scraper_error('2DDL') return sources
def sources(self, url, hostDict, hostprDict): try: sources = [] if url is None: return sources if debrid.status() is False: return sources hostDict = hostprDict + hostDict data = urlparse.parse_qs(url) data = dict([(i, data[i][0]) if data[i] else (i, '') for i in data]) title = data['title'].replace('&', 'and') year = data['year'] query = '%s %s' % (title, year) query = re.sub('(\\\|/| -|:|;|\*|\?|"|\'|<|>|\|)', '', query) url = urlparse.urljoin(self.base_link, self.post_link) post = 'do=search&subaction=search&search_start=0&full_search=0&result_from=1&story=%s' % urllib.quote_plus( query) r = client.request(url, post=post) # log_utils.log('r = %s' % r, log_utils.LOGDEBUG) r = client.parseDOM(r, 'div', attrs={'class': 'box-out margin'}) # log_utils.log('r = %s' % r, log_utils.LOGDEBUG) # switch to client.parseDOM() to rid import r = [(dom_parser.parse_dom(i, 'div', attrs={'class': 'news-title'})) for i in r if data['imdb'] in i] r = [(dom_parser.parse_dom(i[0], 'a', req='href')) for i in r if i] r = [(i[0].attrs['href'], i[0].content) for i in r if i] for item in r: try: name = item[0] s = re.findall( '((?:\d+\.\d+|\d+\,\d+|\d+)\s*(?:GB|GiB|Gb|MB|MiB|Mb))', name) s = s[0] if s else '0' data = client.request(item[0]) data = dom_parser.parse_dom(data, 'div', attrs={'id': 'r-content'}) data = re.findall('\s*<b><a href="(.+?)".+?</a></b>', data[0].content, re.DOTALL) for url in data: try: try: qual = client.request(url) quals = re.findall( 'span class="file-title" id="file-title">(.+?)</span', qual) if quals == []: raise Exception() for q in quals: quality, info = source_utils.get_release_quality( q, url) except: quality = 'SD' info = [] url = client.replaceHTMLCodes(url) url = url.encode('utf-8') if any(x in url for x in ['.rar', '.zip', '.iso']): raise Exception() if not 'turbobit' in url: continue if url in str(sources): continue sources.append({ 'source': 'turbobit', 'quality': quality, 'language': 'en', 'url': url, 'info': info, 'direct': True, 'debridonly': True }) # log_utils.log('sources = %s' % sources, log_utils.LOGDEBUG) except: source_utils.scraper_error('ULTRAHDINDIR') pass except: source_utils.scraper_error('ULTRAHDINDIR') pass # log_utils.log('sources = %s' % sources, log_utils.LOGDEBUG) return sources except: source_utils.scraper_error('ULTRAHDINDIR') return sources
def sources(self, url, hostDict, hostprDict): try: sources = [] if url is None: return sources if debrid.status() is False: return sources data = urlparse.parse_qs(url) data = dict([(i, data[i][0]) if data[i] else (i, '') for i in data]) title = data['tvshowtitle'] if 'tvshowtitle' in data else data['title'] title = title.replace('&', 'and').replace('Special Victims Unit', 'SVU') hdlr = 'S%02dE%02d' % (int(data['season']), int(data['episode'])) if 'tvshowtitle' in data else data['year'] query = '%s %s' % (title, hdlr) query = re.sub('(\\\|/| -|:|;|\*|\?|"|\'|<|>|\|)', '', query) url = urlparse.urljoin(self.base_link, self.search_link.format(query[0].lower(), cleantitle.geturl(query))) # log_utils.log('url = %s' % url, log_utils.LOGDEBUG) r = client.request(url) if '<tbody' not in r: return sources r = client.parseDOM(r, 'tbody')[0] results = client.parseDOM(r, 'tr') posts = [i for i in results if 'magnet:' in i] try: next_page = [i for i in results if 'Next Page' in i] if next_page == []: raise Exception() page = client.parseDOM(next_page, 'a', ret='href', attrs={'title': 'Downloads | Page 2'})[0] r2 = client.request(self.base_link+page) results2 = client.parseDOM(r2, 'tr') posts += [i for i in results2 if 'magnet:' in i] except: pass for post in posts: post = post.replace(' ', ' ') links = client.parseDOM(post, 'a', ret='href') magnet = [i.replace('&', '&') for i in links if 'magnet:' in i][0] url = magnet.split('&tr')[0] if any(x in url.lower() for x in ['french', 'italian', 'spanish', 'truefrench', 'dublado', 'dubbed']): continue name = client.parseDOM(post, 'a', ret='title')[1] t = name.split(hdlr)[0].replace(data['year'], '').replace('(', '').replace(')', '').replace('&', 'and') if cleantitle.get(t) != cleantitle.get(title): continue if hdlr not in name: continue quality, info = source_utils.get_release_quality(name, url) try: size = re.findall('((?:\d+\,\d+\.\d+|\d+\.\d+|\d+\,\d+|\d+)\s*(?:GiB|MiB|GB|MB))', post)[0] div = 1 if size.endswith(('GB', 'GiB')) else 1024 size = float(re.sub('[^0-9|/.|/,]', '', size.replace(',', '.'))) / div size = '%.2f GB' % size info.append(size) except: pass info = ' | '.join(info) sources.append({'source': 'torrent', 'quality': quality, 'language': 'en', 'url': url, 'info': info, 'direct': False, 'debridonly': True}) return sources except: source_utils.scraper_error('MAGNETDL') return sources
def sources(self, url, hostDict, hostprDict): try: sources = [] if url is None: return sources if debrid.status() is False: raise Exception() data = urlparse.parse_qs(url) data = dict([(i, data[i][0]) if data[i] else (i, '') for i in data]) try: if not 'tvshowtitle' in data: raise Exception() links = [] f = [ 'S%02dE%02d' % (int(data['season']), int(data['episode'])) ] t = re.sub('(\\\|/| -|:|;|\*|\?|"|\'|<|>|\|)', '', data['tvshowtitle']) t = t.replace("&", "") q = self.search_link + urllib.quote_plus('%s %s' % (t, f[0])) q = urlparse.urljoin(self.base_link, q) result = client.request(q) print(q) result = json.loads(result) result = result['results'] except: links = result = [] for i in result: try: if not cleantitle.get(t) == cleantitle.get(i['showName']): raise Exception() y = i['release'] y = re.compile('[\.|\(|\[|\s](\d{4}|S\d*E\d*)[\.|\)|\]|\s]' ).findall(y)[-1] y = y.upper() if not any(x == y for x in f): raise Exception() quality = i['quality'] quality = quality.upper() size = i['size'] size = float(size) / 1024 size = '%.2f GB' % size if any(x in quality for x in ['HEVC', 'X265', 'H265']): info = '%s | HEVC' % size else: info = size if '1080P' in quality: quality = '1080p' elif '720P' in quality: quality = 'HD' else: quality = 'SD' url = i['links'] # for x in url.keys(): links.append({'url': url[x], 'quality': quality, 'info': info}) links = [] for x in url.keys(): links.append({'url': url[x], 'quality': quality}) for link in links: try: url = link['url'] quality2 = link['quality'] # url = url[1] # url = link if len(url) > 1: raise Exception() url = url[0].encode('utf-8') host = re.findall( '([\w]+[.][\w]+)$', urlparse.urlparse( url.strip().lower()).netloc)[0] if not host in hostprDict: raise Exception() host = host.encode('utf-8') sources.append({ 'source': host, 'quality': quality2, 'language': 'en', 'url': url, 'info': info, 'direct': False, 'debridonly': True }) except: pass except: pass return sources except: return sources
def sources(self, url, hostDict, hostprDict): sources = [] try: if url is None: return sources if debrid.status() is False: raise Exception() data = urlparse.parse_qs(url) data = dict([(i, data[i][0]) if data[i] else (i, '') for i in data]) post = {'query': data['imdb']} url = urlparse.urljoin(self.base_link, 'engine/ajax/search.php') r = self.scraper.post(url, data=post).content urls = client.parseDOM(r, 'a', ret='href') urls = [i for i in urls if not data['imdb'] in i] hostDict = hostprDict + hostDict links = [] for u in urls: try: data = self.scraper.get(u).content data = re.findall('</iframe>(.+?)QuoteEEnd--><br /><br', data, re.DOTALL)[0] links += re.findall( '''start--><b>(.+?)</b>.+?<b><a href=['"](.+?)['"]''', data, re.DOTALL) except Exception: pass links = [(i[0], i[1]) for i in links if not 'vip' in i[0].lower()] for name, url in links: try: name = re.sub('<.+?>', '', name) if '4K' in name: quality = '4K' elif '1080p' in name: quality = '1080p' elif '720p' in name: quality = '720p' else: quality = 'SD' info = [] if '3D' in name or '.3D.' in url: info.append('3D') quality = '1080p' if any(i in ['hevc', 'h265', 'x265'] for i in name): info.append('HEVC') info = ' | '.join(info) url = client.replaceHTMLCodes(url) url = url.encode('utf-8') if any(x in url for x in ['.rar', '.zip', '.iso', 'turk']): raise Exception() if 'ftp' in url: host = 'CDN' direct = True else: valid, host = source_utils.is_host_valid(url, hostDict) if not valid: raise Exception() host = host direct = False host = client.replaceHTMLCodes(host) host = host.encode('utf-8') sources.append({ 'source': host, 'quality': quality, 'language': 'en', 'url': url, 'info': info, 'direct': direct, 'debridonly': True }) except Exception: pass return sources except Exception: return sources
def sources(self, url, hostDict, hostprDict): try: sources = [] if url is None: return sources if debrid.status() is False: raise Exception() data = urlparse.parse_qs(url) data = dict([(i, data[i][0]) if data[i] else (i, '') for i in data]) title = data['tvshowtitle'] if 'tvshowtitle' in data else data[ 'title'] hdlr = 'S%02dE%02d' % (int(data['season']), int( data['episode'])) if 'tvshowtitle' in data else data['year'] query = '%s S%02dE%02d' % (data['tvshowtitle'], int(data['season']), int(data['episode'])) if \ 'tvshowtitle' in data else '%s' % (data['title']) url = self.search_link % urllib.quote_plus(query).lower() url = urlparse.urljoin(self.base_link, url) headers = {'Referer': url} r = self.scraper.get(url, headers=headers).content items = dom_parser2.parse_dom(r, 'h2') items = [ dom_parser2.parse_dom(i.content, 'a', req=['href', 'rel', 'data-wpel-link']) for i in items ] items = [(i[0].content, i[0].attrs['href']) for i in items] hostDict = hostprDict + hostDict for item in items: try: name = item[0] name = client.replaceHTMLCodes(name) query = query.lower().replace(' ', '-') if not query in item[1]: continue url = item[1] headers = {'Referer': url} r = self.scraper.get(url, headers=headers).content links = dom_parser2.parse_dom( r, 'a', req=['href', 'rel', 'data-wpel-link']) links = [i.attrs['href'] for i in links] for url in links: try: if hdlr in name.upper() and cleantitle.get( title) in cleantitle.get(name): fmt = re.sub( '(.+)(\.|\(|\[|\s)(\d{4}|S\d*E\d*|S\d*)(\.|\)|\]|\s)', '', name.upper()) fmt = re.split('\.|\(|\)|\[|\]|\s|\-', fmt) fmt = [i.lower() for i in fmt] if any( i.endswith(('subs', 'sub', 'dubbed', 'dub')) for i in fmt): raise Exception() if any(i in ['extras'] for i in fmt): raise Exception() quality, info = source_utils.get_release_quality( name, url) try: size = re.findall( '((?:\d+\.\d+|\d+\,\d+|\d+) (?:GB|GiB|MB|MiB))', name[2])[-1] div = 1 if size.endswith( ('GB', 'GiB')) else 1024 size = float( re.sub('[^0-9|/.|/,]', '', size)) / div size = '%.2f GB' % size info.append(size) except: pass info = ' | '.join(info) if not any(x in url for x in ['.rar', '.zip', '.iso']): url = client.replaceHTMLCodes(url) url = url.encode('utf-8') host = \ re.findall('([\w]+[.][\w]+)$', urlparse.urlparse(url.strip().lower()).netloc)[0] if host in hostDict: host = client.replaceHTMLCodes(host) host = host.encode('utf-8') sources.append({ 'source': host, 'quality': quality, 'language': 'en', 'url': url, 'info': info, 'direct': False, 'debridonly': True }) except: pass except: pass check = [i for i in sources if not i['quality'] == 'CAM'] if check: sources = check return sources except: return
def sources(self, url, hostDict, hostprDict): try: sources = [] if url == None: return sources if debrid.status() == False: raise Exception() data = urlparse.parse_qs(url) data = dict([(i, data[i][0]) if data[i] else (i, '') for i in data]) title = data['tvshowtitle'] if 'tvshowtitle' in data else data[ 'title'] hdlr = 'S%02dE%02d' % (int(data['season']), int( data['episode'])) if 'tvshowtitle' in data else data['year'] query = '%s S%02dE%02d' % ( data['tvshowtitle'], int(data['season']), int(data['episode'])) \ if 'tvshowtitle' in data else '%s %s' % (data['title'], data['year']) url = self.search_link % urllib.quote_plus(query) url = urlparse.urljoin(self.base_link, url).replace('-', '+') r = self.scraper.get(url).content if r == None and 'tvshowtitle' in data: season = re.search('S(.*?)E', hdlr) season = season.group(1) url = title r = self.scraper.get(url).content for loopCount in range(0, 2): if loopCount == 1 or (r == None and 'tvshowtitle' in data): r = self.scraper.get(url).content posts = client.parseDOM(r, "table", attrs={"class": "download"}) hostDict = hostprDict + hostDict items = [] for post in posts: try: u = client.parseDOM(post, 'a', ret='href') for i in u: try: name = str(i) items.append(name) except: pass except: pass if len(items) > 0: break for item in items: try: info = [] i = str(item) i = self.base_link + i r = self.scraper.get(i).content u = client.parseDOM(r, "div", attrs={"class": "dl-links"}) for t in u: r = re.compile( 'a href=".+?" rel=".+?">(.+?)<').findall(t) for url in r: if any(x in url for x in ['.rar', '.zip', '.iso']): raise Exception() quality, info = source_utils.get_release_quality( url) valid, host = source_utils.is_host_valid( url, hostDict) sources.append({ 'source': host, 'quality': quality, 'language': 'en', 'url': url, 'info': info, 'direct': False, 'debridonly': True }) except: pass check = [i for i in sources if not i['quality'] == 'CAM'] if check: sources = check return sources except: return
def sources(self, url, hostDict, hostprDict): try: sources = [] if url is None: return sources if debrid.status() is False: raise Exception() data = urlparse.parse_qs(url) data = dict([(i, data[i][0]) if data[i] else (i, '') for i in data]) title = data['tvshowtitle'] if 'tvshowtitle' in data else data['title'] hdlr = 'S%02dE%02d' % (int(data['season']), int(data['episode'])) if 'tvshowtitle' in data else data['year'] category = '+category%3ATV' if 'tvshowtitle' in data else '+category%3AMovies' query = '%s S%02dE%02d' % ( data['tvshowtitle'], int(data['season']), int(data['episode'])) if 'tvshowtitle' in data else '%s %s' % ( data['title'], data['year']) query = re.sub('(\\\|/| -|:|;|\*|\?|"|<|>|\|)', ' ', query) url = self.search_link % urllib.quote_plus(query) url = urlparse.urljoin(self.base_link, url) + str(category) html = client.request(url) html = html.replace(' ', ' ') try: results = \ client.parseDOM(html, 'table', attrs={'class': 'table table-condensed table-torrents vmiddle'})[0] except Exception: return sources rows = re.findall('<tr(.+?)</tr>', results, re.DOTALL) if rows is None: return sources for entry in rows: try: try: name = re.findall('<a class=".+?>(.+?)</a>', entry, re.DOTALL)[0] name = client.replaceHTMLCodes(name).replace('<hl>', '').replace('</hl>', '') if not cleantitle.get(title) in cleantitle.get(name): continue except Exception: continue y = re.findall('[\.|\(|\[|\s](\d{4}|S\d*E\d*|S\d*)[\.|\)|\]|\s]', name)[-1].upper() if not y == hdlr: continue try: seeders = int( re.findall('class="progress prog trans90" title="Seeders: (.+?) \|', entry, re.DOTALL)[0]) except Exception: continue if self.min_seeders > seeders: continue try: link = 'magnet:%s' % (re.findall('href="magnet:(.+?)"', entry, re.DOTALL)[0]) link = str(client.replaceHTMLCodes(link).split('&tr')[0]) except Exception: continue quality, info = source_utils.get_release_quality(name, name) try: size = re.findall('((?:\d+\.\d+|\d+\,\d+|\d+)\s*(?:GB|GiB|MB|MiB))', entry)[-1] div = 1 if size.endswith(('GB', 'GiB')) else 1024 size = float(re.sub('[^0-9|/.|/,]', '', size)) / div size = '%.2f GB' % size info.append(size) except Exception: pass info = ' | '.join(info) sources.append( {'source': 'Torrent', 'quality': quality, 'language': 'en', 'url': link, 'info': info, 'direct': False, 'debridonly': True}) except Exception: continue check = [i for i in sources if not i['quality'] == 'CAM'] if check: sources = check return sources except Exception: return self._sources
def sources(self, url, hostDict, hostprDict): try: sources = [] if url is None: return sources if debrid.status() == False: raise Exception() data = urlparse.parse_qs(url) data = dict([(i, data[i][0]) if data[i] else (i, '') for i in data]) title = data['tvshowtitle'] if 'tvshowtitle' in data else data[ 'title'] hdlr = 'S%02dE%02d' % (int(data['season']), int( data['episode'])) if 'tvshowtitle' in data else data['year'] query = '%s S%02dE%02d' % ( data['tvshowtitle'], int(data['season']), int(data['episode'])) if 'tvshowtitle' in data else '%s %s' % ( data['title'], data['year']) query = re.sub('(\\\|/| -|:|;|\*|\?|"|\'|<|>|\|)', ' ', query) url = self.search_link % urllib.quote_plus(query) url = urlparse.urljoin(self.base_link, url) html = self.scraper.get(url).content posts = client.parseDOM(html, 'item') hostDict = hostprDict + hostDict items = [] for post in posts: try: t = client.parseDOM(post, 'title')[0] u = client.parseDOM(post, 'enclosure', ret='url') s = re.search( '((?:\d+\.\d+|\d+\,\d+|\d+)\s*(?:GB|GiB|MB|MiB))', post) s = s.groups()[0] if s else '0' items += [(t, i, s) for i in u] except: pass for item in items: try: url = item[1] if any(x in url for x in ['.rar', '.zip', '.iso', '.part']): raise Exception() url = client.replaceHTMLCodes(url) url = url.encode('utf-8') valid, host = source_utils.is_host_valid(url, hostDict) if not valid: raise Exception() host = client.replaceHTMLCodes(host) host = host.encode('utf-8') name = item[0] name = client.replaceHTMLCodes(name) t = re.sub( '(\.|\(|\[|\s)(\d{4}|S\d*E\d*|S\d*|3D)(\.|\)|\]|\s|)(.+|)', '', name, flags=re.I) if not cleantitle.get(t) == cleantitle.get(title): raise Exception() y = re.findall( '[\.|\(|\[|\s](\d{4}|S\d*E\d*|S\d*)[\.|\)|\]|\s]', name)[-1].upper() if not y == hdlr: raise Exception() quality, info = source_utils.get_release_quality(name, url) try: size = re.findall( '((?:\d+\.\d+|\d+\,\d+|\d+)\s*(?:GB|GiB|MB|MiB))', item[2])[-1] div = 1 if size.endswith(('GB', 'GiB')) else 1024 size = float(re.sub('[^0-9|/.|/,]', '', size)) / div size = '%.2f GB' % size info.append(size) except: pass info = ' | '.join(info) sources.append({ 'source': host, 'quality': quality, 'language': 'en', 'url': url, 'info': info, 'direct': False, 'debridonly': True }) except: pass check = [i for i in sources if not i['quality'] == 'CAM'] if check: sources = check return sources except: return sources
def sources(self, url, hostDict, hostprDict): try: sources = [] if url is None: return sources if debrid.status() is False: raise Exception() data = urlparse.parse_qs(url) data = dict([(i, data[i][0]) if data[i] else (i, '') for i in data]) title = data['tvshowtitle'] if 'tvshowtitle' in data else data[ 'title'] hdlr = 'S%02dE%02d' % (int(data['season']), int( data['episode'])) if 'tvshowtitle' in data else data['year'] query = '%s S%02dE%02d' % ( data['tvshowtitle'], int(data['season']), int(data['episode']) ) if 'tvshowtitle' in data else '%s' % (data['imdb']) query = re.sub('(\\\|/| -|:|;|\*|\?|"|\'|<|>|\|)', ' ', query) s = self.scraper.get(self.base_link).content s = re.findall('\'(http.+?)\'', s) + re.findall('\"(http.+?)\"', s) s = [ i for i in s if urlparse.urlparse(self.base_link).netloc in i and len(i.strip('/').split('/')) > 3 ] s = s[0] if s else urlparse.urljoin(self.base_link, 'vv') s = s.strip('/') url = s + self.search_link % urllib.quote_plus(query) r = self.scraper.get(url).content r = client.parseDOM(r, 'h2') l = zip(client.parseDOM(r, 'a', ret='href'), client.parseDOM(r, 'a', ret='title')) r = [(i[0], i[1], re.sub('(\.|\(|\[|\s)(\d{4}|3D)(\.|\)|\]|\s|)(.+|)', '', i[1]), re.findall('[\.|\(|\[|\s](\d{4}|)([\.|\)|\]|\s|].+)', i[1])) for i in l] r = [(i[0], i[1], i[2], i[3][0][0], i[3][0][1]) for i in r if i[3]] r = [(i[0], i[1], i[2], i[3], re.split('\.|\(|\)|\[|\]|\s|\-', i[4])) for i in r] r = [ i for i in r if cleantitle.get(title) == cleantitle.get(i[2]) and data['year'] == i[3] ] r = [ i for i in r if not any(x in i[4] for x in [ 'HDCAM', 'CAM', 'DVDR', 'DVDRip', 'DVDSCR', 'HDTS', 'TS', '3D' ]) ] r = [i for i in r if '1080p' in i[4] ][:1] + [i for i in r if '720p' in i[4]][:1] if 'tvshowtitle' in data: posts = [(i[1], i[0]) for i in l] else: posts = [(i[1], i[0]) for i in l] hostDict = hostprDict + hostDict items = [] for post in posts: try: t = post[0] u = self.scraper.get(post[1]).content u = re.findall('"(http.+?)"', u) + re.findall( '"(http.+?)"', u) u = [i for i in u if not '/embed/' in i] u = [i for i in u if not 'youtube' in i] items += [(t, i) for i in u] except: pass seen_urls = set() for item in items: try: name = item[0] name = client.replaceHTMLCodes(name) t = re.sub( '(\.|\(|\[|\s)(\d{4}|S\d*E\d*|S\d*|3D)(\.|\)|\]|\s|)(.+|)', '', name) if not cleantitle.get(t) == cleantitle.get(title): raise Exception() y = re.findall( '[\.|\(|\[|\s](\d{4}|S\d*E\d*|S\d*)[\.|\)|\]|\s]', name)[-1].upper() if not y == hdlr: raise Exception() url = item[1] if url in seen_urls: continue seen_urls.add(url) quality, info = source_utils.get_release_quality(url, name) try: size = re.findall( '((?:\d+\.\d+|\d+\,\d+|\d+) (?:GB|GiB|MB|MiB))', item[2])[-1] div = 1 if size.endswith(('GB', 'GiB')) else 1024 size = float(re.sub('[^0-9|/.|/,]', '', size)) / div size = '%.2f GB' % size info.append(size) except: pass info = ' | '.join(info) if any(x in url for x in ['.rar', '.zip', '.iso']): raise Exception() url = client.replaceHTMLCodes(url) url = url.encode('utf-8') host = re.findall( '([\w]+[.][\w]+)$', urlparse.urlparse(url.strip().lower()).netloc)[0] if not host in hostDict: raise Exception() host = client.replaceHTMLCodes(host) host = host.encode('utf-8') sources.append({ 'source': host, 'quality': quality, 'language': 'en', 'url': url, 'info': info, 'direct': False, 'debridonly': True }) except: pass check = [i for i in sources if not i['quality'] == 'CAM'] if check: sources = check return sources except: return