def tvshow(self, imdb, tvdb, tvshowtitle, localtvshowtitle, aliases, year): try: query = self.tvsearch_link % quote_plus( cleantitle.query(tvshowtitle)) query = urljoin(self.base_link, query.lower()) result = client.request(query, referer=self.base_link) result = client.parseDOM(result, 'div', attrs={'class': 'index_item.+?'}) result = [(dom.parse_dom(i, 'a', req=['href', 'title'])[0]) for i in result if i] if not result: return result = [( i.attrs['href'] ) for i in result if cleantitle.get(tvshowtitle) == cleantitle.get( re.sub( '(\.|\(|\[|\s)(\d{4}|S\d+E\d+|S\d+|3D)(\.|\)|\]|\s|)(.+|)', '', i.attrs['title'], flags=re.I))] if not result: return else: result = result[0] url = client.replaceHTMLCodes(result) try: url = url.encode('utf-8') except: pass return url except: source_utils.scraper_error('PRIMEWIRE') return
def get_sources(self, url): try: r = client.request(url) if not r: return div = client.parseDOM(r, 'div', attrs={'id': 'div2child'}) for row in div: row = client.parseDOM(r, 'div', attrs={'class': 'resultdivbotton'}) if not row: return for post in row: hash = re.findall('<div id="hideinfohash.+?" class="hideinfohash">(.+?)<', post, re.DOTALL)[0] name = re.findall('<div id="hidename.+?" class="hideinfohash">(.+?)<', post, re.DOTALL)[0] name = unquote_plus(name) name = source_utils.clean_name(self.title, name) if source_utils.remove_lang(name, self.episode_title): continue url = 'magnet:?xt=urn:btih:%s&dn=%s' % (hash, name) if url in str(self.sources): continue if not source_utils.check_title(self.title, self.aliases, name, self.hdlr, self.year): continue # filter for episode multi packs (ex. S01E01-E17 is also returned in query) if self.episode_title: if not source_utils.filter_single_episodes(self.hdlr, name): continue try: seeders = int(re.findall('<div class="resultdivbottonseed">([0-9]+|[0-9]+,[0-9]+)<', post, re.DOTALL)[0].replace(',', '')) if self.min_seeders > seeders: continue except: seeders = 0 pass quality, info = source_utils.get_release_quality(name, url) try: size = re.findall('<div class="resultdivbottonlength">(.+?)<', post)[0] dsize, isize = source_utils._size(size) info.insert(0, isize) except: dsize = 0 pass info = ' | '.join(info) self.sources.append({'source': 'torrent', 'seeders': seeders, 'hash': hash, 'name': name, 'quality': quality, 'language': 'en', 'url': url, 'info': info, 'direct': False, 'debridonly': True, 'size': dsize}) except: source_utils.scraper_error('IDOPE') pass
def sources(self, url, hostDict, hostprDict): self.sources = [] try: scraper = cfscrape.create_scraper() if url is None: return self.sources if debrid.status() is False: return self.sources data = 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.aliases = data['aliases'] self.episode_title = data[ 'title'] if 'tvshowtitle' in data else None 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('[^A-Za-z0-9\s\.-]+', '', query) urls = [] url = self.search_link % quote_plus(query) url = urljoin(self.base_link, url) urls.append(url) # urls.append('%s%s' % (url, '&page=2')) # next page seems broken right now # urls.append('%s%s' % (url, '&page=3')) # log_utils.log('urls = %s' % urls, log_utils.LOGDEBUG) links = [] for x in urls: r = scraper.get(x).content if not r: continue list = client.parseDOM(r, 'tr', attrs={'class': 'tlr'}) list += client.parseDOM(r, 'tr', attrs={'class': 'tlz'}) for item in list: links.append(item) threads = [] for link in links: threads.append(workers.Thread(self.get_sources, link)) [i.start() for i in threads] [i.join() for i in threads] return self.sources except: source_utils.scraper_error('EXTRATORRENT') return self.sources
def sources_packs(self, url, hostDict, hostprDict, search_series=False, total_seasons=None, bypass_filter=False): self.sources = [] try: self.search_series = search_series self.total_seasons = total_seasons self.bypass_filter = bypass_filter if url is None: return self.sources if debrid.status() is False: return self.sources data = parse_qs(url) data = dict([(i, data[i][0]) if data[i] else (i, '') for i in data]) self.title = data['tvshowtitle'].replace('&', 'and').replace( 'Special Victims Unit', 'SVU') self.aliases = data['aliases'] self.imdb = data['imdb'] self.year = data['year'] self.season_x = data['season'] self.season_xx = self.season_x.zfill(2) query = re.sub('[^A-Za-z0-9\s\.-]+', '', self.title) queries = [ self.search_link % quote_plus(query + ' S%s' % self.season_xx), self.search_link % quote_plus(query + ' Season %s' % self.season_x) ] if search_series: queries = [ self.search_link % quote_plus(query + ' Season'), self.search_link % quote_plus(query + ' Complete') ] threads = [] for url in queries: link = urljoin(self.base_link, url) threads.append(workers.Thread(self.get_sources_packs, link)) [i.start() for i in threads] [i.join() for i in threads] return self.sources except: source_utils.scraper_error('SKYTORRENTS') return self.sources
def tvshow(self, imdb, tvdb, tvshowtitle, localtvshowtitle, aliases, year): try: url = { 'imdb': imdb, 'tvdb': tvdb, 'tvshowtitle': tvshowtitle, 'year': year } url = urlencode(url) return url except: source_utils.scraper_error('WATCHEPISODES') return
def movie(self, imdb, title, localtitle, aliases, year): try: url = { 'imdb': imdb, 'title': title, 'aliases': aliases, 'year': year } url = urlencode(url) return url except: source_utils.scraper_error('EXTRATORRENT') return
def episode(self, url, imdb, tvdb, title, premiered, season, episode): try: if url is None: return url = 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 = urlencode(url) return url except: source_utils.scraper_error('EXTRATORRENT') return
def get_sources(self, row): try: if 'magnet' not in row: return url = re.findall('href="(magnet:.+?)"', row, re.DOTALL)[0] url = unquote_plus(url).split('&tr')[0].replace('&', '&').replace(' ', '.') if url in str(self.sources): return hash = re.compile('btih:(.*?)&').findall(url)[0] name = url.split('&dn=')[1] name = source_utils.clean_name(self.title, name) if source_utils.remove_lang(name, self.episode_title): return if not source_utils.check_title(self.title, self.aliases, name, self.hdlr, self.year): return # filter for episode multi packs (ex. S01E01-E17 is also returned in query) if self.episode_title: if not source_utils.filter_single_episodes(self.hdlr, name): return try: seeders = int(re.findall('<span style="color:#008000"><strong>\s*([0-9]+)\s*</strong>', row, re.DOTALL)[0].replace(',', '')) if self.min_seeders > seeders: return except: seeders = 0 pass quality, info = source_utils.get_release_quality(name, url) try: size = re.findall('((?:\d+\,\d+\.\d+|\d+\.\d+|\d+\,\d+|\d+)\s*(?:GB|GiB|Gb|MB|MiB|Mb))', row, re.DOTALL)[0] dsize, isize = source_utils._size(size) info.insert(0, isize) except: dsize = 0 pass info = ' | '.join(info) self.sources.append({'source': 'torrent', 'seeders': seeders, 'hash': hash, 'name': name, 'quality': quality, 'language': 'en', 'url': url, 'info': info, 'direct': False, 'debridonly': True, 'size': dsize}) except: source_utils.scraper_error('MAGNET4YOU') pass
def sources(self, url, hostDict, hostprDict): self.sources = [] try: if url is None: return self.sources if debrid.status() is False: return self.sources data = 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.aliases = data['aliases'] self.episode_title = data[ 'title'] if 'tvshowtitle' in data else None 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('[^A-Za-z0-9\s\.-]+', '', query) url = self.search_link % quote_plus(query) url = urljoin(self.base_link, url) # log_utils.log('url = %s' % url, log_utils.LOGDEBUG) try: r = client.request(url, timeout='5') if r is None: return self.sources links = re.findall('<a href=(/torrent/.+?)>', r, re.DOTALL) threads = [] for link in links: threads.append(workers.Thread(self.get_sources, link)) [i.start() for i in threads] [i.join() for i in threads] return self.sources except: source_utils.scraper_error('TORLOCK') return self.sources except: source_utils.scraper_error('TORLOCK') return self.sources
def episode(self, url, imdb, tvdb, title, premiered, season, episode): try: if url is None: return url = urljoin(self.base_link, url) if url.startswith('/') else url url = url.split('online.html')[0] url = '%s%s-online.html' % (url, 'season-%01d-episode-%01d' % (int(season), int(episode))) url = client.replaceHTMLCodes(url) try: url = url.encode('utf-8') except: pass return url except: source_utils.scraper_error('PRIMEWIRE') return
def sources(self, url, hostDict, hostprDict): self.sources = [] try: if url is None: return self.sources if debrid.status() is False: return self.sources data = 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.aliases = data['aliases'] self.episode_title = data[ 'title'] if 'tvshowtitle' in data else None 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('[^A-Za-z0-9\s\.-]+', '', query) urls = [] url = self.search_link % quote_plus(query) url = urljoin(self.base_link, url) urls.append(url) # urls.append(url.replace('page=0', 'page=40')) # server response time WAY to slow to parse 2 pages deep, site sucks. # log_utils.log('urls = %s' % urls, log_utils.LOGDEBUG) threads = [] for url in urls: threads.append(workers.Thread(self.get_sources, url)) [i.start() for i in threads] [i.join() for i in threads] return self.sources except: source_utils.scraper_error('ISOHUNT2') return self.sources
def resolve(self, url): try: if '/stream/' in url or '/watch/' in url: r = client.request(url, referer=self.base_link) link = client.parseDOM(r, 'a', ret='data-href', attrs={'id': 'iframe_play'})[0] else: try: data = client.request(url, referer=self.base_link) data = re.findall(r'\s*(eval.+?)\s*</script', data, re.DOTALL)[0] link = jsunpack.unpack(data) link = link.replace('\\', '') if 'eval' in link: link = jsunpack.unpack(link) link = link.replace('\\', '') host = re.findall('hosted=\'(.+?)\';var', link, re.DOTALL)[0] if 'streamango' in host: loc = re.findall('''loc\s*=\s*['"](.+?)['"]''', link, re.DOTALL)[0] link = 'https://streamango.com/embed/{0}'.format(loc) elif 'openload' in host: loc = re.findall('''loc\s*=\s*['"](.+?)['"]''', link, re.DOTALL)[0] link = 'https://openload.co/embed/{0}'.format(loc) else: link = re.findall('''loc\s*=\s*['"](.+?)['"]\;''', re.DOTALL)[0] except: source_utils.scraper_error('PRIMEWIRE') link = client.request(url, output='geturl', timeout=10) if link == url: return else: return link return link except: source_utils.scraper_error('PRIMEWIRE') return
def sources(self, url, hostDict, hostprDict): self.sources = [] try: if url is None: return self.sources if debrid.status() is False: return self.sources data = 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.aliases = data['aliases'] self.episode_title = data['title'] if 'tvshowtitle' in data else None 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('[^A-Za-z0-9\s\.-]+', '', query) url = self.search_link % quote_plus(query) url = urljoin(self.base_link, url) # log_utils.log('url = %s' % url, log_utils.LOGDEBUG) r = client.request(url) if not r: return self.sources rows = client.parseDOM(r, 'div', attrs={'id': 'profile1'}) threads = [] for row in rows: threads.append(workers.Thread(self.get_sources, row)) [i.start() for i in threads] [i.join() for i in threads] return self.sources except: source_utils.scraper_error('MAGNET4YOU') return self.sources
def sources(self, url, hostDict, hostprDict): scraper = cfscrape.create_scraper() sources = [] try: if url is None: return sources if debrid.status() is False: return sources data = parse_qs(url) data = dict([(i, data[i][0]) if data[i] else (i, '') for i in data]) title = data['title'] aliases = data['aliases'] episode_title = data['title'] if 'tvshowtitle' in data else None year = data['year'] query = re.sub('[^A-Za-z0-9\s\.-]+', '', title) url = self.search_link % quote_plus(query) url = urljoin(self.base_link, url) # log_utils.log('url = %s' % url, log_utils.LOGDEBUG) try: r = scraper.get(url).content if not r: return sources if any(value in str(r) for value in [ 'No movies found', 'something went wrong', 'Connection timed out' ]): return sources r = json.loads(r) id = '' for i in r: if i['original_title'] == title and i[ 'release_date'] == year: id = i['id'] break if id == '': return sources link = '%s%s%s' % (self.base_link, '/movies/torrents?id=', id) result = scraper.get(link).content if 'magnet' not in result: return sources result = re.sub(r'\n', '', result) links = re.findall( r'<tr>.*?<a title="Download:\s*(.+?)"href="(magnet:.+?)">.*?title="File Size">\s*(.+?)\s*</td>.*?title="Seeds">([0-9]+|[0-9]+,[0-9]+)\s*<', result) for link in links: name = link[0] name = unquote_plus(name) name = source_utils.clean_name(title, name) if source_utils.remove_lang(name, episode_title): continue if not source_utils.check_title(title.replace('&', 'and'), aliases, name, year, year): continue url = link[1] try: url = unquote_plus(url).decode('utf8').replace( '&', '&').replace(' ', '.') except: url = unquote_plus(url).replace('&', '&').replace(' ', '.') url = url.split('&tr')[0] hash = re.compile('btih:(.*?)&').findall(url)[0] quality, info = source_utils.get_release_quality(name, url) try: size = link[2] dsize, isize = source_utils._size(size) info.insert(0, isize) except: dsize = 0 pass info = ' | '.join(info) try: seeders = int(link[3].replace(',', '')) if self.min_seeders > seeders: continue except: seeders = 0 pass sources.append({ 'source': 'torrent', 'seeders': seeders, 'hash': hash, 'name': name, 'quality': quality, 'language': 'en', 'url': url, 'info': info, 'direct': False, 'debridonly': True, 'size': dsize }) return sources except: source_utils.scraper_error('MOVIEMAGNET') return sources except: source_utils.scraper_error('MOVIEMAGNET') return sources
def get_sources(self, url): try: r = client.request(url, timeout='10') if not r: return posts = client.parseDOM(r, 'tbody')[0] posts = client.parseDOM(posts, 'tr') for post in posts: post = re.sub(r'\n', '', post) post = re.sub(r'\t', '', post) links = re.compile( '<a href="(/torrent_details/.+?)"><span>(.+?)</span>.*?<td class="size-row">(.+?)</td><td class="sn">([0-9]+)</td>' ).findall(post) for items in links: # item[1] does not contain full info like the &dn= portion of magnet link = urljoin(self.base_link, items[0]) link = client.request(link, timeout='10') if not link: continue magnet = re.compile('(magnet.+?)"').findall(link)[0] url = unquote_plus(magnet).replace('&', '&').replace(' ', '.') url = url.split('&tr')[0] name = unquote_plus(url.split('&dn=')[1]) name = source_utils.clean_name(self.title, name) if source_utils.remove_lang(name, self.episode_title): continue if not source_utils.check_title(self.title, self.aliases, name, self.hdlr, self.year): continue hash = re.compile('btih:(.*?)&').findall(url)[0] # filter for episode multi packs (ex. S01E01-E17 is also returned in query) if self.episode_title: if not source_utils.filter_single_episodes( self.hdlr, name): continue try: seeders = int(items[3].replace(',', '')) if self.min_seeders > seeders: continue except: seeders = 0 pass quality, info = source_utils.get_release_quality(name, url) try: size = re.findall( '((?:\d+\,\d+\.\d+|\d+\.\d+|\d+\,\d+|\d+)\s*(?:GB|GiB|Gb|MB|MiB|Mb))', items[2])[0] dsize, isize = source_utils._size(size) info.insert(0, isize) except: dsize = 0 pass info = ' | '.join(info) self.sources.append({ 'source': 'torrent', 'seeders': seeders, 'hash': hash, 'name': name, 'quality': quality, 'language': 'en', 'url': url, 'info': info, 'direct': False, 'debridonly': True, 'size': dsize }) except: source_utils.scraper_error('ISOHUNT2') pass
def sources(self, url, hostDict, hostprDict): try: sources = [] if url is None: return sources if debrid.status() is False: return sources data = 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') aliases = data['aliases'] episode_title = data['title'] if 'tvshowtitle' in data else None hdlr = 'S%02dE%02d' % (int(data['season']), int( data['episode'])) if 'tvshowtitle' in data else ('(' + data['year'] + ')') # query = '%s %s' % (title, hdlr) #site now fails with year in query query = title query = re.sub('[^A-Za-z0-9\s\.-]+', '', query) if 'tvshowtitle' in data: url = self.show_link % query.replace(' ', '-') else: url = self.search_link % quote_plus(query) url = urljoin(self.base_link, url) # log_utils.log('url = %s' % url, __name__, log_utils.LOGDEBUG) r = client.request(url) if not r: return sources if 'No results were found' in r: return sources r = client.parseDOM(r, 'div', attrs={'class': 'card'}) for i in r: url = re.compile('href="(magnet.+?)\s*?"').findall(i)[0] try: url = unquote_plus(url).decode('utf8').replace( '&', '&').replace(' ', '.') except: url = unquote_plus(url).replace('&', '&').replace(' ', '.') url = url.split('&tr=')[0].replace(' ', '.') hash = re.compile('btih:(.*?)&').findall(url)[0] name = url.split('&dn=')[1] name = source_utils.clean_name(title, name) if source_utils.remove_lang(name, episode_title): continue if not source_utils.check_title( title, aliases, name, hdlr.replace('(', '').replace(')', ''), data['year']): continue seeders = 0 # seeders not available on topnow quality, info = source_utils.get_release_quality(name, url) try: size = re.findall( '((?:\d+\.\d+|\d+\,\d+|\d+)\s*(?:GB|GiB|MB|MiB))', i )[-1] # file size is no longer available on topnow's new site dsize, isize = source_utils._size(size) info.insert(0, isize) except: dsize = 0 pass info = ' | '.join(info) sources.append({ 'source': 'torrent', 'seeders': seeders, 'hash': hash, 'name': name, 'quality': quality, 'language': 'en', 'url': url, 'info': info, 'direct': False, 'debridonly': True, 'size': dsize }) return sources except: source_utils.scraper_error('TOPNOW') return sources
def get_sources(self, link): try: url = 'magnet:%s' % (re.findall('a href="magnet:(.+?)"', link, re.DOTALL)[0]) url = unquote_plus(url).split('&tr')[0].replace('&', '&').replace( ' ', '.') url = source_utils.strip_non_ascii_and_unprintable(url) if url in str(self.sources): return hash = re.compile('btih:(.*?)&').findall(url)[0] name = url.split('&dn=')[1] name = source_utils.clean_name(self.title, name) if source_utils.remove_lang(name, self.episode_title): return if not source_utils.check_title(self.title, self.aliases, name, self.hdlr, self.year): return # filter for episode multi packs (ex. S01E01-E17 is also returned in query) if self.episode_title: if not source_utils.filter_single_episodes(self.hdlr, name): return try: seeders = int( client.parseDOM(link, 'td', attrs={'class': 'sy'})[0].replace(',', '')) if self.min_seeders > seeders: return except: seeders = 0 pass 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))', link)[0] dsize, isize = source_utils._size(size) info.insert(0, isize) except: source_utils.scraper_error('EXTRATORRENT') dsize = 0 pass info = ' | '.join(info) self.sources.append({ 'source': 'torrent', 'seeders': seeders, 'hash': hash, 'name': name, 'quality': quality, 'language': 'en', 'url': url, 'info': info, 'direct': False, 'debridonly': True, 'size': dsize }) except: source_utils.scraper_error('EXTRATORRENT') pass
def sources(self, url, hostDict, hostprDict): sources = [] try: if url is None: return sources data = parse_qs(url) data = dict([(i, data[i][0]) if data[i] else (i, '') for i in data]) title = data['tvshowtitle'] hdlr = 's%02de%02d' % (int(data['season']), int(data['episode'])) query = quote_plus(cleantitle.getsearch(title)) surl = urljoin(self.base_link, self.search_link % query) # log_utils.log('surl = %s' % surl, log_utils.LOGDEBUG) r = client.request(surl, XHR=True) r = json.loads(r) r = r['series'] for i in r: tit = i['value'] if cleantitle.get(title) != cleantitle.get(tit): continue slink = i['seo'] slink = urljoin(self.base_link, slink) r = client.request(slink) if not data['imdb'] in r: continue data = client.parseDOM(r, 'div', {'class': 'el-item\s*'}) epis = [ client.parseDOM(i, 'a', ret='href')[0] for i in data if i ] epis = [i for i in epis if hdlr in i.lower()][0] r = client.request(epis) links = client.parseDOM(r, 'a', ret='data-actuallink') for url in links: try: valid, host = source_utils.is_host_valid(url, hostDict) if not valid: continue sources.append({ 'source': host, 'quality': 'SD', 'info': '', 'language': 'en', 'url': url, 'direct': False, 'debridonly': False }) except: source_utils.scraper_error('WATCHEPISODES') return sources return sources except: source_utils.scraper_error('WATCHEPISODES') return sources
def sources(self, url, hostDict, hostprDict): sources = [] try: if url is None: return sources url = urljoin(self.base_link, url) if not url.startswith('http') else url result = client.request(url) data = re.findall(r'\s*(eval.+?)\s*</script', result, re.DOTALL)[1] data = jsunpack.unpack(data).replace('\\', '') patern = '''rtv='(.+?)';var aa='(.+?)';var ba='(.+?)';var ca='(.+?)';var da='(.+?)';var ea='(.+?)';var fa='(.+?)';var ia='(.+?)';var ja='(.+?)';var ka='(.+?)';''' links_url = re.findall(patern, data, re.DOTALL)[0] slug = 'slug={}'.format(url.split('/')[-1]) links_url = self.base_link + [''.join(links_url)][0].replace( 'slug=', slug) links = client.request(links_url) links = client.parseDOM(links, 'tbody') for i in links: try: data = [(client.parseDOM(i, 'a', ret='href')[0], client.parseDOM(i, 'span', attrs={'class': 'version_host'})[0])][0] url = urljoin(self.base_link, data[0]) url = client.replaceHTMLCodes(url) try: url = url.encode('utf-8') except: pass host = data[1] valid, host = source_utils.is_host_valid(host, hostDict) if not valid: continue quality = client.parseDOM(i, 'span', ret='class')[0] quality, info = source_utils.get_release_quality( quality, url) sources.append({ 'source': host, 'quality': quality, 'info': '', 'language': 'en', 'url': url, 'direct': False, 'debridonly': False }) except: source_utils.scraper_error('PRIMEWIRE') pass return sources except: source_utils.scraper_error('PRIMEWIRE') return sources
def get_sources_packs(self, url): try: r = client.request(url, timeout='5') if not r: return r = client.parseDOM(r, 'table', attrs={'class': 'tmain'})[0] links = re.findall('<a href="(/torrent/.+?)">(.+?)</a>', r, re.DOTALL) for link in links: try: url = link[0].encode('ascii', errors='ignore').decode('ascii', errors='ignore').replace(' ', ' ') except: url = link[0].replace(' ', ' ') if '/torrent/' not in url: continue try: name = link[1].encode('ascii', errors='ignore').decode('ascii', errors='ignore').replace(' ', '.') except: name = link[1].replace(' ', '.') if '<span' in name: nam = name.split('<span')[0].replace(' ', '.') span = client.parseDOM(name, 'span')[0].replace('-', '.') name = '%s%s' % (nam, span) name = source_utils.clean_name(self.title, name) if source_utils.remove_lang(name): continue if not self.search_series: if not self.bypass_filter: if not source_utils.filter_season_pack(self.title, self.aliases, self.year, self.season_x, name): continue package = 'season' elif self.search_series: if not self.bypass_filter: valid, last_season = source_utils.filter_show_pack(self.title, self.aliases, self.imdb, self.year, self.season_x, name, self.total_seasons) if not valid: continue else: last_season = self.total_seasons package = 'show' if not url.startswith('http'): link = urljoin(self.base_link, url) link = client.request(link, timeout='5') if link is None: continue hash = re.findall('<b>Infohash</b></td><td valign=top>(.+?)</td>', link, re.DOTALL)[0] url = 'magnet:?xt=urn:btih:%s&dn=%s' % (hash, name) if url in str(self.sources): continue try: seeders = int(re.findall('<b>Swarm:</b></td><td valign=top><font color=red>([0-9]+)</font>', link, re.DOTALL)[0].replace(',', '')) if self.min_seeders > seeders: # site does not seem to report seeders continue except: seeders = 0 pass 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))', link)[0] dsize, isize = source_utils._size(size) info.insert(0, isize) except: dsize = 0 pass info = ' | '.join(info) item = {'source': 'torrent', 'seeders': seeders, 'hash': hash, 'name': name, 'quality': quality, 'language': 'en', 'url': url, 'info': info, 'direct': False, 'debridonly': True, 'size': dsize, 'package': package} if self.search_series: item.update({'last_season': last_season}) self.sources.append(item) except: source_utils.scraper_error('TORRENTFUNK') pass
def get_sources_packs(self, link): # log_utils.log('link = %s' % str(link), __name__, log_utils.LOGDEBUG) try: r = client.request(link) if not r: return if '<tbody' not in r: return posts = client.parseDOM(r, 'tbody')[0] posts = client.parseDOM(posts, 'tr') except: source_utils.scraper_error('SKYTORRENTS') return for post in posts: try: post = re.sub(r'\n', '', post) post = re.sub(r'\t', '', post) link = re.findall( 'href="(magnet:.+?)".+<td style="text-align: center;color:green;">([0-9]+|[0-9]+,[0-9]+)</td>', post, re.DOTALL) for url, seeders, in link: url = unquote_plus(url).split('&tr')[0].replace( '&', '&').replace(' ', '.') url = source_utils.strip_non_ascii_and_unprintable(url) if url in str(self.sources): return hash = re.compile('btih:(.*?)&').findall(url)[0] name = url.split('&dn=')[1] name = source_utils.clean_name(self.title, name) if source_utils.remove_lang(name): continue if not self.search_series: if not self.bypass_filter: if not source_utils.filter_season_pack( self.title, self.aliases, self.year, self.season_x, name): continue package = 'season' elif self.search_series: if not self.bypass_filter: valid, last_season = source_utils.filter_show_pack( self.title, self.aliases, self.imdb, self.year, self.season_x, name, self.total_seasons) if not valid: continue else: last_season = self.total_seasons package = 'show' try: seeders = int(seeders) if self.min_seeders > seeders: continue except: seeders = 0 pass 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] dsize, isize = source_utils._size(size) info.insert(0, isize) except: dsize = 0 pass info = ' | '.join(info) item = { 'source': 'torrent', 'seeders': seeders, 'hash': hash, 'name': name, 'quality': quality, 'language': 'en', 'url': url, 'info': info, 'direct': False, 'debridonly': True, 'size': dsize, 'package': package } if self.search_series: item.update({'last_season': last_season}) self.sources.append(item) except: source_utils.scraper_error('SKYTORRENTS') pass
def get_sources(self, link): try: url = '%s%s' % (self.base_link, link) result = client.request(url, timeout='5') if result is None: return if 'magnet' not in result: return url = 'magnet:%s' % (re.findall('a href="magnet:(.+?)"', result, re.DOTALL)[0]) url = unquote_plus(url).split('&tr=')[0].replace('&', '&').replace( ' ', '.') url = source_utils.strip_non_ascii_and_unprintable(url) if url in str(self.sources): return hash = re.compile('btih:(.*?)&').findall(url)[0] name = url.split('&dn=')[1] name = source_utils.clean_name(self.title, name) if source_utils.remove_lang(name, self.episode_title): return if not source_utils.check_title(self.title, self.aliases, name, self.hdlr, self.year): return # filter for episode multi packs (ex. S01E01-E17 is also returned in query) if self.episode_title: if not source_utils.filter_single_episodes(self.hdlr, name): return try: seeders = int( re.findall('<dt>SWARM</dt><dd>.*?>([0-9]+)</b>', result, re.DOTALL)[0].replace(',', '')) if self.min_seeders > seeders: return except: seeders = 0 pass quality, info = source_utils.get_release_quality(name, url) try: size = re.findall('<dt>SIZE</dt><dd>(.*? [a-zA-Z]{2})', result, re.DOTALL)[0] dsize, isize = source_utils._size(size) info.insert(0, isize) except: dsize = 0 pass info = ' | '.join(info) self.sources.append({ 'source': 'torrent', 'seeders': seeders, 'hash': hash, 'name': name, 'quality': quality, 'language': 'en', 'url': url, 'info': info, 'direct': False, 'debridonly': True, 'size': dsize }) except: source_utils.scraper_error('TORLOCK') pass
def get_sources_packs(self, link): # log_utils.log('link = %s' % str(link), __name__, log_utils.LOGDEBUG) try: r = client.request(link) if not r: return div = client.parseDOM(r, 'div', attrs={'id': 'div2child'}) for row in div: row = client.parseDOM(r, 'div', attrs={'class': 'resultdivbotton'}) if not row: return for post in row: hash = re.findall('<div id="hideinfohash.+?" class="hideinfohash">(.+?)<', post, re.DOTALL)[0] name = re.findall('<div id="hidename.+?" class="hideinfohash">(.+?)<', post, re.DOTALL)[0] name = unquote_plus(name) name = source_utils.clean_name(self.title, name) if source_utils.remove_lang(name): continue url = 'magnet:?xt=urn:btih:%s&dn=%s' % (hash, name) if url in str(self.sources): continue if not self.search_series: if not self.bypass_filter: if not source_utils.filter_season_pack(self.title, self.aliases, self.year, self.season_x, name): continue package = 'season' elif self.search_series: if not self.bypass_filter: valid, last_season = source_utils.filter_show_pack(self.title, self.aliases, self.imdb, self.year, self.season_x, name, self.total_seasons) if not valid: continue else: last_season = self.total_seasons package = 'show' try: seeders = int(re.findall('<div class="resultdivbottonseed">([0-9]+|[0-9]+,[0-9]+)<', post, re.DOTALL)[0].replace(',', '')) if self.min_seeders > seeders: continue except: seeders = 0 pass quality, info = source_utils.get_release_quality(name, url) try: size = re.findall('<div class="resultdivbottonlength">(.+?)<', post)[0] dsize, isize = source_utils._size(size) info.insert(0, isize) except: dsize = 0 pass info = ' | '.join(info) item = {'source': 'torrent', 'seeders': seeders, 'hash': hash, 'name': name, 'quality': quality, 'language': 'en', 'url': url, 'info': info, 'direct': False, 'debridonly': True, 'size': dsize, 'package': package} if self.search_series: item.update({'last_season': last_season}) self.sources.append(item) except: source_utils.scraper_error('IDOPE') pass
def sources(self, url, hostDict, hostprDict): sources = [] try: if url is None: return sources if debrid.status() is False: return sources data = 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') aliases = data['aliases'] episode_title = data['title'] if 'tvshowtitle' in data else None 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('[^A-Za-z0-9\s\.-]+', '', query) url = self.search_link % quote_plus(query) url = urljoin(self.base_link, url) # log_utils.log('url = %s' % url, log_utils.LOGDEBUG) r = client.request(url) if '<tbody' not in r: return sources posts = client.parseDOM(r, 'tbody')[0] posts = client.parseDOM(posts, 'tr') except: source_utils.scraper_error('SKYTORRENTS') return sources for post in posts: try: post = re.sub(r'\n', '', post) post = re.sub(r'\t', '', post) link = re.findall( 'href="(magnet:.+?)".+<td style="text-align: center;color:green;">([0-9]+|[0-9]+,[0-9]+)</td>', post, re.DOTALL) for url, seeders, in link: url = unquote_plus(url).split('&tr')[0].replace( '&', '&').replace(' ', '.') url = source_utils.strip_non_ascii_and_unprintable(url) if url in str(self.sources): return hash = re.compile('btih:(.*?)&').findall(url)[0] name = url.split('&dn=')[1] name = source_utils.clean_name(title, name) if source_utils.remove_lang(name, episode_title): continue if not source_utils.check_title(title, aliases, name, hdlr, data['year']): continue # filter for episode multi packs (ex. S01E01-E17 is also returned in query) if episode_title: if not source_utils.filter_single_episodes(hdlr, name): continue try: seeders = int(seeders) if self.min_seeders > seeders: continue except: seeders = 0 pass 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] dsize, isize = source_utils._size(size) info.insert(0, isize) except: dsize = 0 pass info = ' | '.join(info) sources.append({ 'source': 'torrent', 'seeders': seeders, 'hash': hash, 'name': name, 'quality': quality, 'language': 'en', 'url': url, 'info': info, 'direct': False, 'debridonly': True, 'size': dsize }) except: source_utils.scraper_error('SKYTORRENTS') return sources return sources
def get_sources(self, link): try: try: url = link[0].encode('ascii', errors='ignore').decode('ascii', errors='ignore').replace(' ', ' ') except: url = link[0].replace(' ', ' ') if '/torrent/' not in url: return try: name = link[1].encode('ascii', errors='ignore').decode('ascii', errors='ignore').replace(' ', '.') except: name = link[1].replace(' ', '.') if '<span' in name: nam = name.split('<span')[0].replace(' ', '.') span = client.parseDOM(name, 'span')[0].replace('-', '.') name = '%s%s' % (nam, span) name = source_utils.clean_name(self.title, name) if source_utils.remove_lang(name, self.episode_title): return if not source_utils.check_title(self.title, self.aliases, name, self.hdlr, self.year): return # filter for episode multi packs (ex. S01E01-E17 is also returned in query) if self.episode_title: if not source_utils.filter_single_episodes(self.hdlr, name): return if not url.startswith('http'): link = urljoin(self.base_link, url) link = client.request(link, timeout='5') if link is None: return hash = re.findall('<b>Infohash</b></td><td valign=top>(.+?)</td>', link, re.DOTALL)[0] url = 'magnet:?xt=urn:btih:%s&dn=%s' % (hash, name) if url in str(self.sources): return try: seeders = int(re.findall('<b>Swarm:</b></td><td valign=top><font color=red>([0-9]+)</font>', link, re.DOTALL)[0].replace(',', '')) if self.min_seeders > seeders: # site does not seem to report seeders return except: seeders = 0 pass 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))', link)[0] dsize, isize = source_utils._size(size) info.insert(0, isize) except: dsize = 0 pass info = ' | '.join(info) self.sources.append({'source': 'torrent', 'seeders': seeders, 'hash': hash, 'name': name, 'quality': quality, 'language': 'en', 'url': url, 'info': info, 'direct': False, 'debridonly': True, 'size': dsize}) except: source_utils.scraper_error('TORRENTFUNK') pass