def sources(self, url, hostDict, hostprDict): try: sources = [] if url == None: return sources hostDict = hostDict + hostprDict r = cfScraper.get(url).content match = re.compile( '<a href="http://www.tvmovieflix.com/report-.+?/(.+?)" target="_blank"><span class="a">Report Broken</span></a></li>', re.DOTALL | re.M).findall(r) for link in match: if "/show/" in url: surl = "http://www.tvmovieflix.com/e/" + link else: surl = "http://www.tvmovieflix.com/m/" + link i = cfScraper.get(surl).content match = re.compile('<IFRAME.+?SRC="(.+?)"', re.DOTALL | re.IGNORECASE).findall(i) for link in match: if "realtalksociety.com" in link: r = requests.get(link).content match = re.compile( '<source src="(.+?)" type="video/mp4">', re.DOTALL | re.IGNORECASE).findall(r) for url in match: valid, host = source_utils.is_host_valid( url, hostDict) quality, info = source_utils.get_release_quality( url, url) sources.append({ 'source': host, 'quality': quality, 'language': 'en', 'info': info, 'url': url, 'direct': True, 'debridonly': False }) else: valid, host = source_utils.is_host_valid( link, hostDict) quality, info = source_utils.get_release_quality( link, link) sources.append({ 'source': host, 'quality': quality, 'language': 'en', 'info': info, 'url': link, 'direct': False, 'debridonly': False }) return sources except: return sources
def _get_sources(self, item): try: name = item[0] quality, info = source_utils.get_release_quality(name, item[1]) info.insert(0, item[2]) data = cfScraper.get(item[1]).content data = ensure_text(data, errors='replace') data = client.parseDOM(data, 'a', ret='href') url = [i for i in data if 'magnet:' in i][0] url = url.split('&tr')[0] info = ' | '.join(info) self._sources.append({ 'source': 'Torrent', 'quality': quality, 'language': 'en', 'url': url, 'info': info, 'direct': False, 'debridonly': True, 'size': item[3], 'name': name }) except: log_utils.log('1337x_exc1', 1) pass
def sources(self, url, hostDict, hostprDict): sources = [] try: if url is None: return sources hostDict = hostprDict + hostDict #headers = {'Referer': url} r = cfScraper.get(url).content u = client.parseDOM(r, "span", attrs={"class": "movie_version_link"}) for t in u: match = client.parseDOM(t, 'a', ret='data-href') for url in match: 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', 'info': info, 'url': url, 'direct': False, 'debridonly': False }) return sources except: return sources
def _get_items(self, r): try: size = re.search(r'<size>([\d]+)</size>', r).groups()[0] seeders = re.search(r'<seeders>([\d]+)</seeders>', r).groups()[0] _hash = re.search(r'<info_hash>([a-zA-Z0-9]+)</info_hash>', r).groups()[0] name = re.search(r'<title>(.+?)</title>', r).groups()[0] url = 'magnet:?xt=urn:btih:%s&dn=%s' % (_hash.upper(), quote_plus(name)) url = url.split('&tr')[0] t = name.split(self.hdlr)[0] try: y = re.findall(r'[\.|\(|\[|\s|\_|\-](S\d+E\d+|S\d+)[\.|\)|\]|\s|\_|\-]', name, re.I)[-1].upper() except BaseException: y = re.findall(r'[\.|\(|\[|\s\_|\-](\d{4})[\.|\)|\]|\s\_|\-]', name, re.I)[-1].upper() quality, info = source_utils.get_release_quality(name, url) try: div = 1000 ** 3 dsize = float(size) / div isize = '%.2f GB' % dsize except BaseException: dsize, isize = 0.0, '' info.insert(0, isize) info = ' | '.join(info) if cleantitle.get(re.sub('(|)', '', t)) == cleantitle.get(self.title): if y == self.hdlr: self._sources.append({'source': 'Torrent', 'quality': quality, 'language': 'en', 'url': url, 'info': info, 'direct': False, 'debridonly': True, 'size': dsize, 'name': name}) except BaseException: pass
def sources(self, url, hostDict, hostprDict): try: sources = [] if url is None: return sources hostDict = hostprDict + hostDict # headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/41.0.2228.0 Safari/537.36'} r = cfScraper.get(url).content qual = re.compile('<span class="calidad2">(.+?)</span>').findall(r) for qcheck in qual: quality, info = source_utils.get_release_quality( qcheck, qcheck) links = re.compile('<iframe src="(.+?)"', re.DOTALL).findall(r) for link in links: valid, host = source_utils.is_host_valid(link, hostDict) if not valid: continue sources.append({ 'source': host, 'quality': quality, 'language': 'en', 'url': link, 'direct': False, 'debridonly': False }) return sources except Exception: failure = traceback.format_exc() log_utils.log('Movie4kis - Exception: \n' + str(failure)) return sources
def sources(self, url, hostDict, hostprDict): try: hostDict = hostprDict + hostDict sources = [] if url == None: return sources page = client.request(url) links = re.compile('<a rel="nofollow" target="blank" href="(.+?)"', re.DOTALL).findall(page) for link in links: link = "https:" + link if not link.startswith('http') else link valid, host = source_utils.is_host_valid(link, hostDict) if valid: quality, info = source_utils.get_release_quality( link, link) sources.append({ 'source': host, 'quality': quality, 'language': 'en', 'url': link, 'info': info, 'direct': False, 'debridonly': False }) return sources except: failure = traceback.format_exc() log_utils.log('watchseriestv - Exception: \n' + str(failure)) return sources
def sources(self, url, hostDict, hostprDict): try: sources = [] if url == None: return sources hostDict = hostprDict + hostDict r = client.request(url) r = re.compile( 'class="watch-button" data-actuallink="(.+?)"').findall(r) for url in r: 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, 'direct': False, 'debridonly': False }) return sources except: log_utils.log('Watchepisodes4 Exception', 1) return sources
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 _get_sources(self, name, url): try: headers = {'User-Agent': client.agent()} r = cfScraper.get(url, headers=headers).content r = ensure_text(r, errors='replace') name = client.replaceHTMLCodes(name) try: _name = name.lower().replace('rr', '').replace('nf', '').replace( 'ul', '').replace('cu', '') except: _name = name l = dom_parser2.parse_dom(r, 'pre', {'class': 'links'}) s = '' for i in l: s += i.content urls = re.findall( r'''((?:http|ftp|https)://[\w_-]+(?:(?:\.[\w_-]+)+)[\w.,@?^=%&:/~+#-]*[\w@?^=%&/~+#-])''', i.content, flags=re.MULTILINE | re.DOTALL) urls = [ i for i in urls if not i.endswith(('.rar', '.zip', '.iso', '.idx', '.sub', '.srt')) ] for url in urls: if url in str(self.sources): continue valid, host = source_utils.is_host_valid(url, self.hostDict) if not valid: continue host = client.replaceHTMLCodes(host) #host = host.encode('utf-8') quality, info = source_utils.get_release_quality(name, url) try: size = re.findall( '((?:\d+\.\d+|\d+\,\d+|\d+)\s*(?:GiB|MiB|GB|MB))', name)[0] dsize, isize = source_utils._size(size) except BaseException: dsize, isize = 0.0, '' info.insert(0, isize) info = ' | '.join(info) self.sources.append({ 'source': host, 'quality': quality, 'language': 'en', 'url': url, 'info': info, 'direct': False, 'debridonly': True, 'size': dsize, 'name': _name }) except: log_utils.log('RMZ - Exception', 1) pass
def sources(self, url, hostDict, hostprDict): sources = [] try: if url is None: return sources if debrid.status() is False: raise Exception() 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 = cleantitle.get_query(title) query = '%s S%02dE%02d' % ( title, int(data['season']), int(data['episode']) ) if 'tvshowtitle' in data else '%s' % data['imdb'] query = re.sub('(\\\|/| -|:|;|\*|\?|"|\'|<|>|\|)', ' ', query) token = cfScraper.get(self.token).content token = json.loads(token)["token"] if 'tvshowtitle' in data: search_link = self.tvsearch.format(token, quote_plus(query), 'format=json_extended') else: search_link = self.msearch.format(token, data['imdb'], 'format=json_extended') control.sleep(250) rjson = cfScraper.get(search_link).content rjson = ensure_text(rjson, errors='ignore') files = json.loads(rjson)['torrent_results'] for file in files: name = file["title"] url = file["download"] url = url.split('&tr')[0] quality, info = source_utils.get_release_quality(name, url) try: dsize = float(file["size"]) / 1073741824 isize = '%.2f GB' % dsize except: dsize, isize = 0.0, '' info.insert(0, isize) info = ' | '.join(info) sources.append({ 'source': 'Torrent', 'quality': quality, 'language': 'en', 'url': url, 'info': info, 'direct': False, 'debridonly': True, 'size': dsize, 'name': name }) return sources except: log_utils.log('torapi - Exception', 1) return sources
def sources(self, url, hostDict, hostprDict): sources = [] try: if debrid.status() is False: return sources 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]) 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(u'(\\\|/| -|:|;|\*|\?|"|\'|<|>|\|)', ' ', query).lower() url = urljoin(self.base_link, self.search_link % query) #r = client.request(url) #r = requests.get(url).content r = cfScraper.get(url).content r = ensure_text(r, errors='replace').replace(' ', ' ') r = client.parseDOM(r, 'div', attrs={'class': 'col s12'}) posts = client.parseDOM(r, 'div')[1:] posts = [i for i in posts if 'magnet/' in i] for post in posts: links = client.parseDOM(post, 'a', ret='href')[0] url = 'magnet:?xt=urn:btih:' + links.lstrip('magnet/') try: name = client.parseDOM(post, 'a', ret='title')[0] if not query in cleantitle.get_title(name): continue except: name = '' quality, info = source_utils.get_release_quality(name, name) try: size = re.findall(r'<b class="cpill .+?-pill">(.+?)</b>', post)[0] dsize, isize = source_utils._size(size) except: dsize, isize = 0.0, '' info.insert(0, isize) info = ' | '.join(info) sources.append({'source': 'Torrent', 'quality': quality, 'language': 'en', 'url': url, 'info': info, 'direct': False, 'debridonly': True, 'size': dsize, 'name': name}) return sources except: log_utils.log('bt4g3 - Exception', 1) return sources
def sources(self, url, hostDict, hostprDict): sources = [] try: self.hostDict = hostDict + hostprDict if url is None: return sources if debrid.status() is False: return 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 = cleantitle.get_query(self.title) self.hdlr = 'S%02dE%02d' % (int(data['season']), int(data['episode'])) if 'tvshowtitle' in data else data['year'] query = '%s S%02dE%02d' % (self.title, int(data['season']), int(data['episode'])) if 'tvshowtitle' in data else '%s %s' % (self.title, data['year']) query = re.sub('(\\\|/| -|:|;|\*|\?|"|\'|<|>|\|)', ' ', query) if 'tvshowtitle' in data: url = self.tvsearch.format(quote(query)) url = urljoin(self.base_link, url) else: url = self.moviesearch.format(quote(query)) url = urljoin(self.base_link, url) r = cfScraper.get(url).content r = ensure_text(r, errors='ignore') posts = client.parseDOM(r, 'table', attrs={'class': 'table2'})[0] posts = client.parseDOM(posts, 'tr') for post in posts: link = client.parseDOM(post, 'a', ret='href')[0] hash = re.findall(r'(\w{40})', link, re.I) if hash: url = 'magnet:?xt=urn:btih:' + hash[0] name = link.split('title=')[1] t = name.split(self.hdlr)[0] if not cleantitle.get(re.sub('(|)', '', t)) == cleantitle.get(self.title): continue try: y = re.findall('[\.|\(|\[|\s|\_|\-](S\d+E\d+|S\d+)[\.|\)|\]|\s|\_|\-]', name, re.I)[-1].upper() except: y = re.findall('[\.|\(|\[|\s\_|\-](\d{4})[\.|\)|\]|\s\_|\-]', name, re.I)[-1].upper() if not y == self.hdlr: continue quality, info = source_utils.get_release_quality(name, name) 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) except: dsize, isize = 0.0, '' info.insert(0, isize) info = ' | '.join(info) sources.append({'source': 'Torrent', 'quality': quality, 'language': 'en', 'url': url, 'info': info, 'direct': False, 'debridonly': True, 'size': dsize, 'name': name}) return sources except: log_utils.log('lime0 - Exception', 1) return sources
def get_sources(self, link): try: url = '%s%s' % (self.base_link, link) result = client.request(url) info_hash = re.findall('<kbd>(.+?)<', result, re.DOTALL)[0] url1 = '%s%s' % ('magnet:?xt=urn:btih:', info_hash) name = re.findall('<h3 class="card-title">(.+?)<', result, re.DOTALL)[0] name = urllib.unquote_plus(name).replace(' ', '.') url = '%s%s%s' % (url1, '&dn=', str(name)) t = name.split(self.hdlr)[0].replace(self.year, '').replace( '(', '').replace(')', '').replace('&', 'and').replace( '.US.', '.').replace('.us.', '.') if cleantitle.get(t) != cleantitle.get(self.title): return if self.hdlr not in name: return size = re.findall( '<div class="col-3">File size:</div><div class="col">(.+?)<', result, re.DOTALL)[0] 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))', size)[0] dsize, isize = utils._size(size) except: dsize, isize = 0, '' info.insert(0, isize) info = ' | '.join(info) self.sources.append({ 'source': 'torrent', 'quality': quality, 'language': 'en', 'url': url, 'info': info, 'direct': False, 'debridonly': True, 'size': dsize }) except: pass
def sources(self, url, hostDict, hostprDict): sources = [] try: if url is None: return sources hostDict = hostprDict + hostDict 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'] 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'])) query = re.sub('(\\\|/| -|:|;|\*|\?|"|\'|<|>|\|)', ' ', query) url = self.search_link % quote_plus(query) url = urljoin(self.base_link, url).replace('+', '-') r = cfScraper.get(url).content r = ensure_text(r, errors='ignore') try: data = re.compile( '<a href="(.+?)" target="_blank" rel="nofollow" title.+?' ).findall(r) for url in data: valid, host = source_utils.is_host_valid(url, hostDict) if valid: quality, info = source_utils.get_release_quality( url, url) sources.append({ 'source': host, 'quality': quality, 'language': 'en', 'url': url, 'direct': False, 'debridonly': False }) except: log_utils.log('projectfree2 - Exception', 1) pass return sources except: log_utils.log('projectfree3 - Exception', 1) return sources
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): try: sources = [] if url is None: return sources hostDict = hostDict + hostprDict data = urlparse.parse_qs(url) data = dict([(i, data[i][0]) if data[i] else (i, '') for i in data]) aliases = eval(data['aliases']) headers = {} if 'tvshowtitle' in data: ep = data['episode'] url = '%s/film/%s-season-%01d/watching.html?ep=%s' % ( self.base_link, cleantitle.geturl(data['tvshowtitle']), int(data['season']), ep) # r = client.request(url, headers=headers, timeout='10', output='geturl') r = cfScraper.get(url).content if url is None: url = self.searchShow(data['tvshowtitle'], data['season'], aliases, headers) else: url = self.searchMovie(data['title'], data['year'], aliases, headers) if url is None: url = '%s/film/%s/watching.html?ep=0' % (self.base_link, cleantitle.geturl(data['title'])) if url is None: raise Exception() # r = client.request(url, headers=headers, timeout='10') r = cfScraper.get(url).content r = client.parseDOM(r, 'div', attrs={'class': 'les-content'}) if 'tvshowtitle' in data: ep = data['episode'] links = client.parseDOM(r, 'a', attrs={'episode-data': ep}, ret='player-data') else: links = client.parseDOM(r, 'a', ret='player-data') for link in links: link = "https:" + link if not link.startswith('http') else link if '123movieshd' in link or 'seriesonline' in link: # r = client.request(link, headers=headers, timeout='10') r = cfScraper.get(link).content r = re.findall('(https:.*?redirector.*?)[\'\"]', r) for i in r: sources.append({'source': 'gvideo', 'quality': directstream.googletag(i)[0]['quality'], 'language': 'en', 'url': i, 'direct': True, 'debridonly': False}) else: valid, host = source_utils.is_host_valid(link, hostDict) if valid: quality, info = source_utils.get_release_quality(link, link) if 'load.php' not in link: sources.append({'source': host, 'quality': quality, 'language': 'en', 'info': info, 'url': link, 'direct': False, 'debridonly': False}) 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 = 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 = cleantitle.get_query(self.title) self.hdlr = 'S%02dE%02d' % (int(data['season']), int(data['episode'])) if 'tvshowtitle' in data else data['year'] query = '%s S%02dE%02d' % ( self.title, int(data['season']), int(data['episode'])) if 'tvshowtitle' in data else '%s %s' % (self.title, data['year']) query = re.sub('(\\\|/| -|:|;|\*|\?|"|\'|<|>|\|)', ' ', query) if 'tvshowtitle' in data: url = self.tvsearch.format(quote_plus(query)) url = urljoin(self.base_link, url) else: url = self.moviesearch.format(quote_plus(query)) url = urljoin(self.base_link, url) items = self._get_items(url) hostDict = hostDict + hostprDict for item in items: try: name = item[0] url = item[1] url = url.split('&tr')[0] quality, info = source_utils.get_release_quality(name, url) info.insert(0, item[2]) info = ' | '.join(info) sources.append({'source': 'Torrent', 'quality': quality, 'language': 'en', 'url': url, 'info': info, 'direct': False, 'debridonly': True, 'size': item[3], 'name': name}) except: log_utils.log('glodls0_exc', 1) pass return sources except: log_utils.log('glodls1_exc', 1) return sources
def sources(self, url, hostDict, hostprDict): try: sources = [] if url == None: return sources html = cfScraper.get(url).content links = re.compile('id="linkplayer.+?href="(.+?)"',re.DOTALL).findall(html) for link in links: quality, info = source_utils.get_release_quality(link, link) host = link.split('//')[1].replace('www.', '') host = host.split('/')[0].split('.')[0].title() valid, host = source_utils.is_host_valid(host, hostDict) if valid: sources.append({'source': host, 'quality': quality, 'language': 'en', 'url': link, 'direct': False, 'debridonly': False}) 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]) 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"] url = file["download"] url = url.split('&tr')[0] quality, info = source_utils.get_release_quality(name, url) dsize = float(file["size"]) / 1073741824 isize = '%.2f GB' % dsize #size = source_utils.convert_size(file["size"]) #size = '[B]%s[/B]' % size info.insert(0, isize) info = ' | '.join(info) sources.append({ 'source': 'Torrent', 'quality': quality, 'language': 'en', 'url': url, 'info': info, 'direct': False, 'debridonly': True, 'size': dsize }) return sources except BaseException: return sources
def _get_sources(self, url): try: item = client.request(url[0]) title = url[1] links = dom_parser2.parse_dom(item, 'a', req='href') links = [i.attrs['href'] for i in links] info = [] try: size = re.findall( '((?:\d+\.\d+|\d+\,\d+|\d+)\s*(?:GiB|MiB|GB|MB))', item)[0] 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) for url in links: if 'youtube' in url: continue if any(x in url.lower() for x in ['.rar.', '.zip.', '.iso.']) or any( url.lower().endswith(x) for x in ['.rar', '.zip', '.iso']): raise Exception() if any(x in url.lower() for x in ['youtube', 'sample', 'trailer']): raise Exception() valid, host = source_utils.is_host_valid(url, self.hostDict) if not valid: continue host = client.replaceHTMLCodes(host) host = host.encode('utf-8') quality, info2 = source_utils.get_release_quality(title, url) if url in str(self._sources): continue self._sources.append({ 'source': host, 'quality': quality, 'language': 'en', 'url': url, 'info': info, 'direct': False, 'debridonly': False }) except Exception: pass
def sources(self, url, hostDict, hostprDict): sources = [] try: if url is None: 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 = cfScraper.get(url).content v = re.compile( '<a href="(.+?)" class="ml-mask jt" title="(.+?)">\s+<span class=".+?">(.+?)</span>' ).findall(r) for url, check, qual in v: t = '%s (%s)' % (data['title'], data['year']) if t in check: key = url.split('-hd')[1] url = 'https://fmovies.tw/moviedownload.php?q=%s' % key r = cfScraper.get(url).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, info = source_utils.get_release_quality( qual, url) valid, host = source_utils.is_host_valid(url, hostDict) if valid: info = ' | '.join(info) sources.append({ 'source': host, 'quality': quality, 'language': 'en', 'url': url, 'info': info, 'direct': False, 'debridonly': False }) return sources except Exception: failure = traceback.format_exc() log_utils.log('---Ganool Testing - Exception: \n' + str(failure)) return sources
def _get_sources(self, item): try: name = item[0] data = client.request(item[1]) url = re.search('''href=["'](magnet:\?[^"']+)''', data).groups()[0] url = url.split('&tr')[0] quality, info = source_utils.get_release_quality(name, url) info.insert(0, item[2]) info = ' | '.join(info) self._sources.append({ 'source': 'Torrent', 'quality': quality, 'language': 'en', 'url': url, 'info': info, 'direct': False, 'debridonly': True, 'size': item[3] }) except BaseException: pass
def sources(self, url, hostDict, hostprDict): sources = [] try: if url == None: return sources hostDict = hostDict + hostprDict sourcePage = ensure_text(cfScraper.get(url).content, errors='replace') thesources = re.compile('<tbody>(.+?)</tbody>', re.DOTALL).findall(sourcePage)[0] links = re.compile( "<a href=\'(.+?)\' target=\'_blank\'>Download</a>", re.DOTALL).findall(thesources) for link in links: linkPage = ensure_text(cfScraper.get(link).content, errors='replace') vlink = re.compile( '<a id="link" rel="nofollow" href="(.+?)" class="btn"', re.DOTALL).findall(linkPage) for zlink in vlink: valid, host = source_utils.is_host_valid(zlink, hostDict) if valid: quality, info = source_utils.get_release_quality( zlink, zlink) sources.append({ 'source': host, 'quality': quality, 'language': 'en', 'url': zlink, 'info': info, 'direct': False, 'debridonly': False }) return sources except: return sources
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_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 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 sources(self, url, hostDict, hostprDict): sources = [] try: if debrid.status() is False: return sources 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'] 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 % quote_plus(query) url = urljoin(self.base_link, url) r = client.request(url) posts = re.findall('<h2 class="title">(.+?)</h2>', r, re.IGNORECASE) hostDict = hostprDict + hostDict urls = [] for item in posts: try: link, name = re.findall('href="(.+?)" title="(.+?)"', item, re.IGNORECASE)[0] if not cleantitle.get(title) in cleantitle.get(name): continue name = client.replaceHTMLCodes(name) try: _name = name.lower().replace('permalink to', '') except: _name = name quality, info = source_utils.get_release_quality( name, link) try: size = re.findall( '((?:\d+\.\d+|\d+\,\d+|\d+)\s*(?:GB|GiB|MB|MiB))', name)[-1] dsize, isize = source_utils._size(size) except Exception: dsize, isize = 0.0, '' info.insert(0, isize) info = ' | '.join(info) links = self.links(link) urls += [(i, quality, info) for i in links] except Exception: pass for item in urls: if 'earn-money' in item[0]: continue if any(x in item[0] for x in ['.rar', '.zip', '.iso']): continue url = client.replaceHTMLCodes(item[0]) #url = url.encode('utf-8') url = ensure_text(url) valid, host = source_utils.is_host_valid(url, hostDict) if not valid: continue host = client.replaceHTMLCodes(host) #host = host.encode('utf-8') host = ensure_text(host) sources.append({ 'source': host, 'quality': item[1], 'language': 'en', 'url': url, 'info': item[2], 'direct': False, 'debridonly': True, 'size': dsize, 'name': _name }) return sources except Exception: 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): try: sources = [] if url is None: return sources if debrid.status() is False: return sources hostDict = hostprDict + hostDict 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 = cleantitle.get_query(title) query = '%s S%02dE%02d' % ( title, int(data['season']), int(data['episode']) ) if 'tvshowtitle' in data else '%s %s' % (title, data['year']) url = self.search_link % quote_plus(query) url = urljoin(self.base_link, url).replace('%3A+', '+') #r = client.request(url) r = cfScraper.get(url).content r = ensure_text(r, errors='replace') posts = client.parseDOM(r, "div", attrs={"class": "postContent"}) items = [] for post in posts: try: p = client.parseDOM(post, "p", attrs={"dir": "ltr"})[1:] for i in p: items.append(i) except: pass try: for item in items: u = client.parseDOM(item, 'a', ret='href') name = re.findall('<strong>(.*?)</strong>', item, re.DOTALL)[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): continue for url in u: if any(x in url for x in ['.rar', '.zip', '.iso']): 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|gb|mb))', item, re.DOTALL)[0] dsize, isize = source_utils._size(size) except: dsize, isize = 0.0, '' info.insert(0, isize) info = ' | '.join(info) 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, 'size': dsize, 'name': name }) except: pass return sources except: log_utils.log('max_rls Exception', 1) return sources
def sources(self, url, hostDict, hostprDict): sources = [] try: if debrid.status() is False: return sources 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'] if 'tvshowtitle' in data else data[ 'title'] title = cleantitle.get_query(title) hdlr = 'S%02dE%02d' % (int(data['season']), int( data['episode'])) if 'tvshowtitle' in data else data['year'] query = '%s s%02de%02d' % (title, int(data['season']), int(data['episode']))\ if 'tvshowtitle' in data else '%s %s' % (title, data['year']) query = re.sub(u'(\\\|/| -|:|;|\*|\?|"|\'|<|>|\|)', ' ', query) url = urljoin( self.base_link, self.search_link.format(query[0].lower(), cleantitle.geturl(query))) r = client.request(url) r = client.parseDOM(r, 'tbody')[0] posts = client.parseDOM(r, 'tr') posts = [i for i in posts if 'magnet:' in i] for post in posts: post = post.replace(' ', ' ') name = client.parseDOM(post, 'a', ret='title')[1] t = name.split(hdlr)[0] if not cleantitle.get(re.sub(r'(|)', '', t)) == cleantitle.get(title): continue try: y = re.findall( u'[\.|\(|\[|\s|\_|\-](S\d+E\d+|S\d+)[\.|\)|\]|\s|\_|\-]', name, re.I)[-1].upper() except BaseException: y = re.findall( u'[\.|\(|\[|\s\_|\-](\d{4})[\.|\)|\]|\s\_|\-]', name, re.I)[-1].upper() if not y == hdlr: continue links = client.parseDOM(post, 'a', ret='href') magnet = [ i.replace('&', '&') for i in links if 'magnet:' in i ][0] url = magnet.split('&tr')[0] quality, info = source_utils.get_release_quality(name, url) try: size = re.findall( r'((?:\d+\,\d+\.\d+|\d+\.\d+|\d+\,\d+|\d+)\s*(?:GiB|MiB|GB|MB))', post)[0] dsize, isize = source_utils._size(size) except: dsize, isize = 0.0, '' info.insert(0, isize) info = ' | '.join(info) sources.append({ 'source': 'Torrent', 'quality': quality, 'language': 'en', 'url': url, 'info': info, 'direct': False, 'debridonly': True, 'size': dsize, 'name': name }) return sources except: log_utils.log('Magnetdl - Exception', 1) return sources