def _get_sources(self, name, url): try: headers = {'User-Agent': client.agent()} r = self.scraper.get(url, headers=headers).content name = client.replaceHTMLCodes(name) l = dom_parser.parse_dom(r, 'div', {'class': 'ppu2h'}) 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 '.rar' not in i or '.zip' not in i or '.iso' not in i or '.idx' not in i or '.sub' not in i ] 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] 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) self.sources.append({ 'source': host, 'quality': quality, 'language': 'en', 'url': url, 'info': info, 'direct': False, 'debridonly': True }) except: source_utils.scraper_error('RAPIDMOVIEZ') pass
def sources(self, url, hostDict, hostprDict): try: sources = [] r = self.scraper.get(url).content try: v = re.findall('document.write\(Base64.decode\("(.+?)"\)', r)[0] b64 = base64.b64decode(v) url = client.parseDOM(b64, 'iframe', ret='src')[0] try: host = re.findall( '([\w]+[.][\w]+)$', urlparse.urlparse(url.strip().lower()).netloc)[0] host = client.replaceHTMLCodes(host) host = host.encode('utf-8') sources.append({ 'source': host, 'quality': 'SD', 'language': 'en', 'url': url.replace('\/', '/'), 'direct': False, 'debridonly': False }) except: pass except: pass r = client.parseDOM(r, 'div', {'class': 'server_line'}) r = [(client.parseDOM(i, 'a', ret='href')[0], client.parseDOM(i, 'p', attrs={'class': 'server_servername'})[0]) for i in r] if r: for i in r: try: host = re.sub('Server|Link\s*\d+', '', i[1]).lower() url = i[0] host = client.replaceHTMLCodes(host) host = host.encode('utf-8') if 'other' in host: continue sources.append({ 'source': host, 'quality': 'SD', 'language': 'en', 'url': url.replace('\/', '/'), 'direct': False, 'debridonly': False }) except: pass return sources except Exception: return
def _get_sources(self, item, hostDict): try: quality, info = source_utils.get_release_quality(item[0], item[1]) size = item[2] if item[2] != '0' else item[0] try: size = re.findall('((?:\d+\,\d+\.\d+|\d+\.\d+|\d+\,\d+|\d+)\s*(?:GB|GiB|MB|MiB))', size)[-1] 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 Exception: pass data = self.scraper.get(item[1]).content try: r = client.parseDOM(data, 'li', attrs={'class': 'elemento'}) r = [(dom_parser2.parse_dom(i, 'a', req='href')[0], dom_parser2.parse_dom(i, 'img', req='alt')[0], dom_parser2.parse_dom(i, 'span', {'class': 'd'})[0]) for i in r] urls = [('http:' + i[0].attrs['href'] if not i[0].attrs['href'].startswith('http') else i[0].attrs['href'], i[1].attrs['alt'], i[2].content) for i in r if i[0] and i[1]] for url, host, qual in urls: try: if any(x in url for x in ['.rar', '.zip', '.iso', ':Upcoming']): raise Exception() url = client.replaceHTMLCodes(url) url = url.encode('utf-8') valid, host = source_utils.is_host_valid(host, hostDict) if not valid: continue host = client.replaceHTMLCodes(host) host = host.encode('utf-8') quality, info = source_utils.get_release_quality(qual, quality) info.append('HEVC') info = ' | '.join(info) self._sources.append( {'source': host, 'quality': quality, 'language': 'en', 'url': url, 'info': info, 'direct': False, 'debridonly': True}) except Exception: pass except Exception: pass except BaseException: return
def sources(self, url, hostDict, hostprDict): try: sources = [] r = self.scraper.get(url).content r = dom_parser2.parse_dom(r, 'p', {'class': 'server_play'}) r = [dom_parser2.parse_dom(i, 'a', req=['href']) for i in r if i] r = [(i[0].attrs['href'], re.search('/(\w+).html', i[0].attrs['href'])) for i in r if i] r = [(i[0], i[1].groups()[0]) for i in r if i[0] and i[1]] for i in r: try: host = i[1] if str(host) in str(hostDict): host = client.replaceHTMLCodes(host) host = host.encode('utf-8') sources.append({ 'source': host, 'quality': 'SD', 'language': 'en', 'url': i[0].replace('\/', '/'), 'direct': False, 'debridonly': False }) except: pass return sources except Exception: return
def __search(self, titles, year): try: query = self.search_link % (urllib.quote_plus( cleantitle.query(titles[0]))) query = urlparse.urljoin(self.base_link, query) t = [cleantitle.get(i) for i in set(titles) if i] y = [ '%s' % str(year), '%s' % str(int(year) + 1), '%s' % str(int(year) - 1), '0' ] r = client.request(query) r = dom_parser.parse_dom(r, 'div', attrs={'class': 'details'}) r = [(dom_parser.parse_dom(i, 'div', attrs={'class': 'title'}), dom_parser.parse_dom(i, 'span', attrs={'class': 'year'})) for i in r] r = [(dom_parser.parse_dom(i[0][0], 'a', req='href'), i[1][0].content) for i in r if i[0] and i[1]] r = [(i[0][0].attrs['href'], client.replaceHTMLCodes(i[0][0].content), i[1]) for i in r if i[0]] r = sorted(r, key=lambda i: int(i[2]), reverse=True) # with year > no year r = [i[0] for i in r if cleantitle.get(i[1]) in t and i[2] in y][0] return source_utils.strip_domain(r) except: return
def __search(self, title, season): try: query = self.search_link % (urllib.quote_plus( cleantitle.query(title))) query = urlparse.urljoin(self.base_link, query) t = cleantitle.get(title) r = client.request(query) r = client.parseDOM(r, 'div', attrs={'class': 'moviefilm'}) r = client.parseDOM(r, 'div', attrs={'class': 'movief'}) r = [(client.parseDOM(i, 'a', ret='href'), client.parseDOM(i, 'a')) for i in r] r = [(i[0][0], i[1][0].lower()) for i in r if len(i[0]) > 0 and len(i[1]) > 0] r = [(i[0], i[1], re.findall('(.+?)\s+(?:saison)\s+(\d+)', i[1])) for i in r] r = [(i[0], i[2][0][0] if len(i[2]) > 0 else i[1], i[2][0][1] if len(i[2]) > 0 else '0') for i in r] r = [(i[0], i[1], re.findall('\((.+?)\)$', i[1]), i[2]) for i in r] r = [(i[0], i[2][0] if len(i[2]) > 0 else i[1], i[3]) for i in r] r = [ i[0] for i in r if t == cleantitle.get(i[1]) and int(i[2]) == int(season) ][0] url = re.findall('(?://.+?|)(/.+)', r)[0] url = client.replaceHTMLCodes(url) url = url.encode('utf-8') return url except: return
def sources(self, url, hostDict, hostprDict): try: sources = [] if url is None: return sources r = self.scraper.get(url, headers={'referer': self.base_link}).content links = client.parseDOM(r, 'a', ret='href', attrs={'target': '.+?'}) links = [x for y, x in enumerate(links) if x not in links[:y]] for i in links: try: url = i url = proxy.parse(url) url = urlparse.parse_qs(urlparse.urlparse(url).query)['r'][0] url = url.decode('base64') url = client.replaceHTMLCodes(url) url = url.encode('utf-8') host = re.findall('([\w]+[.][\w]+)$', urlparse.urlparse(url.strip().lower()).netloc)[0] if host not in hostDict: continue; host = host.encode('utf-8') sources.append({'source': host, 'quality': 'SD', 'language': 'en', 'url': url, 'direct': False, 'debridonly': False}) except: pass return sources except: return sources
def tvshow(self, imdb, tvdb, tvshowtitle, localtvshowtitle, aliases, year): try: query = self.tvsearch_link % urllib.quote_plus( cleantitle.query(tvshowtitle)) query = urlparse.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] 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))][0] url = client.replaceHTMLCodes(result) url = url.encode('utf-8') return url except Exception: return
def sources(self, url, hostDict, hostprDict): sources = [] try: if url == None: return sources data = urlparse.parse_qs(url) data = dict([(i, data[i][0]) if data[i] else (i, '') for i in data]) url = urlparse.urljoin(self.base_link, data.get('url')) season = data.get('season') episode = data.get('episode') r = client.request(url) if season and episode: r = dom_parser.parse_dom(r, 'select', attrs={'id': 'SeasonSelection'}, req='rel')[0] r = client.replaceHTMLCodes(r.attrs['rel'])[1:] r = urlparse.parse_qs(r) r = dict([(i, r[i][0]) if r[i] else (i, '') for i in r]) r = urlparse.urljoin(self.base_link, self.get_links_epi % (r['Addr'], r['SeriesID'], season, episode)) r = client.request(r) r = dom_parser.parse_dom(r, 'ul', attrs={'id': 'HosterList'})[0] r = dom_parser.parse_dom(r, 'li', attrs={'id': re.compile('Hoster_\d+')}, req='rel') r = [(client.replaceHTMLCodes(i.attrs['rel']), i.content) for i in r if i[0] and i[1]] r = [(i[0], re.findall('class="Named"[^>]*>([^<]+).*?(\d+)/(\d+)', i[1])) for i in r] r = [(i[0], i[1][0][0].lower().rsplit('.', 1)[0], i[1][0][2]) for i in r if len(i[1]) > 0] for link, hoster, mirrors in r: valid, hoster = source_utils.is_host_valid(hoster, hostDict) if not valid: continue u = urlparse.parse_qs('&id=%s' % link) u = dict([(x, u[x][0]) if u[x] else (x, '') for x in u]) for x in range(0, int(mirrors)): url = self.mirror_link % (u['id'], u['Hoster'], x + 1) if season and episode: url += "&Season=%s&Episode=%s" % (season, episode) try: sources.append( {'source': hoster, 'quality': 'SD', 'language': 'de', 'url': url, 'direct': False, 'debridonly': False}) except: pass return sources except: return sources
def strip_domain(url): try: if url.lower().startswith('http') or url.startswith('/'): url = re.findall('(?://.+?|)(/.+)', url)[0] url = client.replaceHTMLCodes(url) url = url.encode('utf-8') return url except: return
def resolve(self, url): try: url = json.loads(client.request(url)).get('code') url = url.replace('\/', '/') url = client.replaceHTMLCodes(url).encode('utf-8') if url.startswith('/'): url = 'https:%s' % url return url except: return
def sources(self, url, hostDict, hostprDict): sources = [] try: if url is None: return sources url = urlparse.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 = urlparse.urljoin(self.base_link, data[0]) url = client.replaceHTMLCodes(url) url = url.encode('utf-8') host = data[1] valid, host = source_utils.is_host_valid(host, hostDict) if not valid: raise Exception() quality = client.parseDOM(i, 'span', ret='class')[0] quality, info = source_utils.get_release_quality( quality, url) sources.append({ 'source': host, 'quality': quality, 'language': 'en', 'url': url, 'direct': False, 'debridonly': False }) except BaseException: pass return sources except Exception: return sources
def resolve(self, url): try: r = client.request(url) r = dom_parser2.parse_dom( r, 'a', req=['href', 'data-episodeid', 'data-linkid'])[0] url = r.attrs['href'] url = client.replaceHTMLCodes(url) url = url.encode('utf-8') return url except: return
def getTVShowTranslation(self, thetvdb, lang): try: url = 'http://thetvdb.com/api/%s/series/%s/%s.xml' % ( 'MUQ2MkYyRjkwMDMwQzQ0NA=='.decode('base64'), thetvdb, lang) r = client.request(url) title = client.parseDOM(r, 'SeriesName')[0] title = client.replaceHTMLCodes(title) title = title.encode('utf-8') return title except: pass
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 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]) urls = self.search(data['title'], data['year']) for url in urls: try: link = client.replaceHTMLCodes(url[1]) link = link.encode('utf-8') if link in sources: continue if 'snahp' in link: data = client.request(link) data = client.parseDOM(data, 'center') data = [i for i in data if 'Hidden Link' in i][0] link = client.parseDOM(data, 'a', ret='href')[0] if 'google' in link: quality, info2 = source_utils.get_release_quality( url[0], link) sources.append({ 'source': 'gvideo', 'quality': quality, 'language': 'en', 'url': link, 'direct': False, 'debridonly': False }) else: host = re.findall( '([\w]+[.][\w]+)$', urlparse.urlparse(link.strip().lower()).netloc)[0] if host in hostDict: host = host.encode('utf-8') quality, info2 = source_utils.get_release_quality( url[0], link) sources.append({ 'source': host, 'quality': quality, 'language': 'en', 'url': link, 'direct': False, 'debridonly': False }) except BaseException: pass return sources except BaseException: return sources
def resolve(self, url): try: h = urlparse.urlparse(url.strip().lower()).netloc r = client.request(url) r = r.rsplit('"underplayer"')[0].rsplit("'underplayer'")[0] u = re.findall('\'(.+?)\'', r) + re.findall('\"(.+?)\"', r) u = [client.replaceHTMLCodes(i) for i in u] u = [i for i in u if i.startswith('http') and not h in i] url = u[-1].encode('utf-8') return url except: return
def sources(self, url, hostDict, hostprDict): try: sources = [] if url == None: return sources 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') if url == None: url = self.searchShow(data['tvshowtitle'], data['season'], aliases, headers) else: url = self.searchMovie(data['title'], data['year'], aliases, headers) if url == None: url = '%s/film/%s/watching.html?ep=0' % (self.base_link, cleantitle.geturl(data['title'])) if url == None: raise Exception() r = client.request(url, headers=headers, timeout='10') 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: if '123movieshd' in link or 'seriesonline' in link: r = client.request(link, headers=headers, timeout='10') r = re.findall('(https:.*?redirector.*?)[\'\"]', r) for i in r: try: sources.append({'source': 'gvideo', 'quality': directstream.googletag(i)[0]['quality'], 'language': 'en', 'url': i, 'direct': True, 'debridonly': False}) except: pass else: try: host = re.findall('([\w]+[.][\w]+)$', urlparse.urlparse(link.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': 'SD', 'language': 'en', 'url': link, 'direct': False, 'debridonly': False}) except: pass 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' % (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 episode(self, url, imdb, tvdb, title, premiered, season, episode): try: if url is None: return url = urlparse.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) url = url.encode('utf-8') return url except BaseException: return
def parse(url): try: url = client.replaceHTMLCodes(url) except: pass try: url = urlparse.parse_qs(urlparse.urlparse(url).query)['u'][0] except: pass try: url = urlparse.parse_qs(urlparse.urlparse(url).query)['q'][0] except: pass return url
def episode(self, url, imdb, tvdb, title, premiered, season, episode): try: if not url: return r = client.request(urlparse.urljoin(self.base_link, url)) r = client.parseDOM(r, 'a', attrs={'class': 'item', 'href': '[^\'"]*/saison-%s/episode-%s[^\'"]*' % (season, episode)}, ret='href')[0] url = re.findall('(?://.+?|)(/.+)', r)[0] url = client.replaceHTMLCodes(url) url = url.encode('utf-8') return url except: return
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': True }) except Exception: pass
def sources(self, url, hostDict, hostprDict): try: sources = [] if url == None: return sources url = urlparse.urljoin(self.base_link, url) r = proxy.request(url, 'tv shows') links = client.parseDOM(r, 'a', ret='href', attrs={'target': '.+?'}) links = [x for y, x in enumerate(links) if x not in links[:y]] for i in links: try: url = i url = proxy.parse(url) url = urlparse.parse_qs( urlparse.urlparse(url).query)['r'][0] url = url.decode('base64') 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 = host.encode('utf-8') sources.append({ 'source': host, 'quality': 'SD', 'language': 'en', 'url': url, 'direct': False, 'debridonly': False }) except: pass return sources except: return sources
def sources(self, url, hostDict, hostprDict): sources = [] try: if not url: return sources url = urlparse.urljoin(self.base_link, url) r = self.scraper.get(url).content r = r.replace('\\"', '"') links = dom_parser.parse_dom(r, 'tr', attrs={'id': 'tablemoviesindex2'}) for i in links: try: host = dom_parser.parse_dom(i, 'img', req='alt')[0].attrs['alt'] host = host.split()[0].rsplit('.', 1)[0].strip().lower() host = host.encode('utf-8') valid, host = source_utils.is_host_valid(host, hostDict) if not valid: continue url = dom_parser.parse_dom(i, 'a', req='href')[0].attrs['href'] url = client.replaceHTMLCodes(url) url = urlparse.urljoin(self.base_link, url) url = url.encode('utf-8') sources.append({ 'source': host, 'quality': 'SD', 'language': 'en', 'url': url, 'direct': False, 'debridonly': False }) except: pass return sources except: return sources
def __search(self, titles, year): try: query = self.search_link % (urllib.quote_plus( cleantitle.query(titles[0] + ' ' + year))) query = urlparse.urljoin(self.base_link, query) t = [cleantitle.get(i) for i in set(titles) if i] r = self.scraper.get(query).content r = dom_parser.parse_dom(r, 'figure', attrs={'class': 'pretty-figure'}) r = dom_parser.parse_dom(r, 'figcaption') for i in r: title = client.replaceHTMLCodes(i[0]['title']) title = cleantitle.get(title) if title in t: x = dom_parser.parse_dom(i, 'a', req='href') return source_utils.strip_domain(x[0][0]['href']) return except: return
def sources(self, url, hostDict, hostprDict): sources = [] try: if url is None: return sources url = urlparse.urljoin(self.base_link, url) if not url.startswith('http') else url result = self.scraper.get(url).content links = client.parseDOM(result, '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 = urlparse.urljoin(self.base_link, data[0]) url = client.replaceHTMLCodes(url) url = url.encode('utf-8') host = data[1] valid, host = source_utils.is_host_valid(host, hostDict) if not valid: raise Exception() quality = client.parseDOM(i, 'span', ret='class')[0] quality, info = source_utils.get_release_quality( quality, url) sources.append({'source': host, 'quality': quality, 'language': 'en', 'url': url, 'direct': False, 'debridonly': False}) except Exception: pass return sources except Exception: return sources
def episode(self, url, imdb, tvdb, title, premiered, season, episode): try: if url == None: return url = '%s/serie/%s' % (self.base_link, url) r = proxy.request(url, 'tv shows') r = client.parseDOM(r, 'li', attrs={'itemprop': 'episode'}) t = cleantitle.get(title) r = [(client.parseDOM(i, 'a', ret='href'), client.parseDOM(i, 'span', attrs={'itemprop': 'name'}), re.compile('(\d{4}-\d{2}-\d{2})').findall(i)) for i in r] r = [(i[0], i[1][0].split(' ')[-1], i[2]) for i in r if i[1]] + [(i[0], None, i[2]) for i in r if not i[1]] r = [(i[0], i[1], i[2][0]) for i in r if i[2]] + [(i[0], i[1], None) for i in r if not i[2]] r = [(i[0][0], i[1], i[2]) for i in r if i[0]] url = [ i for i in r if t == cleantitle.get(i[1]) and premiered == i[2] ][:1] if not url: url = [i for i in r if t == cleantitle.get(i[1])] if len(url) > 1 or not url: url = [i for i in r if premiered == i[2]] if len(url) > 1 or not url: raise Exception() url = url[0][0] url = proxy.parse(url) url = re.findall('(?://.+?|)(/.+)', url)[0] url = client.replaceHTMLCodes(url) url = url.encode('utf-8') return url except: return
def sources(self, url, hostDict, hostprDict): sources = [] try: if not url: return sources r = client.request(urlparse.urljoin(self.base_link, url)) r = dom_parser.parse_dom(r, 'div', attrs={'id': 'entries'}) links = re.findall('''(?:link|file)["']?\s*:\s*["'](.+?)["']''', ''.join([i.content for i in r])) links += [l.attrs['src'] for i in r for l in dom_parser.parse_dom(i, 'iframe', req='src')] links += [l.attrs['src'] for i in r for l in dom_parser.parse_dom(i, 'source', req='src')] for i in links: try: i = re.sub('\[.+?\]|\[/.+?\]', '', i) i = client.replaceHTMLCodes(i) valid, host = source_utils.is_host_valid(i, hostDict) if not valid: continue sources.append({'source': host, 'quality': 'SD', 'language': 'ko', 'url': i, 'direct': False, 'debridonly': False}) except: pass return sources except: return sources
def __search(self, title, localtitle, year, content_type): try: t = cleantitle.get(title) tq = cleantitle.get(localtitle) y = [ '%s' % str(year), '%s' % str(int(year) + 1), '%s' % str(int(year) - 1), '0' ] query = urlparse.urljoin(self.base_link, self.search_link) post = urllib.urlencode({'k': "%s"}) % tq r = client.request(query, post=post) r = json.loads(r) r = [ i.get('result') for i in r if i.get('type', '').encode('utf-8') == content_type ] r = [(i.get('url'), i.get('originalTitle'), i.get('title'), i.get('anneeProduction', 0), i.get('dateStart', 0)) for i in r] r = [(i[0], re.sub('<.+?>|</.+?>', '', i[1] if i[1] else ''), re.sub('<.+?>|</.+?>', '', i[2] if i[2] else ''), i[3] if i[3] else re.findall('(\d{4})', i[4])[0]) for i in r if i[3] or i[4]] r = sorted(r, key=lambda i: int(i[3]), reverse=True) # with year > no year r = [ i[0] for i in r if i[3] in y and (t.lower() == cleantitle.get(i[1].lower()) or tq.lower() == cleantitle.query(i[2].lower())) ][0] url = re.findall('(?://.+?|)(/.+)', r)[0] url = client.replaceHTMLCodes(url) url = url.encode('utf-8') return url except: return