def sources(self, url, hostDict, hostprDict): try: sources = [] if url == None: return sources r = cache.get(client.request, 1, url) 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(url.strip().lower()).netloc)[0] host = client.replaceHTMLCodes(host) try: host = host.encode('utf-8') except: pass valid, host = source_utils.is_host_valid(host, hostDict) if valid: 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) try: host = host.encode('utf-8') except: pass if 'other' in host: continue if source_utils.limit_hosts() is True and host in str( sources): continue valid, host = source_utils.is_host_valid( host, hostDict) if valid: sources.append({ 'source': host, 'quality': 'SD', 'language': 'en', 'url': url.replace('\/', '/'), 'direct': False, 'debridonly': False }) except: pass return sources except: return sources
def sources(self, url, hostDict, hostprDict): sources = [] try: if not url: 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')) episode = data.get('episode') r = client.request(url) aj = self.__get_ajax_object(r) b = dom_parser.parse_dom(r, 'img', attrs={'class': 'dgvaup'}, req='data-img')[0].attrs['data-img'] if episode: r = dom_parser.parse_dom(r, 'a', attrs={ 'class': 'btn-stream-ep', 'data-episode': episode }, req=['data-episode', 'data-server']) else: r = dom_parser.parse_dom(r, 'div', attrs={'id': 'lang-de'}) r = dom_parser.parse_dom(r, 'div', attrs={'class': 'movie'}) r = dom_parser.parse_dom(r, 'a', attrs={'class': 'btn-stream'}, req=['data-episode', 'data-server']) r = [(i.attrs['data-episode'], i.attrs['data-server']) for i in r] for epi, server in r: try: x = { 'action': aj.get('load_episodes'), 'episode': epi, 'pid': aj.get('postid'), 'server': server, 'nonce': aj.get('nonce'), 'b': b } x = client.request(aj.get('ajax_url'), post=x, XHR=True, referer=url) x = json.loads(x) q = source_utils.label_to_quality(x.get('q')) x = json.loads(base64.decodestring(x.get('u'))) u = source_utils.evp_decode(x.get('ct'), base64.decodestring(b), x.get('s').decode("hex")) u = u.replace('\/', '/').strip('"') valid, host = source_utils.is_host_valid(u, hostDict) if not valid: continue sources.append({ 'source': host, 'quality': q, 'language': 'de', 'url': u, 'direct': False, 'debridonly': False, 'checkquality': True }) except: pass return sources except: return sources
def sources(self, url, hostDict, hostprDict): try: hostDict = hostDict + hostprDict sources = [] query_bases = [] options = [] if url is None: return sources if not debrid.status(): return sources data = urlparse.parse_qs(url) data = dict([(i, data[i][0]) if data[i] else (i, '') for i in data]) title = (data['tvshowtitle'] if 'tvshowtitle' in data else data['title']) hdlr = 'S%02dE%02d' % (int(data['season']), int(data['episode'])) if 'tvshowtitle' in data else data['year'] # tvshowtitle if 'tvshowtitle' in data: query_bases.append('%s ' % (data['tvshowtitle'].replace("-", ""))) if 'year' in data: query_bases.append('%s %s ' % (data['tvshowtitle'], data['year'])) options.append('S%02dE%02d' % (int(data['season']), int(data['episode']))) options.append('S%02d' % (int(data['season']))) else: query_bases.append('%s %s ' % (data['title'], data['year'])) query_bases.append('%s ' % (data['title'])) query_bases.append('2160p') query_bases.append('') for option in options: for query_base in query_bases: q = re.sub('(\\\|/| -|:|;|\*|\?|"|\'|<|>|\|)', '', query_base + option) q = q.replace(" ", " ").replace(" ", "+") url = self.base_link + self.search_link % q html = self.scraper.get(url) if html.status_code == 200: posts = client.parseDOM(html.content, "div", attrs={"class": "title"}) for post in posts: url = client.parseDOM(post, "a", ret='href') if len(url) > 0: html = self.scraper.get(url[0]) if html.status_code == 200: quotes = client.parseDOM(html.content, "div", attrs={"class": "dlinks"}) for quote in quotes: hrefs = client.parseDOM(quote, "a", ret='href') if not hrefs: continue for href in hrefs: quality = source_utils.check_sd_url(href) href = href.encode('utf-8') valid, host = source_utils.is_host_valid(href, hostDict) if any(x in href for x in ['.rar', '.zip', '.iso']): continue if not valid: continue if hdlr in href.upper() and cleantitle.get(title) in cleantitle.get(href): sources.append( {'source': host, 'quality': quality, 'language': 'en', 'url': href, 'direct': False, 'debridonly': False}) if len(sources) > 0: return sources return sources except: return sources
def sources(self, url, hostDict, hostprDict): sources = [] try: if url is None: return sources typ = url[4] headers = { "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:60.0) Gecko/20100101 Firefox/60.0", "http.content_type": "application/x-www-form-urlencoded; charset=UTF-8" } data = '' if typ == "SERIAL": title = url[0] id = url[1] year = url[2] orgtitle = url[3] sezon = url[5] epizod = url[6] if orgtitle != "0": data = { "id": int(id), "type": typ, "title": title, "year": int(year), "sezon": str(sezon), "odcinek": str(epizod), "site": "filmdb", "browser": "chrome" } else: data = { "id": int(id), "type": typ, "title": title, "originalTitle": str(orgtitle), "year": int(year), "sezon": str(sezon), "odcinek": str(epizod), "site": "filmdb", "browser": "chrome" } if typ == "FILM": title = url[0] id = url[1] year = url[2] orgtitle = url[3] if orgtitle != "0": data = { "id": int(id), "type": typ, "title": str(title), "originalTitle": str(orgtitle), "year": int(year), "site": "filmdb", "browser": "chrome" } else: data = { "id": int(id), "type": typ, "title": str(title), "year": int(year), "site": "filmdb", "browser": "chrome" } data = {"json": json.dumps(data, ensure_ascii=False)} response = requests.post("http://fboost.pl/api/api.php", data=data, headers=headers) content = json.loads(response.content) for code in zip(content[u'link'], content[u'wersja']): wersja = str(code[1]) lang, info = self.get_lang_by_type(wersja) test = requests.post("http://fboost.pl/api/player.php?src=%s" % code[0]).content link = re.search("""iframe src="(.*)" style""", test) link = link.group(1) if len(link) < 2: continue if "cda.pl" in link: try: response = requests.get(link).content test = client.parseDOM( response, 'div', attrs={'class': 'wrapqualitybtn'}) urls = client.parseDOM(test, 'a', ret='href') for url in urls: valid, host = source_utils.is_host_valid( url, hostDict) q = source_utils.check_url(url) sources.append({ 'source': host, 'quality': q, 'language': lang, 'url': url, 'info': info, 'direct': False, 'debridonly': False }) continue except: pass if "rapidvideo.com" in link: try: response = requests.get(link).content test = re.findall( """(https:\/\/www.rapidvideo.com\/e\/.*)">""", response) numGroups = len(test) for i in range(1, numGroups): url = test[i] valid, host = source_utils.is_host_valid( url, hostDict) q = source_utils.check_url(url) sources.append({ 'source': host, 'quality': q, 'language': lang, 'url': url, 'info': info, 'direct': False, 'debridonly': False }) continue except: pass valid, host = source_utils.is_host_valid(link, hostDict) q = source_utils.check_url(link) sources.append({ 'source': host, 'quality': q, 'language': lang, 'url': link, 'info': info, 'direct': False, 'debridonly': False }) return sources except: return sources
def sources(self, url, hostDict, hostprDict): sources = [] try: if not url: return sources data = urlparse.parse_qs(url) data = dict([(i, data[i][0]) if data[i] else (i, '') for i in data]) url = data.get('url') episode = int(data.get('episode', 1)) r = client.request(urlparse.urljoin(self.base_link, url)) r = dom_parser.parse_dom(r, 'div', attrs={'id': 'streams'}) rels = dom_parser.parse_dom(r, 'ul', attrs={'class': 'nav'}) rels = dom_parser.parse_dom(rels, 'li') rels = dom_parser.parse_dom( rels, 'a', attrs={'href': re.compile('#stream_\d*')}, req='href') rels = [(re.findall('stream_(\d+)', i.attrs['href']), re.findall('flag-(\w{2})', i.content)) for i in rels if i] rels = [(i[0][0], ['subbed'] if i[1][0] != 'de' else []) for i in rels if i[0] and 'de' in i[1]] for id, info in rels: rel = dom_parser.parse_dom(r, 'div', attrs={'id': 'stream_%s' % id}) rel = [(dom_parser.parse_dom( i, 'div', attrs={'id': 'streams_episodes_%s' % id}), dom_parser.parse_dom(i, 'tr')) for i in rel] rel = [(i[0][0].content, [x for x in i[1] if 'fa-desktop' in x.content]) for i in rel if i[0] and i[1]] rel = [(i[0], dom_parser.parse_dom(i[1][0].content, 'td')) for i in rel if i[1]] rel = [(i[0], re.findall('\d{3,4}x(\d{3,4})$', i[1][0].content)) for i in rel if i[1]] rel = [(i[0], source_utils.label_to_quality(i[1][0])) for i in rel if len(i[1]) > 0] for html, quality in rel: try: s = dom_parser.parse_dom( html, 'a', attrs={ 'href': re.compile('#streams_episodes_%s_\d+' % id) }) s = [(dom_parser.parse_dom( i, 'div', attrs={'data-loop': re.compile('\d+')}, req='data-loop'), dom_parser.parse_dom(i, 'span')) for i in s] s = [(i[0][0].attrs['data-loop'], [ x.content for x in i[1] if '<strong' in x.content ]) for i in s if i[0]] s = [(i[0], re.findall('<.+?>(\d+)</.+?> (.+?)$', i[1][0])) for i in s if len(i[1]) > 0] s = [(i[0], i[1][0]) for i in s if len(i[1]) > 0] s = [(i[0], int(i[1][0]), re.findall('Episode (\d+):', i[1][1]), re.IGNORECASE) for i in s if len(i[1]) > 1] s = [(i[0], i[1], int(i[2][0]) if len(i[2]) > 0 else -1) for i in s] s = [(i[0], i[2] if i[2] >= 0 else i[1]) for i in s] s = [i[0] for i in s if i[1] == episode][0] enc = dom_parser.parse_dom( html, 'div', attrs={ 'id': re.compile('streams_episodes_%s_%s' % (id, s)) }, req='data-enc')[0].attrs['data-enc'] hosters = dom_parser.parse_dom( html, 'a', attrs={ 'href': re.compile('#streams_episodes_%s_%s' % (id, s)) }) hosters = [ dom_parser.parse_dom(i, 'i', req='class') for i in hosters ] hosters = [ re.findall('hoster-(\w+)', ' '.join([x.attrs['class'] for x in i])) for i in hosters if i ][0] hosters = [(source_utils.is_host_valid( re.sub('(co|to|net|pw|sx|tv|moe|ws|icon)$', '', i), hostDict), i) for i in hosters] hosters = [(i[0][1], i[1]) for i in hosters if i[0] and i[0][0]] info = ' | '.join(info) for source, hoster in hosters: sources.append({ 'source': source, 'quality': quality, 'language': 'de', 'url': [enc, hoster], 'info': info, 'direct': False, 'debridonly': False, 'checkquality': True }) 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 = client.request(url) rels = dom_parser.parse_dom(r, 'nav', attrs={'class': 'player'}) rels = dom_parser.parse_dom(rels, 'ul', attrs={'class': 'idTabs'}) rels = dom_parser.parse_dom(rels, 'li') rels = [(dom_parser.parse_dom(i, 'a', attrs={'class': 'options'}, req='href'), dom_parser.parse_dom(i, 'img', req='src')) for i in rels] rels = [(i[0][0].attrs['href'][1:], re.findall('/flags/(\w+)\.png$', i[1][0].attrs['src'])) for i in rels if i[0] and i[1]] rels = [ i[0] for i in rels if len(i[1]) > 0 and i[1][0].lower() == 'de' ] r = [dom_parser.parse_dom(r, 'div', attrs={'id': i}) for i in rels] r = [(re.findall('link"?\s*:\s*"(.+?)"', ''.join([x.content for x in i])), dom_parser.parse_dom(i, 'iframe', attrs={'class': 'metaframe'}, req='src')) for i in r] r = [ i[0][0] if i[0] else i[1][0].attrs['src'] for i in r if i[0] or i[1] ] for i in r: try: i = re.sub('\[.+?\]|\[/.+?\]', '', i) i = client.replaceHTMLCodes(i) if not i.startswith('http'): i = self.__decode_hash(i) if 'play.seriesever' in i: i = client.request(i) i = dom_parser.parse_dom(i, 'iframe', req='src') if len(i) < 1: continue i = i[0].attrs['src'] valid, host = source_utils.is_host_valid(i, hostDict) if not valid: continue urls, host, direct = source_utils.check_directstreams( i, host) for x in urls: sources.append({ 'source': host, 'quality': x['quality'], 'language': 'de', 'url': x['url'], 'direct': direct, '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: 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 = title.replace('&', 'and').replace('Special Victims Unit', 'SVU') hdlr = 'S%02dE%02d' % (int(data['season']), int( data['episode'])) if 'tvshowtitle' in data else data['year'] query = '%s %s' % (title, hdlr) query = re.sub('(\\\|/| -|:|;|\*|\?|"|\'|<|>|\|)', '', query) url = self.search_link % quote_plus(query) url = urljoin(self.base_link, url).replace('-', '+') # log_utils.log('url = %s' % url, log_utils.LOGDEBUG) r = client.request(url) posts = client.parseDOM(r, "div", attrs={"class": "item-post"}) posts = client.parseDOM(posts, "h3") items = [] for post in posts: try: u = client.parseDOM(post, 'a', ret='href')[0] name1 = u.split('https://onceddl.org/')[1].rstrip('/') name1 = re.sub('[^A-Za-z0-9]+', '.', name1) r = client.request(u) u = client.parseDOM(r, "div", attrs={"class": "single-link"}) for t in u: r = client.parseDOM(t, 'a', ret='href') for url in r: if any(x in url for x in ['.rar', '.zip', '.iso', '.sample.']): continue valid, host = source_utils.is_host_valid( url, hostDict) if valid: if 'OnceDDL_' in url: name = url.split('OnceDDL_')[1] name = re.sub('[^A-Za-z0-9]+', '.', name) else: name = name1 if source_utils.remove_lang(name): continue t = name.split(hdlr)[0].replace( data['year'], '').replace('(', '').replace( ')', '').replace('&', 'and') if cleantitle.get(t) != cleantitle.get(title): continue if hdlr not in name: continue if url in str(sources): continue quality, info = source_utils.get_release_quality( name, url) # size info not available on onceddl dsize = 0 sources.append({ 'source': host, 'quality': quality, 'language': 'en', 'url': url, 'info': info, 'direct': False, 'debridonly': True, 'size': dsize }) except: source_utils.scraper_error('ONCEDDL') pass return sources except: source_utils.scraper_error('ONCEDDL') return sources
def sources(self, url, hostDict, hostprDict): try: sources = [] if url == None: return sources if not str(url).startswith('http'): 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'] if 'season' in data: season = data['season'] if 'episode' in data: episode = data['episode'] year = data['year'] r = client.request(self.base_link, output='extended', timeout='10') cookie = r[4]; headers = r[3]; result = r[0] headers['Cookie'] = cookie query = urlparse.urljoin(self.base_link, self.search_link % urllib.quote_plus(cleantitle.getsearch(title))) r = client.request(query, headers=headers, XHR=True) r = json.loads(r)['content'] r = zip(client.parseDOM(r, 'a', ret='href'), client.parseDOM(r, 'a')) if 'tvshowtitle' in data: cltitle = cleantitle.get(title + 'season' + season) cltitle2 = cleantitle.get(title + 'season%02d' % int(season)) r = [i for i in r if cltitle == cleantitle.get(i[1]) or cltitle2 == cleantitle.get(i[1])] vurl = '%s%s-episode-%s' % (self.base_link, str(r[0][0]).replace('/info', ''), episode) vurl2 = None else: cltitle = cleantitle.getsearch(title) cltitle2 = cleantitle.getsearch('%s (%s)' % (title, year)) r = [i for i in r if cltitle2 == cleantitle.getsearch(i[1]) or cltitle == cleantitle.getsearch(i[1])] vurl = '%s%s-episode-0' % (self.base_link, str(r[0][0]).replace('/info', '')) vurl2 = '%s%s-episode-1' % (self.base_link, str(r[0][0]).replace('/info', '')) r = client.request(vurl, headers=headers) headers['Referer'] = vurl slinks = client.parseDOM(r, 'div', attrs={'class': 'anime_muti_link'}) slinks = client.parseDOM(slinks, 'li', ret='data-video') if len(slinks) == 0 and not vurl2 == None: r = client.request(vurl2, headers=headers) headers['Referer'] = vurl2 slinks = client.parseDOM(r, 'div', attrs={'class': 'anime_muti_link'}) slinks = client.parseDOM(slinks, 'li', ret='data-video') for slink in slinks: try: if 'vidnode.net/streaming.php' in slink: r = client.request('https:%s' % slink, headers=headers) clinks = re.findall(r'sources:\[(.*?)\]', r)[0] clinks = re.findall(r'file:\s*\'(http[^\']+)\',label:\s*\'(\d+)', clinks) for clink in clinks: q = source_utils.label_to_quality(clink[1]) sources.append( {'source': 'cdn', 'quality': q, 'language': 'en', 'url': clink[0], 'direct': True, 'debridonly': False}) else: quality = source_utils.check_url(slink) valid, hoster = source_utils.is_host_valid(slink, hostDict) if valid: sources.append({'source': hoster, 'quality': quality, 'language': 'en', 'url': slink, '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 = client.request(url) r = dom_parser.parse_dom(r, 'div', attrs={'class': 'watch_video'}) r = [ i.attrs['data-src'] for i in dom_parser.parse_dom(r, 'iframe', req='data-src') ] for i in r: try: if 'k-vid' in i: i = client.request(i, referer=url) i = dom_parser.parse_dom( i, 'div', attrs={'class': 'videocontent'}) gvid = dom_parser.parse_dom(i, 'source', req='src') gvid = [ (g.attrs['src'], g.attrs['label'] if 'label' in g.attrs else 'SD') for g in gvid ] gvid = [(x[0], source_utils.label_to_quality(x[1])) for x in gvid if x[0] != 'auto'] for u, q in gvid: try: tag = directstream.googletag(u) if tag: sources.append({ 'source': 'gvideo', 'quality': tag[0].get('quality', 'SD'), 'language': 'ko', 'url': u, 'direct': True, 'debridonly': False }) else: sources.append({ 'source': 'CDN', 'quality': q, 'language': 'ko', 'url': u, 'direct': True, 'debridonly': False }) except: pass i = dom_parser.parse_dom(i, 'iframe', attrs={'id': 'embedvideo'}, req='src')[0].attrs['src'] 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 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 sources(self, url, hostDict, hostprDict): try: sources = [] if url is None: return sources if debrid.status() is False: return sources data = urlparse.parse_qs(url) data = dict([(i, data[i][0]) if data[i] else (i, '') for i in data]) title = data['tvshowtitle'] if 'tvshowtitle' in data else data[ 'title'] title = title.replace('&', 'and').replace('Special Victims Unit', 'SVU') hdlr = 'S%02dE%02d' % (int(data['season']), int( data['episode'])) if 'tvshowtitle' in data else data['year'] query = '%s %s' % (title, hdlr) query = re.sub('(\\\|/| -|:|;|\*|\?|"|\'|<|>|\|)', '', query) url = urlparse.urljoin(self.base_link, self.search_link) # url = url % urllib.quote_plus(query) url = url % urllib.quote(query) # log_utils.log('url = %s' % url, log_utils.LOGDEBUG) r = client.request(url) r = client.parseDOM(r, 'h2') # z = zip(client.parseDOM(r, 'a', ret='href'), client.parseDOM(r, 'a', ret='title')) z = zip(client.parseDOM(r, 'a', ret='href'), client.parseDOM(r, 'a')) if 'tvshowtitle' in data: posts = [(i[1], i[0]) for i in z] else: posts = [(i[1], i[0]) for i in z] hostDict = hostprDict + hostDict items = [] for post in posts: try: try: t = post[0].encode('utf-8') except: t = post[0] u = client.request(post[1]) u = re.findall('\'(http.+?)\'', u) + re.findall( '\"(http.+?)\"', u) u = [i for i in u if '/embed/' not in i] u = [i for i in u if 'youtube' not in i] try: s = re.search( '((?:\d+\.\d+|\d+\,\d+|\d+)\s*(?:GB|GiB|MB|MiB))', post) s = s.groups()[0] if s else '0' except: s = '0' pass items += [(t, i, s) for i in u] except: source_utils.scraper_error('MYVIDEOLINK') pass for item in items: try: url = item[1] url = client.replaceHTMLCodes(url) url = url.encode('utf-8') void = ('.rar', '.zip', '.iso', '.part', '.png', '.jpg', '.bmp', '.gif') if url.endswith(void): continue valid, host = source_utils.is_host_valid(url, hostDict) if not valid: continue host = client.replaceHTMLCodes(host) host = host.encode('utf-8') name = item[0] name = client.replaceHTMLCodes(name) t = name.split(hdlr)[0].replace(data['year'], '').replace( '(', '').replace(')', '').replace('&', 'and') if cleantitle.get(t) != cleantitle.get(title): continue if hdlr not in name: continue quality, info = source_utils.get_release_quality(name, url) try: size = re.findall( '((?:\d+\.\d+|\d+\,\d+|\d+) (?:GB|GiB|MB|MiB))', item[2])[-1] div = 1 if size.endswith(('GB', 'GiB')) else 1024 size = float(re.sub('[^0-9|/.|/,]', '', size)) / div size = '%.2f GB' % size info.append(size) except: pass info = ' | '.join(info) sources.append({ 'source': host, 'quality': quality, 'language': 'en', 'url': url, 'info': info, 'direct': False, 'debridonly': True }) except: source_utils.scraper_error('MYVIDEOLINK') pass return sources except: source_utils.scraper_error('MYVIDEOLINK') return sources
def sources(self, url, hostDict, hostprDict): try: sources = [] if url is None: return sources if debrid.status() is False: return sources hostDict = hostprDict + hostDict data = urlparse.parse_qs(url) data = dict([(i, data[i][0]) if data[i] else (i, '') for i in data]) title = data['tvshowtitle'] if 'tvshowtitle' in data else data['title'] title = title.replace('&', 'and').replace('Special Victims Unit', 'SVU') hdlr = 'S%02dE%02d' % (int(data['season']), int(data['episode'])) if 'tvshowtitle' in data else data['year'] query = '%s %s' % (title, hdlr) query = re.sub('(\\\|/| -|:|;|\*|\?|"|\'|<|>|\|)', '', query) url = self.search_link % urllib.quote_plus(query) url = urlparse.urljoin(self.base_link, url).replace('-', '+') # log_utils.log('url = %s' % url, log_utils.LOGDEBUG) r = client.request(url) # r = self.scraper.get(url).content if r is None and 'tvshowtitle' in data: season = re.search('S(.*?)E', hdlr) season = season.group(1) url = title # r = self.scraper.get(url).content r = client.request(url) for loopCount in range(0,2): if loopCount == 1 or (r is None and 'tvshowtitle' in data): r = self.scraper.get(url).content # r = client.request(url) posts = client.parseDOM(r, "div", attrs={"class": "postpage_movie_download"}) items = [] for post in posts: try: u = client.parseDOM(post, 'a', ret='href') for i in u: name = str(i) items.append(name) except: pass if len(items) > 0: break for item in items: try: i = str(item) # r = self.scraper.get(i).content r = client.request(i) if r is None: continue tit = client.parseDOM(r, 'meta', attrs={'property': 'og:title'}, ret='content')[0] t = tit.split(hdlr)[0].replace(data['year'], '').replace('(', '').replace(')', '').replace('&', 'and') if cleantitle.get(t) != cleantitle.get(title): continue if hdlr not in tit: continue u = client.parseDOM(r, "div", attrs={"class": "multilink_lnks"}) for t in u: r = client.parseDOM(t, 'a', ret='href') for url in r: if 'www.share-online.biz' in url: continue if url in str(sources): continue quality, info = source_utils.get_release_quality(url, url) valid, host = source_utils.is_host_valid(url, hostDict) if valid: sources.append({'source': host, 'quality': quality, 'language': 'en', 'url': url, 'info': info, 'direct': False, 'debridonly': True}) except: source_utils.scraper_error('2DDL') pass return sources except: source_utils.scraper_error('2DDL') return sources
def sources(self, url, hostDict, hostprDict): try: sources = [] if url is None: return sources if debrid.status() is False: raise Exception() data = urlparse.parse_qs(url) data = dict([(i, data[i][0]) if data[i] else (i, '') for i in data]) title = data['tvshowtitle'] if 'tvshowtitle' in data else data[ 'title'] hdlr = 'S%02dE%02d' % (int(data['season']), int( data['episode'])) if 'tvshowtitle' in data else data['year'] query = '%s S%02dE%02d' % (data['tvshowtitle'], int(data['season']), int(data['episode'])) \ if 'tvshowtitle' in data else '%s %s' % (data['title'], data['year']) url = self.search_link % urllib.quote_plus(query) url = urlparse.urljoin(self.base_link, url).replace('%3A+', '+') r = client.request(url) if r is None and 'tvshowtitle' in data: season = re.search('S(.*?)E', hdlr) season = season.group(1) url = title r = client.request(url) for loopCount in range(0, 2): if loopCount == 1 or (r is None and 'tvshowtitle' in data): r = client.request(url) posts = client.parseDOM(r, "h2", attrs={"class": "postTitle"}) hostDict = hostprDict + hostDict items = [] for post in posts: try: u = client.parseDOM(post, 'a', ret='href') for i in u: name = str(i) items.append(name) except: pass if len(items) > 0: break for item in items: try: i = str(item) r = client.request(i) u = client.parseDOM(r, "div", attrs={"class": "postContent"}) for t in u: r = client.parseDOM(t, 'a', ret='href') for url in r: quality, info = source_utils.get_release_quality( url) #if 'SD' in quality: continue valid, host = source_utils.is_host_valid( url, hostDict) sources.append({ 'source': host, 'quality': quality, 'language': 'en', 'url': url, 'info': info, 'direct': False, 'debridonly': True }) except: pass return sources except: return sources
def sources(self, url, hostDict, hostprDict): sources = [] try: if not url: return sources url = urlparse.urljoin(self.base_link, url) r = client.request(url, output='extended') headers = r[3] headers.update({ 'Cookie': r[2].get('Set-Cookie'), 'Referer': self.base_link }) r = r[0] rels = dom_parser.parse_dom(r, 'nav', attrs={'class': 'player'}) rels = dom_parser.parse_dom(rels, 'ul', attrs={'class': 'idTabs'}) rels = dom_parser.parse_dom(rels, 'li') rels = [(dom_parser.parse_dom(i, 'a', attrs={'class': 'options'}, req='href'), dom_parser.parse_dom(i, 'img', req='src')) for i in rels] rels = [(i[0][0].attrs['href'][1:], re.findall('/flags/(\w+)\.png$', i[1][0].attrs['src'])) for i in rels if i[0] and i[1]] rels = [ i[0] for i in rels if len(i[1]) > 0 and i[1][0].lower() == 'de' ] r = [dom_parser.parse_dom(r, 'div', attrs={'id': i}) for i in rels] links = re.findall('''(?:link|file)["']?\s*:\s*["'](.+?)["']''', ''.join([i[0].content for i in r])) links += [ l.attrs['src'] for i in r for l in dom_parser.parse_dom( i, 'iframe', attrs={'class': 'metaframe'}, 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) if '/play/' in i: i = urlparse.urljoin(self.base_link, i) if self.domains[0] in i: i = client.request(i, headers=headers, referer=url) for x in re.findall('''\(["']?(.*)["']?\)''', i): try: i += jsunpack.unpack( base64.decodestring( re.sub('"\s*\+\s*"', '', x))).replace('\\', '') except: pass for x in re.findall('(eval\s*\(function.*?)</script>', i, re.DOTALL): try: i += jsunpack.unpack(x).replace('\\', '') except: pass links = [(match[0], match[1]) for match in re.findall( '''['"]?file['"]?\s*:\s*['"]([^'"]+)['"][^}]*['"]?label['"]?\s*:\s*['"]([^'"]*)''', i, re.DOTALL)] links = [(x[0].replace('\/', '/'), source_utils.label_to_quality(x[1])) for x in links if '/no-video.mp4' not in x[0]] doc_links = [ directstream.google( 'https://drive.google.com/file/d/%s/view' % match) for match in re.findall( '''file:\s*["'](?:[^"']+youtu.be/([^"']+))''', i, re.DOTALL) ] doc_links = [(u['url'], u['quality']) for x in doc_links if x for u in x] links += doc_links for url, quality in links: if self.base_link in url: url = url + '|Referer=' + self.base_link sources.append({ 'source': 'gvideo', 'quality': quality, 'language': 'de', 'url': url, 'direct': True, 'debridonly': False }) else: try: # as long as resolveurl get no Update for this URL (So just a Temp-Solution) did = re.findall( 'youtube.googleapis.com.*?docid=(\w+)', i) if did: i = 'https://drive.google.com/file/d/%s/view' % did[ 0] valid, host = source_utils.is_host_valid( i, hostDict) if not valid: continue urls, host, direct = source_utils.check_directstreams( i, host) for x in urls: sources.append({ 'source': host, 'quality': x['quality'], 'language': 'de', 'url': x['url'], 'direct': direct, 'debridonly': False }) except: pass except: pass return sources except: return sources
def sources(self, url, hostDict, hostprDict): sources = [] 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]) title = data['title'] year = data['year'] query = '%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) posts = client.parseDOM(r, 'item') for post in posts: try: name = client.parseDOM(post, 'title') links = client.parseDOM(post, 'a', ret='href') t = re.sub('(\.|\(|\[|\s|)(\d{4})(\.|\)|\]|\s|)(.+|)', '', name[0]) if not cleantitle.get(t) == cleantitle.get(title): raise Exception() y = re.findall('\(\s*(\d{4})\s*\)', name[0])[0] if not y == year: raise Exception() for url in links: if any(x in url for x in [ '.online', 'xrysoi.se', 'filmer', '.bp', '.blogger' ]): continue url = client.replaceHTMLCodes(url) url = url.encode('utf-8') valid, host = source_utils.is_host_valid(url, hostDict) if 'hdvid' in host: valid = True if not valid: continue quality = 'SD' info = 'SUB' sources.append({ 'source': host, 'quality': quality, 'language': 'gr', 'url': url, 'info': info, 'direct': False, 'debridonly': False }) except: pass return sources except: return sources
def sources(self, url, hostDict, hostprDict): try: sources = [] try: search_url = url['url'] post = url['post'] referer = urlparse.urljoin(self.film_web, post['urlstrony']) result = self.scraper.post(search_url, data=post, headers={ 'referer': referer }).content if not result.startswith('http'): return sources valid, host = source_utils.is_host_valid(result, hostDict) q = source_utils.check_sd_url(result) info = '' if 'lektor' in result: info = 'Lektor' if 'napisy' in result: info = 'Napisy' first_found = { 'source': host, 'quality': '720p', 'language': 'pl', 'url': result, 'info': info, 'direct': False, 'debridonly': False } first_found['info'] = self.get_info_from_others(sources) sources.append(first_found) except: pass search_more_post = url['more'] # search_url = urlparse.urljoin(self.base_link, self.search_more) result = self.scraper.post(self.base_link2, data=search_more_post).content provider = client.parseDOM(result, 'option', ret='value') links = client.parseDOM(result, 'div', ret='data') wersja = client.parseDOM(result, 'div', attrs={'class': 'wersja'}) # result = dom_parser.parse_dom(result, 'a') counter = 0 for link in links: valid, host = source_utils.is_host_valid(link, hostDict) if not valid: continue q = source_utils.check_sd_url(link) sources.append({ 'source': host, 'quality': q, 'language': 'pl', 'url': link, 'info': wersja[counter], 'direct': False, 'debridonly': False }) counter += 1 return sources except: return sources
def sources(self, url, hostDict, hostprDict): try: sources = [] if url is None: return sources if debrid.status() is False: raise Exception() data = urlparse.parse_qs(url) data = dict([(i, data[i][0]) if data[i] else (i, '') for i in data]) title = data['tvshowtitle'] if 'tvshowtitle' in data else data['title'] hdlr = 'S%02dE%02d' % (int(data['season']), int(data['episode'])) if 'tvshowtitle' in data else data['year'] query = '%s s%02de%02d' % ( data['tvshowtitle'], int(data['season']), int(data['episode'])) if 'tvshowtitle' in data else '%s %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) posts = client.parseDOM(r, 'h2') hostDict = hostprDict + hostDict urls = [] for item in posts: try: item = re.compile('a href="(.+?)"').findall(item) name = item[0] query = query.replace(" ", "-").lower() if query not in name: continue name = client.replaceHTMLCodes(name) quality, info = source_utils.get_release_quality(name, item[0]) if any(x in quality for x in ['CAM', 'SD']): continue url = item links = self.links(url) urls += [(i, quality, info) for i in links] except: 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') valid, host = source_utils.is_host_valid(url, hostDict) if not valid: continue host = client.replaceHTMLCodes(host) host = host.encode('utf-8') sources.append({'source': host, 'quality': item[1], 'language': 'en', 'url': url, 'direct': False, 'debridonly': True}) return sources except: return sources
def sources(self, url, hostDict, hostprDict): try: sources = [] if url == None: return sources hostDict += [ 'akamaized.net', 'google.com', 'picasa.com', 'blogspot.com' ] result = self.scraper.get(url, timeout=10).content dom = dom_parser.parse_dom(result, 'a', req='data-video') urls = [ i.attrs['data-video'] if i.attrs['data-video'].startswith('https') else 'https:' + i.attrs['data-video'] for i in dom ] for url in urls: dom = [] if 'vidnode.net' in url: result = self.scraper.get(url, timeout=10).content dom = dom_parser.parse_dom(result, 'source', req=['src', 'label']) dom = [ (i.attrs['src'] if i.attrs['src'].startswith('https') else 'https:' + i.attrs['src'], i.attrs['label']) for i in dom if i ] elif 'ocloud.stream' in url: result = self.scraper.get(url, timeout=10).content base = re.findall('<base href="([^"]+)">', result)[0] hostDict += [base] dom = dom_parser.parse_dom(result, 'a', req=['href', 'id']) dom = [(i.attrs['href'].replace('./embed', base + 'embed'), i.attrs['id']) for i in dom if i] dom = [(re.findall("var\s*ifleID\s*=\s*'([^']+)", client.request(i[0]))[0], i[1]) for i in dom if i] if dom: try: for r in dom: valid, hoster = source_utils.is_host_valid( r[0], hostDict) if not valid: continue quality = source_utils.label_to_quality(r[1]) urls, host, direct = source_utils.check_directstreams( r[0], hoster) for x in urls: if direct: size = source_utils.get_size(x['url']) if size: sources.append({ 'source': host, 'quality': quality, 'language': 'en', 'url': x['url'], 'direct': direct, 'debridonly': False, 'info': size }) else: sources.append({ 'source': host, 'quality': quality, 'language': 'en', 'url': x['url'], 'direct': direct, 'debridonly': False }) except: pass else: valid, hoster = source_utils.is_host_valid(url, hostDict) if not valid: continue try: url.decode('utf-8') sources.append({ 'source': hoster, '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 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) r = client.request(surl, XHR=True, timeout='10') if not r: return sources r = json.loads(r) r = r['series'] for i in r: tit = i['original_name'] if cleantitle.get(title) != cleantitle.get(tit): continue slink = '/' + i['seo_name'] slink = urljoin(self.base_link, slink) r = client.request(slink, timeout='10') data = client.parseDOM(r, 'div', attrs={'class': 'el-item\s*'}) ep = [ i for i in client.parseDOM(data, 'a', ret='href') if hdlr in i.lower() ][0] r = client.request(ep, timeout='10') links = client.parseDOM(r, 'a', attrs={'class': 'watch-button'}, ret='href') for link in links: list = client.request(link, timeout='10') if not list: continue url = client.parseDOM( list, 'a', attrs={'class': 'watch-button actWatched'}, ret='href')[0] try: valid, host = source_utils.is_host_valid(url, hostDict) if not valid: continue sources.append({ 'source': host, 'quality': '720p', 'info': '', 'language': 'en', 'url': url, 'direct': False, 'debridonly': False }) except: source_utils.scraper_error('WATCHEPISODESERIES1') return sources return sources except: source_utils.scraper_error('WATCHEPISODESERIES1') 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]) url = self.searchMovie(data['title'], data['year']) if url is None: return sources r = client.request(url) data = client.parseDOM(r, 'div', attrs={'class': 'playex'})[0] frames = client.parseDOM(data, 'iframe', ret='src') frames += re.compile('''<iframe\s*src=['"](.+?)['"]''', re.DOTALL).findall(data) quality = client.parseDOM(r, 'span', attrs={'class': 'qualityx'})[0] for frame in frames: url = frame.split('=')[1] if frame.startswith('<') else frame url = client.replaceHTMLCodes(url) url = url.encode('utf-8') valid, host = source_utils.is_host_valid(url, hostDict) if valid: quality, info = source_utils.get_release_quality( quality, url) info = ' | '.join(info) sources.append({ 'source': host, 'quality': quality, 'language': 'en', 'url': url, 'info': info, 'direct': False, 'debridonly': False }) elif url.endswith('mp4'): url += '|User-Agent=%s' % urllib.quote_plus(client.agent()) sources.append({ 'source': 'MP4', 'quality': quality, 'language': 'en', 'url': url, 'direct': True, 'debridonly': False }) elif 'mystream' in url: data = client.request(url) links = dom_parser.parse_dom(data, 'source', req=['src', 'label']) for link in links: label = link.attrs['label'] url = link.attrs[ 'src'] + '|User-Agent=%s' % urllib.quote_plus( client.agent()) sources.append({ 'source': 'MYSTREAM', 'quality': label, 'language': 'en', 'url': url, 'direct': True, 'debridonly': False }) else: continue return sources except Exception: return sources
def sources(self, url, hostDict, hostprDict): sources = [] try: if url is None: return data = urlparse.parse_qs(url) data = dict((i, data[i][0]) for i in data) title = data['title'] year = data['year'] tit = cleantitle.geturl(title + ' ' + year) query = urlparse.urljoin(self.base_link, tit) r = self.scraper.get(query, params={ 'referer': self.base_link }).content if not data['imdb'] in r: return sources links = [] try: down = client.parseDOM(r, 'div', attrs={'id': 'tab-download'})[0] down = client.parseDOM(down, 'a', ret='href')[0] data = client.request(down) frames = client.parseDOM(data, 'div', attrs={'class': 'single-link'}) frames = [ client.parseDOM(i, 'a', ret='href')[0] for i in frames if i ] for i in frames: links.append(i) except Exception: pass try: streams = client.parseDOM(r, 'div', attrs={'id': 'tab-stream'})[0] streams = re.findall('''iframe src=(.+?) frameborder''', streams.replace('"', ''), re.I | re.DOTALL) for i in streams: links.append(i) except Exception: pass for url in links: try: valid, host = source_utils.is_host_valid(url, hostDict) if not valid: valid, host = source_utils.is_host_valid( url, hostprDict) if not valid: continue else: rd = True else: rd = False quality, info = source_utils.get_release_quality(url, url) host = client.replaceHTMLCodes(host) host = host.encode('utf-8') if rd: sources.append({ 'source': host, 'quality': quality, 'language': 'en', 'url': url, 'direct': False, 'debridonly': True }) else: sources.append({ 'source': host, 'quality': quality, 'language': 'en', 'url': url, 'direct': False, 'debridonly': False }) except Exception: pass return sources except Exception: return sources
def sources(self, url, hostDict, hostprDict): sources = [] try: if url is None: return sources if debrid.status() is False: raise Exception() hostDict = hostprDict + hostDict data = urlparse.parse_qs(url) data = dict([(i, data[i][0]) if data[i] else (i, '') for i in data]) ref_url = url = data['url'] 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'] hdlr2 = 'season-%01d-episode-%01d' % ( int(data['season']), int(data['episode'])) if 'tvshowtitle' in data else '' imdb = data['imdb'] content = 'episode' if 'tvshowtitle' in data else 'movie' season = data['season'] if 'season' in data else '0' episode = data['episode'] if 'episode' in data else '0' premiered = data['premiered'] if 'premiered' in data else '0' _headers = { 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:61.0) Gecko/20100101 Firefox/61.0' } r = client.request(url, headers=_headers) posts = dom_parser.parse_dom(r, 'article', {'class': ['post', 'excerpt']}) posts = [ (dom_parser.parse_dom(i, 'a', req=['href', 'title']), i.content) for i in posts if imdb in i.content or title.lower() in i.content.lower() and hdlr.lower() in i.content.lower() ] posts = [(i[0][0].attrs['title'], i[0][0].attrs['href'], i[1]) for i in posts] items = [] for item in posts: data = [] try: name = item[0] name = client.replaceHTMLCodes(name) if content == 'episode': if not hdlr2.lower() in item[1].lower(): if not premiered.replace('-', '').replace( '+', '') in item[1].lower().replace( '-', '').replace('+', ''): raise Exception() url = item[1] r = client.request(url, headers=_headers) data += client.parseDOM(r, 'div', attrs={'id': 'content'}) data += client.parseDOM(r, 'div', attrs={'id': 'comments'}) urls = dom_parser.parse_dom(data, 'a', req='href') urls = [i.attrs['href'] for i in urls] for url in urls: try: if any(x in url for x in ['.rar.', '.zip.', '.iso.']) or any( url.endswith(x) for x in ['.rar', '.zip', '.iso']): raise Exception() url = client.replaceHTMLCodes(url) url = url.encode('utf-8') valid, host = source_utils.is_host_valid( url, hostDict) if not valid: continue host = client.replaceHTMLCodes(host) host = host.encode('utf-8') quality, info = source_utils.get_release_quality( url) try: size = re.findall( '((?:\d+\.\d+|\d+\,\d+|\d+) (?:GB|GiB|MB|MiB))', item[2])[-1] div = 1 if size.endswith( ('GB', 'GiB')) else 1024 size = float(re.sub('[^0-9|/.|/,]', '', size)) / div size = '%.2f GB' % size info.append(size) except BaseException: pass info = ' | '.join(info) sources.append({ 'source': host, 'quality': quality, 'language': 'en', 'url': url, 'info': info, 'direct': False, 'debridonly': True }) except BaseException: pass except BaseException: pass return sources except BaseException: return sources
def _get_sources(self, url): try: item = client.request(url[0]) if item is None: return name = url[1] self.title = self.title.replace('!', '') # some shows like "Power" have year and hdlr in name t = name.split(self.hdlr)[0].replace(self.year, '').replace( '(', '').replace(')', '').replace('&', 'and') tc = cleantitle.get(t) if tc != cleantitle.get(self.title): try: if tc == self.aliases[0]: pass else: return except: return if self.hdlr not in name: return links = dom_parser.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: pass info = ' | '.join(info) for url in links: if any(x in url.lower() for x in ['.rar.', '.zip.', '.iso.']) or any( url.lower().endswith(x) for x in ['.rar', '.zip', '.iso']): continue if any(x in url.lower() for x in ['youtube', 'sample', 'trailer']): 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, info2 = source_utils.get_release_quality(name, 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: source_utils.scraper_error('ONLINESERIES') pass
def sources(self, url, hostDict, hostprDict): try: sources = [] if url == None: return sources if debrid.status() is False: raise Exception() data = urlparse.parse_qs(url) data = dict([(i, data[i][0]) if data[i] else (i, '') for i in data]) title = data['tvshowtitle'] if 'tvshowtitle' in data else data[ 'title'] hdlr = 'S%02dE%02d' % (int(data['season']), int( data['episode'])) if 'tvshowtitle' in data else data['year'] query = '%s S%02dE%02d' % ( data['tvshowtitle'], int(data['season']), int(data['episode'])) if 'tvshowtitle' in data else '%s %s' % ( data['title'], data['year']) query = re.sub('(\\\|/| -|:|;|\*|\?|"|\'|<|>|\|)', ' ', query) url = self.search_link % urllib.quote_plus(query) url = urlparse.urljoin(self.base_link, url) html = client.request(url) posts = client.parseDOM(html, 'item') hostDict = hostprDict + hostDict items = [] for post in posts: try: t = client.parseDOM(post, 'title')[0] u = client.parseDOM(post, 'a', ret='href') s = re.search( '((?:\d+\.\d+|\d+\,\d+|\d+)\s*(?:GB|GiB|MB|MiB))', post) s = s.groups()[0] if s else '0' items += [(t, i, s) for i in u] except: pass for item in items: try: url = item[1] if any(x in url for x in ['.rar', '.zip', '.iso']): raise Exception() url = client.replaceHTMLCodes(url) url = url.encode('utf-8') valid, host = source_utils.is_host_valid(url, hostDict) if not valid: raise Exception() host = client.replaceHTMLCodes(host) host = host.encode('utf-8') name = item[0] name = client.replaceHTMLCodes(name) t = re.sub( '(\.|\(|\[|\s)(\d{4}|S\d*E\d*|S\d*|3D)(\.|\)|\]|\s|)(.+|)', '', name, flags=re.I) if not cleantitle.get(t) == cleantitle.get(title): raise Exception() y = re.findall( '[\.|\(|\[|\s](\d{4}|S\d*E\d*|S\d*)[\.|\)|\]|\s]', name)[-1].upper() if not y == hdlr: raise Exception() quality, info = source_utils.get_release_quality(name, url) try: size = re.findall( '((?:\d+\.\d+|\d+\,\d+|\d+)\s*(?:GB|GiB|MB|MiB))', item[2])[-1] div = 1 if size.endswith(('GB', 'GiB')) else 1024 size = float(re.sub('[^0-9|/.|/,]', '', size)) / div size = '%.2f GB' % size info.append(size) except: pass info = ' | '.join(info) sources.append({ 'source': host, 'quality': quality, 'language': 'en', 'url': url, 'info': info, 'direct': False, 'debridonly': True }) except: pass check = [i for i in sources if not i['quality'] == 'CAM'] if check: sources = check return sources except: return
def sources(self, url, hostDict, hostprDict): try: sources = [] 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]) aliases = eval(data['aliases']) mozhdr = { 'User-Agent': 'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-GB; rv:1.9.0.3) Gecko/2008092417 Firefox/3.0.3' } headers = mozhdr headers['X-Requested-With'] = 'XMLHttpRequest' if 'tvshowtitle' in data: episode = int(data['episode']) url = self.searchShow(data['tvshowtitle'], data['season'], aliases, headers) else: episode = 0 url = self.searchMovie(data['title'], data['year'], aliases, headers) headers['Referer'] = url ref_url = url mid = re.findall('-(\d*)\.', url)[0] data = {'id': mid} r = self.scraper.post(url, headers=headers).content try: u = urlparse.urljoin(self.base_link, self.server_link % mid) r = self.scraper.get(u, headers=mozhdr).content r = json.loads(r)['html'] rl = client.parseDOM(r, 'div', attrs={'class': 'pas-list'}) rh = client.parseDOM(r, 'div', attrs={'class': 'pas-header'}) ids = client.parseDOM(rl, 'li', ret='data-id') servers = client.parseDOM(rl, 'li', ret='data-server') labels = client.parseDOM(rl, 'a', ret='title') r = zip(ids, servers, labels) rrr = zip(client.parseDOM(rh, 'li', ret='data-id'), client.parseDOM(rh, 'li', ret='class')) types = {} for rr in rrr: types[rr[0]] = rr[1] for eid in r: try: try: ep = re.findall('episode.*?(\d+).*?', eid[2].lower())[0] except: ep = 0 if (episode == 0) or (int(ep) == episode): t = str(int(time.time() * 1000)) quali = source_utils.get_release_quality(eid[2])[0] if 'embed' in types[eid[1]]: url = urlparse.urljoin( self.base_link, self.embed_link % (eid[0])) xml = self.scraperget(url, headers=headers).content url = json.loads(xml)['src'] valid, hoster = source_utils.is_host_valid( url, hostDict) if not valid: continue q = source_utils.check_sd_url(url) q = q if q != 'SD' else quali sources.append({ 'source': hoster, 'quality': q, 'language': 'en', 'url': url, 'direct': False, 'debridonly': False }) continue else: url = urlparse.urljoin( self.base_link, self.token_link % (eid[0], mid, t)) script = self.scraper.get(url, headers=headers).content if '$_$' in script: params = self.uncensored1(script) elif script.startswith('[]') and script.endswith( '()'): params = self.uncensored2(script) elif '_x=' in script: x = re.search('''_x=['"]([^"']+)''', script).group(1) y = re.search('''_y=['"]([^"']+)''', script).group(1) params = {'x': x, 'y': y} else: raise Exception() u = urlparse.urljoin( self.base_link, self.source_link % (eid[0], params['x'], params['y'])) length = 0 count = 0 while length == 0 and count < 11: r = self.scraper.get(u, headers=headers).content length = len(r) if length == 0: count += 1 uri = None uri = json.loads(r)['playlist'][0]['sources'] try: uri = [i['file'] for i in uri if 'file' in i] except: try: uri = [uri['file']] except: continue for url in uri: if 'googleapis' in url: q = source_utils.check_sd_url(url) sources.append({ 'source': 'gvideo', 'quality': q, 'language': 'en', 'url': url, 'direct': True, 'debridonly': False }) continue valid, hoster = source_utils.is_host_valid( url, hostDict) # urls, host, direct = source_utils.check_directstreams(url, hoster) q = quali if valid: # for z in urls: if hoster == 'gvideo': direct = True try: q = directstream.googletag( url)[0]['quality'] except: pass url = directstream.google(url, ref=ref_url) else: direct = False sources.append({ 'source': hoster, 'quality': q, 'language': 'en', 'url': url, 'direct': direct, 'debridonly': False }) else: sources.append({ 'source': 'CDN', 'quality': q, 'language': 'en', 'url': url, 'direct': True, 'debridonly': False }) except: pass except: pass return sources except: return sources
def sources(self, url, hostDict, hostprDict): try: sources = [] if url == None: return sources if debrid.status() == False: raise Exception() data = urlparse.parse_qs(url) data = dict([(i, data[i][0]) if data[i] else (i, '') for i in data]) title = data['tvshowtitle'] if 'tvshowtitle' in data else data[ 'title'] hdlr = 'S%02dE%02d' % (int(data['season']), int( data['episode'])) if 'tvshowtitle' in data else data['year'] query = '%s S%02dE%02d' % ( data['tvshowtitle'], int(data['season']), int(data['episode'])) \ if 'tvshowtitle' in data else '%s %s' % (data['title'], data['year']) url = self.search_link % urllib.quote_plus(query) url = urlparse.urljoin(self.base_link, url).replace('-', '+') r = self.scraper.get(url).content if r == None and 'tvshowtitle' in data: season = re.search('S(.*?)E', hdlr) season = season.group(1) url = title r = self.scraper.get(url).content for loopCount in range(0, 2): if loopCount == 1 or (r == None and 'tvshowtitle' in data): r = self.scraper.get(url).content posts = client.parseDOM(r, "h2") hostDict = hostprDict + hostDict items = [] for post in posts: try: u = client.parseDOM(post, 'a', ret='href') for i in u: try: name = str(i) items.append(name) except: pass except: pass if len(items) > 0: break for item in items: try: info = [] i = str(item) r = self.scraper.get(i).content u = client.parseDOM(r, "div", attrs={"class": "entry-content"}) for t in u: r = re.compile('a href="(.+?)">.+?<').findall(t) query = query.replace(' ', '.') for url in r: if not query in url: continue if any(x in url for x in ['.rar', '.zip', '.iso']): raise Exception() quality, info = source_utils.get_release_quality( url) valid, host = source_utils.is_host_valid( url, hostDict) sources.append({ 'source': host, 'quality': quality, 'language': 'en', 'url': url, 'info': info, 'direct': False, 'debridonly': True }) except: pass check = [i for i in sources if not i['quality'] == 'CAM'] if check: sources = check return sources except: return
def sources(self, url, hostDict, hostprDict): sources = [] try: if url is None: return sources if debrid.status() is False: raise Exception() data = urlparse.parse_qs(url) data = dict([(i, data[i][0]) if data[i] else (i, '') for i in data]) post = {'query': data['imdb']} url = urlparse.urljoin(self.base_link, 'engine/ajax/search.php') r = self.scraper.post(url, data=post).content urls = client.parseDOM(r, 'a', ret='href') urls = [i for i in urls if not data['imdb'] in i] hostDict = hostprDict + hostDict links = [] for u in urls: try: data = self.scraper.get(u).content data = re.findall('</iframe>(.+?)QuoteEEnd--><br /><br', data, re.DOTALL)[0] links += re.findall( '''start--><b>(.+?)</b>.+?<b><a href=['"](.+?)['"]''', data, re.DOTALL) except Exception: pass links = [(i[0], i[1]) for i in links if not 'vip' in i[0].lower()] for name, url in links: try: name = re.sub('<.+?>', '', name) if '4K' in name: quality = '4K' elif '1080p' in name: quality = '1080p' elif '720p' in name: quality = '720p' else: quality = 'SD' info = [] if '3D' in name or '.3D.' in url: info.append('3D') quality = '1080p' if any(i in ['hevc', 'h265', 'x265'] for i in name): info.append('HEVC') info = ' | '.join(info) url = client.replaceHTMLCodes(url) url = url.encode('utf-8') if any(x in url for x in ['.rar', '.zip', '.iso', 'turk']): raise Exception() if 'ftp' in url: host = 'CDN' direct = True else: valid, host = source_utils.is_host_valid(url, hostDict) if not valid: raise Exception() host = host direct = False host = client.replaceHTMLCodes(host) host = host.encode('utf-8') sources.append({ 'source': host, 'quality': quality, 'language': 'en', 'url': url, 'info': info, 'direct': direct, 'debridonly': True }) except Exception: pass return sources except Exception: return sources