def _get_episode_url(self, show_url, video): show_url = scraper_utils.urljoin(self.base_url, show_url) html = self._http_get(show_url, cache_limit=8) pattern = '''href=['"]([^'"]+)[^>]+>\s*%s\.\s*Sezon<''' % ( video.season) match = re.search(pattern, html) if match: episode_pattern = '''href=['"]([^'"]+-%s-sezon-%s-bolum[^'"]*)''' % ( video.season, video.episode) season_url = scraper_utils.urljoin(self.base_url, match.group(1)) html = self._http_get(season_url, cache_limit=2) ep_url = self._default_get_episode_url(html, video, episode_pattern) if ep_url: return ep_url # front page fallback html = self._http_get(self.base_url, cache_limit=2) for slug in reversed(show_url.split('/')): if slug: break ep_url_frag = 'href="([^"]+/{slug}-{season}-sezon-{episode}-bolum[^"]*)'.format( slug=slug, season=video.season, episode=video.episode) match = re.search(ep_url_frag, html) if match: return scraper_utils.pathify_url(match.group(1))
def get_sources(self, video): source_url = self.get_url(video) hosters = [] sources = {} if not source_url or source_url == FORCE_NO_MATCH: return hosters url = scraper_utils.urljoin(self.base_url, source_url) html = self._http_get(url, require_debrid=True, cache_limit=.5) if not html: url = scraper_utils.urljoin(self.old_base_url, source_url) html = self._http_get(url, require_debrid=True, cache_limit=.5) sources.update(self.__get_post_links(html, video)) if kodi.get_setting('%s-include_comments' % (self.get_name())) == 'true': for _attrs, comment in dom_parser2.parse_dom( html, 'div', {'id': re.compile('commentbody-\d+')}): sources.update(self.__get_comment_links(comment, video)) for source in sources: if scraper_utils.excluded_link(source): continue host = urlparse.urlparse(source).hostname hoster = { 'multi-part': False, 'host': host, 'class': self, 'views': None, 'url': source, 'rating': None, 'quality': sources[source], 'direct': False } hosters.append(hoster) return hosters
def search(self, video_type, title, year, season=''): # @UnusedVariable results = [] search_url = scraper_utils.urljoin(self.base_url, SEARCH_URL) referer = scraper_utils.urljoin(self.base_url, '/search/?q=%s') referer = referer % (urllib.quote_plus(title)) headers = {'Referer': referer} headers.update(XHR) params = { 'searchTerm': title, 'type': SEARCH_TYPES[video_type], 'limit': 500 } html = self._http_get(search_url, params=params, headers=headers, auth=False, cache_limit=2) js_data = scraper_utils.parse_json(html, search_url) if 'results' in js_data: for result in js_data['results']: match_year = str(result.get('year', '')) match_url = result.get('permalink', '') match_title = result.get('title', '') if not year or not match_year or year == match_year: result = { 'title': scraper_utils.cleanse_title(match_title), 'year': match_year, 'url': scraper_utils.pathify_url(match_url) } results.append(result) return results
def get_sources(self, video): source_url = self.get_url(video) hosters = [] sources = [] if not source_url or source_url == FORCE_NO_MATCH: return hosters page_url = scraper_utils.urljoin(self.base_url, source_url) html = self._http_get(page_url, cache_limit=1) iframes = dom_parser2.parse_dom(html, 'iframe', req='src') for attrs, _content in iframes: iframe_url = attrs['src'] if 'docs.google.com' in iframe_url: sources = scraper_utils.parse_google(self, iframe_url) break else: iframe_url = scraper_utils.urljoin(self.base_url, iframe_url) html = self._http_get(iframe_url, cache_limit=1) iframes += dom_parser2.parse_dom(html, 'iframe', req='src') for source in sources: host = scraper_utils.get_direct_hostname(self, source) hoster = { 'multi-part': False, 'host': host, 'class': self, 'quality': scraper_utils.gv_get_quality(source), 'views': None, 'rating': None, 'url': source, 'direct': True } hosters.append(hoster) return hosters
def get_sources(self, video): hosters = [] source_url = self.get_url(video) if not source_url or source_url == FORCE_NO_MATCH: return hosters page_url = scraper_utils.urljoin(self.base_url, source_url) html = self._http_get(page_url, cache_limit=.5) videos = re.findall('''onclick\s*=\s*"loadVideo\('([^']+)''', html) subs = self.__get_subs(html) for v_id, icon in map(None, videos, subs): ajax_url = scraper_utils.urljoin(self.base_url, AJAX_URL) data = {'vid': v_id, 'tip': 1, 'type': 'loadVideo'} headers = {'Referer': page_url} headers.update(XHR) html = self._http_get(ajax_url, data=data, headers=headers, cache_limit=.5) sub = ICONS.get(icon, DEFAULT_SUB) hosters += self.__get_cloud_links(html, page_url, sub) hosters += self.__get_embedded_links(html, sub) hosters += self.__get_iframe_links(html, sub) hosters += self.__get_json_links(html, sub) if not kodi.get_setting('scraper_url'): break return hosters
def __get_source_page(self, video_type, page_url): match = re.search('/movie/(.*?)-(\d+)\.html', page_url) if not match: return '', '', '' slug, movie_id = match.groups() vid_type = 'movie' if video_type == VIDEO_TYPES.MOVIE else 'series' qp_url = QP_URL.format(slug=slug, movie_id=movie_id, vid_type=vid_type) qp_url = scraper_utils.urljoin(self.base_url, qp_url) headers = {'Referer': scraper_utils.urljoin(self.base_url, page_url)} headers.update(XHR) html = self._http_get(qp_url, headers=headers, cache_limit=8) watching_url = dom_parser2.parse_dom(html, 'a', {'title': re.compile('View all episodes')}, req='href') if not watching_url: return '', '', '' watching_url = watching_url[0].attrs['href'] page_html = self._http_get(watching_url, headers={'Referer': scraper_utils.urljoin(self.base_url, page_url)}, cache_limit=8) for attrs, _content in dom_parser2.parse_dom(page_html, 'img', {'class': 'hidden'}, req='src'): _img = self._http_get(attrs['src'], headers={'Referer': watching_url}, cache_limit=8) sl_url = SL_URL.format(movie_id=movie_id) sl_url = scraper_utils.urljoin(self.base_url, sl_url) html = self._http_get(sl_url, headers=headers, cache_limit=8) js_data = scraper_utils.parse_json(html, sl_url) try: html = js_data['html'] except: html = '' return movie_id, watching_url, html
def search(self, video_type, title, year, season=''): results = [] search_url = scraper_utils.urljoin(self.base_url, '/movies/search') html = self._http_get(search_url, params={'s': title}, cache_limit=8) for _attrs, item in dom_parser2.parse_dom(html, 'div', {'class': 'item_movie'}): match = dom_parser2.parse_dom(item, 'a', req=['href', 'title']) if not match: continue match_title_year = match[0].attrs['title'] match_url = match[0].attrs['href'] is_season = re.search('S(?:eason\s+)?(\d+)', match_title_year, re.I) match_vt = video_type == (VIDEO_TYPES.MOVIE and not is_season) or (video_type == VIDEO_TYPES.SEASON and is_season) match_year = '' if video_type == VIDEO_TYPES.SEASON: if not season and not match_vt: continue if match_vt: if season and int(is_season.group(1)) != int(season): continue else: if season and int(season) != 1: continue site_title, site_year = scraper_utils.extra_year(match_title_year) if scraper_utils.normalize_title(site_title) not in scraper_utils.normalize_title(title) or year != site_year: continue match_title = match_title_year else: if not match_vt: continue match_title, match_year = scraper_utils.extra_year(match_title_year) match_url = scraper_utils.urljoin(match_url, 'watching.html') if not year or not match_year or year == match_year: result = {'url': scraper_utils.pathify_url(match_url), 'title': scraper_utils.cleanse_title(match_title), 'year': match_year} results.append(result) return results
def _get_episode_url(self, show_url, video): episode_pattern = 'href="([^"]+/season/%s/episode/%s/?)"' % (video.season, video.episode) title_pattern = 'href="(?P<url>[^"]+)"[^>]+title="(?:S\d+\s*E\d+:\s*)?(?P<title>[^"]+)' headers = {'Referer': scraper_utils.urljoin(self.base_url, show_url)} season_url = scraper_utils.urljoin(show_url, '/season/%s' % (video.season)) season_url = scraper_utils.urljoin(self.base_url, season_url) html = self._http_get(season_url, headers=headers, cache_limit=2) fragment = dom_parser2.parse_dom(html, 'div', {'id': 'episodes'}) return self._default_get_episode_url(fragment, video, episode_pattern, title_pattern)
def get_sources(self, video): source_url = self.get_url(video) hosters = [] sources = {} headers = {'Accept-Language': 'en-US,en;q=0.5'} if not source_url or source_url == FORCE_NO_MATCH: return hosters page_url = scraper_utils.urljoin(self.base_url, source_url) html = self._http_get(page_url, headers=headers, cache_limit=2) if video.video_type == VIDEO_TYPES.MOVIE: sources.update(self.__scrape_sources(html, page_url)) pages = set([ r.attrs['href'] for r in dom_parser2.parse_dom( html, 'a', {'class': 'btn-eps'}, req='href') ]) active = set([ r.attrs['href'] for r in dom_parser2.parse_dom( html, 'a', {'class': 'active'}, req='href') ]) for page in list(pages - active): page_url = scraper_utils.urljoin(self.base_url, page) html = self._http_get(page_url, headers=headers, cache_limit=2) sources.update(self.__scrape_sources(html, page_url)) else: for page in self.__match_episode(video, html): page_url = scraper_utils.urljoin(self.base_url, page) html = self._http_get(page_url, headers=headers, cache_limit=2) sources.update(self.__scrape_sources(html, page_url)) for source, values in sources.iteritems(): if not source.lower().startswith('http'): continue if values['direct']: host = scraper_utils.get_direct_hostname(self, source) if host != 'gvideo': stream_url = source + scraper_utils.append_headers( { 'User-Agent': scraper_utils.get_ua(), 'Referer': page_url }) else: stream_url = source else: host = urlparse.urlparse(source).hostname stream_url = source hoster = { 'multi-part': False, 'host': host, 'class': self, 'quality': values['quality'], 'views': None, 'rating': None, 'url': stream_url, 'direct': values['direct'] } hosters.append(hoster) return hosters
def get_sources(self, video): hosters = [] source_url = self.get_url(video) if not source_url or source_url == FORCE_NO_MATCH: return hosters url = scraper_utils.urljoin(self.base_url, source_url) html = self._http_get(url, cache_limit=.5) views = None fragment = dom_parser2.parse_dom( html, 'img', {'src': re.compile('[^"]*view_icon.png')}) if fragment: match = re.search('(\d+)', fragment[0].content) if match: views = match.group(1) match = re.search('href="([^"]+-full-movie-[^"]+)', html) if match: url = match.group(1) html = self._http_get(url, cache_limit=.5) sources = self.__get_embedded(html) for link in dom_parser2.parse_dom(html, 'span', {'class': 'btn-eps'}, req='link'): link = link.attrs['link'] ajax_url = scraper_utils.urljoin(self.base_url, AJAX_URL) headers = {'Referer': url} headers.update(XHR) html = self._http_get(ajax_url, params={'v': link}, headers=headers, cache_limit=.5) sources.update(self.__get_sources(html)) for source in sources: if sources[source]['direct']: host = scraper_utils.get_direct_hostname(self, source) else: host = urlparse.urlparse(source).hostname stream_url = source + scraper_utils.append_headers( {'User-Agent': scraper_utils.get_ua()}) direct = sources[source]['direct'] quality = sources[source]['quality'] hoster = { 'multi-part': False, 'host': host, 'class': self, 'quality': quality, 'views': views, 'rating': None, 'url': stream_url, 'direct': direct } hosters.append(hoster) return hosters
def search(self, video_type, title, year, season=''): results = [] search_url = scraper_utils.urljoin(self.base_url, '/search/') headers = {'Accept-Language': 'en-US,en;q=0.5'} html = self._http_get(search_url, params={'q': title}, headers=headers, cache_limit=8) norm_title = scraper_utils.normalize_title(title) for _attrs, item in dom_parser2.parse_dom(html, 'div', {'class': 'ml-item'}): match_title = dom_parser2.parse_dom(item, 'span', {'class': 'mli-info'}) match_url = dom_parser2.parse_dom(item, 'a', req='href') year_frag = dom_parser2.parse_dom(item, 'img', req='alt') is_episodes = dom_parser2.parse_dom(item, 'span', {'class': 'mli-eps'}) if (video_type == VIDEO_TYPES.MOVIE and not is_episodes) or (video_type == VIDEO_TYPES.SEASON and is_episodes): if match_title and match_url: match_url = match_url[0].attrs['href'] match_title = match_title[0].content match_title = re.sub('</?h2>', '', match_title) match_title = re.sub('\s+\d{4}$', '', match_title) if video_type == VIDEO_TYPES.SEASON: if season and not re.search( 'Season\s+0*%s$' % (season), match_title): continue if not match_url.endswith('/'): match_url += '/' match_url = scraper_utils.urljoin(match_url, 'watch/') match_year = '' if video_type == VIDEO_TYPES.MOVIE and year_frag: match = re.search('\s*-\s*(\d{4})$', year_frag[0].attrs['alt']) if match: match_year = match.group(1) match_norm_title = scraper_utils.normalize_title( match_title) title_match = (norm_title in match_norm_title) or (match_norm_title in norm_title) if title_match and (not year or not match_year or year == match_year): result = { 'title': scraper_utils.cleanse_title(match_title), 'year': match_year, 'url': scraper_utils.pathify_url(match_url) } results.append(result) return results
def get_sources(self, video): hosters = [] sources = {} source_url = self.get_url(video) if not source_url or source_url == FORCE_NO_MATCH: return hosters page_url = scraper_utils.urljoin(self.base_url, source_url) html = self._http_get(page_url, cache_limit=.5) match = re.search("load_player\('([^']+)", html) if not match: return hosters headers = {'Referer': page_url, 'Server': 'cloudflare-nginx', 'Accept': 'text/html, */*; q=0.01', 'Accept-Language': 'en-US,en;q=0.5', 'Accept-Formating': 'application/json, text/javascript', 'Accept-Encoding': 'gzip, deflate'} headers.update(XHR) params = {'id': match.group(1)} player_url = scraper_utils.urljoin(self.base_url, PLAYER_URL) html = self._http_get(player_url, params=params, headers=headers, cache_limit=1) js_data = scraper_utils.parse_json(html, player_url) pl_url = js_data.get('value') or js_data.get('download') if not pl_url: return hosters headers = {'Referer': page_url} if pl_url.startswith('//'): pl_url = 'https:' + pl_url html = self._http_get(pl_url, headers=headers, allow_redirect=False, cache_limit=0) if html.startswith('http'): streams = [(html, '')] else: js_data = scraper_utils.parse_json(html, pl_url) try: streams = [(source['file'], source.get('label', '')) for source in js_data['playlist'][0]['sources']] except: streams = [] for stream in streams: stream_url, label = stream if scraper_utils.get_direct_hostname(self, stream_url) == 'gvideo': sources[stream_url] = {'quality': scraper_utils.gv_get_quality(stream_url), 'direct': True} else: if label: quality = scraper_utils.height_get_quality(label) else: quality = QUALITIES.HIGH sources[stream_url] = {'quality': quality, 'direct': False} for source, value in sources.iteritems(): direct = value['direct'] quality = value['quality'] if direct: host = scraper_utils.get_direct_hostname(self, source) else: host = urlparse.urlparse(source).hostname stream_url = source + scraper_utils.append_headers({'User-Agent': scraper_utils.get_ua()}) hoster = {'multi-part': False, 'host': host, 'class': self, 'quality': quality, 'views': None, 'rating': None, 'url': stream_url, 'direct': direct} hosters.append(hoster) return hosters
def get_sources(self, video): hosters = [] source_url = self.get_url(video) if not source_url or source_url == FORCE_NO_MATCH: return hosters page_url = scraper_utils.urljoin(self.base_url, source_url) html = self._http_get(page_url, cache_limit=8) fragment = dom_parser2.parse_dom(html, 'div', {'class': 'playex'}) if fragment: html = fragment[0].content iframe_url = dom_parser2.parse_dom(html, 'iframe', req='src') if not iframe_url: return hosters iframe_url = iframe_url[0].attrs['src'] if iframe_url.startswith('/'): iframe_url = scraper_utils.urljoin(self.base_url, iframe_url) html = self._http_get(iframe_url, headers={'Referer': page_url}, cache_limit=.5) obj = dom_parser2.parse_dom(html, 'object', req='data') if obj: streams = dict((stream_url, { 'quality': scraper_utils.gv_get_quality(stream_url), 'direct': True }) for stream_url in scraper_utils.parse_google( self, obj[0].attrs['data'])) else: streams = scraper_utils.parse_sources_list(self, html) for stream_url, values in streams.iteritems(): host = scraper_utils.get_direct_hostname(self, stream_url) if host == 'gvideo': quality = scraper_utils.gv_get_quality(stream_url) else: quality = values['quality'] stream_url += scraper_utils.append_headers({ 'User-Agent': scraper_utils.get_ua(), 'Referer': page_url }) source = { 'multi-part': False, 'url': stream_url, 'host': host, 'class': self, 'quality': quality, 'views': None, 'rating': None, 'direct': True } hosters.append(source) return hosters
def search(self, video_type, title, year, season=''): # @UnusedVariable results = [] search_url = scraper_utils.urljoin(self.base_url, '/results') params = {'q': title} referer = search_url + '?' + urllib.urlencode(params) headers = {'Referer': referer} headers.update(XHR) _html = self._http_get(scraper_utils.urljoin(self.base_url, 'av'), headers=headers, method='POST', cache_limit=0) cookies = {'begin_referer': referer, 'prounder': 1} html = self._http_get(search_url, params=params, cookies=cookies, cache_limit=8) if any('jquery.js' in match.attrs['src'] for match in dom_parser2.parse_dom(html, 'script', req='src')): html = self._http_get(search_url, params=params, cookies=cookies, cache_limit=0) for _attrs, result in dom_parser2.parse_dom(html, 'div', {'class': 'cell'}): title_frag = dom_parser2.parse_dom(result, 'div', {'class': 'video_title'}) year_frag = dom_parser2.parse_dom(result, 'div', {'class': 'video_quality'}) if not title_frag: continue match = dom_parser2.parse_dom(title_frag[0].content, 'a', req='href') if not match: continue match_url = match[0].attrs['href'] match_title = match[0].content try: match = re.search('\s+(\d{4})\s+', year_frag[0].content) match_year = match.group(1) except: match_year = '' if not year or not match_year or year == match_year: result = { 'url': scraper_utils.pathify_url(match_url), 'title': scraper_utils.cleanse_title(match_title), 'year': match_year } results.append(result) return results
def get_sources(self, video): hosters = [] source_url = self.get_url(video) if not source_url or source_url == FORCE_NO_MATCH: return hosters page_url = scraper_utils.urljoin(self.base_url, source_url) html = self._http_get(page_url, cache_limit=.5) page_quality = dom_parser2.parse_dom(html, 'dd', {'class': 'status'}) if page_quality: page_quality = QUALITY_MAP.get(page_quality[0].content, QUALITIES.HIGH) else: page_quality = QUALITIES.HIGH if video.video_type == VIDEO_TYPES.EPISODE: fragment = dom_parser2.parse_dom(html, 'div', {'id': 'servers-list'}) gk_html = fragment[0].content if fragment else '' else: gk_html = html link_url = scraper_utils.urljoin(self.base_url, LINK_URL) player_url = scraper_utils.urljoin(self.base_url, PLAYER_URL) for stream_url, quality in scraper_utils.get_gk_links( self, gk_html, page_url, page_quality, link_url, player_url).iteritems(): host = scraper_utils.get_direct_hostname(self, stream_url) if host == 'gvideo': direct = True quality = quality else: host = urlparse.urlparse(stream_url).hostname quality = scraper_utils.get_quality(video, host, quality) direct = False if host is not None: stream_url += scraper_utils.append_headers( {'User-Agent': scraper_utils.get_ua()}) hoster = { 'multi-part': False, 'host': host, 'class': self, 'quality': quality, 'views': None, 'rating': None, 'url': stream_url, 'direct': direct } hosters.append(hoster) return hosters
def __add_torrent(self, hash_id): list_url = scraper_utils.urljoin(self.base_url, LIST_URL) js_data = self._json_get(list_url, cache_limit=0) for transfer in js_data.get('transfers', []): if transfer['hash'].lower() == hash_id: return True add_url = scraper_utils.urljoin(self.base_url, ADD_URL) data = {'src': MAGNET_LINK % hash_id} js_data = self._json_get(add_url, data=data, cache_limit=0) if js_data.get('status') == 'success': return True else: return False
def get_sources(self, video): source_url = self.get_url(video) sources = [] if not source_url or source_url == FORCE_NO_MATCH: return sources page_url = scraper_utils.urljoin(self.base_url, source_url) html = self._http_get(page_url, cache_limit=8) for attrs, _content in dom_parser2.parse_dom(html, 'img', req=['data-id', 'data-name']): film_id, data_name = attrs['data-id'], attrs['data-name'] data = {'id': film_id, 'n': data_name} server_url = scraper_utils.urljoin(self.base_url, SERVER_URL) server_url = server_url % (film_id) headers = {'Referer': page_url} headers.update(XHR) html = self._http_get(server_url, data=data, headers=headers, cache_limit=.5) for attrs, _content in dom_parser2.parse_dom(html, 'a', req='data-id'): data = {'epid': attrs['data-id']} ep_url = scraper_utils.urljoin(self.base_url, EP_URL) ep_url = ep_url % (attrs['data-id']) headers = {'Referer': page_url} headers.update(XHR) html = self._http_get(ep_url, data=data, headers=headers, cache_limit=.5) js_data = scraper_utils.parse_json(html, ep_url) try: links = [r.attrs['src'] for r in dom_parser2.parse_dom(js_data['link']['embed'], 'iframe', req='src')] except: try: links = js_data['link']['l'] except: links = [] try: heights = js_data['link']['q'] except: heights = [] for stream_url, height in map(None, links, heights): match = re.search('movie_url=(.*)', stream_url) if match: stream_url = match.group(1) host = scraper_utils.get_direct_hostname(self, stream_url) if host == 'gvideo': quality = scraper_utils.gv_get_quality(stream_url) stream_url += scraper_utils.append_headers({'User-Agent': scraper_utils.get_ua(), 'Referer': page_url}) direct = True else: host = urlparse.urlparse(stream_url).hostname if height: quality = scraper_utils.height_get_quality(height) else: quality = QUALITIES.HD720 direct = False source = {'multi-part': False, 'url': stream_url, 'host': host, 'class': self, 'quality': quality, 'views': None, 'rating': None, 'direct': direct} sources.append(source) return sources
def resolve_link(self, link): if not link.startswith('http'): url = scraper_utils.urljoin(self.base_url, link) html = self._http_get(url, cache_limit=.5) match = re.search('href="([^"]+).*?value="Continue to video"', html) if match: url = scraper_utils.urljoin(self.base_url, match.group(1)) html = self._http_get(url, cache_limit=.5) redirect = dom_parser2.parse_dom(html, 'meta', {'http-equiv': 'refresh'}, req='content') if redirect: match = re.search('url=([^"]+)', redirect[0].attrs['content']) if match: return match.group(1) return link
def resolve_link(self, link): url = scraper_utils.urljoin(self.base_url, link) html = self._http_get(url, cache_limit=.5) match = re.search('"file"\s*:\s*"([^"]+)', html) if match: file_link = match.group(1) stream_url = scraper_utils.urljoin(self.base_url, file_link) cj = self._set_cookies(self.base_url, {}) request = urllib2.Request(stream_url) request.add_header('User-Agent', scraper_utils.get_ua()) request.add_unredirected_header('Host', request.get_host()) request.add_unredirected_header('Referer', url) cj.add_cookie_header(request) response = urllib2.urlopen(request) return response.geturl()
def _get_episode_url(self, show_url, video): url = scraper_utils.urljoin(self.base_url, show_url) html = self._http_get(url, cache_limit=24) fragment = dom_parser2.parse_dom(html, 'div', {'class': 'poster'}) if not fragment: return show_url = dom_parser2.parse_dom(fragment[0].content, 'a', req='href') if not show_url: return show_url = scraper_utils.urljoin(self.base_url, show_url[0].attrs['href']) html = self._http_get(show_url, cache_limit=2) fragment = dom_parser2.parse_dom(html, 'div', {'id': 'servers'}) episode_pattern = 'href="([^"]+)[^>]+>[Ee][Pp]\s*(?:[Ss]0*%s-)?E?p?0*%s(?!\d)' % ( video.season, video.episode) return self._default_get_episode_url(fragment or html, video, episode_pattern)
def get_sources(self, video): hosters = [] source_url = self.get_url(video) if not source_url or source_url == FORCE_NO_MATCH: return hosters url = scraper_utils.urljoin(self.base_url, source_url) headers = {'User-Agent': LOCAL_UA} html = self._http_get(url, require_debrid=True, headers=headers, cache_limit=.5) for match in re.finditer( "<span\s+class='info2'(.*?)(<span\s+class='info|<hr\s*/>)", html, re.DOTALL): for match2 in re.finditer('href="([^"]+)', match.group(1)): stream_url = match2.group(1) meta = scraper_utils.parse_episode_link(stream_url) quality = scraper_utils.height_get_quality(meta['height']) host = urlparse.urlparse(stream_url).hostname hoster = { 'multi-part': False, 'host': host, 'class': self, 'views': None, 'url': stream_url, 'rating': None, 'quality': quality, 'direct': False } hosters.append(hoster) return hosters
def get_sources(self, video): source_url = self.get_url(video) hosters = [] if not source_url or source_url == FORCE_NO_MATCH: return hosters url = scraper_utils.urljoin(self.base_url, source_url) html = self._http_get(url, cache_limit=.5) for match in re.finditer( '<td>\s*<a\s+href="([^"]+)(?:[^>]+>){2}\s*(?: )*\s*([^<]+)', html): stream_url, host = match.groups() hoster = { 'multi-part': False, 'host': host, 'class': self, 'quality': scraper_utils.get_quality(video, host, QUALITIES.HIGH), 'views': None, 'rating': None, 'url': stream_url, 'direct': False } hosters.append(hoster) return hosters
def get_sources(self, video): source_url = self.get_url(video) hosters = [] if not source_url or source_url == FORCE_NO_MATCH: return hosters page_url = scraper_utils.urljoin(self.base_url, source_url) headers = {'Refer': self.base_url} html = self._http_get(page_url, headers=headers, cache_limit=.5) for _attrs, table in dom_parser2.parse_dom(html, 'table', {'class': 'W'}): for _attrs, row in dom_parser2.parse_dom(table, 'tr'): td = dom_parser2.parse_dom(row, 'td') stream_url = dom_parser2.parse_dom(row, 'a', req='href') if not td or not stream_url: continue host = td[0].content host = re.sub('<!--.*?-->', '', host) host = re.sub('<([^\s]+)[^>]*>.*?</\\1>', '', host) host = host.strip() stream_url = stream_url[0].attrs['href'] quality = scraper_utils.get_quality(video, host, QUALITIES.HIGH) hoster = { 'multi-part': False, 'host': host, 'class': self, 'quality': quality, 'views': None, 'rating': None, 'url': stream_url, 'direct': False } hosters.append(hoster) return hosters
def search(self, video_type, title, year, season=''): # @UnusedVariable results = [] search_url = scraper_utils.urljoin(self.base_url, '/ajax/search.php') timestamp = int(time.time() * 1000) query = { 'q': title, 'limit': 100, 'timestamp': timestamp, 'verifiedCheck': '' } html = self._http_get(search_url, data=query, headers=XHR, cache_limit=1) if video_type in [VIDEO_TYPES.TVSHOW, VIDEO_TYPES.EPISODE]: media_type = 'TV SHOW' else: media_type = 'MOVIE' js_data = scraper_utils.parse_json(html, search_url) for item in js_data: if not item['meta'].upper().startswith(media_type): continue result = { 'title': scraper_utils.cleanse_title(item['title']), 'url': scraper_utils.pathify_url(item['permalink']), 'year': '' } results.append(result) return results
def search(self, video_type, title, year, season=''): # @UnusedVariable results = [] search_url = scraper_utils.urljoin(self.base_url, '/bestmatch-fund-movies-%s.html') search_title = title.replace(' ', '-') search_title = re.sub('[^A-Za-z0-9-]', '', search_title).lower() search_url = search_url % (search_title) html = self._http_get(search_url, cache_limit=1) for _attrs, item in dom_parser2.parse_dom(html, 'div', {'class': 'thumbsTitle'}): match = dom_parser2.parse_dom(item, 'a', req='href') if not match: continue match_url, match_title_year = match[0].attrs['href'], match[ 0].content match_title, match_year = scraper_utils.extra_year( match_title_year) if (not year or not match_year or year == match_year): result = { 'url': scraper_utils.pathify_url(match_url), 'title': scraper_utils.cleanse_title(match_title), 'year': match_year } results.append(result) return results
def __login(self): url = scraper_utils.urljoin(self.base_url, '/apis/v2/user/login.json') data = { 'email': self.username, 'password': self.password, 'rememberMe': True } referer = scraper_utils.urljoin(self.base_url, '/login') headers = {'Content-Type': 'application/json', 'Referer': referer} headers.update(XHR) html = super(self.__class__, self)._http_get(url, data=json.dumps(data), headers=headers, cache_limit=0) js_data = scraper_utils.parse_json(html, url) return js_data.get('status') == 'success'
def search(self, video_type, title, year, season=''): # @UnusedVariable results = [] search_url = scraper_utils.urljoin(self.base_url, 'http://dwatchseries.to/search/%s') headers = {'Referer': self.base_url} headers.update(XHR) params = {'ajax': 1, 's': title, 'type': 'TVShows'} html = self._http_get(search_url, params=params, cache_limit=8) for attrs, match_title in dom_parser2.parse_dom(html, 'a', req='href'): match_url = attrs['href'] match_title = re.sub('</?[^>]*>', '', match_title) match = re.search('\((\d{4})\)$', match_url) if match: match_year = match.group(1) else: match_year = '' if not year or not match_year or year == match_year: result = { 'url': scraper_utils.pathify_url(match_url), 'title': scraper_utils.cleanse_title(match_title), 'year': match_year } results.append(result) return results
def get_sources(self, video): source_url = self.get_url(video) hosters = [] if not source_url or source_url == FORCE_NO_MATCH: return hosters url = scraper_utils.urljoin(self.base_url, source_url) html = self._http_get(url, cache_limit=.5) match = re.search('Views?\s*:\s*(\d+)', html, re.I) if match: views = match.group(1) else: views = None pattern = 'href="[^"]+/rd\.html\?url=([^"]+)' for match in re.finditer(pattern, html): url = match.group(1) host = urlparse.urlsplit(url).hostname hoster = { 'multi-part': False, 'host': host, 'url': url, 'class': self, 'rating': None, 'views': views, 'quality': scraper_utils.get_quality(video, host, QUALITIES.HIGH), 'direct': False } hosters.append(hoster) return hosters
def __get_ajax_sources(self, html, page_url): hosters = [] match = re.search('''url\s*:\s*"([^"]+)"\s*,\s*data:'id=''', html) if match: ajax_url = match.group(1) for data_id in re.findall("kaynakdegis\('([^']+)", html): url = scraper_utils.urljoin(self.base_url, ajax_url) data = {'id': data_id} headers = {'Referer': page_url} headers.update(XHR) result = self._http_get(url, data=data, headers=headers, cache_limit=.5) js_data = scraper_utils.parse_json(result, url) if 'iframe' in js_data: if self.base_url in js_data['iframe']: hosters += self.__get_iframe_sources( js_data['iframe'], page_url) else: hosters.append( self.__create_source(js_data['iframe'], 720, page_url, direct=False)) else: hosters += self.__get_js_sources(js_data, page_url) pass return hosters
def get_sources(self, video): hosters = [] source_url = self.get_url(video) if not source_url or source_url == FORCE_NO_MATCH: return hosters url = scraper_utils.urljoin(self.base_url, source_url) html = self._http_get(url, cache_limit=.5) fragment = dom_parser2.parse_dom(html, 'tbody') if fragment: fragment = fragment[0].content for attrs, content in dom_parser2.parse_dom(fragment, 'a', req='href'): stream_url = attrs['href'] match = dom_parser2.parse_dom(content, 'img') if not match: continue host = match[0].content.strip() quality = scraper_utils.get_quality(video, host, QUALITIES.HIGH) hoster = { 'multi-part': False, 'host': host, 'class': self, 'quality': quality, 'views': None, 'rating': None, 'url': stream_url, 'direct': False } hosters.append(hoster) return hosters