def search(self, video_type, title, year, season=''): # @UnusedVariable results = [] search_url = scraper_utils.urljoin(self.base_url, '/index.php') params = {'search': title, 'image.x': 0, 'image.y': 0} html = self._http_get(search_url, params=params, cache_limit=1) # Are we on a results page? if not re.search('window\.location', html): pattern = '<td[^>]+class="movieText"[^>]*>(.*?)</p>.*?href="(/watch/[^"]+)' for match in re.finditer(pattern, html, re.DOTALL): match_title_year, match_url = match.groups('') # skip p**n if '-XXX-' in match_url.upper() or ' XXX:' in match_title_year: continue match_title_year = re.sub('</?.*?>', '', match_title_year) match_title, match_year = scraper_utils.extra_year(match_title_year) if not year or not match_year or year == match_year: result = {'url': match_url, 'title': scraper_utils.cleanse_title(match_title), 'year': match_year} results.append(result) else: match = re.search('window\.location\s+=\s+"([^"]+)', html) if not match: return results url = match.group(1) if url != 'movies.php': result = {'url': scraper_utils.pathify_url(url), 'title': scraper_utils.cleanse_title(title), 'year': year} results.append(result) return results
def __get_ok(self, embed, flashvars): hosters = [] link = flashvars[0].attrs['value'] match = re.search('metadataUrl=([^"]+)', link) if match: referer = scraper_utils.cleanse_title( urllib.unquote(embed[0].attrs['data'])) ok_url = scraper_utils.cleanse_title(urllib.unquote( match.group(1))) html = self._http_get(ok_url, data='ok', headers={'Referer': referer}, cache_limit=.25) js_data = scraper_utils.parse_json(html, ok_url) stream_url = js_data.get('movie', {}).get('url') if stream_url is not None: host = urlparse.urlparse(stream_url).hostname hoster = { 'multi-part': False, 'host': host, 'class': self, 'quality': QUALITIES.HD720, 'views': None, 'rating': None, 'url': stream_url, 'direct': False, 'subs': 'Turkish Subtitles' } hosters.append(hoster) return hosters
def __get_iframe_sources(self, iframe_url, page_url): hosters = [] headers = {'Referer': page_url} html = self._http_get(iframe_url, headers=headers, cache_limit=.5) sources = dom_parser2.parse_dom(html, 'div', {'class': 'dzst-player'}, req='data-dzst-player') if sources: sources = scraper_utils.cleanse_title(sources[0].attrs['data-dzst-player'].replace('=', '=')) js_data = scraper_utils.parse_json(scraper_utils.cleanse_title(sources), iframe_url) sources = js_data.get('tr', {}) for key in sources: hosters.append(self.__create_source(sources[key], key, page_url, subs=True)) return hosters
def search(self, video_type, title, year, season=''): # @UnusedVariable results = [] if video_type == VIDEO_TYPES.TVSHOW and title: test_url = '/tv-show/%s/' % (scraper_utils.to_slug(title)) test_url = scraper_utils.urljoin(self.base_url, test_url) html = self._http_get(test_url, require_debrid=True, cache_limit=24) posts = dom_parser2.parse_dom(html, 'div', {'id': re.compile('post-\d+')}) if posts: result = { 'url': scraper_utils.pathify_url(test_url), 'title': scraper_utils.cleanse_title(title), 'year': '' } results.append(result) elif video_type == VIDEO_TYPES.MOVIE: search_title = re.sub('[^A-Za-z0-9 ]', '', title.lower()) html = self._http_get(self.base_url, params={'s': search_title}, require_debrid=True, cache_limit=1) norm_title = scraper_utils.normalize_title(title) for _attrs, post in dom_parser2.parse_dom( html, 'div', {'id': re.compile('post-\d+')}): match = re.search( '<h\d+[^>]*>\s*<a\s+href="([^"]+)[^>]*>(.*?)</a>', post) if match: post_url, post_title = match.groups() if '/tv-show/' in post or self.__too_old(post): continue post_title = re.sub('<[^>]*>', '', post_title) meta = scraper_utils.parse_movie_link(post_title) full_title = '%s [%s] (%sp)' % ( meta['title'], meta['extra'], meta['height']) match_year = meta['year'] match_norm_title = scraper_utils.normalize_title( meta['title']) if (match_norm_title in norm_title or norm_title in match_norm_title) and (not year or not match_year or year == match_year): result = { 'url': scraper_utils.pathify_url(post_url), 'title': scraper_utils.cleanse_title(full_title), 'year': match_year } results.append(result) return results
def search(self, video_type, title, year, season=''): # @UnusedVariable results = [] search_url = '/search/' + urllib.quote_plus(title) html = self._http_get(search_url, require_debrid=True, cache_limit=1) if video_type == VIDEO_TYPES.TVSHOW: seen_urls = {} for _attr, post in dom_parser2.parse_dom( html, 'div', {'id': re.compile('post-\d+')}): if CATEGORIES[video_type] not in post: continue match = re.search( '<span>\s*TAGS:\s*</span>\s*<a\s+href="([^"]+)[^>]+>([^<]+)', post, re.I) if match: show_url, match_title = match.groups() if show_url in seen_urls: continue result = { 'url': scraper_utils.pathify_url(show_url), 'title': scraper_utils.cleanse_title(match_title), 'year': '' } seen_urls[show_url] = result results.append(result) elif video_type == VIDEO_TYPES.MOVIE: norm_title = scraper_utils.normalize_title(title) headings = re.findall('<h2>\s*<a\s+href="([^"]+)[^>]+>(.*?)</a>', html) posts = [ result.content for result in dom_parser2.parse_dom( html, 'div', {'id': re.compile('post-\d+')}) ] for heading, post in zip(headings, posts): if CATEGORIES[video_type] not in post or self.__too_old(post): continue post_url, post_title = heading meta = scraper_utils.parse_movie_link(post_title) full_title = '%s [%s] (%sp)' % (meta['title'], meta['extra'], meta['height']) match_year = meta['year'] match_norm_title = scraper_utils.normalize_title(meta['title']) if (match_norm_title in norm_title or norm_title in match_norm_title) and (not year or not match_year or year == match_year): result = { 'url': scraper_utils.pathify_url(post_url), 'title': scraper_utils.cleanse_title(full_title), 'year': match_year } results.append(result) return results
def search(self, video_type, title, year, season=''): # @UnusedVariable results = [] seen_urls = set() search_url = scraper_utils.urljoin(self.base_url, '/yabanci-diziler/') html = self._http_get(search_url, cache_limit=48) norm_title = scraper_utils.normalize_title(title) for _attrs, item in dom_parser2.parse_dom(html, 'div', {'class': 'category-post'}): match_url = dom_parser2.parse_dom(item, 'a', req='href') match_title = dom_parser2.parse_dom(item, 'h3') if match_url and match_title: match_url = scraper_utils.pathify_url( match_url[0].attrs['href']) match_title = match_title[0].content if match_url in seen_urls: continue seen_urls.add(match_url) if norm_title in scraper_utils.normalize_title(match_title): result = { 'url': match_url, 'title': scraper_utils.cleanse_title(match_title), 'year': '' } results.append(result) return results
def search(self, video_type, title, year, season=''): # @UnusedVariable results = [] self.__get_token() if self.__token is None: return results search_url, u = self.__get_search_url() search_url = scraper_utils.urljoin(API_BASE_URL, search_url) timestamp = int(time.time() * 1000) s = self.__get_s() query = {'q': title, 'limit': '100', 'timestamp': timestamp, 'verifiedCheck': self.__token, 'set': s, 'rt': self.__get_rt(self.__token + s), 'sl': self.__get_sl(u)} headers = {'Referer': self.base_url} html = self._http_get(search_url, data=query, headers=headers, cache_limit=1) if video_type in [VIDEO_TYPES.TVSHOW, VIDEO_TYPES.EPISODE]: media_type = 'TV SHOW' else: media_type = 'MOVIE' for item in scraper_utils.parse_json(html, search_url): if not item['meta'].upper().startswith(media_type): continue match_year = str(item['year']) if 'year' in item and item['year'] else '' if not year or not match_year or year == match_year: result = {'title': scraper_utils.cleanse_title(item['title']), 'url': scraper_utils.pathify_url(item['permalink'].replace('/show/', '/tv-show/')), 'year': match_year} results.append(result) return results
def search(self, video_type, title, year, season=''): # @UnusedVariable results = [] xml_url = scraper_utils.urljoin(self.base_url, '/series.xml') xml = self._http_get(xml_url, cache_limit=24) if not xml: return results try: norm_title = scraper_utils.normalize_title(title) match_year = '' for element in ET.fromstring(xml).findall('.//dizi'): name = element.find('adi') if name is not None and norm_title in scraper_utils.normalize_title( name.text): url = element.find('url') if url is not None and (not year or not match_year or year == match_year): result = { 'url': scraper_utils.pathify_url(url.text), 'title': scraper_utils.cleanse_title(name.text), 'year': '' } results.append(result) except (ParseError, ExpatError) as e: logger.log('Dizilab Search Parse Error: %s' % (e), log_utils.LOGWARNING) return results
def search(self, video_type, title, year, season=''): # @UnusedVariable results = [] search_in = 'm' if video_type == VIDEO_TYPES.MOVIE else 't' search_url = scraper_utils.urljoin(self.base_url, '/search') html = self._http_get(search_url, data={ 'searchquery': title, 'searchin': search_in }, cache_limit=8) fragment = dom_parser2.parse_dom(html, 'div', {'class': 'search-page'}) if not fragment: return results fragment = dom_parser2.parse_dom(fragment[0].content, 'table') if not fragment: return results for attrs, match_title_year in dom_parser2.parse_dom( fragment[0].content, 'a', req='href'): match_url = attrs['href'] 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 search(self, video_type, title, year, season=''): # @UnusedVariable results = [] html = self._http_get(self.base_url, params={'s': title}, cache_limit=1) if re.search('Sorry, but nothing matched', html, re.I): return results fragment = dom_parser2.parse_dom(html, 'ul', {'class': 'listing-videos'}) if not fragment: return results for attrs, match_title_year in dom_parser2.parse_dom( fragment[0].content, 'a', req='href'): match_url = attrs['href'] match_title_year = re.sub('</?[^>]*>', '', match_title_year) match_title, match_year = scraper_utils.extra_year( match_title_year) 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 search(self, video_type, title, year, season=''): # @UnusedVariable results = [] html = self._http_get(self.base_url, params={'s': title}, cache_limit=8) for _attrs, item in dom_parser2.parse_dom( html, 'div', {'class': 'browse-movie-bottom'}): match = dom_parser2.parse_dom(item, 'a', req='href') if match: 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 match_year: div = dom_parser2.parse_dom(item, 'div', {'class': 'browse-movie-year'}) if div: match_year = div[0].content.strip() match_url += '?watching' 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 search(self, video_type, title, year, season=''): # @UnusedVariable results = [] search_url = scraper_utils.urljoin(self.base_url, '/videos/search/') headers = {'Referer': ''} html = self._http_get(search_url, params={ 'search': title, 've': 1 }, headers=headers, cache_limit=8) for _attrs, article in dom_parser2.parse_dom(html, 'article', {'class': 'movie_item'}): match = dom_parser2.parse_dom(article, 'a', req=['href', 'data-title']) if match: match_url = match[0].attrs['href'] match_title = match[0].attrs['data-title'] match_year = '' 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 search(self, video_type, title, year, season=''): # @UnusedVariable results = [] page_url = scraper_utils.urljoin(self.base_url, '/tvseries/search.php') html = self._http_get(page_url, params={'dayq': title}, cache_limit=48) html = re.sub('<!--.*?-->', '', html) norm_title = scraper_utils.normalize_title(title) for _attrs, td in dom_parser2.parse_dom(html, 'td', {'class': 'topic_content'}): match_url = dom_parser2.parse_dom(td, 'a', req='href') match_title_year = dom_parser2.parse_dom(td, 'img', req='alt') if not match_url or not match_title_year: continue match_url = match_url[0].attrs['href'] match_title_year = match_title_year[0].attrs['alt'] if not match_url.startswith('/'): match_url = '/tvseries/' + match_url match_title, match_year = scraper_utils.extra_year( match_title_year) if (norm_title in scraper_utils.normalize_title(match_title)) and ( 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 search(self, video_type, title, year, season=''): # @UnusedVariable results = [] search_url = scraper_utils.urljoin(self.base_url, '/search') html = self._http_get(search_url, params={'q': title}, cache_limit=8) for _attrs, item in dom_parser2.parse_dom(html, 'div', {'class': 'movie-item'}): match = dom_parser2.parse_dom(item, 'a', {'itemprop': 'url'}, 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 match_year: try: match_year = dom_parser2.parse_dom( item, 'div', {'class': 'overlay-year'})[0].content except: match_year = '' 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 search(self, video_type, title, year, season=''): # @UnusedVariable results = [] html = self._http_get(self.base_url, params={'s': title}, cache_limit=8) for _attrs, item in dom_parser2.parse_dom(html, 'div', {'class': 'movie-details'}): match_url = dom_parser2.parse_dom(item, 'a', req='href') match_title = dom_parser2.parse_dom(item, 'a') match_year = dom_parser2.parse_dom(item, 'span', {'class': 'movie-release'}) if match_url and match_title: match_url = match_url[0].attrs['href'] match_title = match_title[0].content if match_year: match_year = match_year[0].content.strip() else: match_year = '' 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 search(self, video_type, title, year, season=''): # @UnusedVariable results = [] search_url = scraper_utils.urljoin(self.base_url, '/search/searchBoxSuggestion') html = self._http_get(search_url, params={ 'top': 8, 'query': title }, cache_limit=8) js_data = scraper_utils.parse_json(html, search_url) for item in js_data: entityName = match_title_year = item.get('Value', '') if entityName: match_title, match_year2 = scraper_utils.extra_year( match_title_year) match_year = str(item.get('ReleaseYear', '')) if not match_year: match_year = match_year2 match_url = '/ontology/EntityDetails?' + urllib.urlencode( { 'entityName': entityName, 'ignoreMediaLinkError': 'false' }) 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 search(self, video_type, title, year, season=''): # @UnusedVariable results = [] params = {'c': 'movie', 'm': 'filter', 'keyword': title} html = self._http_get(self.base_url, params=params, cache_limit=8) for attrs, item in dom_parser2.parse_dom(html, 'div', {'class': 'recent-item'}, req='title'): match_url = dom_parser2.parse_dom(item, 'a', req='href') if not match_url: continue match_url = match_url[0].attrs['href'] is_series = re.search('/series/', match_url, re.I) if (video_type == VIDEO_TYPES.MOVIE and is_series) or (video_type == VIDEO_TYPES.TVSHOW and not is_series): continue match_title_year = attrs['title'] match_title, match_year = scraper_utils.extra_year( match_title_year) 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 search(self, video_type, title, year, season=''): # @UnusedVariable results = [] search_url = scraper_utils.urljoin(self.base_url, '/search') search_type = 'movies' if video_type == VIDEO_TYPES.MOVIE else 'series' html = self._http_get(search_url, params={'query': title.lower(), 'type': search_type}, cache_limit=8) for _attrs, item in dom_parser2.parse_dom(html, 'div', {'class': 'one_movie-item'}): match_url = dom_parser2.parse_dom(item, 'a', req='href') match_title = dom_parser2.parse_dom(item, 'img', req='alt') media_type = dom_parser2.parse_dom(item, 'div', {'class': 'movie-series'}) if not media_type: media_type = VIDEO_TYPES.MOVIE elif media_type[0].content == 'TV SERIE': media_type = VIDEO_TYPES.TVSHOW if match_url and match_title and video_type == media_type: match_url = match_url[0].attrs['href'] match_title = match_title[0].attrs['alt'] match_year = re.search('-(\d{4})-', match_url) if match_year: match_year = match_year.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 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, '/advanced-search/') headers = {'Referer': self.base_url} params = {'search_query': title, 'orderby': '', 'order': '', 'wpas': 1} html = self._http_get(search_url, params=params, headers=headers, cache_limit=8) norm_title = scraper_utils.normalize_title(title) for _attrs, item in dom_parser2.parse_dom(html, 'div', {'class': 'datos'}): match = dom_parser2.parse_dom(item, 'a', req='href') if not match: continue match_url = match[0].attrs['href'] is_tvshow = '/tvshows/' in match_url if is_tvshow and video_type == VIDEO_TYPES.MOVIE or not is_tvshow and video_type == VIDEO_TYPES.TVSHOW: continue match_title = match[0].content match_title, match_year = scraper_utils.extra_year(match_title) if scraper_utils.normalize_title(match_title) in norm_title 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 search(self, video_type, title, year, season=''): # @UnusedVariable html = self._http_get(self.base_url, params={'s': title}, cache_limit=1) results = [] for _attrs, item in dom_parser2.parse_dom(html, 'div', {'class': 'item'}): match_url = dom_parser2.parse_dom(item, 'a', req='href') match_title = dom_parser2.parse_dom(item, 'span', {'class': 'tt'}) year_frag = dom_parser2.parse_dom(item, 'span', {'class': 'year'}) if match_url and match_title: match_url = match_url[0].attrs['href'] match_title = match_title[0].content if re.search('\d+\s*x\s*\d+', match_title): continue # exclude episodes match_title, match_year = scraper_utils.extra_year(match_title) if not match_year and year_frag: match_year = year_frag[0].content 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 search(self, video_type, title, year, season=''): # @UnusedVariable results = [] data = { 'hash': 'indexert', 'do': 'search', 'subaction': 'search', 'search_start': 0, 'full_search': 0, 'result_from': 1, 'story': title } search_url = scraper_utils.urljoin(self.base_url, 'index.php') html = self._http_get(search_url, params={'do': 'search'}, data=data, cache_limit=8) if dom_parser2.parse_dom(html, 'div', {'class': 'sresult'}): for _attrs, item in dom_parser2.parse_dom( html, 'div', {'class': 'short_content'}): match_url = dom_parser2.parse_dom(item, 'a', req='href') match_title_year = dom_parser2.parse_dom( item, 'div', {'class': 'short_header'}) if match_url and match_title_year: match_url = match_url[0].attrs['href'] match_title, match_year = scraper_utils.extra_year( match_title_year[0].content) 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 search(self, video_type, title, year, season=''): # @UnusedVariable results = [] url = scraper_utils.urljoin(self.base_url, '/arsiv') html = self._http_get(url, cache_limit=48) norm_title = scraper_utils.normalize_title(title) fragment = dom_parser2.parse_dom(html, 'div', {'class': 'ts-list-content'}) if not fragment: return results items = dom_parser2.parse_dom(fragment[0].content, 'h1', {'class': 'ts-list-name'}) details = dom_parser2.parse_dom(fragment[0].content, 'ul') for item, detail in zip(items, details): match = dom_parser2.parse_dom(item.content, 'a', req='href') match_year = re.search('<span>(\d{4})</span>', detail.content) if not match: continue match_url = match[0].attrs['href'] match_title = match[0].content match_year = match_year.group(1) if match_year else '' if norm_title in scraper_utils.normalize_title(match_title): result = { 'url': scraper_utils.pathify_url(match_url), 'title': scraper_utils.cleanse_title(match_title), 'year': match_year } results.append(result) return results
def search(self, video_type, title, year, season=''): # @UnusedVariable results = [] html = self._http_get(self.base_url, params={'s': title}, cache_limit=4) for _attrs, movie in dom_parser2.parse_dom(html, 'div', {'class': 'movie'}): match_url = dom_parser2.parse_dom(movie, 'a', req='href') match_title_year = dom_parser2.parse_dom(movie, 'img', req='alt') if match_url and match_title_year: match_url = match_url[0].attrs['href'] if re.search('season-\d+-episode\d+', match_url): continue match_title_year = match_title_year[0].attrs['alt'] match_title, match_year = scraper_utils.extra_year( match_title_year) if not match_year: match_year = dom_parser2.parse_dom(movie, 'div', {'class': 'year'}) try: match_year = match_year[0].content 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 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 search(self, video_type, title, year, season=''): results = [] search_url = scraper_utils.urljoin(self.base_url, '/wp-content/plugins/ajax-search-pro/ajax_search.php') data = {'action': 'ajaxsearchpro_search', 'aspp': title, 'asid': '1', 'asp_inst_id': '1_1', 'options': 'current_page_id=7&qtranslate_lang=0&set_intitle=None&customset%5B%5D=post'} html = self._http_get(search_url, data=data, headers=XHR, cache_limit=8) norm_title = scraper_utils.normalize_title(title) for attrs, match_title_year in dom_parser2.parse_dom(html, 'a', {'class': 'asp_res_url'}): match_url = attrs['href'] match_title_year = re.sub('</?[^>]*>', '', match_title_year) is_season = re.search('Season\s+(\d+)\s*', match_title_year, re.I) if (not is_season and video_type == VIDEO_TYPES.MOVIE) or (is_season and video_type == VIDEO_TYPES.SEASON): match_year = '' if video_type == VIDEO_TYPES.SEASON: if season and int(is_season.group(1)) != int(season): continue match_title = match_title_year match_title = re.sub('\s*\d{4}', '', match_title) else: match_title, match_year = scraper_utils.extra_year(match_title_year) 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 = {'url': scraper_utils.pathify_url(match_url), 'title': scraper_utils.cleanse_title(match_title), 'year': match_year} results.append(result) return results
def search(self, video_type, title, year, season=''): # @UnusedVariable results = [] html = self._http_get(self.base_url, params={'s': title}, cache_limit=8) for _attrs, item in dom_parser2.parse_dom(html, 'div', {'class': 'cover'}): match = dom_parser2.parse_dom(item, 'a', req=['href', 'title']) if not match: continue match_url, match_title_year = match[0].attrs['href'], match[ 0].attrs['title'] if re.search('S\d+E\d+', match_title_year, re.I): continue match_title, match_year = scraper_utils.extra_year( match_title_year) if not match_year: match = re.search('-(\d{4})-', match_url) if match: match_year = match.group(1) 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 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 search(self, video_type, title, year, season=''): results = [] search_url = scraper_utils.urljoin(self.base_url, '/search/') title = re.sub('[^A-Za-z0-9 ]', '', title) search_url += '%s.html' % (urllib.quote_plus(title)) html = self._http_get(search_url, cache_limit=8) 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') match_year = re.search('class="jt-info">(\d{4})<', item) 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 not match_title or not match_url: continue 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 match_year = match_year.group(1) if match_year else '' 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 search(self, video_type, title, year, season=''): # @UnusedVariable results = [] search_title = re.sub('[^A-Za-z0-9. ]', '', title) url = '/search/%s/' % (urllib.quote(search_title)) url = scraper_utils.urljoin(self.base_url, url) html = self._http_get(url, cache_limit=48) norm_title = scraper_utils.normalize_title(title) for _attrs, item in dom_parser2.parse_dom(html, 'article', {'class': 'movie-details'}): match_url = dom_parser2.parse_dom(item, 'a', req='href') match_title = dom_parser2.parse_dom(item, 'h2', {'class': 'movie-title'}) match_year = dom_parser2.parse_dom(item, 'div', {'class': 'movie-year'}) if match_url and match_title: match_url = match_url[0].attrs['href'] match_title = match_title[0].content match_year = match_year[0].content if match_year else '' if norm_title in scraper_utils.normalize_title( match_title) and (not match_year or not 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