Python dom_parser.parse_dom函数代码示例

    def search(self, video_type, title, year):
        results = []
        search_url = urlparse.urljoin(self.__get_base_url(video_type), '/?s=%s' % (urllib.quote_plus(title)))
        html = self._http_get(search_url, cache_limit=1)
        for movie in dom_parser.parse_dom(html, 'div', {'class': 'movie'}):
            match = re.search('href="([^"]+)', movie)
            if match:
                match_url = match.group(1)
                if re.search('season-\d+-episode\d+', match_url): continue
                match_title_year = dom_parser.parse_dom(movie, 'img', ret='alt')
                if match_title_year:
                    match_title_year = match_title_year[0]
                    match = re.search('(.*?)\s+\((\d{4})\)', match_title_year)
                    if match:
                        match_title, match_year = match.groups()
                    else:
                        match_title = match_title_year
                        match_year = dom_parser.parse_dom(movie, 'div', {'class': 'year'})
                        try: match_year = match_year[0]
                        except: match_year = ''
                        
                    if not year or not match_year or year == match_year:
                        result = {'url': self._pathify_url(match_url), 'title': match_title, 'year': match_year}
                        results.append(result)

        return results

    def get_sources(self, video):
        source_url = self.get_url(video)
        hosters = []
        if source_url and source_url != FORCE_NO_MATCH:
            page_url = urlparse.urljoin(self.base_url, source_url)
            html = self._http_get(page_url, cache_limit=.25)
            match = re.search('''<option[^>]+value\s*=\s*["']([^"']+)[^>]*>(?:Altyaz.{1,3}s.{1,3}z)<''', html)
            if match:
                option_url = urlparse.urljoin(self.base_url, match.group(1))
                html = self._http_get(option_url, cache_limit=.25)
                fragment = dom_parser.parse_dom(html, 'span', {'class': 'object-wrapper'})
                if fragment:
                    iframe_url = dom_parser.parse_dom(fragment[0], 'iframe', ret='src')
                    if iframe_url:
                        html = self._http_get(iframe_url[0], cache_limit=.25)

                        seen_urls = {}
                        for match in re.finditer('"?file"?\s*:\s*"([^"]+)"\s*,\s*"?label"?\s*:\s*"(\d+)p?[^"]*"', html):
                            stream_url, height = match.groups()
                            if stream_url not in seen_urls:
                                seen_urls[stream_url] = True
                                stream_url += '|User-Agent=%s' % (scraper_utils.get_ua())
                                host = self._get_direct_hostname(stream_url)
                                if host == 'gvideo':
                                    quality = scraper_utils.gv_get_quality(stream_url)
                                else:
                                    quality = scraper_utils.height_get_quality(height)
                                hoster = {'multi-part': False, 'host': self._get_direct_hostname(stream_url), 'class': self, 'quality': quality, 'views': None, 'rating': None, 'url': stream_url, 'direct': True}
                                hosters.append(hoster)
    
        return hosters

    def get_sources(self, video):
        source_url = self.get_url(video)
        hosters = []
        if source_url and source_url != FORCE_NO_MATCH:
            url = urlparse.urljoin(self.base_url, source_url)
            html = self._http_get(url, cache_limit=.5)
            
            fragment = dom_parser.parse_dom(html, 'div', {'class': '[^"]*movie_langs_list[^"]*'})
            if fragment:
                for match in re.finditer('href="([^"]+)', fragment[0]):
                    match = re.search('movie-player/(.*)', match.group(1))
                    if match:
                        player_url = urlparse.urljoin(self.base_url, PLAYER_URL % (match.group(1)))
                        html = self._http_get(player_url, cache_limit=.5)
                        match = re.search('<source\s+src="([^"]+)', html)
                        if match:
                            stream_url = match.group(1)
                            hoster = {'multi-part': False, 'url': stream_url, 'class': self, 'quality': self._gv_get_quality(stream_url), 'host': self._get_direct_hostname(stream_url), 'rating': None, 'views': None, 'direct': True}
                            hosters.append(hoster)
                        
                        fragment2 = dom_parser.parse_dom(html, 'ul', {'class': 'servers'})
                        if fragment2:
                            for match in re.finditer('href="([^"]+).*?<span>(.*?)</span>', fragment2[0]):
                                other_url, quality = match.groups()
                                match = re.search('movie-player/(.*)', other_url)
                                if match:
                                    other_url = urlparse.urljoin(self.base_url, PLAYER_URL % (match.group(1)))
                                    if other_url == player_url: continue
                                    hoster = {'multi-part': False, 'url': other_url, 'class': self, 'quality': QUALITY_MAP.get(quality, QUALITIES.HD720), 'host': self._get_direct_hostname(other_url), 'rating': None, 'views': None, 'direct': True}
                                    hosters.append(hoster)

        return hosters

    def search(self, video_type, title, year):
        search_url = urlparse.urljoin(self.base_url, '/?query=')
        search_url += urllib.quote_plus(title)
        html = self._http_get(search_url, cache_limit=.25)
        results = []
        info = dom_parser.parse_dom(html, 'div', {'class': 'movie-info'})
        for item in info:
            match_title = dom_parser.parse_dom(item, 'span', {'class': 'movie-title'})
            match_year = dom_parser.parse_dom(item, 'span', {'class': 'movie-year'})
            if match_title:
                match_title = self.__strip_link(match_title[0])
                if match_year:
                    match_year = self.__strip_link(match_year[0])
                else:
                    match_year = ''
                    
                match = re.search('href="([^"]+)', item)
                if match:
                    url = match.group(1)
                else:
                    continue
    
                if not year or not match_year or year == match_year:
                    result = {'title': match_title, 'year': match_year, 'url': url.replace(self.base_url, '')}
                    results.append(result)

        return results

    def search(self, video_type, title, year):
        search_url = urlparse.urljoin(self.base_url, '/arsiv?limit=&tur=&orderby=&ulke=&order=&yil=&dizi_adi=')
        search_url += urllib.quote_plus(title)
        html = self._http_get(search_url, cache_limit=8)
        results = []
        for item in dom_parser.parse_dom(html, 'div', {'class': 'tv-series-single'}):
            try:
                url = re.search('href="([^"]+)', item).group(1)
            except:
                url = ''

            try:
                match_year = re.search('<span>\s*(\d{4})\s*</span>', item).group(1)
            except:
                match_year = ''
            
            try:
                match_title = dom_parser.parse_dom(item, 'a', {'class': 'title'})
                match_title = re.search('([^>]+)$', match_title[0]).group(1)
                match_title = match_title.strip()
            except:
                match_title = ''
            
            if url and match_title and (not year or not match_year or year == match_year):
                result = {'url': self._pathify_url(url), 'title': match_title, 'year': ''}
                results.append(result)

        return results

    def __movie_search(self, title, year):
        results = []
        search_url = urlparse.urljoin(self.base_url, '/search?q=')
        search_url += urllib.quote_plus(title)
        html = self._http_get(search_url, cache_limit=1)
        norm_title = scraper_utils.normalize_title(title)
        for item in dom_parser.parse_dom(html, 'div', {'class': 'video_item'}):
            match_url = dom_parser.parse_dom(item, 'a', ret='href')
            match_title = dom_parser.parse_dom(item, 'img', ret='alt')
            match_year = ''
            if match_url and match_title:
                match_url = match_url[0]
                match_title = match_title[0]
                
                if match_year:
                    match_year = match_year[0]
                else:
                    match_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 get_sources(self, video):
        source_url = self.get_url(video)
        hosters = []
        if source_url and source_url != FORCE_NO_MATCH:
            page_url = urlparse.urljoin(self.base_url, source_url)
            html = self._http_get(page_url, cache_limit=.25)
            for link in dom_parser.parse_dom(html, 'div', {'class': '[^"]*ldr-item[^"]*'}):
                stream_url = dom_parser.parse_dom(link, 'a', ret='data-actuallink')
                
                views = None
                watched = dom_parser.parse_dom(link, 'div', {'class': 'click-count'})
                if watched:
                    match = re.search(' (\d+) ', watched[0])
                    if match:
                        views = match.group(1)
                        
                score = dom_parser.parse_dom(link, 'div', {'class': '\s*point\s*'})
                if score:
                    score = int(score[0])
                    rating = score * 10 if score else None
                
                if stream_url:
                    stream_url = stream_url[0].strip()
                    host = urlparse.urlparse(stream_url).hostname
                    quality = scraper_utils.get_quality(video, host, QUALITIES.HIGH)
                    hoster = {'multi-part': False, 'host': host, 'class': self, 'quality': quality, 'views': views, 'rating': rating, 'url': stream_url, 'direct': False}
                    hosters.append(hoster)

        return hosters

    def search(self, video_type, title, year, season=''):
        results = []
        search_url = urlparse.urljoin(self.base_url, SEARCH_URL)
        search_url += urllib.quote_plus(title)
        html = self._http_get(search_url, cache_limit=8)
        fragment = dom_parser.parse_dom(html, 'div', {'class': '[^"]*items[^"]*'})
        if fragment:
            for item in dom_parser.parse_dom(fragment[0], 'div', {'class': 'item'}):
                match_url = dom_parser.parse_dom(item, 'a', {'class': 'header'}, ret='href')
                match_title_year = dom_parser.parse_dom(item, 'a', {'class': 'header'})
                if match_url and match_title_year:
                    match_url = match_url[0]
                    match_title_year = match_title_year[0]
                    r = re.search('(.*?)\s+\((\d{4})\)', match_title_year)
                    if r:
                        match_title, match_year = r.groups()
                    else:
                        match_title = match_title_year
                        match_year = ''
                    
                    if not year or not match_year or year == match_year:
                        result = {'url': scraper_utils.pathify_url(match_url), 'title': match_title, 'year': match_year}
                        results.append(result)

        return results

 def search(self, video_type, title, year, season=''):
     search_url = urlparse.urljoin(self.base_url, '/search/%s.html' % urllib.quote_plus(title))
     html = self._http_get(search_url, cache_limit=.25)
     results = []
     fragment = dom_parser.parse_dom(html, 'div', {'class': 'list-movie'})
     if fragment:
         for item in dom_parser.parse_dom(fragment[0], 'div', {'class': 'movie'}):
             match = re.search('class="movie-name".*?href="([^"]+)[^>]+>([^<]+)', item)
             if match:
                 url, match_title = match.groups()
                 is_season = re.search('\s+-\s+[Ss](\d+)$', match_title)
                 if not is_season and video_type == VIDEO_TYPES.MOVIE or is_season and VIDEO_TYPES.SEASON:
                     match_year = ''
                     if video_type == VIDEO_TYPES.MOVIE:
                         for info_frag in dom_parser.parse_dom(item, 'p', {'class': 'info'}):
                             match = re.search('(\d{4})', info_frag)
                             if match:
                                 match_year = match.group(1)
                                 break
                         
                         if not match_year:
                             match = re.search('(\d{4})$', url)
                             if match:
                                 match_year = match.group(1)
                     else:
                         if season and int(is_season.group(1)) != int(season):
                             continue
                             
                     if (not year or not match_year or year == match_year):
                         result = {'url': scraper_utils.pathify_url(url), 'title': scraper_utils.cleanse_title(match_title), 'year': match_year}
                         results.append(result)
     
     return results

    def search(self, video_type, title, year, season=''):
        search_url = urlparse.urljoin(self.base_url, '/search/?q=')
        search_url += urllib.quote_plus(title)
        html = self._http_get(search_url, cache_limit=8)
        results = []
        for item in dom_parser.parse_dom(html, 'div', {'class': 'ml-item'}):
            match_title = dom_parser.parse_dom(item, 'span', {'class': 'mli-info'})
            match_url = re.search('href="([^"]+)', item, re.DOTALL)
            year_frag = dom_parser.parse_dom(item, 'img', ret='alt')
            is_episodes = dom_parser.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.group(1)
                    match_title = match_title[0]
                    match_title = re.sub('</?h2>', '', match_title)
                    match_title = re.sub('\s+\d{4}$', '', match_title)
                    if video_type == VIDEO_TYPES.SEASON:
                        if season and not re.search('Season\s+%s$' % (season), match_title): continue
                        
                    if not match_url.endswith('/'): match_url += '/'
                    match_url = urlparse.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])
                        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=''):
        results = []
        search_url = urlparse.urljoin(self.base_url, '/search/')
        search_url += urllib.quote_plus(title)
        html = self._http_get(search_url, cache_limit=1)
        for fragment in dom_parser.parse_dom(html, 'div', {'class': 'inner'}):
            name = dom_parser.parse_dom(fragment, 'div', {'class': 'name'})
            if name:
                match = re.search('href="([^"]+)[^>]+>(.*?)</a>', name[0])
                if match:
                    match_url, match_title_year = match.groups()
                    if 'tv-series' in match_url and video_type == VIDEO_TYPES.MOVIE: continue
                    
                    match_title_year = re.sub('</?[^>]*>', '', match_title_year)
                    match_title_year = re.sub('[Ww]atch\s+[Mm]ovie\s*', '', match_title_year)
                    match_title_year = match_title_year.replace('&#8217;', "'")
                    match = re.search('(.*?)\s+\((\d{4})[^)]*\)$', match_title_year)
                    if match:
                        match_title, match_year = match.groups()
                    else:
                        match_title = match_title_year
                        match_year = ''
    
                    if not match_year:
                        year_span = dom_parser.parse_dom(fragment, 'span', {'class': 'year'})
                        if year_span:
                            year_text = dom_parser.parse_dom(year_span[0], 'a')
                            if year_text:
                                match_year = year_text[0].strip()
    
                    if not year or not match_year or year == match_year:
                        result = {'title': scraper_utils.cleanse_title(match_title), 'url': scraper_utils.pathify_url(match_url), 'year': match_year}
                        results.append(result)

        return results

 def _get_episode_url(self, show_url, video):
     sxe = '(\.|_| )S%02dE%02d(\.|_| )' % (int(video.season), int(video.episode))
     force_title = scraper_utils.force_title(video)
     title_fallback = kodi.get_setting('title-fallback') == 'true'
     norm_title = scraper_utils.normalize_title(video.ep_title)
     try: airdate_pattern = video.ep_airdate.strftime('(\.|_| )%Y(\.|_| )%m(\.|_| )%d(\.|_| )')
     except: airdate_pattern = ''
     
     page_url = [show_url]
     too_old = False
     while page_url and not too_old:
         url = urlparse.urljoin(self.base_url, page_url[0])
         html = self._http_get(url, require_debrid=True, cache_limit=1)
         posts = dom_parser.parse_dom(html, 'div', {'id': 'post-\d+'})
         for post in posts:
             if self.__too_old(post):
                 too_old = True
                 break
             if CATEGORIES[VIDEO_TYPES.TVSHOW] in post and show_url in post:
                 match = re.search('<a\s+href="([^"]+)[^>]+>(.*?)</a>', post)
                 if match:
                     url, title = match.groups()
                     if not force_title:
                         if re.search(sxe, title) or (airdate_pattern and re.search(airdate_pattern, title)):
                             return scraper_utils.pathify_url(url)
                     else:
                         if title_fallback and norm_title:
                             match = re.search('</strong>(.*?)</p>', post)
                             if match and norm_title == scraper_utils.normalize_title(match.group(1)):
                                 return scraper_utils.pathify_url(url)
             
         page_url = dom_parser.parse_dom(html, 'a', {'class': 'nextpostslink'}, ret='href')

 def search(self, video_type, title, year, season=''):
     search_url = urlparse.urljoin(self.base_url, '/search.php?q=%s&limit=20&timestamp=%s' % (urllib.quote_plus(title), int(time.time())))
     html = self._http_get(search_url, cache_limit=.25)
     results = []
     items = dom_parser.parse_dom(html, 'li')
     if len(items) >= 2:
         items = items[1:]
         for item in items:
             match_url = dom_parser.parse_dom(item, 'a', ret='href')
             match_title_year = dom_parser.parse_dom(item, 'strong')
             if match_url and match_title_year:
                 match_url = match_url[0]
                 match_title_year = re.sub('</?strong>', '', match_title_year[0])
                 is_season = re.search('S(?:eason\s+)?(\d+)$', match_title_year, re.I)
                 if not is_season and video_type == VIDEO_TYPES.MOVIE or is_season and VIDEO_TYPES.SEASON:
                     if video_type == VIDEO_TYPES.MOVIE:
                         match = re.search('(.*?)(?:\s+\(?(\d{4})\)?)', match_title_year)
                         if match:
                             match_title, match_year = match.groups()
                         else:
                             match_title = match_title_year
                             match_year = ''
                     else:
                         log_utils.log(is_season.group(1))
                         if season and int(is_season.group(1)) != int(season):
                             continue
                         match_title = match_title_year
                         match_year = ''
                 
                     result = {'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):
        results = []
        search_url = urlparse.urljoin(self.base_url, SEARCH_URL)
        search_url = search_url % (urllib.quote_plus(title))
        html = self._http_get(search_url, headers=XHR, cache_limit=1)
        for film in dom_parser.parse_dom(html, "li", {"class": "films-item"}):
            match_url = dom_parser.parse_dom(film, "a", ret="href")
            match_title = dom_parser.parse_dom(film, "div", {"class": "films-item-title"})
            match_year = dom_parser.parse_dom(film, "div", {"class": "films-item-year"})
            if match_url and match_title:
                match_url = match_url[0]
                match_title = match_title[0]
                match_title = re.sub("</?span>", "", match_title)
                if match_year:
                    match = re.search("(\d+)", match_year[0])
                    if match:
                        match_year = match.group(1)
                    else:
                        match_year = ""
                else:
                    match_year = ""

                if not year or not match_year or year == match_year:
                    result = {"title": match_title, "year": match_year, "url": match_url}
                    results.append(result)

        return results

 def get_sources(self, video):
     source_url = self.get_url(video)
     hosters = []
     if source_url and source_url != FORCE_NO_MATCH:
         url = urlparse.urljoin(self.base_url, source_url)
         html = self._http_get(url, cache_limit=.5)
         q_str = dom_parser.parse_dom(html, 'span', {'class': 'calidad\d*'})
         if q_str:
             if q_str[0].upper() == 'COMING SOON':
                 return hosters
             
             try:
                 quality = self._height_get_quality(q_str[0])
             except:
                 quality = QUALITIES.HIGH
         else:
             quality = QUALITIES.HIGH
         fragment = dom_parser.parse_dom(html, 'div', {'id': 'player\d+'})
         if fragment:
             for match in re.finditer('<iframe[^>]+src="([^"]+)', fragment[0], re.I):
                 stream_url = match.group(1)
                 host = urlparse.urlparse(stream_url).hostname
                 hoster = {'multi-part': False, 'url': stream_url, 'host': host, 'class': self, 'quality': quality, 'views': None, 'rating': None, 'direct': False}
                 hosters.append(hoster)
     return hosters