• 设为首页
  • 点击收藏
  • 手机版
    手机扫一扫访问
    迪恩网络手机版
  • 关注官方公众号
    微信扫一扫关注
    迪恩网络公众号

Python scraper_utils.height_get_quality函数代码示例

原作者: [db:作者] 来自: [db:来源] 收藏 邀请

本文整理汇总了Python中salts_lib.scraper_utils.height_get_quality函数的典型用法代码示例。如果您正苦于以下问题:Python height_get_quality函数的具体用法?Python height_get_quality怎么用?Python height_get_quality使用的例子?那么恭喜您, 这里精选的函数代码示例或许可以为您提供帮助。



在下文中一共展示了height_get_quality函数的20个代码示例,这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞,您的评价将有助于我们的系统推荐出更棒的Python代码示例。

示例1: resolve_link

    def resolve_link(self, link):
        try:
            headers = dict([item.split('=') for item in (link.split('|')[1]).split('&')])
            for key in headers: headers[key] = urllib.unquote(headers[key])
            link = link.split('|')[0]
        except:
            headers = {}

        if not link.startswith('http'):
            link = urlparse.urljoin(self.base_url, link)
        html = self._http_get(link, headers=headers, cache_limit=0)
                    
        fragment = dom_parser.parse_dom(html, 'div', {'class': 'player'})
        if fragment:
            iframe_url = dom_parser.parse_dom(fragment[0], 'iframe', ret='src')
            if iframe_url:
                iframe_url = iframe_url[0]
                headers = {'Referer': link}
                html = self._http_get(iframe_url, headers=headers, cache_limit=0)
                sitekey = dom_parser.parse_dom(html, 'div', {'class': 'g-recaptcha'}, ret='data-sitekey')
                if sitekey:
                    token = recaptcha_v2.UnCaptchaReCaptcha().processCaptcha(sitekey[0], lang='en')
                    if token:
                        data = {'g-recaptcha-response': token}
                        html = self._http_get(iframe_url, data=data, cache_limit=0)
                        log_utils.log(html)
                        
                match = re.search("\.replace\(\s*'([^']+)'\s*,\s*'([^']*)'\s*\)", html, re.I)
                if match:
                    html = html.replace(match.group(1), match.group(2))

                match = re.search("window\.atob[\([]+'([^']+)", html)
                if match:
                    func_count = len(re.findall('window\.atob', html))
                    html = match.group(1)
                    for _i in xrange(func_count):
                        html = base64.decodestring(html)
                
                streams = []
                for match in re.finditer('''<source[^>]+src=["']([^'"]+)[^>]+label=['"]([^'"]+)''', html):
                    streams.append(match.groups())
                
                if len(streams) > 1:
                    if not self.auto_pick:
                        result = xbmcgui.Dialog().select(i18n('choose_stream'), [e[1] for e in streams])
                        if result > -1:
                            return streams[result][0] + '|User-Agent=%s' % (scraper_utils.get_ua())
                    else:
                        best_stream = ''
                        best_q = 0
                        for stream in streams:
                            stream_url, label = stream
                            if Q_ORDER[scraper_utils.height_get_quality(label)] > best_q:
                                best_q = Q_ORDER[scraper_utils.height_get_quality(label)]
                                best_stream = stream_url
                        
                        if best_stream:
                            return best_stream + '|User-Agent=%s' % (scraper_utils.get_ua())
                elif streams:
                    return streams[0][0] + '|User-Agent=%s' % (scraper_utils.get_ua())
开发者ID:dsjh,项目名称:tknorris-beta-repo,代码行数:60,代码来源:watchhd_scraper.py


示例2: get_sources

 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, require_debrid=True, cache_limit=.5)
         title = dom_parser.parse_dom(html, 'title')
         if title:
             title = re.sub('^\[ST\]\s*&#8211;\s*', '', title[0])
             meta = scraper_utils.parse_episode_link(title)
             page_quality = scraper_utils.height_get_quality(meta['height'])
         else:
             page_quality = QUALITIES.HIGH
         
         fragment = dom_parser.parse_dom(html, 'section', {'class': '[^"]*entry-content[^"]*'})
         if fragment:
             for section in dom_parser.parse_dom(fragment[0], 'p'):
                 match = re.search('([^<]*)', section)
                 meta = scraper_utils.parse_episode_link(match.group(1))
                 if meta['episode'] != '-1' or meta['airdate']:
                     section_quality = scraper_utils.height_get_quality(meta['height'])
                 else:
                     section_quality = page_quality
                     
                 if Q_ORDER[section_quality] < Q_ORDER[page_quality]:
                     quality = section_quality
                 else:
                     quality = page_quality
                     
                 for stream_url in dom_parser.parse_dom(section, 'a', ret='href'):
                     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
开发者ID:EPiC-APOC,项目名称:repository.xvbmc,代码行数:34,代码来源:tvshow_scraper.py


示例3: __get_links_from_json2

 def __get_links_from_json2(self, url, page_url, video_type):
     sources = {}
     headers = {'Referer': page_url}
     headers.update(XHR)
     html = self._http_get(url, headers=headers, cache_limit=0)
     js_data = scraper_utils.parse_json(html, url)
     try:
         playlist = js_data.get('playlist', [])
         for source in playlist[0].get('sources', []):
             stream_url = source['file']
             if scraper_utils.get_direct_hostname(self, stream_url) == 'gvideo':
                 quality = scraper_utils.gv_get_quality(stream_url)
             elif 'label' in source:
                 quality = scraper_utils.height_get_quality(source['label'])
             else:
                 if video_type == VIDEO_TYPES.MOVIE:
                     meta = scraper_utils.parse_movie_link(stream_url)
                 else:
                     meta = scraper_utils.parse_episode_link(stream_url)
                 quality = scraper_utils.height_get_quality(meta['height'])
             sources[stream_url] = {'quality': quality, 'direct': True}
             logger.log('Adding stream: %s Quality: %s' % (stream_url, quality), log_utils.LOGDEBUG)
     except Exception as e:
         logger.log('Exception during yesmovies extract: %s' % (e), log_utils.LOGDEBUG)
     return sources
开发者ID:CYBERxNUKE,项目名称:xbmc-addon,代码行数:25,代码来源:yesmovies_scraper.py


示例4: get_sources

    def get_sources(self, video):
        source_url = self.get_url(video)
        hosters = []
        sources = []
        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('var\s+view_id\s*=\s*"([^"]+)', html)
            if match:
                view_data = {'id': match.group(1), 'tip': 'view', 'dil': 'or'}
                html = self._http_get(self.ajax_url, data=view_data, headers=XHR, cache_limit=.25)
                html = html.strip()
                html = re.sub(r'\\n|\\t', '', html)
                match = re.search('var\s+sources\s*=\s*(\[.*?\])', html)
                if match:
                    raw_data = match.group(1)
                    raw_data = raw_data.replace('\\', '')
                else:
                    raw_data = html
                
                js_data = scraper_utils.parse_json(raw_data, self.ajax_url)
                if 'data' in js_data:
                    src = dom_parser.parse_dom(js_data['data'], 'iframe', ret='src')
                    if src:
                        html = self._http_get(src[0], cache_limit=.25)
                        match = re.search('url=([^"]+)', html)
                        if match:
                            stream_url = match.group(1).replace('&gt;', '')
                            sources.append({'label': '720p', 'file': stream_url})
                            direct = False
                        else:
                            src = dom_parser.parse_dom(html, 'iframe', ret='src')
                            if src:
                                sources.append({'label': '720p', 'file': src[0]})
                                direct = False
                            else:
                                for match in re.finditer('"file"\s*:\s*"([^"]+)"\s*,\s*"label"\s*:\s*"([^"]+)', html):
                                    sources.append({'label': match.group(2), 'file': match.group(1)})
                                direct = True
                else:
                    sources = js_data
                    direct = True

                for source in sources:
                    stream_url = source['file'] + '|User-Agent=%s' % (scraper_utils.get_ua())
                    if direct:
                        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(source['label'])
                    else:
                        host = urlparse.urlparse(stream_url).hostname
                        quality = scraper_utils.height_get_quality(source['label'])
                
                    hoster = {'multi-part': False, 'host': host, 'class': self, 'quality': quality, 'views': None, 'rating': None, 'url': stream_url, 'direct': direct}
                    hosters.append(hoster)
    
        return hosters
开发者ID:c0ns0le,项目名称:YCBuilds,代码行数:59,代码来源:dizigold_scraper.py


示例5: get_sources

    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 = {'Referer': page_url}
        html = self._http_get(page_url, headers=headers, cache_limit=.5)
        if video.video_type == VIDEO_TYPES.MOVIE:
            fragment = dom_parser2.parse_dom(html, 'div', {'class': 'poster'})
            if fragment:
                movie_url = dom_parser2.parse_dom(fragment[0].content, 'a', req='href')
                if movie_url:
                    page_url = scraper_utils.urljoin(self.base_url, movie_url[0].attrs['href'])
                    html = self._http_get(page_url, cache_limit=.5)
                    episodes = self.__get_episodes(html)
                    page_url = self.__get_best_page(episodes)
                    if not page_url:
                        return hosters
                    else:
                        page_url = scraper_utils.urljoin(self.base_url, page_url)
                        html = self._http_get(page_url, cache_limit=.5)
        
        streams = dom_parser2.parse_dom(html, 'iframe', req='src')
        if streams:
            streams = [(attrs['src'], 480) for attrs, _content in streams]
            direct = False
        else:
            streams = [(attrs['src'], attrs.get('data-res', 480)) for attrs, _content in dom_parser2.parse_dom(html, 'source', req=['src'])]
            direct = True
            
        headers = {'User-Agent': scraper_utils.get_ua(), 'Referer': page_url}
        for stream_url, height in streams:
            if 'video.php' in stream_url or 'moviexk.php' in stream_url:
                if 'title=' in stream_url:
                    title = stream_url.split('title=')[-1]
                    stream_url = stream_url.replace(title, urllib.quote(title))
                redir_url = self._http_get(stream_url, headers=headers, allow_redirect=False, method='HEAD', cache_limit=0)
                if redir_url.startswith('http'):
                    redir_url = redir_url.replace(' ', '').split(';codec')[0]
                    stream_url = redir_url
                else:
                    continue
            
            if direct:
                host = scraper_utils.get_direct_hostname(self, stream_url)
                if host == 'gvideo':
                    quality = scraper_utils.gv_get_quality(stream_url)
                else:
                    quality = scraper_utils.height_get_quality(height)
                stream_url += scraper_utils.append_headers(headers)
            else:
                host = urlparse.urlparse(stream_url).hostname
                quality = scraper_utils.height_get_quality(height)
            
            source = {'multi-part': False, 'url': stream_url, 'host': host, 'class': self, 'quality': quality, 'views': None, 'rating': None, 'direct': direct}
            hosters.append(source)

        return hosters
开发者ID:CYBERxNUKE,项目名称:xbmc-addon,代码行数:58,代码来源:moviexk_scraper.py


示例6: __get_links

    def __get_links(self, url, video):
        hosters = []
        search_url = urlparse.urljoin(self.base_url, SEARCH_URL)
        query = self.__translate_search(url)
        result = self._http_get(search_url, data=query, allow_redirect=False, cache_limit=.5)
        if 'files' in result:
            for item in result['files']:
                checks = [False] * 6
                if 'type' not in item or item['type'].upper() != 'VIDEO': checks[0] = True
                if 'is_ready' in item and item['is_ready'] != '1': checks[1] = True
                if 'av_result' in item and item['av_result'] in ['warning', 'infected']: checks[2] = True
                if 'video_info' not in item: checks[3] = True
                if 'video_info' in item and item['video_info'] and not re.search('#0:(?:0|1)(?:\(eng\)|\(und\))?:\s*Audio:', item['video_info']): checks[4] = True
                if video.video_type == VIDEO_TYPES.EPISODE:
                    sxe = '[. ][Ss]%02d[Ee]%02d[. ]' % (int(video.season), int(video.episode))
                    if not re.search(sxe, item['name']):
                        if video.ep_airdate:
                            airdate_pattern = '[. ]%s[. ]%02d[. ]%02d[. ]' % (video.ep_airdate.year, video.ep_airdate.month, video.ep_airdate.day)
                            if not re.search(airdate_pattern, item['name']): checks[5] = True
                    
                if any(checks):
                    log_utils.log('Furk.net result excluded: %s - |%s|' % (checks, item['name']), log_utils.LOGDEBUG)
                    continue
                
                match = re.search('(\d{3,})\s?x\s?(\d{3,})', item['video_info'])
                if match:
                    width, _ = match.groups()
                    quality = scraper_utils.width_get_quality(width)
                else:
                    if video.video_type == VIDEO_TYPES.MOVIE:
                        _, _, height, _ = scraper_utils.parse_movie_link(item['name'])
                        quality = scraper_utils.height_get_quality(height)
                    elif video.video_type == VIDEO_TYPES.EPISODE:
                        _, _, _, height, _ = scraper_utils.parse_episode_link(item['name'])
                        if int(height) > -1:
                            quality = scraper_utils.height_get_quality(height)
                        else:
                            quality = QUALITIES.HIGH
                    else:
                        quality = QUALITIES.HIGH
                    
                if 'url_pls' in item:
                    size_gb = scraper_utils.format_size(int(item['size']), 'B')
                    if self.max_bytes and int(item['size']) > self.max_bytes:
                        log_utils.log('Result skipped, Too big: |%s| - %s (%s) > %s (%sGB)' % (item['name'], item['size'], size_gb, self.max_bytes, self.max_gb))
                        continue

                    stream_url = item['url_pls']
                    host = self._get_direct_hostname(stream_url)
                    hoster = {'multi-part': False, 'class': self, 'views': None, 'url': stream_url, 'rating': None, 'host': host, 'quality': quality, 'direct': True}
                    hoster['size'] = size_gb
                    hoster['extra'] = item['name']
                    hosters.append(hoster)
                else:
                    log_utils.log('Furk.net result skipped - no playlist: |%s|' % (json.dumps(item)), log_utils.LOGDEBUG)
                    
        return hosters
开发者ID:freeworldxbmc,项目名称:KAOSbox-Repo,代码行数:57,代码来源:furk_scraper.py


示例7: __get_quality

 def __get_quality(self, item, video):
     if 'width' in item:
         return scraper_utils.width_get_quality(item['width'])
     elif 'height' in item:
         return scraper_utils.height_get_quality(item['height'])
     else:
         if video.video_type == VIDEO_TYPES.MOVIE:
             _title, _year, height, _extra = scraper_utils.parse_movie_link(item['name'])
         else:
             _title, _season, _episode, height, _extra = scraper_utils.parse_episode_link(item['name'])
         return scraper_utils.height_get_quality(height)
开发者ID:c0ns0le,项目名称:YCBuilds,代码行数:11,代码来源:premiumizev2_scraper.py


示例8: __get_quality

 def __get_quality(self, item, video):
     if 'width' in item and item['width']:
         return scraper_utils.width_get_quality(item['width'])
     elif 'height' in item and item['height']:
         return scraper_utils.height_get_quality(item['height'])
     elif 'name' in item:
         if video.video_type == VIDEO_TYPES.MOVIE:
             meta = scraper_utils.parse_movie_link(item['name'])
         else:
             meta = scraper_utils.parse_episode_link(item['name'])
         return scraper_utils.height_get_quality(meta['height'])
     else:
         return QUALITIES.HIGH
开发者ID:EPiC-APOC,项目名称:repository.xvbmc,代码行数:13,代码来源:premiumizev2_scraper.py


示例9: get_sources

    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)
            pattern = '\$\.post\("([^"]+)"\s*,\s*\{(.*?)\}'
            match = re.search(pattern, html)
            if match:
                post_url, post_data = match.groups()
                data = self.__get_data(post_data)
                html = self._http_get(post_url, data=data, cache_limit=.5)
                js_result = scraper_utils.parse_json(html, post_url)
                for key in js_result:
                    stream_url = js_result[key]
                    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(key)
                        
                    hoster = {'multi-part': False, 'host': host, 'class': self, 'quality': quality, 'views': None, 'rating': None, 'url': stream_url, 'direct': True}
                    hosters.append(hoster)

        return hosters
开发者ID:c0ns0le,项目名称:YCBuilds,代码行数:25,代码来源:dizipas_scraper.py


示例10: get_sources

 def get_sources(self, video):
     source_url = self.get_url(video)
     sources = []
     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)
         is_3d = False
         page_quality = QUALITIES.HD720
         title = dom_parser.parse_dom(html, 'title')
         if title:
             title = title[0]
             match = re.search('(\d{3,})p', title)
             if match:
                 page_quality = scraper_utils.height_get_quality(match.group(1))
             
             is_3d = True if re.search('\s+3D\s+', title) else False
         
         fragments = dom_parser.parse_dom(html, 'div', {'class': 'txt-block'}) + dom_parser.parse_dom(html, 'li', {'class': 'elemento'})
         for fragment in fragments:
             for match in re.finditer('href="([^"]+)', fragment):
                 stream_url = match.group(1)
                 host = urlparse.urlparse(stream_url).hostname
                 q_str = dom_parser.parse_dom(fragment, 'span', {'class': 'd'})
                 q_str = q_str[0].upper() if q_str else ''
                 base_quality = QUALITY_MAP.get(q_str, page_quality)
                 quality = scraper_utils.get_quality(video, host, base_quality)
                 source = {'multi-part': False, 'url': stream_url, 'host': host, 'class': self, 'quality': quality, 'views': None, 'rating': None, 'direct': False}
                 source['format'] = 'x265'
                 source['3D'] = is_3d
                 sources.append(source)
                 
     return sources
开发者ID:EPiC-APOC,项目名称:repository.xvbmc,代码行数:32,代码来源:hevcbluray_scraper.py


示例11: __get_gk_links

 def __get_gk_links(self, html, page_url, video_type, episode):
     sources = {}
     for link in dom_parser.parse_dom(html, 'div', {'class': '[^"]*server_line[^"]*'}):
         film_id = dom_parser.parse_dom(link, 'a', ret='data-film')
         name_id = dom_parser.parse_dom(link, 'a', ret='data-name')
         server_id = dom_parser.parse_dom(link, 'a', ret='data-server')
         if film_id and name_id and server_id:
             data = {'ipplugins': 1, 'ip_film': film_id[0], 'ip_server': server_id[0], 'ip_name': name_id[0]}
             headers = {'Referer': page_url}
             headers.update(XHR)
             url = urlparse.urljoin(self.base_url, LINK_URL)
             html = self._http_get(url, data=data, headers=headers, cache_limit=.25)
             js_data = scraper_utils.parse_json(html, url)
             if 's' in js_data and isinstance(js_data['s'], basestring):
                 url = urlparse.urljoin(self.base_url, LINK_URL3)
                 params = {'u': js_data['s'], 'w': '100%', 'h': 450, 's': js_data['v']}
                 html = self._http_get(url, params=params, headers=headers, cache_limit=.25)
                 js_data = scraper_utils.parse_json(html, url)
                 if 'data' in js_data and js_data['data']:
                     if isinstance(js_data['data'], basestring):
                         sources[js_data['data']] = QUALITIES.HIGH
                     else:
                         for link in js_data['data']:
                             stream_url = link['files']
                             if self._get_direct_hostname(stream_url) == 'gvideo':
                                 quality = scraper_utils.gv_get_quality(stream_url)
                             elif 'quality' in link:
                                 quality = scraper_utils.height_get_quality(link['quality'])
                             else:
                                 quality = QUALITIES.HIGH
                             sources[stream_url] = quality
                 
     return sources
开发者ID:EPiC-APOC,项目名称:repository.xvbmc,代码行数:33,代码来源:moviesub_scraper.py


示例12: get_sources

 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)
     html = self._http_get(page_url, cache_limit=.5)
     match = re.search('var\s*video_id="([^"]+)', html)
     if not match: return hosters
     
     video_id = match.group(1)
     data = {'v': video_id}
     headers = {'Referer': page_url}
     headers.update(XHR)
     html = self._http_get(INFO_URL, data=data, headers=headers, cache_limit=.5)
     sources = scraper_utils.parse_json(html, INFO_URL)
     for source in sources:
         match = re.search('url=(.*)', sources[source])
         if not match: continue
         
         stream_url = urllib.unquote(match.group(1))
         host = scraper_utils.get_direct_hostname(self, stream_url)
         if host == 'gvideo':
             quality = scraper_utils.gv_get_quality(stream_url)
         else:
             quality = scraper_utils.height_get_quality(source)
         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': True}
         hosters.append(hoster)
     return hosters
开发者ID:CYBERxNUKE,项目名称:xbmc-addon,代码行数:29,代码来源:fmovie_scraper.py


示例13: get_sources

 def get_sources(self, video):
     source_url = self.get_url(video)
     hosters = []
     norm_title = scraper_utils.normalize_title(video.title)
     if source_url and source_url != FORCE_NO_MATCH:
         source_url = urlparse.urljoin(self.base_url, source_url)
         for line in self._get_files(source_url, cache_limit=24):
             if not line['directory']:
                 match = {}
                 if video.video_type == VIDEO_TYPES.MOVIE:
                     meta = scraper_utils.parse_movie_link(line['link'])
                     if norm_title in scraper_utils.normalize_title(meta['title']):
                         match = line
                 elif self.__episode_match(line, video):
                     match = line
                     meta = scraper_utils.parse_episode_link(line['link'])
                     
                 if match:
                     if meta['dubbed']: continue
                     stream_url = match['url'] + '|User-Agent=%s' % (scraper_utils.get_ua())
                     stream_url = stream_url.replace(self.base_url, '')
                     quality = scraper_utils.height_get_quality(meta['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}
                     if 'format' in meta: hoster['format'] = meta['format']
                     if 'size' in match: hoster['size'] = scraper_utils.format_size(int(match['size']))
                     hosters.append(hoster)
         
     return hosters
开发者ID:EPiC-APOC,项目名称:repository.xvbmc,代码行数:28,代码来源:farda_scraper.py


示例14: __get_gk_links

 def __get_gk_links(self, html, page_url, video_type, episode):
     sources = {}
     phimid = dom_parser.parse_dom(html, 'input', {'name': 'phimid'}, ret='value')
     if phimid and video_type == VIDEO_TYPES.EPISODE:
         url = urlparse.urljoin(self.tv_base_url, '/ajax.php')
         data = {'ipos_server': 1, 'phimid': phimid[0], 'keyurl': episode}
         headers = XHR
         headers['Referer'] = page_url
         html = self._http_get(url, data=data, headers=headers, cache_limit=.5)
         
     for link in dom_parser.parse_dom(html, 'div', {'class': '[^"]*server_line[^"]*'}):
         film_id = dom_parser.parse_dom(link, 'a', ret='data-film')
         name_id = dom_parser.parse_dom(link, 'a', ret='data-name')
         server_id = dom_parser.parse_dom(link, 'a', ret='data-server')
         if film_id and name_id and server_id:
             data = {'ipplugins': 1, 'ip_film': film_id[0], 'ip_server': server_id[0], 'ip_name': name_id[0]}
             headers = XHR
             headers['Referer'] = page_url
             url = urlparse.urljoin(self.__get_base_url(video_type), LINK_URL)
             html = self._http_get(url, data=data, headers=headers, cache_limit=.25)
             js_data = scraper_utils.parse_json(html, url)
             if 's' in js_data:
                 if isinstance(js_data['s'], basestring):
                     sources[js_data['s']] = QUALITIES.HIGH
                 else:
                     for link in js_data['s']:
                         stream_url = link['file']
                         if self._get_direct_hostname(stream_url) == 'gvideo':
                             quality = scraper_utils.gv_get_quality(stream_url)
                         elif 'label' in link:
                             quality = scraper_utils.height_get_quality(link['label'])
                         else:
                             quality = QUALITIES.HIGH
                         sources[stream_url] = quality
     return sources
开发者ID:kevintone,项目名称:tdbaddon,代码行数:35,代码来源:moviesub_scraper.py


示例15: __get_cloud_links

 def __get_cloud_links(self, html, page_url, sub):
     hosters = []
     html = html.replace('\\"', '"').replace('\\/', '/')
     match = re.search("dizi_kapak_getir\('([^']+)", html)
     if match:
         ep_id = match.group(1)
         for script_url in dom_parser.parse_dom(html, 'script', {'data-cfasync': 'false'}, ret='src'):
             html = self._http_get(script_url, cache_limit=24)
             match1 = re.search("var\s+kapak_url\s*=\s*'([^']+)", html)
             match2 = re.search("var\s+aCtkp\s*=\s*'([^']+)", html)
             if match1 and match2:
                 link_url = '%s?fileid=%s&access_token=%s' % (match1.group(1), ep_id, match2.group(1))
                 headers = {'Referer': page_url}
                 html = self._http_get(link_url, headers=headers, cache_limit=.5)
                 js_data = scraper_utils.parse_json(html, link_url)
                 for variant in js_data.get('variants', {}):
                     stream_host = random.choice(variant.get('hosts', []))
                     if stream_host:
                         stream_url = STREAM_URL % (stream_host, variant['path'], scraper_utils.get_ua(), urllib.quote(page_url))
                         if not stream_url.startswith('http'):
                             stream_url = 'http://' + stream_url
                         host = self._get_direct_hostname(stream_url)
                         if 'width' in variant:
                             quality = scraper_utils.width_get_quality(variant['width'])
                         elif 'height' in variant:
                             quality = scraper_utils.height_get_quality(variant['height'])
                         else:
                             quality = QUALITIES.HIGH
                         hoster = {'multi-part': False, 'host': host, 'class': self, 'quality': quality, 'views': None, 'rating': None, 'url': stream_url, 'direct': True}
                         hoster['subs'] = sub
                         hosters.append(hoster)
     return hosters
开发者ID:EPiC-APOC,项目名称:repository.xvbmc,代码行数:32,代码来源:dizilab_scraper.py


示例16: get_sources

 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=.5)
         match = re.search('var\s*video_id="([^"]+)', html)
         if match:
             video_id = match.group(1)
             url = urlparse.urljoin(self.base_url, VIDEO_URL)
             data = {'v': video_id}
             headers = XHR
             headers['Referer'] = page_url
             html = self._http_get(url, data=data, headers=headers, cache_limit=.5)
             sources = scraper_utils.parse_json(html, url)
             for source in sources:
                 match = re.search('url=(.*)', sources[source])
                 if match:
                     stream_url = urllib.unquote(match.group(1))
                     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(source)
                     stream_url += '|User-Agent=%s' % (scraper_utils.get_ua())
                     hoster = {'multi-part': False, 'host': host, 'class': self, 'quality': quality, 'views': None, 'rating': None, 'url': stream_url, 'direct': True}
                     hosters.append(hoster)
     return hosters
开发者ID:assli100,项目名称:kodi-openelec,代码行数:28,代码来源:xmovies8_scraper.py


示例17: __get_streams_from_m3u8

 def __get_streams_from_m3u8(self, playlist, st_url, vid_id, stream_id):
     sources = {}
     quality = QUALITIES.HIGH
     audio_group = ''
     audio_stream = ''
     stream_name = 'Unknown'
     bandwidth = 0
     for line in playlist:
         if line.startswith('#EXT-X-MEDIA'):
             match = re.search('GROUP-ID="([^"]+).*?URI="([^"]+)', line)
             if match:
                 audio_group, audio_stream = match.groups()
         if line.startswith('#EXT-X-STREAM-INF'):
             match = re.search('BANDWIDTH=(\d+).*?NAME="(\d+p)', line)
             if match:
                 bandwidth, stream_name = match.groups()
                 quality = scraper_utils.height_get_quality(stream_name)
         elif line.endswith('m3u8'):
             stream_url = urlparse.urljoin(st_url, line)
             query = {'audio_group': audio_group, 'audio_stream': audio_stream, 'stream_name': stream_name, 'bandwidth': bandwidth, 'video_stream': stream_url,
                      'vid_id': vid_id, 'stream_id': stream_id}
             stream_url = urllib.urlencode(query)
             sources[stream_url] = quality
             
     return sources
开发者ID:Stevie-Bs,项目名称:repository.xvbmc,代码行数:25,代码来源:torba_scraper.py


示例18: get_sources

    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)

            if re.search('<span[^>]+>\s*Low Quality\s*</span>', html):
                quality = QUALITIES.LOW
            else:
                quality = QUALITIES.HIGH
            
            for match in re.finditer('gkpluginsphp.*?link\s*:\s*"([^"]+)', html):
                data = {'link': match.group(1)}
                headers = XHR
                headers['Referer'] = url
                gk_url = urlparse.urljoin(self.base_url, GK_URL)
                html = self._http_get(gk_url, data=data, headers=headers, cache_limit=.25)
                js_result = scraper_utils.parse_json(html, gk_url)
                if 'link' in js_result and 'func' not in js_result:
                    if isinstance(js_result['link'], list):
                        sources = dict((link['link'], scraper_utils.height_get_quality(link['label'])) for link in js_result['link'])
                    else:
                        sources = {js_result['link']: quality}
                    
                    for source in sources:
                        host = self._get_direct_hostname(source)
                        hoster = {'multi-part': False, 'url': source, 'class': self, 'quality': sources[source], 'host': host, 'rating': None, 'views': None, 'direct': True}
                        hosters.append(hoster)

        return hosters
开发者ID:freeworldxbmc,项目名称:KAOSbox-Repo,代码行数:31,代码来源:viooz_scraper.py


示例19: __get_gk_links

 def __get_gk_links(self, link, iframe_url):
     sources = {}
     data = {'link': link}
     headers = XHR
     headers.update({'Referer': iframe_url, 'User-Agent': USER_AGENT})
     html = self._http_get(GK_URL, data=data, headers=headers, cache_limit=.25)
     js_data = scraper_utils.parse_json(html, GK_URL)
     if 'link' in js_data:
         if isinstance(js_data['link'], basestring):
             stream_url = js_data['link']
             if self._get_direct_hostname(stream_url) == 'gvideo':
                 temp = self._parse_google(stream_url)
                 for source in temp:
                     sources[source] = {'quality': scraper_utils.gv_get_quality(source), 'direct': True}
             else:
                 sources[stream_url] = {'quality': QUALITIES.HIGH, 'direct': False}
         else:
             for link in js_data['link']:
                 stream_url = link['link']
                 if self._get_direct_hostname(stream_url) == 'gvideo':
                     quality = scraper_utils.gv_get_quality(stream_url)
                 elif 'label' in link:
                     quality = scraper_utils.height_get_quality(link['label'])
                 else:
                     quality = QUALITIES.HIGH
                 sources[stream_url] = {'quality': quality, 'direct': True}
     return sources
开发者ID:freeworldxbmc,项目名称:KAOSbox-Repo,代码行数:27,代码来源:pubfilm_scraper.py


示例20: get_sources

    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=8)
        for _attrs, fragment in dom_parser2.parse_dom(html, 'div', {'class': 'movieplay'}):
            iframe_src = dom_parser2.parse_dom(fragment, 'iframe', req='src')
            if iframe_src:
                iframe_src = iframe_src[0].attrs['src']
                if re.search('o(pen)?load', iframe_src, re.I):
                    meta = scraper_utils.parse_movie_link(iframe_src)
                    quality = scraper_utils.height_get_quality(meta['height'])
                    links = {iframe_src: {'quality': quality, 'direct': False}}
                else:
                    links = self.__get_links(iframe_src, url)

                for link in links:
                    direct = links[link]['direct']
                    quality = links[link]['quality']
                    if direct:
                        host = scraper_utils.get_direct_hostname(self, link)
                        if host == 'gvideo':
                            quality = scraper_utils.gv_get_quality(link)
                        stream_url = link + scraper_utils.append_headers({'User-Agent': scraper_utils.get_ua(), 'Referer': url})
                    else:
                        host = urlparse.urlparse(link).hostname
                        stream_url = link
                        
                    source = {'multi-part': False, 'url': stream_url, 'host': host, 'class': self, 'quality': quality, 'views': None, 'rating': None, 'direct': direct}
                    hosters.append(source)

        return hosters
开发

鲜花

握手

雷人

路过

鸡蛋
该文章已有0人参与评论

请发表评论

全部评论

专题导读
上一篇:
Python scraper_utils.normalize_title函数代码示例发布时间:2022-05-27
下一篇:
Python scraper_utils.gv_get_quality函数代码示例发布时间:2022-05-27
热门推荐
阅读排行榜

扫描微信二维码

查看手机版网站

随时了解更新最新资讯

139-2527-9053

在线客服(服务时间 9:00~18:00)

在线QQ客服
地址:深圳市南山区西丽大学城创智工业园
电邮:jeky_zhao#qq.com
移动电话:139-2527-9053

Powered by 互联科技 X3.4© 2001-2213 极客世界.|Sitemap