Python scraper_utils.get_quality函数代码示例

    def get_sources(self, video):
        source_url = self.get_url(video)
        hosters = []
        if not source_url or source_url == FORCE_NO_MATCH: return hosters
        url = scraper_utils.urljoin(self.base_url, source_url)
        html = self._http_get(url, cache_limit=.5)

        match = re.search('((?:pic|emb|vb|dir|emb2)=[^<]+)', html)
        if match:
            embeds = match.group(1)
            for stream_url in embeds.split('&'):
                if stream_url.startswith('dir='):
                    headers = {'Referer': url}
                    html = self._http_get(DIR_URL, params={'v': stream_url[3:]}, headers=headers, auth=False, allow_redirect=False, cache_limit=.5)
                    if html.startswith('http'):
                        stream_url = html + scraper_utils.append_headers({'User-Agent': scraper_utils.get_ua(), 'Referer': url})
                        host = scraper_utils.get_direct_hostname(self, stream_url)
                        direct = True
                        quality = QUALITIES.HD720
                    else:
                        continue
                elif stream_url.startswith('vb='):
                    stream_url = 'http://www.vidbux.com/%s' % (stream_url[3:])
                    host = 'vidbux.com'
                    direct = False
                    quality = scraper_utils.get_quality(video, host, QUALITIES.HD1080)
                elif stream_url.startswith('pic='):
                    data = {'url': stream_url[4:]}
                    html = self._http_get(PHP_URL, data=data, auth=False, cache_limit=1)
                    js_data = scraper_utils.parse_json(html, PHP_URL)
                    host = scraper_utils.get_direct_hostname(self, stream_url)
                    direct = True
                    for item in js_data:
                        if item.get('medium') == 'video':
                            stream_url = item['url']
                            quality = scraper_utils.width_get_quality(item['width'])
                            break
                    else:
                        continue
                elif stream_url.startswith(('emb=', 'emb2=')):
                    stream_url = re.sub('emb\d*=', '', stream_url)
                    host = urlparse.urlparse(stream_url).hostname
                    direct = False
                    quality = scraper_utils.get_quality(video, host, QUALITIES.HD720)
                else:
                    continue

                hoster = {'multi-part': False, 'host': host, 'class': self, 'quality': quality, 'views': None, 'rating': None, 'url': stream_url, 'direct': direct}
                hosters.append(hoster)

        return hosters

 def get_sources(self, video):
     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

    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': 'video-embed'})
            if fragment:
                sources = dom_parser.parse_dom(fragment[0], 'source', ret='src')
                sources += dom_parser.parse_dom(fragment[0], 'iframe', ret='src')
                
                for source in sources:
                    if self._get_direct_hostname(source) == 'gvideo':
                        direct = True
                        quality = scraper_utils.gv_get_quality(source)
                        host = self._get_direct_hostname(source)
                    else:
                        direct = False
                        host = urlparse.urlparse(source).hostname
                        quality = scraper_utils.get_quality(video, host, QUALITIES.HD720)

                    hoster = {'multi-part': False, 'url': source, 'host': host, 'class': self, 'quality': quality, 'views': None, 'rating': None, 'direct': direct}
                    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)

            q_str = ''
            quality = None
            match = re.search('>Category.*?td_col">([^<]+)', html)
            if match:
                quality = QUALITY_MAP.get(match.group(1).upper(), None)
            else:
                match = re.search('>Release.*?td_col">([^<]+)', html)
                if match:
                    q_str = match.group(1).upper()
                
            pattern = "td_cols.*?href='([^']+)"
            for match in re.finditer(pattern, html):
                url = match.group(1)
                if re.search('\.rar(\.|$)', url):
                    continue

                hoster = {'multi-part': False, 'class': self, 'views': None, 'url': url, 'rating': None, 'direct': False}
                hoster['host'] = urlparse.urlsplit(url).hostname
                if quality is None:
                    hoster['quality'] = scraper_utils.blog_get_quality(video, q_str, hoster['host'])
                else:
                    hoster['quality'] = scraper_utils.get_quality(video, hoster['host'], quality)
                hosters.append(hoster)

        return hosters

    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=0.5)
            if video.video_type == VIDEO_TYPES.EPISODE:
                html = self.__get_episode_fragment(html, video)
            for item in dom_parser.parse_dom(html, "div", {"class": "linkTr"}):
                stream_url = dom_parser.parse_dom(item, "div", {"class": '[^"]*linkHiddenUrl[^"]*'})
                q_str = dom_parser.parse_dom(item, "div", {"class": '[^"]*linkQualityText[^"]*'})
                if stream_url and q_str:
                    stream_url = stream_url[0]
                    q_str = q_str[0]
                    host = urlparse.urlparse(stream_url).hostname
                    base_quality = QUALITY_MAP.get(q_str, QUALITIES.HIGH)
                    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,
                    }
                    sources.append(source)

        return 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)

            fragment = dom_parser.parse_dom(html, 'table', {'id': 'streamlinks'})
            if fragment:
                max_age = 0
                now = min_age = int(time.time())
                for row in dom_parser.parse_dom(fragment[0], 'tr', {'id': 'pt\d+'}):
                    if video.video_type == VIDEO_TYPES.MOVIE:
                        pattern = 'href="([^"]+).*?/>([^<]+).*?(?:<td>.*?</td>\s*){1}<td>(.*?)</td>\s*<td>(.*?)</td>'
                    else:
                        pattern = 'href="([^"]+).*?/>([^<]+).*?(<span class="linkdate">.*?)</td>\s*<td>(.*?)</td>'
                    match = re.search(pattern, row, re.DOTALL)
                    if match:
                        url, host, age, quality = match.groups()
                        age = self.__get_age(now, age)
                        quality = quality.upper()
                        if age > max_age: max_age = age
                        if age < min_age: min_age = age
                        host = host.strip()
                        hoster = {'multi-part': False, 'class': self, 'url': scraper_utils.pathify_url(url), 'host': host, 'age': age, 'views': None, 'rating': None, 'direct': False}
                        hoster['quality'] = scraper_utils.get_quality(video, host, QUALITY_MAP.get(quality, QUALITIES.HIGH))
                        hosters.append(hoster)
    
                unit = (max_age - min_age) / 100
                if unit > 0:
                    for hoster in hosters:
                        hoster['rating'] = (hoster['age'] - min_age) / unit
        return hosters

    def get_sources(self, video):
        hosters = []
        source_url = self.get_url(video)
        if not source_url or source_url == FORCE_NO_MATCH: return hosters
        page_url = scraper_utils.urljoin(self.base_url, source_url)
        html = self._http_get(page_url, cache_limit=.25)
        for _attrs, link in dom_parser2.parse_dom(html, 'div', {'class': 'ldr-item'}):
            stream_url = dom_parser2.parse_dom(link, 'a', req='data-actuallink')
            
            try:
                watched = dom_parser2.parse_dom(link, 'div', {'class': 'click-count'})
                match = re.search(' (\d+) ', watched[0].content)
                views = match.group(1)
            except:
                views = None
                    
            try:
                score = dom_parser2.parse_dom(link, 'div', {'class': 'point'})
                score = int(score[0].content)
                rating = score * 10 if score else None
            except:
                rating = None
            
            if stream_url:
                stream_url = stream_url[0].attrs['data-actuallink'].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 get_sources(self, video):
     hosters = []
     source_url = self.get_url(video)
     if not source_url or source_url == FORCE_NO_MATCH: return hosters
     page_url = scraper_utils.urljoin(self.base_url, source_url)
     html = self._http_get(page_url, cache_limit=.5)
     
     best_quality = QUALITIES.HIGH
     fragment = dom_parser2.parse_dom(html, 'div', {'class': 'entry'})
     if fragment:
         for match in re.finditer('href="[^"]*/movies-quality/[^"]*[^>]*>([^<]+)', fragment[0].content, re.I):
             quality = Q_MAP.get(match.group(1).upper(), QUALITIES.HIGH)
             if Q_ORDER[quality] > Q_ORDER[best_quality]:
                 best_quality = quality
                 
     sources = []
     for attrs, _content in dom_parser2.parse_dom(html, 'a', req='data-vid'):
         try:
             vid_url = dom_parser2.parse_dom(scraper_utils.cleanse_title(attrs['data-vid']), 'iframe', req='src')
             sources.append(vid_url[0])
         except:
             pass
         
     fragment = dom_parser2.parse_dom(html, 'table', {'class': 'additional-links'})
     if fragment:
         sources += dom_parser2.parse_dom(fragment[0].content, 'a', req='href')
             
     for stream_url in sources:
         stream_url = stream_url.attrs.get('href') or stream_url.attrs.get('src')
         host = urlparse.urlparse(stream_url).hostname
         quality = scraper_utils.get_quality(video, host, best_quality)
         hoster = {'multi-part': False, 'host': host, 'class': self, 'quality': quality, 'views': None, 'rating': None, 'url': stream_url, 'direct': False}
         hosters.append(hoster)
     return hosters

 def 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=1)
     for _attrs, item in dom_parser2.parse_dom(html, 'a', {'class': 'full-torrent1'}):
         stream_url = dom_parser2.parse_dom(item, 'span', req='onclick')
         host = dom_parser2.parse_dom(item, 'div', {'class': 'small_server'})
         match = re.search('Views:\s*(?:</[^>]*>)?\s*(\d+)', item, re.I)
         views = match.group(1) if match else None
         match = re.search('Size:\s*(?:</[^>]*>)?\s*(\d+)', item, re.I)
         size = int(match.group(1)) * 1024 * 1024 if match else None
         if not stream_url or not host: continue
         
         stream_url = stream_url[0].attrs['onclick']
         host = host[0].content.lower()
         host = host.replace('stream server: ', '')
         match = re.search("'(/redirect/[^']+)", stream_url)
         if match: stream_url = match.group(1)
         quality = scraper_utils.get_quality(video, host, QUALITIES.HIGH)
         hoster = {'multi-part': False, 'host': host, 'class': self, 'quality': quality, 'views': views, 'rating': None, 'url': stream_url, 'direct': False}
         if size is not None: hoster['size'] = scraper_utils.format_size(size, 'B')
         hosters.append(hoster)
     return hosters

    def get_sources(self, video):
        source_url = self.get_url(video)
        hosters = []
        if not source_url or source_url == FORCE_NO_MATCH: return hosters
        page_url = scraper_utils.urljoin(self.base_url, source_url)
        html = self._http_get(page_url, cache_limit=.5)
        for _attrs, row in dom_parser2.parse_dom(html, 'tr', {'id': 'linktr'}):
            redirect = dom_parser2.parse_dom(row, 'span', req='id')
            link = dom_parser2.parse_dom(row, 'a', req='href')
            if link and link[0].attrs['href'].startswith('http'):
                stream_url = link[0].attrs['href']
            elif redirect:
                stream_url = redirect[0].attrs['id']
            else:
                stream_url = ''

            if stream_url.startswith('http'):
                host = urlparse.urlparse(stream_url).hostname
            else:
                host = dom_parser2.parse_dom(row, 'h9')
                host = host[0].content if host else ''
                
            if stream_url and host:
                quality = scraper_utils.get_quality(video, host, QUALITIES.HIGH)
                hoster = {'multi-part': False, 'host': host, 'class': self, 'quality': quality, 'views': None, 'rating': None, 'url': stream_url, 'direct': False}
                hosters.append(hoster)
            
        return hosters

    def 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=8)
            hosts = dom_parser.parse_dom(html, 'p', {'class': 'server_servername'})
            links = dom_parser.parse_dom(html, 'p', {'class': 'server_play'})
            for host, link_frag in zip(hosts, links):
                stream_url = dom_parser.parse_dom(link_frag, 'a', ret='href')
                if stream_url:
                    stream_url = stream_url[0]
                    host = re.sub('^Server\s*', '', host, re.I)
                    host = re.sub('\s*Link\s+\d+', '', host)
                    if host.lower() == 'google':
                        sources = self.__get_gvideo_links(stream_url)
                    else:
                        sources = [{'host': host, 'link': stream_url}]
                    
                    for source in sources:
                        stream_url = source['link']
                        host = self._get_direct_hostname(stream_url)
                        if host == 'gvideo':
                            quality = scraper_utils.gv_get_quality(stream_url)
                            stream_url += '|User-Agent=%s' % (scraper_utils.get_ua())
                            direct = True
                        else:
                            host = HOST_SUB.get(source['host'].lower(), source['host'])
                            quality = scraper_utils.get_quality(video, host, QUALITIES.HIGH)
                            direct = False
                        hoster = {'multi-part': False, 'url': stream_url, 'host': host, 'class': self, 'quality': quality, 'views': None, 'rating': None, 'direct': direct}
                        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=0.5)

            quality = None
            match = re.search("Links\s+-\s+Quality\s*([^<]*)</h1>", html, re.DOTALL | re.I)
            if match:
                quality = QUALITY_MAP.get(match.group(1).strip().upper())

            for match in re.finditer('id="link_name">\s*([^<]+).*?href="([^"]+)', html, re.DOTALL):
                host, url = match.groups()
                hoster = {
                    "multi-part": False,
                    "host": host,
                    "class": self,
                    "url": url,
                    "quality": scraper_utils.get_quality(video, host, quality),
                    "rating": None,
                    "views": None,
                    "direct": False,
                }
                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)

            match = re.search('This movie is of poor quality', html, re.I)
            if match:
                quality = QUALITIES.LOW
            else:
                quality = QUALITIES.HIGH

            for match in re.finditer('href="([^"]+/embed\d*/[^"]+)', html):
                url = match.group(1)
                embed_html = self._http_get(url, cache_limit=.5)
                hosters += self.__get_links(embed_html)
            
            pattern = 'href="([^"]+)[^>]*>\s*<[^>]+play_video.gif'
            for match in re.finditer(pattern, html, re.I):
                stream_url = match.group(1)
                host = urlparse.urlparse(stream_url).hostname
                quality = scraper_utils.get_quality(video, host, quality)
                hoster = {'multi-part': False, 'url': stream_url, 'host': host, 'class': self, 'quality': quality, 'rating': None, 'views': None, 'direct': False}
                hosters.append(hoster)
        return hosters

    def __get_links(self, url, video):
        hosters = []
        seen_urls = set()
        for search_type in SEARCH_TYPES:
            search_url, params = self.__translate_search(url, search_type)
            if not search_url: continue
            html = self._http_get(search_url, params=params, cache_limit=.5)
            js_result = scraper_utils.parse_json(html, search_url)
            if js_result.get('status') != 'success':
                logger.log('Alluc API Error: |%s|%s|: %s' % (search_url, params, js_result.get('message', 'Unknown Error')), log_utils.LOGWARNING)
                continue
            
            for result in js_result['result']:
                stream_url = result['hosterurls'][0]['url']
                if len(result['hosterurls']) > 1: continue
                if result['extension'] == 'rar': continue
                if stream_url in seen_urls: continue

                if scraper_utils.release_check(video, result['title']):
                    host = urlparse.urlsplit(stream_url).hostname
                    quality = scraper_utils.get_quality(video, host, self._get_title_quality(result['title']))
                    hoster = {'multi-part': False, 'class': self, 'views': None, 'url': stream_url, 'rating': None, 'host': host, 'quality': quality, 'direct': False}
                    hoster['extra'] = scraper_utils.cleanse_title(result['title'])
                    if video.video_type == VIDEO_TYPES.MOVIE:
                        meta = scraper_utils.parse_movie_link(hoster['extra'])
                    else:
                        meta = scraper_utils.parse_episode_link(hoster['extra'])
                    if 'format' in meta: hoster['format'] = meta['format']
                    
                    hosters.append(hoster)
                    seen_urls.add(stream_url)

        return hosters

    def get_sources(self, video):
        hosters = []
        source_url = self.get_url(video)
        if not source_url or source_url == FORCE_NO_MATCH: return hosters
        url = scraper_utils.urljoin(self.base_url, source_url)
        html = self._http_get(url, cache_limit=.5)
        page_quality = QUALITIES.HD720 if video.video_type == VIDEO_TYPES.MOVIE else QUALITIES.HIGH
        for _attrs, fragment in dom_parser2.parse_dom(html, 'div', {'class': 'embed-responsive'}):
            iframe_url = dom_parser2.parse_dom(fragment, 'iframe', req='data-src')
            if iframe_url:
                iframe_url = iframe_url[0].attrs['data-src']
                iframe_host = urlparse.urlparse(iframe_url).hostname
                if iframe_host in DIRECT_HOSTS:
                    sources = self.__parse_streams(iframe_url, url)
                else:
                    sources = {iframe_url: {'quality': scraper_utils.get_quality(video, iframe_host, page_quality), 'direct': False}}
            
            for source in sources:
                quality = sources[source]['quality']
                direct = sources[source]['direct']
                if direct:
                    host = scraper_utils.get_direct_hostname(self, source)
                    stream_url = source + scraper_utils.append_headers({'User-Agent': scraper_utils.get_ua()})
                else:
                    host = urlparse.urlparse(source).hostname
                    stream_url = source
                
                hoster = {'multi-part': False, 'url': stream_url, 'host': host, 'class': self, 'quality': quality, 'views': None, 'rating': None, 'direct': direct}
                hosters.append(hoster)

        return hosters