- title = self._html_search_regex(r'title="(.+?)"', webpage, 'title')
- uploader = self._html_search_regex(r'http://www.zippcast.com/profile/(.+?)">', webpage, 'uploader')
- url = self._html_search_regex(r'<source src="(.+?)" type="', webpage, 'url')
- description = self._html_search_regex(r'<span class="vdescr".+>(.+?)</span>', webpage, 'description')
- thumbnail = self._html_search_regex(r'poster="(.+?)" controls>', webpage, 'thumbnail')
- categories = self._html_search_regex(r'<a href="http://www.zippcast.com/categories/(.+?)"', webpage, 'categories')
- view_count = self._html_search_regex(r'<td align="right"><h3>(.+?) views!', webpage, 'view_count')
+ webpage = self._download_webpage(
+ 'http://www.zippcast.com/video/%s' % video_id, video_id)
+
+ formats = []
+ video_url = self._search_regex(
+ r'<source[^>]+src=(["\'])(?P<url>.+?)\1', webpage,
+ 'video url', default=None, group='url')
+ if video_url:
+ formats.append({
+ 'url': video_url,
+ 'format_id': 'http',
+ 'preference': 0, # direct link is almost always of worse quality
+ })
+ src_url = self._search_regex(
+ r'src\s*:\s*(?:escape\()?(["\'])(?P<url>http://.+?)\1',
+ webpage, 'src', default=None, group='url')
+ ext = determine_ext(src_url)
+ if ext == 'm3u8':
+ formats.extend(self._extract_m3u8_formats(
+ src_url, video_id, 'mp4', entry_protocol='m3u8_native',
+ m3u8_id='hls', fatal=False))
+ elif ext == 'f4m':
+ formats.extend(self._extract_f4m_formats(
+ src_url, video_id, f4m_id='hds', fatal=False))
+ self._sort_formats(formats)
+
+ title = self._og_search_title(webpage)
+ description = self._og_search_description(webpage) or self._html_search_meta(
+ 'description', webpage)
+ uploader = self._search_regex(
+ r'<a[^>]+href="https?://[^/]+/profile/[^>]+>([^<]+)</a>',
+ webpage, 'uploader', fatal=False)
+ thumbnail = self._og_search_thumbnail(webpage)
+ view_count = str_to_int(self._search_regex(
+ r'>([\d,.]+) views!', webpage, 'view count', fatal=False))
+
+ categories = re.findall(
+ r'<a[^>]+href="https?://[^/]+/categories/[^"]+">([^<]+),?<',
+ webpage)
+ tags = re.findall(
+ r'<a[^>]+href="https?://[^/]+/search/tags/[^"]+">([^<]+),?<',
+ webpage)