yt_dlp/extractor/worldstarhiphop.py

   1 from .common import InfoExtractor
   2
   3
   4 class WorldStarHipHopIE(InfoExtractor):
   5     _VALID_URL = r'https?://(?:www|m)\.worldstar(?:candy|hiphop)\.com/(?:videos|android)/video\.php\?.*?\bv=(?P<id>[^&]+)'
   6     _TESTS = [{
   7         'url': 'http://www.worldstarhiphop.com/videos/video.php?v=wshh6a7q1ny0G34ZwuIO',
   8         'md5': '9d04de741161603bf7071bbf4e883186',
   9         'info_dict': {
  10             'id': 'wshh6a7q1ny0G34ZwuIO',
  11             'ext': 'mp4',
  12             'title': 'KO Of The Week: MMA Fighter Gets Knocked Out By Swift Head Kick!',
  13         },
  14     }, {
  15         'url': 'http://m.worldstarhiphop.com/android/video.php?v=wshh6a7q1ny0G34ZwuIO',
  16         'only_matching': True,
  17     }]
  18
  19     def _real_extract(self, url):
  20         video_id = self._match_id(url)
  21         webpage = self._download_webpage(url, video_id)
  22
  23         entries = self._parse_html5_media_entries(url, webpage, video_id)
  24
  25         if not entries:
  26             return self.url_result(url, 'Generic')
  27
  28         title = self._html_search_regex(
  29             [r'(?s)<div class="content-heading">\s*<h1>(.*?)</h1>',
  30              r'<span[^>]+class="tc-sp-pinned-title">(.*)</span>'],
  31             webpage, 'title')
  32
  33         info = entries[0]
  34         info.update({
  35             'id': video_id,
  36             'title': title,
  37         })
  38         return info