yt_dlp/extractor/thestar.py

   1 from .common import InfoExtractor
   2
   3
   4 class TheStarIE(InfoExtractor):
   5     _VALID_URL = r'https?://(?:www\.)?thestar\.com/(?:[^/]+/)*(?P<id>.+)\.html'
   6     _TEST = {
   7         'url': 'http://www.thestar.com/life/2016/02/01/mankind-why-this-woman-started-a-men-s-skincare-line.html',
   8         'md5': '2c62dd4db2027e35579fefb97a8b6554',
   9         'info_dict': {
  10             'id': '4732393888001',
  11             'ext': 'mp4',
  12             'title': 'Mankind: Why this woman started a men\'s skin care line',
  13             'description': 'Robert Cribb talks to Young Lee, the founder of Uncle Peter\'s MAN.',
  14             'uploader_id': '794267642001',
  15             'timestamp': 1454353482,
  16             'upload_date': '20160201',
  17         },
  18         'params': {
  19             # m3u8 download
  20             'skip_download': True,
  21         },
  22     }
  23     BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/794267642001/default_default/index.html?videoId=%s'
  24
  25     def _real_extract(self, url):
  26         display_id = self._match_id(url)
  27         webpage = self._download_webpage(url, display_id)
  28         brightcove_id = self._search_regex(
  29             r'mainartBrightcoveVideoId["\']?\s*:\s*["\']?(\d+)',
  30             webpage, 'brightcove id')
  31         return self.url_result(
  32             self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id,
  33             'BrightcoveNew', brightcove_id)