yt_dlp/extractor/nrl.py

   1 from .common import InfoExtractor
   2
   3
   4 class NRLTVIE(InfoExtractor):
   5     _WORKING = False
   6     _VALID_URL = r'https?://(?:www\.)?nrl\.com/tv(/[^/]+)*/(?P<id>[^/?&#]+)'
   7     _TEST = {
   8         'url': 'https://www.nrl.com/tv/news/match-highlights-titans-v-knights-862805/',
   9         'info_dict': {
  10             'id': 'YyNnFuaDE6kPJqlDhG4CGQ_w89mKTau4',
  11             'ext': 'mp4',
  12             'title': 'Match Highlights: Titans v Knights',
  13         },
  14         'params': {
  15             # m3u8 download
  16             'skip_download': True,
  17         },
  18     }
  19
  20     def _real_extract(self, url):
  21         display_id = self._match_id(url)
  22         webpage = self._download_webpage(url, display_id)
  23         q_data = self._parse_json(self._html_search_regex(
  24             r'(?s)q-data="({.+?})"', webpage, 'player data'), display_id)
  25         ooyala_id = q_data['videoId']
  26         return self.url_result(
  27             'ooyala:' + ooyala_id, 'Ooyala', ooyala_id, q_data.get('title'))