yt_dlp/extractor/nrl.py

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