youtube_dl/extractor/nrl.py

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