yt_dlp/extractor/willow.py

   1 from ..utils import ExtractorError
   2 from .common import InfoExtractor
   3
   4
   5 class WillowIE(InfoExtractor):
   6     _VALID_URL = r'https?://(www\.)?willow\.tv/videos/(?P<id>[0-9a-z-_]+)'
   7     _GEO_COUNTRIES = ['US']
   8
   9     _TESTS = [{
  10         'url': 'http://willow.tv/videos/d5winning-moment-eng-vs-ind-streaming-online-4th-test-india-tour-of-england-2021',
  11         'info_dict': {
  12             'id': '169662',
  13             'display_id': 'd5winning-moment-eng-vs-ind-streaming-online-4th-test-india-tour-of-england-2021',
  14             'ext': 'mp4',
  15             'title': 'Winning Moment: 4th Test, England vs India',
  16             'thumbnail': 'https://aimages.willow.tv/ytThumbnails/6748_D5winning_moment.jpg',
  17             'duration': 233,
  18             'timestamp': 1630947954,
  19             'upload_date': '20210906',
  20             'location': 'Kennington Oval, London',
  21             'series': 'India tour of England 2021',
  22         },
  23         'params': {
  24             'skip_download': True,  # AES-encrypted m3u8
  25         },
  26     }, {
  27         'url': 'http://willow.tv/videos/highlights-short-ind-vs-nz-streaming-online-2nd-t20i-new-zealand-tour-of-india-2021',
  28         'only_matching': True,
  29     }]
  30
  31     def _real_extract(self, url):
  32         video_id = self._match_id(url)
  33         webpage = self._download_webpage(url, video_id)
  34         video_data = self._parse_json(self._html_search_regex(
  35             r'var\s+data_js\s*=\s*JSON\.parse\(\'(.+)\'\)', webpage,
  36             'data_js'), video_id)
  37
  38         video = next((v for v in video_data.get('trending_videos') or []
  39                       if v.get('secureurl')), None)
  40         if not video:
  41             raise ExtractorError('No videos found')
  42
  43         formats = self._extract_m3u8_formats(video['secureurl'], video_id, 'mp4')
  44
  45         return {
  46             'id': str(video.get('content_id')),
  47             'display_id': video.get('video_slug'),
  48             'title': video.get('video_name') or self._html_search_meta('twitter:title', webpage),
  49             'formats': formats,
  50             'thumbnail': video.get('yt_thumb_url') or self._html_search_meta(
  51                 'twitter:image', webpage, default=None),
  52             'duration': video.get('duration_seconds'),
  53             'timestamp': video.get('created_date'),
  54             'location': video.get('venue'),
  55             'series': video.get('series_name'),
  56         }