yt_dlp/extractor/swearnet.py

   1 from .common import InfoExtractor
   2 from ..utils import ExtractorError, int_or_none, traverse_obj
   3
   4
   5 class SwearnetEpisodeIE(InfoExtractor):
   6     _VALID_URL = r'https?://www\.swearnet\.com/shows/(?P<id>[\w-]+)/seasons/(?P<season_num>\d+)/episodes/(?P<episode_num>\d+)'
   7     _TESTS = [{
   8         'url': 'https://www.swearnet.com/shows/gettin-learnt-with-ricky/seasons/1/episodes/1',
   9         'info_dict': {
  10             'id': '232819',
  11             'ext': 'mp4',
  12             'episode_number': 1,
  13             'episode': 'Episode 1',
  14             'duration': 719,
  15             'description': 'md5:c48ef71440ce466284c07085cd7bd761',
  16             'season': 'Season 1',
  17             'title': 'Episode 1 - Grilled Cheese Sammich',
  18             'season_number': 1,
  19             'thumbnail': 'https://cdn.vidyard.com/thumbnails/232819/_RX04IKIq60a2V6rIRqq_Q_small.jpg',
  20         }
  21     }]
  22
  23     def _get_formats_and_subtitle(self, video_source, video_id):
  24         video_source = video_source or {}
  25         formats, subtitles = [], {}
  26         for key, value in video_source.items():
  27             if key == 'hls':
  28                 for video_hls in value:
  29                     fmts, subs = self._extract_m3u8_formats_and_subtitles(video_hls.get('url'), video_id)
  30                     formats.extend(fmts)
  31                     self._merge_subtitles(subs, target=subtitles)
  32             else:
  33                 formats.extend({
  34                     'url': video_mp4.get('url'),
  35                     'ext': 'mp4'
  36                 } for video_mp4 in value)
  37
  38         return formats, subtitles
  39
  40     def _get_direct_subtitle(self, caption_json):
  41         subs = {}
  42         for caption in caption_json:
  43             subs.setdefault(caption.get('language') or 'und', []).append({
  44                 'url': caption.get('vttUrl'),
  45                 'name': caption.get('name')
  46             })
  47
  48         return subs
  49
  50     def _real_extract(self, url):
  51         display_id, season_number, episode_number = self._match_valid_url(url).group('id', 'season_num', 'episode_num')
  52         webpage = self._download_webpage(url, display_id)
  53
  54         try:
  55             external_id = self._search_regex(r'externalid\s*=\s*"([^"]+)', webpage, 'externalid')
  56         except ExtractorError:
  57             if 'Upgrade Now' in webpage:
  58                 self.raise_login_required()
  59             raise
  60
  61         json_data = self._download_json(
  62             f'https://play.vidyard.com/player/{external_id}.json', display_id)['payload']['chapters'][0]
  63
  64         formats, subtitles = self._get_formats_and_subtitle(json_data['sources'], display_id)
  65         self._merge_subtitles(self._get_direct_subtitle(json_data.get('captions')), target=subtitles)
  66
  67         return {
  68             'id': str(json_data['videoId']),
  69             'title': json_data.get('name') or self._html_search_meta(['og:title', 'twitter:title'], webpage),
  70             'description': (json_data.get('description')
  71                             or self._html_search_meta(['og:description', 'twitter:description'], webpage)),
  72             'duration': int_or_none(json_data.get('seconds')),
  73             'formats': formats,
  74             'subtitles': subtitles,
  75             'season_number': int_or_none(season_number),
  76             'episode_number': int_or_none(episode_number),
  77             'thumbnails': [{'url': thumbnail_url}
  78                            for thumbnail_url in traverse_obj(json_data, ('thumbnailUrls', ...))]
  79         }