yt_dlp/extractor/beacon.py

   1 import json
   2
   3 from .common import InfoExtractor
   4 from ..utils import (
   5     ExtractorError,
   6     parse_iso8601,
   7     traverse_obj,
   8 )
   9
  10
  11 class BeaconTvIE(InfoExtractor):
  12     _VALID_URL = r'https?://(?:www\.)?beacon\.tv/content/(?P<id>[\w-]+)'
  13
  14     _TESTS = [{
  15         'url': 'https://beacon.tv/content/welcome-to-beacon',
  16         'md5': 'b3f5932d437f288e662f10f3bfc5bd04',
  17         'info_dict': {
  18             'id': 'welcome-to-beacon',
  19             'ext': 'mp4',
  20             'upload_date': '20240509',
  21             'description': 'md5:ea2bd32e71acf3f9fca6937412cc3563',
  22             'thumbnail': 'https://cdn.jwplayer.com/v2/media/I4CkkEvN/poster.jpg?width=720',
  23             'title': 'Your home for Critical Role!',
  24             'timestamp': 1715227200,
  25             'duration': 105.494,
  26         },
  27     }, {
  28         'url': 'https://beacon.tv/content/re-slayers-take-trailer',
  29         'md5': 'd879b091485dbed2245094c8152afd89',
  30         'info_dict': {
  31             'id': 're-slayers-take-trailer',
  32             'ext': 'mp4',
  33             'title': 'The Re-Slayer’s Take | Official Trailer',
  34             'timestamp': 1715189040,
  35             'upload_date': '20240508',
  36             'duration': 53.249,
  37             'thumbnail': 'https://cdn.jwplayer.com/v2/media/PW5ApIw3/poster.jpg?width=720',
  38         },
  39     }]
  40
  41     def _real_extract(self, url):
  42         video_id = self._match_id(url)
  43         webpage = self._download_webpage(url, video_id)
  44
  45         content_data = traverse_obj(self._search_nextjs_data(webpage, video_id), (
  46             'props', 'pageProps', '__APOLLO_STATE__',
  47             lambda k, v: k.startswith('Content:') and v['slug'] == video_id, any))
  48         if not content_data:
  49             raise ExtractorError('Failed to extract content data')
  50
  51         jwplayer_data = traverse_obj(content_data, (
  52             (('contentVideo', 'video', 'videoData'),
  53              ('contentPodcast', 'podcast', 'audioData')), {json.loads}, {dict}, any))
  54         if not jwplayer_data:
  55             if content_data.get('contentType') not in ('videoPodcast', 'video', 'podcast'):
  56                 raise ExtractorError('Content is not a video/podcast', expected=True)
  57             if traverse_obj(content_data, ('contentTier', '__ref')) != 'MemberTier:65b258d178f89be87b4dc0a4':
  58                 self.raise_login_required('This video/podcast is for members only')
  59             raise ExtractorError('Failed to extract content')
  60
  61         return {
  62             **self._parse_jwplayer_data(jwplayer_data, video_id),
  63             **traverse_obj(content_data, {
  64                 'title': ('title', {str}),
  65                 'description': ('description', {str}),
  66                 'timestamp': ('publishedAt', {parse_iso8601}),
  67             }),
  68         }