yt_dlp/extractor/dailywire.py

   1 from .common import InfoExtractor
   2 from ..utils import (
   3     determine_ext,
   4     float_or_none,
   5     join_nonempty,
   6     traverse_obj,
   7     url_or_none,
   8 )
   9
  10
  11 class DailyWireBaseIE(InfoExtractor):
  12     _JSON_PATH = {
  13         'episode': ('props', 'pageProps', 'episodeData', 'episode'),
  14         'videos': ('props', 'pageProps', 'videoData', 'video'),
  15         'podcasts': ('props', 'pageProps', 'episode'),
  16     }
  17
  18     def _get_json(self, url):
  19         sites_type, slug = self._match_valid_url(url).group('sites_type', 'id')
  20         json_data = self._search_nextjs_data(self._download_webpage(url, slug), slug)
  21         return slug, traverse_obj(json_data, self._JSON_PATH[sites_type])
  22
  23
  24 class DailyWireIE(DailyWireBaseIE):
  25     _VALID_URL = r'https?://(?:www\.)dailywire(?:\.com)/(?P<sites_type>episode|videos)/(?P<id>[\w-]+)'
  26     _TESTS = [{
  27         'url': 'https://www.dailywire.com/episode/1-fauci',
  28         'info_dict': {
  29             'id': 'ckzsl50xnqpy30850in3v4bu7',
  30             'ext': 'mp4',
  31             'display_id': '1-fauci',
  32             'title': '1. Fauci',
  33             'description': 'md5:9df630347ef85081b7e97dd30bc22853',
  34             'thumbnail': 'https://daily-wire-production.imgix.net/episodes/ckzsl50xnqpy30850in3v4bu7/ckzsl50xnqpy30850in3v4bu7-1648237399554.jpg',
  35             'creator': 'Caroline Roberts',
  36             'series_id': 'ckzplm0a097fn0826r2vc3j7h',
  37             'series': 'China: The Enemy Within',
  38         },
  39     }, {
  40         'url': 'https://www.dailywire.com/episode/ep-124-bill-maher',
  41         'info_dict': {
  42             'id': 'cl0ngbaalplc80894sfdo9edf',
  43             'ext': 'mp3',
  44             'display_id': 'ep-124-bill-maher',
  45             'title': 'Ep. 124 - Bill Maher',
  46             'thumbnail': 'https://daily-wire-production.imgix.net/episodes/cl0ngbaalplc80894sfdo9edf/cl0ngbaalplc80894sfdo9edf-1647065568518.jpg',
  47             'creator': 'Caroline Roberts',
  48             'description': 'md5:adb0de584bcfa9c41374999d9e324e98',
  49             'series_id': 'cjzvep7270hp00786l9hwccob',
  50             'series': 'The Sunday Special',
  51         },
  52     }, {
  53         'url': 'https://www.dailywire.com/videos/the-hyperions',
  54         'only_matching': True,
  55     }]
  56
  57     def _real_extract(self, url):
  58         slug, episode_info = self._get_json(url)
  59         urls = traverse_obj(
  60             episode_info, (('segments', 'videoUrl'), ..., ('video', 'audio')), expected_type=url_or_none)
  61
  62         formats, subtitles = [], {}
  63         for url in urls:
  64             if determine_ext(url) != 'm3u8':
  65                 formats.append({'url': url})
  66                 continue
  67             format_, subs_ = self._extract_m3u8_formats_and_subtitles(url, slug)
  68             formats.extend(format_)
  69             self._merge_subtitles(subs_, target=subtitles)
  70         return {
  71             'id': episode_info['id'],
  72             'display_id': slug,
  73             'title': traverse_obj(episode_info, 'title', 'name'),
  74             'description': episode_info.get('description'),
  75             'creator': join_nonempty(('createdBy', 'firstName'), ('createdBy', 'lastName'), from_dict=episode_info, delim=' '),
  76             'duration': float_or_none(episode_info.get('duration')),
  77             'is_live': episode_info.get('isLive'),
  78             'thumbnail': traverse_obj(episode_info, 'thumbnail', 'image', expected_type=url_or_none),
  79             'formats': formats,
  80             'subtitles': subtitles,
  81             'series_id': traverse_obj(episode_info, ('show', 'id')),
  82             'series': traverse_obj(episode_info, ('show', 'name')),
  83         }
  84
  85
  86 class DailyWirePodcastIE(DailyWireBaseIE):
  87     _VALID_URL = r'https?://(?:www\.)dailywire(?:\.com)/(?P<sites_type>podcasts)/(?P<podcaster>[\w-]+/(?P<id>[\w-]+))'
  88     _TESTS = [{
  89         'url': 'https://www.dailywire.com/podcasts/morning-wire/get-ready-for-recession-6-15-22',
  90         'info_dict': {
  91             'id': 'cl4f01d0w8pbe0a98ydd0cfn1',
  92             'ext': 'm4a',
  93             'display_id': 'get-ready-for-recession-6-15-22',
  94             'title': 'Get Ready for Recession | 6.15.22',
  95             'description': 'md5:c4afbadda4e1c38a4496f6d62be55634',
  96             'thumbnail': 'https://daily-wire-production.imgix.net/podcasts/ckx4otgd71jm508699tzb6hf4-1639506575562.jpg',
  97             'duration': 900.117667,
  98         },
  99     }]
 100
 101     def _real_extract(self, url):
 102         slug, episode_info = self._get_json(url)
 103         audio_id = traverse_obj(episode_info, 'audioMuxPlaybackId', 'VUsAipTrBVSgzw73SpC2DAJD401TYYwEp')
 104
 105         return {
 106             'id': episode_info['id'],
 107             'url': f'https://stream.media.dailywire.com/{audio_id}/audio.m4a',
 108             'display_id': slug,
 109             'title': episode_info.get('title'),
 110             'duration': float_or_none(episode_info.get('duration')),
 111             'thumbnail': episode_info.get('thumbnail'),
 112             'description': episode_info.get('description'),
 113         }