yt_dlp/extractor/bravotv.py

   1 from .adobepass import AdobePassIE
   2 from ..networking import HEADRequest
   3 from ..utils import (
   4     extract_attributes,
   5     float_or_none,
   6     get_element_html_by_class,
   7     int_or_none,
   8     merge_dicts,
   9     parse_age_limit,
  10     remove_end,
  11     str_or_none,
  12     traverse_obj,
  13     unescapeHTML,
  14     unified_timestamp,
  15     update_url_query,
  16     url_or_none,
  17 )
  18
  19
  20 class BravoTVIE(AdobePassIE):
  21     _VALID_URL = r'https?://(?:www\.)?(?P<site>bravotv|oxygen)\.com/(?:[^/]+/)+(?P<id>[^/?#]+)'
  22     _TESTS = [{
  23         'url': 'https://www.bravotv.com/top-chef/season-16/episode-15/videos/the-top-chef-season-16-winner-is',
  24         'info_dict': {
  25             'id': '3923059',
  26             'ext': 'mp4',
  27             'title': 'The Top Chef Season 16 Winner Is...',
  28             'description': 'Find out who takes the title of Top Chef!',
  29             'upload_date': '20190314',
  30             'timestamp': 1552591860,
  31             'season_number': 16,
  32             'episode_number': 15,
  33             'series': 'Top Chef',
  34             'episode': 'The Top Chef Season 16 Winner Is...',
  35             'duration': 190.357,
  36             'season': 'Season 16',
  37             'thumbnail': r're:^https://.+\.jpg',
  38         },
  39         'params': {'skip_download': 'm3u8'},
  40     }, {
  41         'url': 'https://www.bravotv.com/top-chef/season-20/episode-1/london-calling',
  42         'info_dict': {
  43             'id': '9000234570',
  44             'ext': 'mp4',
  45             'title': 'London Calling',
  46             'description': 'md5:5af95a8cbac1856bd10e7562f86bb759',
  47             'upload_date': '20230310',
  48             'timestamp': 1678410000,
  49             'season_number': 20,
  50             'episode_number': 1,
  51             'series': 'Top Chef',
  52             'episode': 'London Calling',
  53             'duration': 3266.03,
  54             'season': 'Season 20',
  55             'chapters': 'count:7',
  56             'thumbnail': r're:^https://.+\.jpg',
  57             'age_limit': 14,
  58         },
  59         'params': {'skip_download': 'm3u8'},
  60         'skip': 'This video requires AdobePass MSO credentials',
  61     }, {
  62         'url': 'https://www.oxygen.com/in-ice-cold-blood/season-1/closing-night',
  63         'info_dict': {
  64             'id': '3692045',
  65             'ext': 'mp4',
  66             'title': 'Closing Night',
  67             'description': 'md5:3170065c5c2f19548d72a4cbc254af63',
  68             'upload_date': '20180401',
  69             'timestamp': 1522623600,
  70             'season_number': 1,
  71             'episode_number': 1,
  72             'series': 'In Ice Cold Blood',
  73             'episode': 'Closing Night',
  74             'duration': 2629.051,
  75             'season': 'Season 1',
  76             'chapters': 'count:6',
  77             'thumbnail': r're:^https://.+\.jpg',
  78             'age_limit': 14,
  79         },
  80         'params': {'skip_download': 'm3u8'},
  81         'skip': 'This video requires AdobePass MSO credentials',
  82     }, {
  83         'url': 'https://www.oxygen.com/in-ice-cold-blood/season-2/episode-16/videos/handling-the-horwitz-house-after-the-murder-season-2',
  84         'info_dict': {
  85             'id': '3974019',
  86             'ext': 'mp4',
  87             'title': '\'Handling The Horwitz House After The Murder (Season 2, Episode 16)',
  88             'description': 'md5:f9d638dd6946a1c1c0533a9c6100eae5',
  89             'upload_date': '20190617',
  90             'timestamp': 1560790800,
  91             'season_number': 2,
  92             'episode_number': 16,
  93             'series': 'In Ice Cold Blood',
  94             'episode': '\'Handling The Horwitz House After The Murder (Season 2, Episode 16)',
  95             'duration': 68.235,
  96             'season': 'Season 2',
  97             'thumbnail': r're:^https://.+\.jpg',
  98             'age_limit': 14,
  99         },
 100         'params': {'skip_download': 'm3u8'},
 101     }, {
 102         'url': 'https://www.bravotv.com/below-deck/season-3/ep-14-reunion-part-1',
 103         'only_matching': True,
 104     }]
 105
 106     def _real_extract(self, url):
 107         site, display_id = self._match_valid_url(url).group('site', 'id')
 108         webpage = self._download_webpage(url, display_id)
 109         settings = self._search_json(
 110             r'<script[^>]+data-drupal-selector="drupal-settings-json"[^>]*>', webpage, 'settings', display_id)
 111         tve = extract_attributes(get_element_html_by_class('tve-video-deck-app', webpage) or '')
 112         query = {
 113             'manifest': 'm3u',
 114             'formats': 'm3u,mpeg4',
 115         }
 116
 117         if tve:
 118             account_pid = tve.get('data-mpx-media-account-pid') or 'HNK2IC'
 119             account_id = tve['data-mpx-media-account-id']
 120             metadata = self._parse_json(
 121                 tve.get('data-normalized-video', ''), display_id, fatal=False, transform_source=unescapeHTML)
 122             video_id = tve.get('data-guid') or metadata['guid']
 123             if tve.get('data-entitlement') == 'auth':
 124                 auth = traverse_obj(settings, ('tve_adobe_auth', {dict})) or {}
 125                 site = remove_end(site, 'tv')
 126                 release_pid = tve['data-release-pid']
 127                 resource = self._get_mvpd_resource(
 128                     tve.get('data-adobe-pass-resource-id') or auth.get('adobePassResourceId') or site,
 129                     tve['data-title'], release_pid, tve.get('data-rating'))
 130                 query.update({
 131                     'switch': 'HLSServiceSecure',
 132                     'auth': self._extract_mvpd_auth(
 133                         url, release_pid, auth.get('adobePassRequestorId') or site, resource),
 134                 })
 135
 136         else:
 137             ls_playlist = traverse_obj(settings, ('ls_playlist', ..., {dict}), get_all=False) or {}
 138             account_pid = ls_playlist.get('mpxMediaAccountPid') or 'PHSl-B'
 139             account_id = ls_playlist['mpxMediaAccountId']
 140             video_id = ls_playlist['defaultGuid']
 141             metadata = traverse_obj(
 142                 ls_playlist, ('videos', lambda _, v: v['guid'] == video_id, {dict}), get_all=False)
 143
 144         tp_url = f'https://link.theplatform.com/s/{account_pid}/media/guid/{account_id}/{video_id}'
 145         tp_metadata = self._download_json(
 146             update_url_query(tp_url, {'format': 'preview'}), video_id, fatal=False)
 147
 148         seconds_or_none = lambda x: float_or_none(x, 1000)
 149         chapters = traverse_obj(tp_metadata, ('chapters', ..., {
 150             'start_time': ('startTime', {seconds_or_none}),
 151             'end_time': ('endTime', {seconds_or_none}),
 152         }))
 153         # prune pointless single chapters that span the entire duration from short videos
 154         if len(chapters) == 1 and not traverse_obj(chapters, (0, 'end_time')):
 155             chapters = None
 156
 157         m3u8_url = self._request_webpage(HEADRequest(
 158             update_url_query(f'{tp_url}/stream.m3u8', query)), video_id, 'Checking m3u8 URL').url
 159         if 'mpeg_cenc' in m3u8_url:
 160             self.report_drm(video_id)
 161         formats, subtitles = self._extract_m3u8_formats_and_subtitles(m3u8_url, video_id, 'mp4', m3u8_id='hls')
 162
 163         return {
 164             'id': video_id,
 165             'formats': formats,
 166             'subtitles': subtitles,
 167             'chapters': chapters,
 168             **merge_dicts(traverse_obj(tp_metadata, {
 169                 'title': 'title',
 170                 'description': 'description',
 171                 'duration': ('duration', {seconds_or_none}),
 172                 'timestamp': ('pubDate', {seconds_or_none}),
 173                 'season_number': (('pl1$seasonNumber', 'nbcu$seasonNumber'), {int_or_none}),
 174                 'episode_number': (('pl1$episodeNumber', 'nbcu$episodeNumber'), {int_or_none}),
 175                 'series': (('pl1$show', 'nbcu$show'), (None, ...), {str}),
 176                 'episode': (('title', 'pl1$episodeNumber', 'nbcu$episodeNumber'), {str_or_none}),
 177                 'age_limit': ('ratings', ..., 'rating', {parse_age_limit}),
 178             }, get_all=False), traverse_obj(metadata, {
 179                 'title': 'title',
 180                 'description': 'description',
 181                 'duration': ('durationInSeconds', {int_or_none}),
 182                 'timestamp': ('airDate', {unified_timestamp}),
 183                 'thumbnail': ('thumbnailUrl', {url_or_none}),
 184                 'season_number': ('seasonNumber', {int_or_none}),
 185                 'episode_number': ('episodeNumber', {int_or_none}),
 186                 'episode': 'episodeTitle',
 187                 'series': 'show',
 188             }))
 189         }