yt_dlp/extractor/cbs.py

   1 from .brightcove import BrightcoveNewIE
   2 from .common import InfoExtractor
   3 from .theplatform import ThePlatformFeedIE
   4 from .youtube import YoutubeIE
   5 from ..utils import (
   6     ExtractorError,
   7     extract_attributes,
   8     get_element_html_by_id,
   9     int_or_none,
  10     find_xpath_attr,
  11     smuggle_url,
  12     xpath_element,
  13     xpath_text,
  14     update_url_query,
  15     url_or_none,
  16 )
  17
  18
  19 class CBSBaseIE(ThePlatformFeedIE):  # XXX: Do not subclass from concrete IE
  20     def _parse_smil_subtitles(self, smil, namespace=None, subtitles_lang='en'):
  21         subtitles = {}
  22         for k, ext in [('sMPTE-TTCCURL', 'tt'), ('ClosedCaptionURL', 'ttml'), ('webVTTCaptionURL', 'vtt')]:
  23             cc_e = find_xpath_attr(smil, self._xpath_ns('.//param', namespace), 'name', k)
  24             if cc_e is not None:
  25                 cc_url = cc_e.get('value')
  26                 if cc_url:
  27                     subtitles.setdefault(subtitles_lang, []).append({
  28                         'ext': ext,
  29                         'url': cc_url,
  30                     })
  31         return subtitles
  32
  33     def _extract_common_video_info(self, content_id, asset_types, mpx_acc, extra_info):
  34         tp_path = 'dJ5BDC/media/guid/%d/%s' % (mpx_acc, content_id)
  35         tp_release_url = f'https://link.theplatform.com/s/{tp_path}'
  36         info = self._extract_theplatform_metadata(tp_path, content_id)
  37
  38         formats, subtitles = [], {}
  39         last_e = None
  40         for asset_type, query in asset_types.items():
  41             try:
  42                 tp_formats, tp_subtitles = self._extract_theplatform_smil(
  43                     update_url_query(tp_release_url, query), content_id,
  44                     'Downloading %s SMIL data' % asset_type)
  45             except ExtractorError as e:
  46                 last_e = e
  47                 if asset_type != 'fallback':
  48                     continue
  49                 query['formats'] = ''  # blank query to check if expired
  50                 try:
  51                     tp_formats, tp_subtitles = self._extract_theplatform_smil(
  52                         update_url_query(tp_release_url, query), content_id,
  53                         'Downloading %s SMIL data, trying again with another format' % asset_type)
  54                 except ExtractorError as e:
  55                     last_e = e
  56                     continue
  57             formats.extend(tp_formats)
  58             subtitles = self._merge_subtitles(subtitles, tp_subtitles)
  59         if last_e and not formats:
  60             self.raise_no_formats(last_e, True, content_id)
  61
  62         extra_info.update({
  63             'id': content_id,
  64             'formats': formats,
  65             'subtitles': subtitles,
  66         })
  67         info.update({k: v for k, v in extra_info.items() if v is not None})
  68         return info
  69
  70     def _extract_video_info(self, *args, **kwargs):
  71         # Extract assets + metadata and call _extract_common_video_info
  72         raise NotImplementedError('This method must be implemented by subclasses')
  73
  74     def _real_extract(self, url):
  75         return self._extract_video_info(self._match_id(url))
  76
  77
  78 class CBSIE(CBSBaseIE):
  79     _VALID_URL = r'''(?x)
  80         (?:
  81             cbs:|
  82             https?://(?:www\.)?(?:
  83                 cbs\.com/(?:shows|movies)/(?:video|[^/]+/video|[^/]+)/|
  84                 colbertlateshow\.com/(?:video|podcasts)/)
  85         )(?P<id>[\w-]+)'''
  86
  87     # All tests are blocked outside US
  88     _TESTS = [{
  89         'url': 'https://www.cbs.com/shows/video/xrUyNLtl9wd8D_RWWAg9NU2F_V6QpB3R/',
  90         'info_dict': {
  91             'id': 'xrUyNLtl9wd8D_RWWAg9NU2F_V6QpB3R',
  92             'ext': 'mp4',
  93             'title': 'Tough As Nails - Dreams Never Die',
  94             'description': 'md5:a3535a62531cdd52b0364248a2c1ae33',
  95             'duration': 2588,
  96             'timestamp': 1639015200,
  97             'upload_date': '20211209',
  98             'uploader': 'CBSI-NEW',
  99         },
 100         'params': {
 101             # m3u8 download
 102             'skip_download': True,
 103         },
 104     }, {
 105         'url': 'https://www.cbs.com/shows/video/sZH1MGgomIosZgxGJ1l263MFq16oMtW1/',
 106         'info_dict': {
 107             'id': 'sZH1MGgomIosZgxGJ1l263MFq16oMtW1',
 108             'title': 'The Late Show - 3/16/22 (Michael Buble, Rose Matafeo)',
 109             'timestamp': 1647488100,
 110             'description': 'md5:d0e6ec23c544b7fa8e39a8e6844d2439',
 111             'uploader': 'CBSI-NEW',
 112             'upload_date': '20220317',
 113         },
 114         'params': {
 115             'ignore_no_formats_error': True,
 116             'skip_download': True,
 117         },
 118         'expected_warnings': [
 119             'This content expired on', 'No video formats found', 'Requested format is not available'],
 120     }, {
 121         'url': 'http://colbertlateshow.com/video/8GmB0oY0McANFvp2aEffk9jZZZ2YyXxy/the-colbeard/',
 122         'only_matching': True,
 123     }, {
 124         'url': 'http://www.colbertlateshow.com/podcasts/dYSwjqPs_X1tvbV_P2FcPWRa_qT6akTC/in-the-bad-room-with-stephen/',
 125         'only_matching': True,
 126     }]
 127
 128     def _extract_video_info(self, content_id, site='cbs', mpx_acc=2198311517):
 129         items_data = self._download_xml(
 130             'https://can.cbs.com/thunder/player/videoPlayerService.php',
 131             content_id, query={'partner': site, 'contentId': content_id})
 132         video_data = xpath_element(items_data, './/item')
 133         title = xpath_text(video_data, 'videoTitle', 'title') or xpath_text(video_data, 'videotitle', 'title')
 134
 135         asset_types = {}
 136         has_drm = False
 137         for item in items_data.findall('.//item'):
 138             asset_type = xpath_text(item, 'assetType')
 139             query = {
 140                 'mbr': 'true',
 141                 'assetTypes': asset_type,
 142             }
 143             if not asset_type:
 144                 # fallback for content_ids that videoPlayerService doesn't return anything for
 145                 asset_type = 'fallback'
 146                 query['formats'] = 'M3U+none,MPEG4,M3U+appleHlsEncryption,MP3'
 147                 del query['assetTypes']
 148             if asset_type in asset_types:
 149                 continue
 150             elif any(excluded in asset_type for excluded in ('HLS_FPS', 'DASH_CENC', 'OnceURL')):
 151                 if 'DASH_CENC' in asset_type:
 152                     has_drm = True
 153                 continue
 154             if asset_type.startswith('HLS') or 'StreamPack' in asset_type:
 155                 query['formats'] = 'MPEG4,M3U'
 156             elif asset_type in ('RTMP', 'WIFI', '3G'):
 157                 query['formats'] = 'MPEG4,FLV'
 158             asset_types[asset_type] = query
 159
 160         if not asset_types and has_drm:
 161             self.report_drm(content_id)
 162
 163         return self._extract_common_video_info(content_id, asset_types, mpx_acc, extra_info={
 164             'title': title,
 165             'series': xpath_text(video_data, 'seriesTitle'),
 166             'season_number': int_or_none(xpath_text(video_data, 'seasonNumber')),
 167             'episode_number': int_or_none(xpath_text(video_data, 'episodeNumber')),
 168             'duration': int_or_none(xpath_text(video_data, 'videoLength'), 1000),
 169             'thumbnail': url_or_none(xpath_text(video_data, 'previewImageURL')),
 170         })
 171
 172
 173 class ParamountPressExpressIE(InfoExtractor):
 174     _VALID_URL = r'https?://(?:www\.)?paramountpressexpress\.com(?:/[\w-]+)+/(?P<yt>yt-)?video/?\?watch=(?P<id>[\w-]+)'
 175     _TESTS = [{
 176         'url': 'https://www.paramountpressexpress.com/cbs-entertainment/shows/survivor/video/?watch=pnzew7e2hx',
 177         'md5': '56631dbcadaab980d1fc47cb7b76cba4',
 178         'info_dict': {
 179             'id': '6322981580112',
 180             'ext': 'mp4',
 181             'title': 'I’m Felicia',
 182             'description': 'md5:88fad93f8eede1c9c8f390239e4c6290',
 183             'uploader_id': '6055873637001',
 184             'upload_date': '20230320',
 185             'timestamp': 1679334960,
 186             'duration': 49.557,
 187             'thumbnail': r're:^https://.+\.jpg',
 188             'tags': [],
 189         },
 190     }, {
 191         'url': 'https://www.paramountpressexpress.com/cbs-entertainment/video/?watch=2s5eh8kppc',
 192         'md5': 'edcb03e3210b88a3e56c05aa863e0e5b',
 193         'info_dict': {
 194             'id': '6323036027112',
 195             'ext': 'mp4',
 196             'title': '‘Y&R’ Set Visit: Jerry O’Connell Quizzes Cast on Pre-Love Scene Rituals and More',
 197             'description': 'md5:b929867a357aac5544b783d834c78383',
 198             'uploader_id': '6055873637001',
 199             'upload_date': '20230321',
 200             'timestamp': 1679430180,
 201             'duration': 132.032,
 202             'thumbnail': r're:^https://.+\.jpg',
 203             'tags': [],
 204         },
 205     }, {
 206         'url': 'https://www.paramountpressexpress.com/paramount-plus/yt-video/?watch=OX9wJWOcqck',
 207         'info_dict': {
 208             'id': 'OX9wJWOcqck',
 209             'ext': 'mp4',
 210             'title': 'Rugrats | Season 2 Official Trailer | Paramount+',
 211             'description': 'md5:1f7e26f5625a9f0d6564d9ad97a9f7de',
 212             'uploader': 'Paramount Plus',
 213             'uploader_id': '@paramountplus',
 214             'uploader_url': 'http://www.youtube.com/@paramountplus',
 215             'channel': 'Paramount Plus',
 216             'channel_id': 'UCrRttZIypNTA1Mrfwo745Sg',
 217             'channel_url': 'https://www.youtube.com/channel/UCrRttZIypNTA1Mrfwo745Sg',
 218             'upload_date': '20230316',
 219             'duration': 88,
 220             'age_limit': 0,
 221             'availability': 'public',
 222             'live_status': 'not_live',
 223             'playable_in_embed': True,
 224             'view_count': int,
 225             'like_count': int,
 226             'channel_follower_count': int,
 227             'thumbnail': 'https://i.ytimg.com/vi/OX9wJWOcqck/maxresdefault.jpg',
 228             'categories': ['Entertainment'],
 229             'tags': ['Rugrats'],
 230         },
 231     }, {
 232         'url': 'https://www.paramountpressexpress.com/showtime/yt-video/?watch=_ljssSoDLkw',
 233         'info_dict': {
 234             'id': '_ljssSoDLkw',
 235             'ext': 'mp4',
 236             'title': 'Lavell Crawford: THEE Lavell Crawford Comedy Special Official Trailer | SHOWTIME',
 237             'description': 'md5:39581bcc3fd810209b642609f448af70',
 238             'uploader': 'SHOWTIME',
 239             'uploader_id': '@Showtime',
 240             'uploader_url': 'http://www.youtube.com/@Showtime',
 241             'channel': 'SHOWTIME',
 242             'channel_id': 'UCtwMWJr2BFPkuJTnSvCESSQ',
 243             'channel_url': 'https://www.youtube.com/channel/UCtwMWJr2BFPkuJTnSvCESSQ',
 244             'upload_date': '20230209',
 245             'duration': 49,
 246             'age_limit': 0,
 247             'availability': 'public',
 248             'live_status': 'not_live',
 249             'playable_in_embed': True,
 250             'view_count': int,
 251             'like_count': int,
 252             'comment_count': int,
 253             'channel_follower_count': int,
 254             'thumbnail': 'https://i.ytimg.com/vi_webp/_ljssSoDLkw/maxresdefault.webp',
 255             'categories': ['People & Blogs'],
 256             'tags': 'count:27',
 257         },
 258     }]
 259
 260     def _real_extract(self, url):
 261         display_id, is_youtube = self._match_valid_url(url).group('id', 'yt')
 262         if is_youtube:
 263             return self.url_result(display_id, YoutubeIE)
 264
 265         webpage = self._download_webpage(url, display_id)
 266         video_id = self._search_regex(
 267             r'\bvideo_id\s*=\s*["\'](\d+)["\']\s*,', webpage, 'Brightcove ID')
 268         token = self._search_regex(r'\btoken\s*=\s*["\']([\w.-]+)["\']', webpage, 'token')
 269
 270         player = extract_attributes(get_element_html_by_id('vcbrightcoveplayer', webpage) or '')
 271         account_id = player.get('data-account') or '6055873637001'
 272         player_id = player.get('data-player') or 'OtLKgXlO9F'
 273         embed = player.get('data-embed') or 'default'
 274
 275         return self.url_result(smuggle_url(
 276             f'https://players.brightcove.net/{account_id}/{player_id}_{embed}/index.html?videoId={video_id}',
 277             {'token': token}), BrightcoveNewIE)