yt_dlp/extractor/startrek.py

   1 from .common import InfoExtractor
   2 from ..utils import int_or_none, urljoin
   3
   4
   5 class StarTrekIE(InfoExtractor):
   6     _WORKING = False
   7     _VALID_URL = r'(?P<base>https?://(?:intl|www)\.startrek\.com)/videos/(?P<id>[^/]+)'
   8     _TESTS = [{
   9         'url': 'https://intl.startrek.com/videos/watch-welcoming-jess-bush-to-the-ready-room',
  10         'md5': '491df5035c9d4dc7f63c79caaf9c839e',
  11         'info_dict': {
  12             'id': 'watch-welcoming-jess-bush-to-the-ready-room',
  13             'ext': 'mp4',
  14             'title': 'WATCH: Welcoming Jess Bush to The Ready Room',
  15             'duration': 1888,
  16             'timestamp': 1655388000,
  17             'upload_date': '20220616',
  18             'description': 'md5:1ffee884e3920afbdd6dd04e926a1221',
  19             'thumbnail': r're:https://(?:intl|www)\.startrek\.com/sites/default/files/styles/video_1920x1080/public/images/2022-06/pp_14794_rr_thumb_107_yt_16x9\.jpg(?:\?.+)?',
  20             'subtitles': {'en-US': [{
  21                 'url': r're:https://(?:intl|www)\.startrek\.com/sites/default/files/video/captions/2022-06/TRR_SNW_107_v4\.vtt',
  22             }, {
  23                 'url': 'https://media.startrek.com/2022/06/16/2043801155561/1069981_hls/trr_snw_107_v4-c4bfc25d/stream_vtt.m3u8',
  24             }]},
  25         },
  26     }, {
  27         'url': 'https://www.startrek.com/videos/watch-ethan-peck-and-gia-sandhu-beam-down-to-the-ready-room',
  28         'md5': 'f5ad74fbb86e91e0882fc0a333178d1d',
  29         'info_dict': {
  30             'id': 'watch-ethan-peck-and-gia-sandhu-beam-down-to-the-ready-room',
  31             'ext': 'mp4',
  32             'title': 'WATCH: Ethan Peck and Gia Sandhu Beam Down to The Ready Room',
  33             'duration': 1986,
  34             'timestamp': 1654221600,
  35             'upload_date': '20220603',
  36             'description': 'md5:b3aa0edacfe119386567362dec8ed51b',
  37             'thumbnail': r're:https://www\.startrek\.com/sites/default/files/styles/video_1920x1080/public/images/2022-06/pp_14792_rr_thumb_105_yt_16x9_1.jpg(?:\?.+)?',
  38             'subtitles': {'en-US': [{
  39                 'url': r're:https://(?:intl|www)\.startrek\.com/sites/default/files/video/captions/2022-06/TRR_SNW_105_v5\.vtt',
  40             }]},
  41         },
  42     }]
  43
  44     def _real_extract(self, url):
  45         urlbase, video_id = self._match_valid_url(url).group('base', 'id')
  46         webpage = self._download_webpage(url, video_id)
  47
  48         player = self._search_regex(
  49             r'(<\s*div\s+id\s*=\s*"cvp-player-[^<]+<\s*/div\s*>)', webpage, 'player')
  50
  51         hls = self._html_search_regex(r'\bdata-hls\s*=\s*"([^"]+)"', player, 'HLS URL')
  52         formats, subtitles = self._extract_m3u8_formats_and_subtitles(hls, video_id, 'mp4')
  53
  54         captions = self._html_search_regex(
  55             r'\bdata-captions-url\s*=\s*"([^"]+)"', player, 'captions URL', fatal=False)
  56         if captions:
  57             subtitles.setdefault('en-US', [])[:0] = [{'url': urljoin(urlbase, captions)}]
  58
  59         # NB: Most of the data in the json_ld is undesirable
  60         json_ld = self._search_json_ld(webpage, video_id, fatal=False)
  61
  62         return {
  63             'id': video_id,
  64             'title': self._html_search_regex(
  65                 r'\bdata-title\s*=\s*"([^"]+)"', player, 'title', json_ld.get('title')),
  66             'description': self._html_search_regex(
  67                 r'(?s)<\s*div\s+class\s*=\s*"header-body"\s*>(.+?)<\s*/div\s*>',
  68                 webpage, 'description', fatal=False),
  69             'duration': int_or_none(self._html_search_regex(
  70                 r'\bdata-duration\s*=\s*"(\d+)"', player, 'duration', fatal=False)),
  71             'formats': formats,
  72             'subtitles': subtitles,
  73             'thumbnail': urljoin(urlbase, self._html_search_regex(
  74                 r'\bdata-poster-url\s*=\s*"([^"]+)"', player, 'thumbnail', fatal=False)),
  75             'timestamp': json_ld.get('timestamp'),
  76         }