yt_dlp/extractor/magellantv.py

   1 from .common import InfoExtractor
   2 from ..utils import parse_age_limit, parse_duration, traverse_obj
   3
   4
   5 class MagellanTVIE(InfoExtractor):
   6     _VALID_URL = r'https?://(?:www\.)?magellantv\.com/(?:watch|video)/(?P<id>[\w-]+)'
   7     _TESTS = [{
   8         'url': 'https://www.magellantv.com/watch/my-dads-on-death-row?type=v',
   9         'info_dict': {
  10             'id': 'my-dads-on-death-row',
  11             'ext': 'mp4',
  12             'title': 'My Dad\'s On Death Row',
  13             'description': 'md5:33ba23b9f0651fc4537ed19b1d5b0d7a',
  14             'duration': 3780.0,
  15             'age_limit': 14,
  16             'tags': ['Justice', 'Reality', 'United States', 'True Crime'],
  17         },
  18         'params': {'skip_download': 'm3u8'},
  19     }, {
  20         'url': 'https://www.magellantv.com/video/james-bulger-the-new-revelations',
  21         'info_dict': {
  22             'id': 'james-bulger-the-new-revelations',
  23             'ext': 'mp4',
  24             'title': 'James Bulger: The New Revelations',
  25             'description': 'md5:7b97922038bad1d0fe8d0470d8a189f2',
  26             'duration': 2640.0,
  27             'age_limit': 0,
  28             'tags': ['Investigation', 'True Crime', 'Justice', 'Europe'],
  29         },
  30         'params': {'skip_download': 'm3u8'},
  31     }, {
  32         'url': 'https://www.magellantv.com/watch/celebration-nation',
  33         'info_dict': {
  34             'id': 'celebration-nation',
  35             'ext': 'mp4',
  36             'tags': ['Art & Culture', 'Human Interest', 'Anthropology', 'China', 'History'],
  37             'duration': 2640.0,
  38             'title': 'Ancestors',
  39         },
  40         'params': {'skip_download': 'm3u8'},
  41     }]
  42
  43     def _real_extract(self, url):
  44         video_id = self._match_id(url)
  45         webpage = self._download_webpage(url, video_id)
  46         data = traverse_obj(self._search_nextjs_data(webpage, video_id), (
  47             'props', 'pageProps', 'reactContext',
  48             (('video', 'detail'), ('series', 'currentEpisode')), {dict}), get_all=False)
  49         formats, subtitles = self._extract_m3u8_formats_and_subtitles(data['jwpVideoUrl'], video_id)
  50
  51         return {
  52             'id': video_id,
  53             'formats': formats,
  54             'subtitles': subtitles,
  55             **traverse_obj(data, {
  56                 'title': ('title', {str}),
  57                 'description': ('metadata', 'description', {str}),
  58                 'duration': ('duration', {parse_duration}),
  59                 'age_limit': ('ratingCategory', {parse_age_limit}),
  60                 'tags': ('tags', ..., {str}),
  61             }),
  62         }