yt_dlp/extractor/berufetv.py

   1 from .common import InfoExtractor
   2 from ..utils import float_or_none, mimetype2ext, traverse_obj
   3
   4
   5 class BerufeTVIE(InfoExtractor):
   6     _VALID_URL = r'https?://(?:www\.)?web\.arbeitsagentur\.de/berufetv/[^?#]+/film;filmId=(?P<id>[\w-]+)'
   7     _TESTS = [{
   8         'url': 'https://web.arbeitsagentur.de/berufetv/studienberufe/wirtschaftswissenschaften/wirtschaftswissenschaften-volkswirtschaft/film;filmId=DvKC3DUpMKvUZ_6fEnfg3u',
   9         'md5': '041b6432ec8e6838f84a5c30f31cc795',
  10         'info_dict': {
  11             'id': 'DvKC3DUpMKvUZ_6fEnfg3u',
  12             'ext': 'mp4',
  13             'title': 'Volkswirtschaftslehre',
  14             'description': 'md5:6bd87d0c63163480a6489a37526ee1c1',
  15             'categories': ['Studien&shy;beruf'],
  16             'tags': ['Studienfilm'],
  17             'duration': 602.440,
  18             'thumbnail': r're:^https://asset-out-cdn\.video-cdn\.net/private/videos/DvKC3DUpMKvUZ_6fEnfg3u/thumbnails/793063\?quality=thumbnail&__token__=[^\s]+$',
  19         },
  20     }]
  21
  22     def _real_extract(self, url):
  23         video_id = self._match_id(url)
  24
  25         movie_metadata = self._download_json(
  26             'https://rest.arbeitsagentur.de/infosysbub/berufetv/pc/v1/film-metadata',
  27             video_id, 'Downloading JSON metadata',
  28             headers={'X-API-Key': '79089773-4892-4386-86e6-e8503669f426'}, fatal=False)
  29
  30         meta = traverse_obj(
  31             movie_metadata, ('metadaten', lambda _, i: video_id == i['miId']),
  32             get_all=False, default={})
  33
  34         video = self._download_json(
  35             f'https://d.video-cdn.net/play/player/8YRzUk6pTzmBdrsLe9Y88W/video/{video_id}',
  36             video_id, 'Downloading video JSON')
  37
  38         formats, subtitles = [], {}
  39         for key, source in video['videoSources']['html'].items():
  40             if key == 'auto':
  41                 fmts, subs = self._extract_m3u8_formats_and_subtitles(source[0]['source'], video_id)
  42                 formats += fmts
  43                 subtitles = subs
  44             else:
  45                 formats.append({
  46                     'url': source[0]['source'],
  47                     'ext': mimetype2ext(source[0]['mimeType']),
  48                     'format_id': key,
  49                 })
  50
  51         for track in video.get('videoTracks') or []:
  52             if track.get('type') != 'SUBTITLES':
  53                 continue
  54             subtitles.setdefault(track['language'], []).append({
  55                 'url': track['source'],
  56                 'name': track.get('label'),
  57                 'ext': 'vtt',
  58             })
  59
  60         return {
  61             'id': video_id,
  62             'title': meta.get('titel') or traverse_obj(video, ('videoMetaData', 'title')),
  63             'description': meta.get('beschreibung'),
  64             'thumbnail': meta.get('thumbnail') or f'https://asset-out-cdn.video-cdn.net/private/videos/{video_id}/thumbnails/active',
  65             'duration': float_or_none(video.get('duration'), scale=1000),
  66             'categories': [meta['kategorie']] if meta.get('kategorie') else None,
  67             'tags': meta.get('themengebiete'),
  68             'subtitles': subtitles,
  69             'formats': formats,
  70         }