yt_dlp/extractor/cellebrite.py

   1 from .vidyard import VidyardBaseIE, VidyardIE
   2 from ..utils import ExtractorError, make_archive_id, url_basename
   3
   4
   5 class CellebriteIE(VidyardBaseIE):
   6     _VALID_URL = r'https?://cellebrite\.com/(?:\w+)?/(?P<id>[\w-]+)'
   7     _TESTS = [{
   8         'url': 'https://cellebrite.com/en/collect-data-from-android-devices-with-cellebrite-ufed/',
   9         'info_dict': {
  10             'id': 'ZqmUss3dQfEMGpauambPuH',
  11             'display_id': '16025876',
  12             'ext': 'mp4',
  13             'title': 'Ask the Expert: Chat Capture - Collect Data from Android Devices in Cellebrite UFED',
  14             'description': 'md5:dee48fe12bbae5c01fe6a053f7676da4',
  15             'thumbnail': 'https://cellebrite.com/wp-content/uploads/2021/05/Chat-Capture-1024x559.png',
  16             'duration': 455.979,
  17             '_old_archive_ids': ['cellebrite 16025876'],
  18         },
  19     }, {
  20         'url': 'https://cellebrite.com/en/how-to-lawfully-collect-the-maximum-amount-of-data-from-android-devices/',
  21         'info_dict': {
  22             'id': 'QV1U8a2yzcxigw7VFnqKyg',
  23             'display_id': '29018255',
  24             'ext': 'mp4',
  25             'title': 'How to Lawfully Collect the Maximum Amount of Data From Android Devices',
  26             'description': 'md5:0e943a9ac14c374d5d74faed634d773c',
  27             'thumbnail': 'https://cellebrite.com/wp-content/uploads/2022/07/How-to-Lawfully-Collect-the-Maximum-Amount-of-Data-From-Android-Devices.png',
  28             'duration': 134.315,
  29             '_old_archive_ids': ['cellebrite 29018255'],
  30         },
  31     }]
  32
  33     def _real_extract(self, url):
  34         slug = self._match_id(url)
  35         webpage = self._download_webpage(url, slug)
  36         vidyard_url = next(VidyardIE._extract_embed_urls(url, webpage), None)
  37         if not vidyard_url:
  38             raise ExtractorError('No Vidyard video embeds found on page')
  39
  40         video_id = url_basename(vidyard_url)
  41         info = self._process_video_json(self._fetch_video_json(video_id)['chapters'][0], video_id)
  42         if info.get('display_id'):
  43             info['_old_archive_ids'] = [make_archive_id(self, info['display_id'])]
  44         if thumbnail := self._og_search_thumbnail(webpage, default=None):
  45             info.setdefault('thumbnails', []).append({'url': thumbnail})
  46
  47         return {
  48             'description': self._og_search_description(webpage, default=None),
  49             **info,
  50         }