yt_dlp/extractor/cellebrite.py

   1 from .common import InfoExtractor
   2 from ..utils import traverse_obj
   3
   4
   5 class CellebriteIE(InfoExtractor):
   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': '16025876',
  11             'ext': 'mp4',
  12             'description': 'md5:174571cb97083fd1d457d75c684f4e2b',
  13             'thumbnail': 'https://cellebrite.com/wp-content/uploads/2021/05/Chat-Capture-1024x559.png',
  14             'title': 'Ask the Expert: Chat Capture - Collect Data from Android Devices in Cellebrite UFED',
  15             'duration': 455,
  16             'tags': [],
  17         }
  18     }, {
  19         'url': 'https://cellebrite.com/en/how-to-lawfully-collect-the-maximum-amount-of-data-from-android-devices/',
  20         'info_dict': {
  21             'id': '29018255',
  22             'ext': 'mp4',
  23             'duration': 134,
  24             'tags': [],
  25             'description': 'md5:e9a3d124c7287b0b07bad2547061cacf',
  26             'thumbnail': 'https://cellebrite.com/wp-content/uploads/2022/07/How-to-Lawfully-Collect-the-Maximum-Amount-of-Data-From-Android-Devices.png',
  27             'title': 'Android Extractions Explained',
  28         }
  29     }]
  30
  31     def _get_formats_and_subtitles(self, json_data, display_id):
  32         formats = [{'url': url} for url in traverse_obj(json_data, ('mp4', ..., 'url')) or []]
  33         subtitles = {}
  34
  35         for url in traverse_obj(json_data, ('hls', ..., 'url')) or []:
  36             fmt, sub = self._extract_m3u8_formats_and_subtitles(
  37                 url, display_id, ext='mp4', headers={'Referer': 'https://play.vidyard.com/'})
  38             formats.extend(fmt)
  39             self._merge_subtitles(sub, target=subtitles)
  40
  41         return formats, subtitles
  42
  43     def _real_extract(self, url):
  44         display_id = self._match_id(url)
  45         webpage = self._download_webpage(url, display_id)
  46
  47         player_uuid = self._search_regex(
  48             r'<img\s[^>]*\bdata-uuid\s*=\s*"([^"\?]+)', webpage, 'player UUID')
  49         json_data = self._download_json(
  50             f'https://play.vidyard.com/player/{player_uuid}.json', display_id)['payload']['chapters'][0]
  51
  52         formats, subtitles = self._get_formats_and_subtitles(json_data['sources'], display_id)
  53         return {
  54             'id': str(json_data['videoId']),
  55             'title': json_data.get('name') or self._og_search_title(webpage),
  56             'formats': formats,
  57             'subtitles': subtitles,
  58             'description': json_data.get('description') or self._og_search_description(webpage),
  59             'duration': json_data.get('seconds'),
  60             'tags': json_data.get('tags'),
  61             'thumbnail': self._og_search_thumbnail(webpage),
  62             'http_headers': {'Referer': 'https://play.vidyard.com/'},
  63         }