diff options
Diffstat (limited to 'yt_dlp/extractor/cellebrite.py')
| -rw-r--r-- | yt_dlp/extractor/cellebrite.py | 71 |
1 files changed, 29 insertions, 42 deletions
diff --git a/yt_dlp/extractor/cellebrite.py b/yt_dlp/extractor/cellebrite.py index e90365a..54367c4 100644 --- a/yt_dlp/extractor/cellebrite.py +++ b/yt_dlp/extractor/cellebrite.py @@ -1,63 +1,50 @@ -from .common import InfoExtractor -from ..utils import traverse_obj +from .vidyard import VidyardBaseIE, VidyardIE +from ..utils import ExtractorError, make_archive_id, url_basename -class CellebriteIE(InfoExtractor): +class CellebriteIE(VidyardBaseIE): _VALID_URL = r'https?://cellebrite\.com/(?:\w+)?/(?P<id>[\w-]+)' _TESTS = [{ 'url': 'https://cellebrite.com/en/collect-data-from-android-devices-with-cellebrite-ufed/', 'info_dict': { - 'id': '16025876', + 'id': 'ZqmUss3dQfEMGpauambPuH', + 'display_id': '16025876', 'ext': 'mp4', - 'description': 'md5:174571cb97083fd1d457d75c684f4e2b', - 'thumbnail': 'https://cellebrite.com/wp-content/uploads/2021/05/Chat-Capture-1024x559.png', 'title': 'Ask the Expert: Chat Capture - Collect Data from Android Devices in Cellebrite UFED', - 'duration': 455, - 'tags': [], + 'description': 'md5:dee48fe12bbae5c01fe6a053f7676da4', + 'thumbnail': 'https://cellebrite.com/wp-content/uploads/2021/05/Chat-Capture-1024x559.png', + 'duration': 455.979, + '_old_archive_ids': ['cellebrite 16025876'], }, }, { 'url': 'https://cellebrite.com/en/how-to-lawfully-collect-the-maximum-amount-of-data-from-android-devices/', 'info_dict': { - 'id': '29018255', + 'id': 'QV1U8a2yzcxigw7VFnqKyg', + 'display_id': '29018255', 'ext': 'mp4', - 'duration': 134, - 'tags': [], - 'description': 'md5:e9a3d124c7287b0b07bad2547061cacf', + 'title': 'How to Lawfully Collect the Maximum Amount of Data From Android Devices', + 'description': 'md5:0e943a9ac14c374d5d74faed634d773c', 'thumbnail': 'https://cellebrite.com/wp-content/uploads/2022/07/How-to-Lawfully-Collect-the-Maximum-Amount-of-Data-From-Android-Devices.png', - 'title': 'Android Extractions Explained', + 'duration': 134.315, + '_old_archive_ids': ['cellebrite 29018255'], }, }] - def _get_formats_and_subtitles(self, json_data, display_id): - formats = [{'url': url} for url in traverse_obj(json_data, ('mp4', ..., 'url')) or []] - subtitles = {} - - for url in traverse_obj(json_data, ('hls', ..., 'url')) or []: - fmt, sub = self._extract_m3u8_formats_and_subtitles( - url, display_id, ext='mp4', headers={'Referer': 'https://play.vidyard.com/'}) - formats.extend(fmt) - self._merge_subtitles(sub, target=subtitles) - - return formats, subtitles - def _real_extract(self, url): - display_id = self._match_id(url) - webpage = self._download_webpage(url, display_id) - - player_uuid = self._search_regex( - r'<img\s[^>]*\bdata-uuid\s*=\s*"([^"\?]+)', webpage, 'player UUID') - json_data = self._download_json( - f'https://play.vidyard.com/player/{player_uuid}.json', display_id)['payload']['chapters'][0] + slug = self._match_id(url) + webpage = self._download_webpage(url, slug) + vidyard_url = next(VidyardIE._extract_embed_urls(url, webpage), None) + if not vidyard_url: + raise ExtractorError('No Vidyard video embeds found on page') + + video_id = url_basename(vidyard_url) + info = self._process_video_json(self._fetch_video_json(video_id)['chapters'][0], video_id) + if info.get('display_id'): + info['_old_archive_ids'] = [make_archive_id(self, info['display_id'])] + if thumbnail := self._og_search_thumbnail(webpage, default=None): + info.setdefault('thumbnails', []).append({'url': thumbnail}) - formats, subtitles = self._get_formats_and_subtitles(json_data['sources'], display_id) return { - 'id': str(json_data['videoId']), - 'title': json_data.get('name') or self._og_search_title(webpage), - 'formats': formats, - 'subtitles': subtitles, - 'description': json_data.get('description') or self._og_search_description(webpage), - 'duration': json_data.get('seconds'), - 'tags': json_data.get('tags'), - 'thumbnail': self._og_search_thumbnail(webpage), - 'http_headers': {'Referer': 'https://play.vidyard.com/'}, + 'description': self._og_search_description(webpage, default=None), + **info, } |