yt_dlp/extractor/blackboardcollaborate.py

   1 from .common import InfoExtractor
   2 from ..utils import parse_iso8601
   3
   4
   5 class BlackboardCollaborateIE(InfoExtractor):
   6     _VALID_URL = r'''(?x)
   7                         https?://
   8                         (?P<region>[a-z-]+)\.bbcollab\.com/
   9                         (?:
  10                             collab/ui/session/playback/load|
  11                             recording
  12                         )/
  13                         (?P<id>[^/]+)'''
  14     _TESTS = [
  15         {
  16             'url': 'https://us-lti.bbcollab.com/collab/ui/session/playback/load/0a633b6a88824deb8c918f470b22b256',
  17             'md5': 'bb7a055682ee4f25fdb5838cdf014541',
  18             'info_dict': {
  19                 'id': '0a633b6a88824deb8c918f470b22b256',
  20                 'title': 'HESI A2 Information Session - Thursday, May 6, 2021 - recording_1',
  21                 'ext': 'mp4',
  22                 'duration': 1896000,
  23                 'timestamp': 1620331399,
  24                 'upload_date': '20210506',
  25             },
  26         },
  27         {
  28             'url': 'https://us.bbcollab.com/collab/ui/session/playback/load/76761522adfe4345a0dee6794bbcabda',
  29             'only_matching': True,
  30         },
  31         {
  32             'url': 'https://ca.bbcollab.com/collab/ui/session/playback/load/b6399dcb44df4f21b29ebe581e22479d',
  33             'only_matching': True,
  34         },
  35         {
  36             'url': 'https://eu.bbcollab.com/recording/51ed7b50810c4444a106e48cefb3e6b5',
  37             'only_matching': True,
  38         },
  39         {
  40             'url': 'https://au.bbcollab.com/collab/ui/session/playback/load/2bccf7165d7c419ab87afc1ec3f3bb15',
  41             'only_matching': True,
  42         },
  43     ]
  44
  45     def _real_extract(self, url):
  46         mobj = self._match_valid_url(url)
  47         region = mobj.group('region')
  48         video_id = mobj.group('id')
  49         info = self._download_json(
  50             f'https://{region}.bbcollab.com/collab/api/csa/recordings/{video_id}/data', video_id)
  51         duration = info.get('duration')
  52         title = info['name']
  53         upload_date = info.get('created')
  54         streams = info['streams']
  55         formats = [{'format_id': k, 'url': url} for k, url in streams.items()]
  56
  57         return {
  58             'duration': duration,
  59             'formats': formats,
  60             'id': video_id,
  61             'timestamp': parse_iso8601(upload_date),
  62             'title': title,
  63         }