yt-dlp/yt_dlp/extractor/blackboardcollaborate.py

from .common import InfoExtractor
from ..utils import parse_iso8601


class BlackboardCollaborateIE(InfoExtractor):
    _VALID_URL = r'''(?x)
                        https?://
                        (?P<region>[a-z-]+)\.bbcollab\.com/
                        (?:
                            collab/ui/session/playback/load|
                            recording
                        )/
                        (?P<id>[^/]+)'''
    _TESTS = [
        {
            'url': 'https://us-lti.bbcollab.com/collab/ui/session/playback/load/0a633b6a88824deb8c918f470b22b256',
            'md5': 'bb7a055682ee4f25fdb5838cdf014541',
            'info_dict': {
                'id': '0a633b6a88824deb8c918f470b22b256',
                'title': 'HESI A2 Information Session - Thursday, May 6, 2021 - recording_1',
                'ext': 'mp4',
                'duration': 1896000,
                'timestamp': 1620331399,
                'upload_date': '20210506',
            },
        },
        {
            'url': 'https://us.bbcollab.com/collab/ui/session/playback/load/76761522adfe4345a0dee6794bbcabda',
            'only_matching': True,
        },
        {
            'url': 'https://ca.bbcollab.com/collab/ui/session/playback/load/b6399dcb44df4f21b29ebe581e22479d',
            'only_matching': True,
        },
        {
            'url': 'https://eu.bbcollab.com/recording/51ed7b50810c4444a106e48cefb3e6b5',
            'only_matching': True,
        },
        {
            'url': 'https://au.bbcollab.com/collab/ui/session/playback/load/2bccf7165d7c419ab87afc1ec3f3bb15',
            'only_matching': True,
        },
    ]

    def _real_extract(self, url):
        mobj = self._match_valid_url(url)
        region = mobj.group('region')
        video_id = mobj.group('id')
        info = self._download_json(
            f'https://{region}.bbcollab.com/collab/api/csa/recordings/{video_id}/data', video_id)
        duration = info.get('duration')
        title = info['name']
        upload_date = info.get('created')
        streams = info['streams']
        formats = [{'format_id': k, 'url': url} for k, url in streams.items()]

        return {
            'duration': duration,
            'formats': formats,
            'id': video_id,
            'timestamp': parse_iso8601(upload_date),
            'title': title,
        }