yt_dlp/extractor/ciscowebex.py

   1 from .common import InfoExtractor
   2 from ..utils import (
   3     ExtractorError,
   4     int_or_none,
   5     try_get,
   6     unified_timestamp,
   7 )
   8
   9
  10 class CiscoWebexIE(InfoExtractor):
  11     IE_NAME = 'ciscowebex'
  12     IE_DESC = 'Cisco Webex'
  13     _VALID_URL = r'''(?x)
  14                     (?P<url>https?://(?P<subdomain>[^/#?]*)\.webex\.com/(?:
  15                         (?P<siteurl_1>[^/#?]*)/(?:ldr|lsr).php\?(?:[^#]*&)*RCID=(?P<rcid>[0-9a-f]{32})|
  16                         (?:recordingservice|webappng)/sites/(?P<siteurl_2>[^/#?]*)/recording/(?:playback/|play/)?(?P<id>[0-9a-f]{32})
  17                     ))'''
  18
  19     _TESTS = [{
  20         'url': 'https://demosubdomain.webex.com/demositeurl/ldr.php?RCID=e58e803bc0f766bb5f6376d2e86adb5b',
  21         'only_matching': True,
  22     }, {
  23         'url': 'http://demosubdomain.webex.com/demositeurl/lsr.php?RCID=bc04b4a7b5ea2cc3a493d5ae6aaff5d7',
  24         'only_matching': True,
  25     }, {
  26         'url': 'https://demosubdomain.webex.com/recordingservice/sites/demositeurl/recording/88e7a42f7b19f5b423c54754aecc2ce9/playback',
  27         'only_matching': True,
  28     }]
  29
  30     def _real_extract(self, url):
  31         mobj = self._match_valid_url(url)
  32         rcid = mobj.group('rcid')
  33         if rcid:
  34             webpage = self._download_webpage(url, None, note='Getting video ID')
  35             url = self._search_regex(self._VALID_URL, webpage, 'redirection url', group='url')
  36         url = self._request_webpage(url, None, note='Resolving final URL').url
  37         mobj = self._match_valid_url(url)
  38         subdomain = mobj.group('subdomain')
  39         siteurl = mobj.group('siteurl_1') or mobj.group('siteurl_2')
  40         video_id = mobj.group('id')
  41
  42         password = self.get_param('videopassword')
  43
  44         headers = {'Accept': 'application/json'}
  45         if password:
  46             headers['accessPwd'] = password
  47
  48         stream, urlh = self._download_json_handle(
  49             f'https://{subdomain}.webex.com/webappng/api/v1/recordings/{video_id}/stream',
  50             video_id, headers=headers, query={'siteurl': siteurl}, expected_status=(403, 429))
  51
  52         if urlh.status == 403:
  53             if stream['code'] == 53004:
  54                 self.raise_login_required()
  55             if stream['code'] == 53005:
  56                 if password:
  57                     raise ExtractorError('Wrong password', expected=True)
  58                 raise ExtractorError(
  59                     'This video is protected by a password, use the --video-password option', expected=True)
  60             raise ExtractorError(f'{self.IE_NAME} said: {stream["code"]} - {stream["message"]}', expected=True)
  61
  62         if urlh.status == 429:
  63             self.raise_login_required(
  64                 f'{self.IE_NAME} asks you to solve a CAPTCHA. Solve CAPTCHA in browser and',
  65                 method='cookies')
  66
  67         video_id = stream.get('recordUUID') or video_id
  68
  69         formats = [{
  70             'format_id': 'video',
  71             'url': stream['fallbackPlaySrc'],
  72             'ext': 'mp4',
  73             'vcodec': 'avc1.640028',
  74             'acodec': 'mp4a.40.2',
  75         }]
  76         if stream.get('preventDownload') is False:
  77             mp4url = try_get(stream, lambda x: x['downloadRecordingInfo']['downloadInfo']['mp4URL'])
  78             if mp4url:
  79                 formats.append({
  80                     'format_id': 'video',
  81                     'url': mp4url,
  82                     'ext': 'mp4',
  83                     'vcodec': 'avc1.640028',
  84                     'acodec': 'mp4a.40.2',
  85                 })
  86             audiourl = try_get(stream, lambda x: x['downloadRecordingInfo']['downloadInfo']['audioURL'])
  87             if audiourl:
  88                 formats.append({
  89                     'format_id': 'audio',
  90                     'url': audiourl,
  91                     'ext': 'mp3',
  92                     'vcodec': 'none',
  93                     'acodec': 'mp3',
  94                 })
  95
  96         return {
  97             'id': video_id,
  98             'title': stream['recordName'],
  99             'description': stream.get('description'),
 100             'uploader': stream.get('ownerDisplayName'),
 101             'uploader_id': stream.get('ownerUserName') or stream.get('ownerId'),
 102             'timestamp': unified_timestamp(stream.get('createTime')),
 103             'duration': int_or_none(stream.get('duration'), 1000),
 104             'webpage_url': f'https://{subdomain}.webex.com/recordingservice/sites/{siteurl}/recording/playback/{video_id}',
 105             'formats': formats,
 106         }