yt_dlp/extractor/ciscowebex.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..utils import (
   6     int_or_none,
   7     try_get,
   8     unified_timestamp,
   9 )
  10
  11
  12 class CiscoWebexIE(InfoExtractor):
  13     IE_NAME = 'ciscowebex'
  14     IE_DESC = 'Cisco Webex'
  15     _VALID_URL = r'''(?x)
  16                     (?P<url>https?://(?P<subdomain>[^/#?]*)\.webex\.com/(?:
  17                         (?P<siteurl_1>[^/#?]*)/(?:ldr|lsr).php\?(?:[^#]*&)*RCID=(?P<rcid>[0-9a-f]{32})|
  18                         (?:recordingservice|webappng)/sites/(?P<siteurl_2>[^/#?]*)/recording/(?:playback/|play/)?(?P<id>[0-9a-f]{32})
  19                     ))'''
  20
  21     _TESTS = [{
  22         'url': 'https://demosubdomain.webex.com/demositeurl/ldr.php?RCID=e58e803bc0f766bb5f6376d2e86adb5b',
  23         'only_matching': True,
  24     }, {
  25         'url': 'http://demosubdomain.webex.com/demositeurl/lsr.php?RCID=bc04b4a7b5ea2cc3a493d5ae6aaff5d7',
  26         'only_matching': True,
  27     }, {
  28         'url': 'https://demosubdomain.webex.com/recordingservice/sites/demositeurl/recording/88e7a42f7b19f5b423c54754aecc2ce9/playback',
  29         'only_matching': True,
  30     }]
  31
  32     def _real_extract(self, url):
  33         mobj = self._match_valid_url(url)
  34         rcid = mobj.group('rcid')
  35         if rcid:
  36             webpage = self._download_webpage(url, None, note='Getting video ID')
  37             url = self._search_regex(self._VALID_URL, webpage, 'redirection url', group='url')
  38         url = self._request_webpage(url, None, note='Resolving final URL').geturl()
  39         mobj = self._match_valid_url(url)
  40         subdomain = mobj.group('subdomain')
  41         siteurl = mobj.group('siteurl_1') or mobj.group('siteurl_2')
  42         video_id = mobj.group('id')
  43
  44         stream = self._download_json(
  45             'https://%s.webex.com/webappng/api/v1/recordings/%s/stream' % (subdomain, video_id),
  46             video_id, fatal=False, query={'siteurl': siteurl})
  47         if not stream:
  48             self.raise_login_required(method='cookies')
  49
  50         video_id = stream.get('recordUUID') or video_id
  51
  52         formats = [{
  53             'format_id': 'video',
  54             'url': stream['fallbackPlaySrc'],
  55             'ext': 'mp4',
  56             'vcodec': 'avc1.640028',
  57             'acodec': 'mp4a.40.2',
  58         }]
  59         if stream.get('preventDownload') is False:
  60             mp4url = try_get(stream, lambda x: x['downloadRecordingInfo']['downloadInfo']['mp4URL'])
  61             if mp4url:
  62                 formats.append({
  63                     'format_id': 'video',
  64                     'url': mp4url,
  65                     'ext': 'mp4',
  66                     'vcodec': 'avc1.640028',
  67                     'acodec': 'mp4a.40.2',
  68                 })
  69             audiourl = try_get(stream, lambda x: x['downloadRecordingInfo']['downloadInfo']['audioURL'])
  70             if audiourl:
  71                 formats.append({
  72                     'format_id': 'audio',
  73                     'url': audiourl,
  74                     'ext': 'mp3',
  75                     'vcodec': 'none',
  76                     'acodec': 'mp3',
  77                 })
  78         self._sort_formats(formats)
  79
  80         return {
  81             'id': video_id,
  82             'title': stream['recordName'],
  83             'description': stream.get('description'),
  84             'uploader': stream.get('ownerDisplayName'),
  85             'uploader_id': stream.get('ownerUserName') or stream.get('ownerId'),  # mail or id
  86             'timestamp': unified_timestamp(stream.get('createTime')),
  87             'duration': int_or_none(stream.get('duration'), 1000),
  88             'webpage_url': 'https://%s.webex.com/recordingservice/sites/%s/recording/playback/%s' % (subdomain, siteurl, video_id),
  89             'formats': formats,
  90         }