yt_dlp/extractor/zoom.py

   1 from .common import InfoExtractor
   2 from ..utils import (
   3     ExtractorError,
   4     int_or_none,
   5     str_or_none,
   6     js_to_json,
   7     parse_filesize,
   8     urlencode_postdata,
   9     urljoin,
  10 )
  11
  12
  13 class ZoomIE(InfoExtractor):
  14     IE_NAME = 'zoom'
  15     _VALID_URL = r'(?P<base_url>https?://(?:[^.]+\.)?zoom.us/)rec(?:ording)?/(?:play|share)/(?P<id>[A-Za-z0-9_.-]+)'
  16     _TEST = {
  17         'url': 'https://economist.zoom.us/rec/play/dUk_CNBETmZ5VA2BwEl-jjakPpJ3M1pcfVYAPRsoIbEByGsLjUZtaa4yCATQuOL3der8BlTwxQePl_j0.EImBkXzTIaPvdZO5',
  18         'md5': 'ab445e8c911fddc4f9adc842c2c5d434',
  19         'info_dict': {
  20             'id': 'dUk_CNBETmZ5VA2BwEl-jjakPpJ3M1pcfVYAPRsoIbEByGsLjUZtaa4yCATQuOL3der8BlTwxQePl_j0.EImBkXzTIaPvdZO5',
  21             'ext': 'mp4',
  22             'title': 'China\'s "two sessions" and the new five-year plan',
  23         },
  24         'skip': 'Recording requires email authentication to access',
  25     }
  26
  27     def _real_extract(self, url):
  28         base_url, play_id = self._match_valid_url(url).groups()
  29         webpage = self._download_webpage(url, play_id)
  30
  31         try:
  32             form = self._form_hidden_inputs('password_form', webpage)
  33         except ExtractorError:
  34             form = None
  35         if form:
  36             password = self.get_param('videopassword')
  37             if not password:
  38                 raise ExtractorError(
  39                     'This video is protected by a passcode, use the --video-password option', expected=True)
  40             is_meeting = form.get('useWhichPasswd') == 'meeting'
  41             validation = self._download_json(
  42                 base_url + 'rec/validate%s_passwd' % ('_meet' if is_meeting else ''),
  43                 play_id, 'Validating passcode', 'Wrong passcode', data=urlencode_postdata({
  44                     'id': form[('meet' if is_meeting else 'file') + 'Id'],
  45                     'passwd': password,
  46                     'action': form.get('action'),
  47                 }))
  48             if not validation.get('status'):
  49                 raise ExtractorError(validation['errorMessage'], expected=True)
  50             webpage = self._download_webpage(url, play_id)
  51
  52         data = self._parse_json(self._search_regex(
  53             r'(?s)window\.__data__\s*=\s*({.+?});',
  54             webpage, 'data'), play_id, js_to_json)
  55
  56         subtitles = {}
  57         for _type in ('transcript', 'cc', 'chapter'):
  58             if data.get('%sUrl' % _type):
  59                 subtitles[_type] = [{
  60                     'url': urljoin(base_url, data['%sUrl' % _type]),
  61                     'ext': 'vtt',
  62                 }]
  63
  64         formats = []
  65
  66         if data.get('viewMp4Url'):
  67             formats.append({
  68                 'format_note': 'Camera stream',
  69                 'url': str_or_none(data.get('viewMp4Url')),
  70                 'width': int_or_none(data.get('viewResolvtionsWidth')),
  71                 'height': int_or_none(data.get('viewResolvtionsHeight')),
  72                 'format_id': str_or_none(data.get('recordingId')),
  73                 'ext': 'mp4',
  74                 'filesize_approx': parse_filesize(data.get('fileSize')),
  75                 'preference': 0
  76             })
  77
  78         if data.get('shareMp4Url'):
  79             formats.append({
  80                 'format_note': 'Screen share stream',
  81                 'url': str_or_none(data.get('shareMp4Url')),
  82                 'width': int_or_none(data.get('shareResolvtionsWidth')),
  83                 'height': int_or_none(data.get('shareResolvtionsHeight')),
  84                 'format_id': str_or_none(data.get('shareVideoId')),
  85                 'ext': 'mp4',
  86                 'preference': -1
  87             })
  88
  89         return {
  90             'id': play_id,
  91             'title': data.get('topic'),
  92             'subtitles': subtitles,
  93             'formats': formats,
  94             'http_headers': {
  95                 'Referer': base_url,
  96             },
  97         }