yt_dlp/extractor/zoom.py

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