yt_dlp/extractor/zoom.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..utils import (
   6     ExtractorError,
   7     int_or_none,
   8     url_or_none,
   9     parse_filesize,
  10     urlencode_postdata
  11 )
  12
  13
  14 class ZoomIE(InfoExtractor):
  15     IE_NAME = 'zoom'
  16     _VALID_URL = r'https://(?:.*).?zoom.us/rec(?:ording)?/(play|share)/(?P<id>[A-Za-z0-9\-_.]+)'
  17
  18     _TEST = {
  19         'url': 'https://zoom.us/recording/play/SILVuCL4bFtRwWTtOCFQQxAsBQsJljFtm9e4Z_bvo-A8B-nzUSYZRNuPl3qW5IGK',
  20         'info_dict': {
  21             'md5': '031a5b379f1547a8b29c5c4c837dccf2',
  22             'title': "GAZ Transformational Tuesdays W/ Landon & Stapes",
  23             'id': "SILVuCL4bFtRwWTtOCFQQxAsBQsJljFtm9e4Z_bvo-A8B-nzUSYZRNuPl3qW5IGK",
  24             'ext': "mp4"
  25         }
  26     }
  27
  28     def _real_extract(self, url):
  29         display_id = self._match_id(url)
  30         webpage = self._download_webpage(url, display_id)
  31
  32         password_protected = self._search_regex(r'<form[^>]+?id="(password_form)"', webpage, 'password field', fatal=False, default=None)
  33         if password_protected is not None:
  34             self._verify_video_password(url, display_id, webpage)
  35             webpage = self._download_webpage(url, display_id)
  36
  37         video_url = self._search_regex(r"viewMp4Url: \'(.*)\'", webpage, 'video url')
  38         title = self._html_search_regex([r"topic: \"(.*)\",", r"<title>(.*) - Zoom</title>"], webpage, 'title')
  39         viewResolvtionsWidth = self._search_regex(r"viewResolvtionsWidth: (\d*)", webpage, 'res width', fatal=False)
  40         viewResolvtionsHeight = self._search_regex(r"viewResolvtionsHeight: (\d*)", webpage, 'res height', fatal=False)
  41         fileSize = parse_filesize(self._search_regex(r"fileSize: \'(.+)\'", webpage, 'fileSize', fatal=False))
  42
  43         urlprefix = url.split("zoom.us")[0] + "zoom.us/"
  44
  45         formats = []
  46         formats.append({
  47             'url': url_or_none(video_url),
  48             'width': int_or_none(viewResolvtionsWidth),
  49             'height': int_or_none(viewResolvtionsHeight),
  50             'http_headers': {'Accept': 'video/webm,video/ogg,video/*;q=0.9,application/ogg;q=0.7,audio/*;q=0.6,*/*;q=0.5',
  51                              'Referer': urlprefix},
  52             'ext': "mp4",
  53             'filesize_approx': int_or_none(fileSize)
  54         })
  55         self._sort_formats(formats)
  56
  57         return {
  58             'id': display_id,
  59             'title': title,
  60             'formats': formats
  61         }
  62
  63     def _verify_video_password(self, url, video_id, webpage):
  64         password = self._downloader.params.get('videopassword')
  65         if password is None:
  66             raise ExtractorError('This video is protected by a password, use the --video-password option', expected=True)
  67         meetId = self._search_regex(r'<input[^>]+?id="meetId" value="([^\"]+)"', webpage, 'meetId')
  68         data = urlencode_postdata({
  69             'id': meetId,
  70             'passwd': password,
  71             'action': "viewdetailedpage",
  72             'recaptcha': ""
  73         })
  74         validation_url = url.split("zoom.us")[0] + "zoom.us/rec/validate_meet_passwd"
  75         validation_response = self._download_json(
  76             validation_url, video_id,
  77             note='Validating Password...',
  78             errnote='Wrong password?',
  79             data=data)
  80
  81         if validation_response['errorCode'] != 0:
  82             raise ExtractorError('Login failed, %s said: %r' % (self.IE_NAME, validation_response['errorMessage']))