yt_dlp/extractor/godtube.py

   1 from .common import InfoExtractor
   2 from ..utils import (
   3     parse_duration,
   4     parse_iso8601,
   5 )
   6
   7
   8 class GodTubeIE(InfoExtractor):
   9     _WORKING = False
  10     _VALID_URL = r'https?://(?:www\.)?godtube\.com/watch/\?v=(?P<id>[\da-zA-Z]+)'
  11     _TESTS = [
  12         {
  13             'url': 'https://www.godtube.com/watch/?v=0C0CNNNU',
  14             'md5': '77108c1e4ab58f48031101a1a2119789',
  15             'info_dict': {
  16                 'id': '0C0CNNNU',
  17                 'ext': 'mp4',
  18                 'title': 'Woman at the well.',
  19                 'duration': 159,
  20                 'timestamp': 1205712000,
  21                 'uploader': 'beverlybmusic',
  22                 'upload_date': '20080317',
  23                 'thumbnail': r're:^https?://.*\.jpg$',
  24             },
  25         },
  26     ]
  27
  28     def _real_extract(self, url):
  29         mobj = self._match_valid_url(url)
  30         video_id = mobj.group('id')
  31
  32         config = self._download_xml(
  33             f'http://www.godtube.com/resource/mediaplayer/{video_id.lower()}.xml',
  34             video_id, 'Downloading player config XML')
  35
  36         video_url = config.find('file').text
  37         uploader = config.find('author').text
  38         timestamp = parse_iso8601(config.find('date').text)
  39         duration = parse_duration(config.find('duration').text)
  40         thumbnail = config.find('image').text
  41
  42         media = self._download_xml(
  43             f'http://www.godtube.com/media/xml/?v={video_id}', video_id, 'Downloading media XML')
  44
  45         title = media.find('title').text
  46
  47         return {
  48             'id': video_id,
  49             'url': video_url,
  50             'title': title,
  51             'thumbnail': thumbnail,
  52             'timestamp': timestamp,
  53             'uploader': uploader,
  54             'duration': duration,
  55         }