yt_dlp/extractor/xbef.py

   1 from .common import InfoExtractor
   2 from ..compat import compat_urllib_parse_unquote
   3
   4
   5 class XBefIE(InfoExtractor):
   6     _VALID_URL = r'https?://(?:www\.)?xbef\.com/video/(?P<id>[0-9]+)'
   7     _TEST = {
   8         'url': 'http://xbef.com/video/5119-glamourous-lesbians-smoking-drinking-and-fucking',
   9         'md5': 'a478b565baff61634a98f5e5338be995',
  10         'info_dict': {
  11             'id': '5119',
  12             'ext': 'mp4',
  13             'title': 'md5:7358a9faef8b7b57acda7c04816f170e',
  14             'age_limit': 18,
  15             'thumbnail': r're:^http://.*\.jpg',
  16         }
  17     }
  18
  19     def _real_extract(self, url):
  20         video_id = self._match_id(url)
  21         webpage = self._download_webpage(url, video_id)
  22
  23         title = self._html_search_regex(
  24             r'<h1[^>]*>(.*?)</h1>', webpage, 'title')
  25
  26         config_url_enc = self._download_webpage(
  27             'http://xbef.com/Main/GetVideoURLEncoded/%s' % video_id, video_id,
  28             note='Retrieving config URL')
  29         config_url = compat_urllib_parse_unquote(config_url_enc)
  30         config = self._download_xml(
  31             config_url, video_id, note='Retrieving config')
  32
  33         video_url = config.find('./file').text
  34         thumbnail = config.find('./image').text
  35
  36         return {
  37             'id': video_id,
  38             'url': video_url,
  39             'title': title,
  40             'thumbnail': thumbnail,
  41             'age_limit': 18,
  42         }