Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/xbef.py

   1 from __future__ import unicode_literals
   2
   3 from .common import InfoExtractor
   4 from ..compat import (
   5     compat_urllib_parse,
   6 )
   7
   8
   9 class XBefIE(InfoExtractor):
  10     _VALID_URL = r'http://(?:www\.)?xbef\.com/video/(?P<id>[0-9]+)'
  11     _TEST = {
  12         'url': 'http://xbef.com/video/5119-glamourous-lesbians-smoking-drinking-and-fucking',
  13         'md5': 'a478b565baff61634a98f5e5338be995',
  14         'info_dict': {
  15             'id': '5119',
  16             'ext': 'mp4',
  17             'title': 'md5:7358a9faef8b7b57acda7c04816f170e',
  18             'age_limit': 18,
  19             'thumbnail': 're:^http://.*\.jpg',
  20         }
  21     }
  22
  23     def _real_extract(self, url):
  24         video_id = self._match_id(url)
  25         webpage = self._download_webpage(url, video_id)
  26
  27         title = self._html_search_regex(
  28             r'<h1[^>]*>(.*?)</h1>', webpage, 'title')
  29
  30         config_url_enc = self._download_webpage(
  31             'http://xbef.com/Main/GetVideoURLEncoded/%s' % video_id, video_id,
  32             note='Retrieving config URL')
  33         config_url = compat_urllib_parse.unquote(config_url_enc)
  34         config = self._download_xml(
  35             config_url, video_id, note='Retrieving config')
  36
  37         video_url = config.find('./file').text
  38         thumbnail = config.find('./image').text
  39
  40         return {
  41             'id': video_id,
  42             'url': video_url,
  43             'title': title,
  44             'thumbnail': thumbnail,
  45             'age_limit': 18,
  46         }