youtube_dl/extractor/xbef.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..utils import (
   7     compat_urllib_parse,
   8 )
   9
  10
  11 class XBefIE(InfoExtractor):
  12     _VALID_URL = r'http://(?:www\.)?xbef\.com/video/(?P<id>[0-9]+)'
  13     _TEST = {
  14         'url': 'http://xbef.com/video/5119-glamourous-lesbians-smoking-drinking-and-fucking',
  15         'md5': 'a478b565baff61634a98f5e5338be995',
  16         'info_dict': {
  17             'id': '5119',
  18             'ext': 'mp4',
  19             'title': 'md5:7358a9faef8b7b57acda7c04816f170e',
  20             'age_limit': 18,
  21             'thumbnail': 're:^http://.*\.jpg',
  22         }
  23     }
  24
  25     def _real_extract(self, url):
  26         m = re.match(self._VALID_URL, url)
  27         video_id = m.group('id')
  28
  29         webpage = self._download_webpage(url, video_id)
  30         title = self._html_search_regex(
  31             r'<h1[^>]*>(.*?)</h1>', webpage, 'title')
  32
  33         config_url_enc = self._download_webpage(
  34             'http://xbef.com/Main/GetVideoURLEncoded/%s' % video_id, video_id,
  35             note='Retrieving config URL')
  36         config_url = compat_urllib_parse.unquote(config_url_enc)
  37         config = self._download_xml(
  38             config_url, video_id, note='Retrieving config')
  39
  40         video_url = config.find('./file').text
  41         thumbnail = config.find('./image').text
  42
  43         return {
  44             'id': video_id,
  45             'url': video_url,
  46             'title': title,
  47             'thumbnail': thumbnail,
  48             'age_limit': 18,
  49         }
  50