youtube_dl/extractor/foxgay.py

   1 from __future__ import unicode_literals
   2
   3 from .common import InfoExtractor
   4
   5
   6 class FoxgayIE(InfoExtractor):
   7     _VALID_URL = r'http://(?:www\.)?foxgay\.com/videos/(?:\S+-)?(?P<id>\d+)\.shtml'
   8     _TEST = {
   9         'url': 'http://foxgay.com/videos/fuck-turkish-style-2582.shtml',
  10         'md5': '80d72beab5d04e1655a56ad37afe6841',
  11         'info_dict': {
  12             'id': '2582',
  13             'ext': 'mp4',
  14             'title': 'md5:6122f7ae0fc6b21ebdf59c5e083ce25a',
  15             'description': 'md5:5e51dc4405f1fd315f7927daed2ce5cf',
  16             'age_limit': 18,
  17             'thumbnail': 're:https?://.*\.jpg$',
  18         },
  19     }
  20
  21     def _real_extract(self, url):
  22         video_id = self._match_id(url)
  23         webpage = self._download_webpage(url, video_id)
  24
  25         title = self._html_search_regex(
  26             r'<title>(?P<title>.*?)</title>',
  27             webpage, 'title', fatal=False)
  28         description = self._html_search_regex(
  29             r'<div class="ico_desc"><h2>(?P<description>.*?)</h2>',
  30             webpage, 'description', fatal=False)
  31
  32         # Find the URL for the iFrame which contains the actual video.
  33         iframe = self._download_webpage(
  34             self._html_search_regex(r'iframe src="(?P<frame>.*?)"', webpage, 'video frame'),
  35             video_id)
  36         video_url = self._html_search_regex(
  37             r"v_path = '(?P<vid>http://.*?)'", iframe, 'url')
  38         thumb_url = self._html_search_regex(
  39             r"t_path = '(?P<thumb>http://.*?)'", iframe, 'thumbnail', fatal=False)
  40
  41         return {
  42             'id': video_id,
  43             'title': title,
  44             'url': video_url,
  45             'description': description,
  46             'thumbnail': thumb_url,
  47             'age_limit': 18,
  48         }