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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..compat import compat_urllib_parse_unquote
   6
   7
   8 class XNXXIE(InfoExtractor):
   9     _VALID_URL = r'https?://(?:video|www)\.xnxx\.com/video-?(?P<id>[0-9a-z]+)/'
  10     _TESTS = [{
  11         'url': 'http://www.xnxx.com/video-55awb78/skyrim_test_video',
  12         'md5': 'ef7ecee5af78f8b03dca2cf31341d3a0',
  13         'info_dict': {
  14             'id': '55awb78',
  15             'ext': 'flv',
  16             'title': 'Skyrim Test Video',
  17             'age_limit': 18,
  18         },
  19     }, {
  20         'url': 'http://video.xnxx.com/video1135332/lida_naked_funny_actress_5_',
  21         'only_matching': True,
  22     }, {
  23         'url': 'http://www.xnxx.com/video-55awb78/',
  24         'only_matching': True,
  25     }]
  26
  27     def _real_extract(self, url):
  28         video_id = self._match_id(url)
  29         webpage = self._download_webpage(url, video_id)
  30
  31         video_url = self._search_regex(r'flv_url=(.*?)&amp;',
  32                                        webpage, 'video URL')
  33         video_url = compat_urllib_parse_unquote(video_url)
  34
  35         video_title = self._html_search_regex(r'<title>(.*?)\s+-\s+XNXX.COM',
  36                                               webpage, 'title')
  37
  38         video_thumbnail = self._search_regex(r'url_bigthumb=(.*?)&amp;',
  39                                              webpage, 'thumbnail', fatal=False)
  40
  41         return {
  42             'id': video_id,
  43             'url': video_url,
  44             'title': video_title,
  45             'ext': 'flv',
  46             'thumbnail': video_thumbnail,
  47             'age_limit': 18,
  48         }