youtube_dl/extractor/xvideos.py

   1 import re
   2
   3 from .common import InfoExtractor
   4 from ..utils import (
   5     compat_urllib_parse,
   6 )
   7
   8
   9 class XVideosIE(InfoExtractor):
  10     _VALID_URL = r'^(?:https?://)?(?:www\.)?xvideos\.com/video([0-9]+)(?:.*)'
  11     _TEST = {
  12         u'url': u'http://www.xvideos.com/video939581/funny_porns_by_s_-1',
  13         u'file': u'939581.flv',
  14         u'md5': u'1d0c835822f0a71a7bf011855db929d0',
  15         u'info_dict': {
  16             u"title": u"Funny Porns By >>>>S<<<<<< -1",
  17             u"age_limit": 18,
  18         }
  19     }
  20
  21     def _real_extract(self, url):
  22         mobj = re.match(self._VALID_URL, url)
  23         video_id = mobj.group(1)
  24
  25         webpage = self._download_webpage(url, video_id)
  26
  27         self.report_extraction(video_id)
  28
  29         # Extract video URL
  30         video_url = compat_urllib_parse.unquote(self._search_regex(r'flv_url=(.+?)&',
  31             webpage, u'video URL'))
  32
  33         # Extract title
  34         video_title = self._html_search_regex(r'<title>(.*?)\s+-\s+XVID',
  35             webpage, u'title')
  36
  37         # Extract video thumbnail
  38         video_thumbnail = self._search_regex(r'http://(?:img.*?\.)xvideos.com/videos/thumbs/[a-fA-F0-9]+/[a-fA-F0-9]+/[a-fA-F0-9]+/[a-fA-F0-9]+/([a-fA-F0-9.]+jpg)',
  39             webpage, u'thumbnail', fatal=False)
  40
  41         info = {
  42             'id': video_id,
  43             'url': video_url,
  44             'uploader': None,
  45             'upload_date': None,
  46             'title': video_title,
  47             'ext': 'flv',
  48             'thumbnail': video_thumbnail,
  49             'description': None,
  50             'age_limit': 18,
  51         }
  52
  53         return [info]