Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/xvideos.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 XVideosIE(InfoExtractor):
  12     _VALID_URL = r'^(?:https?://)?(?:www\.)?xvideos\.com/video([0-9]+)(?:.*)'
  13     _TEST = {
  14         'url': 'http://www.xvideos.com/video939581/funny_porns_by_s_-1',
  15         'file': '939581.flv',
  16         'md5': '1d0c835822f0a71a7bf011855db929d0',
  17         'info_dict': {
  18             "title": "Funny Porns By >>>>S<<<<<< -1",
  19             "age_limit": 18,
  20         }
  21     }
  22
  23     def _real_extract(self, url):
  24         mobj = re.match(self._VALID_URL, url)
  25         video_id = mobj.group(1)
  26
  27         webpage = self._download_webpage(url, video_id)
  28
  29         self.report_extraction(video_id)
  30
  31         # Extract video URL
  32         video_url = compat_urllib_parse.unquote(
  33             self._search_regex(r'flv_url=(.+?)&', webpage, 'video URL'))
  34
  35         # Extract title
  36         video_title = self._html_search_regex(
  37             r'<title>(.*?)\s+-\s+XVID', webpage, 'title')
  38
  39         # Extract video thumbnail
  40         video_thumbnail = self._search_regex(
  41             r'url_bigthumb=(.+?)&amp', webpage, 'thumbnail', fatal=False)
  42
  43         return {
  44             'id': video_id,
  45             'url': video_url,
  46             'uploader': None,
  47             'upload_date': None,
  48             'title': video_title,
  49             'ext': 'flv',
  50             'thumbnail': video_thumbnail,
  51             'description': None,
  52             'age_limit': 18,
  53         }