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

   1 import re
   2
   3 from .common import InfoExtractor
   4 from ..utils import (
   5     ExtractorError,
   6 )
   7
   8
   9 class YouJizzIE(InfoExtractor):
  10     _VALID_URL = r'^(?:https?://)?(?:\w+\.)?youjizz\.com/videos/(?P<videoid>[^.]+).html$'
  11
  12     def _real_extract(self, url):
  13         mobj = re.match(self._VALID_URL, url)
  14
  15         video_id = mobj.group('videoid')
  16
  17         # Get webpage content
  18         webpage = self._download_webpage(url, video_id)
  19
  20         # Get the video title
  21         video_title = self._html_search_regex(r'<title>(?P<title>.*)</title>',
  22             webpage, u'title').strip()
  23
  24         # Get the embed page
  25         result = re.search(r'https?://www.youjizz.com/videos/embed/(?P<videoid>[0-9]+)', webpage)
  26         if result is None:
  27             raise ExtractorError(u'ERROR: unable to extract embed page')
  28
  29         embed_page_url = result.group(0).strip()
  30         video_id = result.group('videoid')
  31
  32         webpage = self._download_webpage(embed_page_url, video_id)
  33
  34         # Get the video URL
  35         video_url = self._search_regex(r'so.addVariable\("file",encodeURIComponent\("(?P<source>[^"]+)"\)\);',
  36             webpage, u'video URL')
  37
  38         info = {'id': video_id,
  39                 'url': video_url,
  40                 'title': video_title,
  41                 'ext': 'flv',
  42                 'format': 'flv',
  43                 'player_url': embed_page_url}
  44
  45         return [info]