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     _TEST = {
  12         u'url': u'http://www.youjizz.com/videos/zeichentrick-1-2189178.html',
  13         u'file': u'2189178.flv',
  14         u'md5': u'07e15fa469ba384c7693fd246905547c',
  15         u'info_dict': {
  16             u"title": u"Zeichentrick 1",
  17             u"age_limit": 18,
  18         }
  19     }
  20
  21     def _real_extract(self, url):
  22         mobj = re.match(self._VALID_URL, url)
  23
  24         video_id = mobj.group('videoid')
  25
  26         # Get webpage content
  27         webpage = self._download_webpage(url, video_id)
  28
  29         age_limit = self._rta_search(webpage)
  30
  31         # Get the video title
  32         video_title = self._html_search_regex(r'<title>(?P<title>.*)</title>',
  33             webpage, u'title').strip()
  34
  35         # Get the embed page
  36         result = re.search(r'https?://www.youjizz.com/videos/embed/(?P<videoid>[0-9]+)', webpage)
  37         if result is None:
  38             raise ExtractorError(u'ERROR: unable to extract embed page')
  39
  40         embed_page_url = result.group(0).strip()
  41         video_id = result.group('videoid')
  42
  43         webpage = self._download_webpage(embed_page_url, video_id)
  44
  45         # Get the video URL
  46         m_playlist = re.search(r'so.addVariable\("playlist", ?"(?P<playlist>.+?)"\);', webpage)
  47         if m_playlist is not None:
  48             playlist_url = m_playlist.group('playlist')
  49             playlist_page = self._download_webpage(playlist_url, video_id,
  50                                                    u'Downloading playlist page')
  51             m_levels = list(re.finditer(r'<level bitrate="(\d+?)" file="(.*?)"', playlist_page))
  52             if len(m_levels) == 0:
  53                 raise ExtractorError(u'Unable to extract video url')
  54             videos = [(int(m.group(1)), m.group(2)) for m in m_levels]
  55             (_, video_url) = sorted(videos)[0]
  56             video_url = video_url.replace('%252F', '%2F')
  57         else:
  58             video_url = self._search_regex(r'so.addVariable\("file",encodeURIComponent\("(?P<source>[^"]+)"\)\);',
  59                                            webpage, u'video URL')
  60
  61         info = {'id': video_id,
  62                 'url': video_url,
  63                 'title': video_title,
  64                 'ext': 'flv',
  65                 'format': 'flv',
  66                 'player_url': embed_page_url,
  67                 'age_limit': age_limit}
  68
  69         return [info]