youtube_dl/extractor/youjizz.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..utils import (
   7     ExtractorError,
   8 )
   9
  10
  11 class YouJizzIE(InfoExtractor):
  12     _VALID_URL = r'^(?:https?://)?(?:\w+\.)?youjizz\.com/videos/(?P<videoid>[^.]+)\.html$'
  13     _TEST = {
  14         'url': 'http://www.youjizz.com/videos/zeichentrick-1-2189178.html',
  15         'file': '2189178.flv',
  16         'md5': '07e15fa469ba384c7693fd246905547c',
  17         'info_dict': {
  18             "title": "Zeichentrick 1",
  19             "age_limit": 18,
  20         }
  21     }
  22
  23     def _real_extract(self, url):
  24         mobj = re.match(self._VALID_URL, url)
  25
  26         video_id = mobj.group('videoid')
  27
  28         # Get webpage content
  29         webpage = self._download_webpage(url, video_id)
  30
  31         age_limit = self._rta_search(webpage)
  32
  33         # Get the video title
  34         video_title = self._html_search_regex(r'<title>(?P<title>.*)</title>',
  35             webpage, 'title').strip()
  36
  37         # Get the embed page
  38         result = re.search(r'https?://www.youjizz.com/videos/embed/(?P<videoid>[0-9]+)', webpage)
  39         if result is None:
  40             raise ExtractorError('ERROR: unable to extract embed page')
  41
  42         embed_page_url = result.group(0).strip()
  43         video_id = result.group('videoid')
  44
  45         webpage = self._download_webpage(embed_page_url, video_id)
  46
  47         # Get the video URL
  48         m_playlist = re.search(r'so.addVariable\("playlist", ?"(?P<playlist>.+?)"\);', webpage)
  49         if m_playlist is not None:
  50             playlist_url = m_playlist.group('playlist')
  51             playlist_page = self._download_webpage(playlist_url, video_id,
  52                                                    'Downloading playlist page')
  53             m_levels = list(re.finditer(r'<level bitrate="(\d+?)" file="(.*?)"', playlist_page))
  54             if len(m_levels) == 0:
  55                 raise ExtractorError('Unable to extract video url')
  56             videos = [(int(m.group(1)), m.group(2)) for m in m_levels]
  57             (_, video_url) = sorted(videos)[0]
  58             video_url = video_url.replace('%252F', '%2F')
  59         else:
  60             video_url = self._search_regex(r'so.addVariable\("file",encodeURIComponent\("(?P<source>[^"]+)"\)\);',
  61                                            webpage, 'video URL')
  62
  63         return {
  64             'id': video_id,
  65             'url': video_url,
  66             'title': video_title,
  67             'ext': 'flv',
  68             'format': 'flv',
  69             'player_url': embed_page_url,
  70             'age_limit': age_limit,
  71         }