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