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