_ Git - youtube-dl/blob - youtube_dl/extractor/vbox7.py

   1 # encoding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..utils import urlencode_postdata
   6
   7
   8 class Vbox7IE(InfoExtractor):
   9     _VALID_URL = r'https?://(?:www\.)?vbox7\.com/play:(?P<id>[^/]+)'
  10     _TESTS = [{
  11         'url': 'http://vbox7.com/play:0946fff23c',
  12         'md5': 'a60f9ab3a3a2f013ef9a967d5f7be5bf',
  13         'info_dict': {
  14             'id': '0946fff23c',
  15             'ext': 'mp4',
  16             'title': 'Борисов: Притеснен съм за бъдещето на България',
  17         },
  18     }, {
  19         'url': 'http://vbox7.com/play:249bb972c2',
  20         'md5': '99f65c0c9ef9b682b97313e052734c3f',
  21         'info_dict': {
  22             'id': '249bb972c2',
  23             'ext': 'mp4',
  24             'title': 'Смях! Чудо - чист за секунди - Скрита камера',
  25         },
  26         'skip': 'georestricted',
  27     }]
  28
  29     def _real_extract(self, url):
  30         video_id = self._match_id(url)
  31
  32         webpage = self._download_webpage(url, video_id)
  33
  34         title = self._html_search_regex(
  35             r'<title>(.*)</title>', webpage, 'title').split('/')[0].strip()
  36
  37         video_url = self._search_regex(
  38             r'src\s*:\s*(["\'])(?P<url>.+?.mp4.*?)\1',
  39             webpage, 'video url', default=None, group='url')
  40
  41         thumbnail_url = self._og_search_thumbnail(webpage)
  42
  43         if not video_url:
  44             info_response = self._download_webpage(
  45                 'http://vbox7.com/play/magare.do', video_id,
  46                 'Downloading info webpage',
  47                 data=urlencode_postdata({'as3': '1', 'vid': video_id}),
  48                 headers={'Content-Type': 'application/x-www-form-urlencoded'})
  49             final_url, thumbnail_url = map(
  50                 lambda x: x.split('=')[1], info_response.split('&'))
  51
  52         if '/na.mp4' in video_url:
  53             self.raise_geo_restricted()
  54
  55         return {
  56             'id': video_id,
  57             'url': self._proto_relative_url(video_url, 'http:'),
  58             'title': title,
  59             'thumbnail': thumbnail_url,
  60         }