youtube_dl/extractor/vbox7.py

   1 # encoding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..compat import compat_urlparse
   6 from ..utils import (
   7     ExtractorError,
   8     sanitized_Request,
   9     urlencode_postdata,
  10 )
  11
  12
  13 class Vbox7IE(InfoExtractor):
  14     _VALID_URL = r'https?://(?:www\.)?vbox7\.com/play:(?P<id>[^/]+)'
  15     _TESTS = [{
  16         'url': 'http://vbox7.com/play:0946fff23c',
  17         'md5': 'a60f9ab3a3a2f013ef9a967d5f7be5bf',
  18         'info_dict': {
  19             'id': '0946fff23c',
  20             'ext': 'mp4',
  21             'title': 'Борисов: Притеснен съм за бъдещето на България',
  22         },
  23     }, {
  24         'url': 'http://vbox7.com/play:249bb972c2',
  25         'md5': '99f65c0c9ef9b682b97313e052734c3f',
  26         'info_dict': {
  27             'id': '249bb972c2',
  28             'ext': 'mp4',
  29             'title': 'Смях! Чудо - чист за секунди - Скрита камера',
  30         },
  31         'skip': 'georestricted',
  32     }]
  33
  34     def _real_extract(self, url):
  35         video_id = self._match_id(url)
  36
  37         webpage = self._download_webpage(url, video_id)
  38
  39         title = self._html_search_regex(
  40             r'<title>(.*)</title>', webpage, 'title').split('/')[0].strip()
  41
  42         video_url = self._search_regex(
  43             r'src\s*:\s*(["\'])(?P<url>.+?.mp4.*?)\1',
  44             webpage, 'video url', default=None, group='url')
  45
  46         thumbnail_url = self._og_search_thumbnail(webpage)
  47
  48         if not video_url:
  49             info_response = self._download_webpage(
  50                 'http://vbox7.com/play/magare.do', video_id,
  51                 'Downloading info webpage',
  52                 data=urlencode_postdata({'as3': '1', 'vid': video_id}),
  53                 headers={'Content-Type': 'application/x-www-form-urlencoded'})
  54             final_url, thumbnail_url = map(
  55                 lambda x: x.split('=')[1], info_response.split('&'))
  56
  57         if '/na.mp4' in video_url:
  58             self.raise_geo_restricted()
  59
  60         return {
  61             'id': video_id,
  62             'url': self._proto_relative_url(video_url, 'http:'),
  63             'title': title,
  64             'thumbnail': thumbnail_url,
  65         }