Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/vbox7.py

   1 # encoding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..utils import urlencode_postdata
   8
   9
  10 class Vbox7IE(InfoExtractor):
  11     _VALID_URL = r'https?://(?:www\.)?vbox7\.com/(?:play:|emb/external\.php\?.*?\bvid=)(?P<id>[\da-fA-F]+)'
  12     _TESTS = [{
  13         'url': 'http://vbox7.com/play:0946fff23c',
  14         'md5': 'a60f9ab3a3a2f013ef9a967d5f7be5bf',
  15         'info_dict': {
  16             'id': '0946fff23c',
  17             'ext': 'mp4',
  18             'title': 'Борисов: Притеснен съм за бъдещето на България',
  19         },
  20     }, {
  21         'url': 'http://vbox7.com/play:249bb972c2',
  22         'md5': '99f65c0c9ef9b682b97313e052734c3f',
  23         'info_dict': {
  24             'id': '249bb972c2',
  25             'ext': 'mp4',
  26             'title': 'Смях! Чудо - чист за секунди - Скрита камера',
  27         },
  28         'skip': 'georestricted',
  29     }, {
  30         'url': 'http://vbox7.com/emb/external.php?vid=a240d20f9c&autoplay=1',
  31         'only_matching': True,
  32     }]
  33
  34     @staticmethod
  35     def _extract_url(webpage):
  36         mobj = re.search(
  37             '<iframe[^>]+src=(?P<q>["\'])(?P<url>(?:https?:)?//vbox7\.com/emb/external\.php.+?)(?P=q)',
  38             webpage)
  39         if mobj:
  40             return mobj.group('url')
  41
  42     def _real_extract(self, url):
  43         video_id = self._match_id(url)
  44
  45         webpage = self._download_webpage(
  46             'http://vbox7.com/play:%s' % video_id, video_id)
  47
  48         title = self._html_search_regex(
  49             r'<title>(.+?)</title>', webpage, 'title').split('/')[0].strip()
  50
  51         video_url = self._search_regex(
  52             r'src\s*:\s*(["\'])(?P<url>.+?.mp4.*?)\1',
  53             webpage, 'video url', default=None, group='url')
  54
  55         thumbnail_url = self._og_search_thumbnail(webpage)
  56
  57         if not video_url:
  58             info_response = self._download_webpage(
  59                 'http://vbox7.com/play/magare.do', video_id,
  60                 'Downloading info webpage',
  61                 data=urlencode_postdata({'as3': '1', 'vid': video_id}),
  62                 headers={'Content-Type': 'application/x-www-form-urlencoded'})
  63             final_url, thumbnail_url = map(
  64                 lambda x: x.split('=')[1], info_response.split('&'))
  65
  66         if '/na.mp4' in video_url:
  67             self.raise_geo_restricted()
  68
  69         return {
  70             'id': video_id,
  71             'url': self._proto_relative_url(video_url, 'http:'),
  72             'title': title,
  73             'thumbnail': thumbnail_url,
  74         }