youtube-dl

Another place where youtube-dl lives on
git clone git://git.oshgnacknak.de/youtube-dl.git
Log | Files | Refs | README | LICENSE

vbox7.py (3413B)

      1 # coding: utf-8
      2 from __future__ import unicode_literals
      3 
      4 import re
      5 
      6 from .common import InfoExtractor
      7 from ..utils import ExtractorError
      8 
      9 
     10 class Vbox7IE(InfoExtractor):
     11     _VALID_URL = r'''(?x)
     12                     https?://
     13                         (?:[^/]+\.)?vbox7\.com/
     14                         (?:
     15                             play:|
     16                             (?:
     17                                 emb/external\.php|
     18                                 player/ext\.swf
     19                             )\?.*?\bvid=
     20                         )
     21                         (?P<id>[\da-fA-F]+)
     22                     '''
     23     _GEO_COUNTRIES = ['BG']
     24     _TESTS = [{
     25         'url': 'http://vbox7.com/play:0946fff23c',
     26         'md5': 'a60f9ab3a3a2f013ef9a967d5f7be5bf',
     27         'info_dict': {
     28             'id': '0946fff23c',
     29             'ext': 'mp4',
     30             'title': 'Борисов: Притеснен съм за бъдещето на България',
     31             'description': 'По думите му е опасно страната ни да бъде обявена за "сигурна"',
     32             'thumbnail': r're:^https?://.*\.jpg$',
     33             'timestamp': 1470982814,
     34             'upload_date': '20160812',
     35             'uploader': 'zdraveibulgaria',
     36         },
     37         'params': {
     38             'proxy': '127.0.0.1:8118',
     39         },
     40     }, {
     41         'url': 'http://vbox7.com/play:249bb972c2',
     42         'md5': '99f65c0c9ef9b682b97313e052734c3f',
     43         'info_dict': {
     44             'id': '249bb972c2',
     45             'ext': 'mp4',
     46             'title': 'Смях! Чудо - чист за секунди - Скрита камера',
     47         },
     48         'skip': 'georestricted',
     49     }, {
     50         'url': 'http://vbox7.com/emb/external.php?vid=a240d20f9c&autoplay=1',
     51         'only_matching': True,
     52     }, {
     53         'url': 'http://i49.vbox7.com/player/ext.swf?vid=0946fff23c&autoplay=1',
     54         'only_matching': True,
     55     }]
     56 
     57     @staticmethod
     58     def _extract_url(webpage):
     59         mobj = re.search(
     60             r'<iframe[^>]+src=(?P<q>["\'])(?P<url>(?:https?:)?//vbox7\.com/emb/external\.php.+?)(?P=q)',
     61             webpage)
     62         if mobj:
     63             return mobj.group('url')
     64 
     65     def _real_extract(self, url):
     66         video_id = self._match_id(url)
     67 
     68         response = self._download_json(
     69             'https://www.vbox7.com/ajax/video/nextvideo.php?vid=%s' % video_id,
     70             video_id)
     71 
     72         if 'error' in response:
     73             raise ExtractorError(
     74                 '%s said: %s' % (self.IE_NAME, response['error']), expected=True)
     75 
     76         video = response['options']
     77 
     78         title = video['title']
     79         video_url = video['src']
     80 
     81         if '/na.mp4' in video_url:
     82             self.raise_geo_restricted(countries=self._GEO_COUNTRIES)
     83 
     84         uploader = video.get('uploader')
     85 
     86         webpage = self._download_webpage(
     87             'http://vbox7.com/play:%s' % video_id, video_id, fatal=None)
     88 
     89         info = {}
     90 
     91         if webpage:
     92             info = self._search_json_ld(
     93                 webpage.replace('"/*@context"', '"@context"'), video_id,
     94                 fatal=False)
     95 
     96         info.update({
     97             'id': video_id,
     98             'title': title,
     99             'url': video_url,
    100             'uploader': uploader,
    101             'thumbnail': self._proto_relative_url(
    102                 info.get('thumbnail') or self._og_search_thumbnail(webpage),
    103                 'http:'),
    104         })
    105         return info