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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5 from .common import InfoExtractor
   6
   7 class SpiegeltvIE(InfoExtractor):
   8     _VALID_URL = r'https?://(?:www\.)?spiegel\.tv/filme/(?P<id>[\-a-z0-9]+)'
   9     _TEST = {
  10         'url': 'http://www.spiegel.tv/filme/flug-mh370/',
  11                                 'md5': '700d62dc485f3a81cf9d52144e5ead59',
  12         'info_dict': {
  13             'id': 'flug-mh370',
  14             'ext': 'm4v',
  15             'title': 'Flug MH370',
  16             'description': 'Das Rätsel um die Boeing 777 der Malaysia-Airlines',
  17         }
  18     }
  19
  20     def _real_extract(self, url):
  21         mobj = re.match(self._VALID_URL, url)
  22         video_id = mobj.group('id')
  23
  24         webpage = self._download_webpage(url, video_id)
  25         title = self._html_search_regex(r'<h1.*?>(.*?)</h1>', webpage, 'title')
  26
  27         apihost           = 'http://spiegeltv-ivms2-restapi.s3.amazonaws.com';
  28
  29         version_json      = self._download_json('%s/version.json' % apihost, None)
  30         version_name      = version_json['version_name']
  31
  32         slug_json         = self._download_json('%s/%s/restapi/slugs/%s.json' % (apihost, version_name, video_id), None)
  33         oid               = slug_json['object_id']
  34
  35         media_json        = self._download_json('%s/%s/restapi/media/%s.json' % (apihost, version_name, oid), None)
  36         uuid              = media_json['uuid']
  37         is_wide           = media_json['is_wide']
  38
  39         server_json       = self._download_json('http://www.spiegel.tv/streaming_servers/', None)
  40         server            = server_json[0]['endpoint']
  41
  42         thumbnails = []
  43         for image in media_json['images']:
  44           thumbnails.append({'url': image['url'], 'resolution': str(image['width']) + 'x' + str(image['height']) })
  45
  46         description = media_json['subtitle']
  47         duration = int(round(media_json['duration_in_ms'] / 1000))
  48
  49         if is_wide:
  50           format = '16x9'
  51         else:
  52           format = '4x3'
  53
  54         url = server + 'mp4:' + uuid + '_spiegeltv_0500_' + format + '.m4v'
  55
  56         return_dict = {
  57             'id': video_id,
  58             'title': title,
  59             'url': url,
  60             'ext': 'm4v',
  61             'description': description,
  62             'duration': duration,
  63             'thumbnails': thumbnails
  64         }
  65         return return_dict