_ 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         'info_dict': {
  12             'id': 'flug-mh370',
  13             'ext': 'm4v',
  14             'title': 'Flug MH370',
  15             'description': 'Das Rätsel um die Boeing 777 der Malaysia-Airlines',
  16         },
  17         'params': {
  18             # rtmp download
  19             'skip_download': True,
  20         }
  21     }
  22
  23     def _real_extract(self, url):
  24         mobj = re.match(self._VALID_URL, url)
  25         video_id = mobj.group('id')
  26
  27         webpage = self._download_webpage(url, video_id)
  28         title = self._html_search_regex(r'<h1.*?>(.*?)</h1>', webpage, 'title')
  29
  30         apihost           = 'http://spiegeltv-ivms2-restapi.s3.amazonaws.com';
  31
  32         version_json      = self._download_json('%s/version.json' % apihost, None)
  33         version_name      = version_json['version_name']
  34
  35         slug_json         = self._download_json('%s/%s/restapi/slugs/%s.json' % (apihost, version_name, video_id), None)
  36         oid               = slug_json['object_id']
  37
  38         media_json        = self._download_json('%s/%s/restapi/media/%s.json' % (apihost, version_name, oid), None)
  39         uuid              = media_json['uuid']
  40         is_wide           = media_json['is_wide']
  41
  42         server_json       = self._download_json('http://www.spiegel.tv/streaming_servers/', None)
  43         server            = server_json[0]['endpoint']
  44
  45         thumbnails = []
  46         for image in media_json['images']:
  47           thumbnails.append({'url': image['url'], 'resolution': str(image['width']) + 'x' + str(image['height']) })
  48
  49         description = media_json['subtitle']
  50         duration = int(round(media_json['duration_in_ms'] / 1000))
  51
  52         if is_wide:
  53           format = '16x9'
  54         else:
  55           format = '4x3'
  56
  57         url = server + 'mp4:' + uuid + '_spiegeltv_0500_' + format + '.m4v'
  58
  59         return_dict = {
  60             'id': video_id,
  61             'title': title,
  62             'url': url,
  63             'ext': 'm4v',
  64             'description': description,
  65             'duration': duration,
  66             'thumbnails': thumbnails
  67         }
  68         return return_dict