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
   8 class SpiegeltvIE(InfoExtractor):
   9     _VALID_URL = r'https?://(?:www\.)?spiegel\.tv/filme/(?P<id>[\-a-z0-9]+)'
  10     _TEST = {
  11         'url': 'http://www.spiegel.tv/filme/flug-mh370/',
  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             'thumbnail': 're:http://.*\.jpg$',
  18         },
  19         'params': {
  20             # rtmp download
  21             'skip_download': True,
  22         }
  23     }
  24
  25     def _real_extract(self, url):
  26         mobj = re.match(self._VALID_URL, url)
  27         video_id = mobj.group('id')
  28
  29         webpage = self._download_webpage(url, video_id)
  30         title = self._html_search_regex(r'<h1.*?>(.*?)</h1>', webpage, 'title')
  31
  32         apihost = 'http://spiegeltv-ivms2-restapi.s3.amazonaws.com'
  33         version_json = self._download_json(
  34             '%s/version.json' % apihost, video_id,
  35             note='Downloading version information')
  36         version_name = version_json['version_name']
  37
  38         slug_json = self._download_json(
  39             '%s/%s/restapi/slugs/%s.json' % (apihost, version_name, video_id),
  40             video_id,
  41             note='Downloading object information')
  42         oid = slug_json['object_id']
  43
  44         media_json = self._download_json(
  45             '%s/%s/restapi/media/%s.json' % (apihost, version_name, oid),
  46             video_id, note='Downloading media information')
  47         uuid = media_json['uuid']
  48         is_wide = media_json['is_wide']
  49
  50         server_json = self._download_json(
  51             'http://www.spiegel.tv/streaming_servers/', video_id,
  52             note='Downloading server information')
  53         server = server_json[0]['endpoint']
  54
  55         thumbnails = []
  56         for image in media_json['images']:
  57             thumbnails.append({
  58                 'url': image['url'],
  59                 'width': image['width'],
  60                 'height': image['height'],
  61             })
  62
  63         description = media_json['subtitle']
  64         duration = media_json['duration_in_ms'] / 1000.
  65
  66         if is_wide:
  67             format = '16x9'
  68         else:
  69             format = '4x3'
  70
  71         url = server + 'mp4:' + uuid + '_spiegeltv_0500_' + format + '.m4v'
  72
  73         return {
  74             'id': video_id,
  75             'title': title,
  76             'url': url,
  77             'ext': 'm4v',
  78             'description': description,
  79             'duration': duration,
  80             'thumbnails': thumbnails
  81         }