youtube_dl/extractor/spiegeltv.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..utils import float_or_none
   6
   7
   8 class SpiegeltvIE(InfoExtractor):
   9     _VALID_URL = r'https?://(?:www\.)?spiegel\.tv/filme/(?P<id>[\-a-z0-9]+)'
  10     _TESTS = [{
  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         video_id = self._match_id(url)
  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         version_json = self._download_json(
  32             '%s/version.json' % apihost, video_id,
  33             note='Downloading version information')
  34         version_name = version_json['version_name']
  35
  36         slug_json = self._download_json(
  37             '%s/%s/restapi/slugs/%s.json' % (apihost, version_name, video_id),
  38             video_id,
  39             note='Downloading object information')
  40         oid = slug_json['object_id']
  41
  42         media_json = self._download_json(
  43             '%s/%s/restapi/media/%s.json' % (apihost, version_name, oid),
  44             video_id, note='Downloading media information')
  45         uuid = media_json['uuid']
  46         is_wide = media_json['is_wide']
  47
  48         server_json = self._download_json(
  49             'http://www.spiegel.tv/streaming_servers/', video_id,
  50             note='Downloading server information')
  51         server = server_json[0]['endpoint']
  52
  53         thumbnails = []
  54         for image in media_json['images']:
  55             thumbnails.append({
  56                 'url': image['url'],
  57                 'width': image['width'],
  58                 'height': image['height'],
  59             })
  60
  61         description = media_json['subtitle']
  62         duration = float_or_none(media_json.get('duration_in_ms'), scale=1000)
  63         format = '16x9' if is_wide else '4x3'
  64
  65         url = server + 'mp4:' + uuid + '_spiegeltv_0500_' + format + '.m4v'
  66
  67         return {
  68             'id': video_id,
  69             'title': title,
  70             'url': url,
  71             'ext': 'm4v',
  72             'description': description,
  73             'duration': duration,
  74             'thumbnails': thumbnails
  75         }