Raphaël G. Git Repositories - youtubedl/blob - 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         'url': 'http://www.spiegel.tv/#/filme/alleskino-die-wahrheit-ueber-maenner/',
  25         'only_matching': True,
  26     }]
  27
  28     def _real_extract(self, url):
  29         if '/#/' in url:
  30             url = url.replace('/#/', '/')
  31         video_id = self._match_id(url)
  32         webpage = self._download_webpage(url, video_id)
  33         title = self._html_search_regex(r'<h1.*?>(.*?)</h1>', webpage, 'title')
  34
  35         apihost = 'http://spiegeltv-ivms2-restapi.s3.amazonaws.com'
  36         version_json = self._download_json(
  37             '%s/version.json' % apihost, video_id,
  38             note='Downloading version information')
  39         version_name = version_json['version_name']
  40
  41         slug_json = self._download_json(
  42             '%s/%s/restapi/slugs/%s.json' % (apihost, version_name, video_id),
  43             video_id,
  44             note='Downloading object information')
  45         oid = slug_json['object_id']
  46
  47         media_json = self._download_json(
  48             '%s/%s/restapi/media/%s.json' % (apihost, version_name, oid),
  49             video_id, note='Downloading media information')
  50         uuid = media_json['uuid']
  51         is_wide = media_json['is_wide']
  52
  53         server_json = self._download_json(
  54             'http://spiegeltv-prod-static.s3.amazonaws.com/projectConfigs/projectConfig.json',
  55             video_id, note='Downloading server information')
  56         server = server_json['streamingserver'][0]['endpoint']
  57
  58         thumbnails = []
  59         for image in media_json['images']:
  60             thumbnails.append({
  61                 'url': image['url'],
  62                 'width': image['width'],
  63                 'height': image['height'],
  64             })
  65
  66         description = media_json['subtitle']
  67         duration = float_or_none(media_json.get('duration_in_ms'), scale=1000)
  68         format = '16x9' if is_wide else '4x3'
  69
  70         url = server + 'mp4:' + uuid + '_spiegeltv_0500_' + format + '.m4v'
  71
  72         return {
  73             'id': video_id,
  74             'title': title,
  75             'url': url,
  76             'ext': 'm4v',
  77             'description': description,
  78             'duration': duration,
  79             'thumbnails': thumbnails,
  80             'rtmp_live': True,
  81         }