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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5 import json
   6 import urllib
   7 from .common import InfoExtractor
   8
   9 class SpiegeltvIE(InfoExtractor):
  10     _VALID_URL = r'https?://(?:www\.)?spiegel\.tv/filme/(?P<id>[\-a-z0-9]+)'
  11     _TEST = {
  12         'url': 'http://www.spiegel.tv/filme/flug-mh370/',
  13                                 'md5': '700d62dc485f3a81cf9d52144e5ead59',
  14         'info_dict': {
  15             'id': 'flug-mh370',
  16             'ext': 'm4v',
  17             'title': 'Flug MH370',
  18             'description': 'Das Rätsel um die Boeing 777 der Malaysia-Airlines',
  19         }
  20     }
  21
  22     def _real_extract(self, url):
  23         mobj = re.match(self._VALID_URL, url)
  24         video_id = mobj.group('id')
  25
  26         webpage = self._download_webpage(url, video_id)
  27         title = self._html_search_regex(r'<h1.*?>(.*?)</h1>', webpage, 'title')
  28
  29         apihost           = 'http://spiegeltv-ivms2-restapi.s3.amazonaws.com';
  30
  31         version_json_code = urllib.urlopen('%s/version.json' % apihost).read()
  32         version_json      = json.loads(version_json_code)
  33         version_name      = version_json['version_name']
  34
  35         slug_json_code    = urllib.urlopen('%s/%s/restapi/slugs/%s.json' % (apihost, version_name, video_id)).read()
  36         slug_json         = json.loads(slug_json_code)
  37         oid               = slug_json['object_id']
  38
  39         media_json_code   = urllib.urlopen('%s/%s/restapi/media/%s.json' % (apihost, version_name, oid)).read()
  40         media_json        = json.loads(media_json_code)
  41
  42         uuid              = media_json['uuid']
  43         is_wide           = media_json['is_wide']
  44
  45         server_json_code  = urllib.urlopen('http://www.spiegel.tv/streaming_servers/').read()
  46         server_json       = json.loads(server_json_code)
  47         server            = server_json[0]['endpoint']
  48
  49         thumbnails = []
  50         for image in media_json['images']:
  51           thumbnails.append({'url': image['url'], 'resolution': str(image['width']) + 'x' + str(image['height']) })
  52
  53         description = media_json['subtitle']
  54         duration = int(round(media_json['duration_in_ms'] / 1000))
  55
  56         if is_wide:
  57           format = '16x9'
  58         else:
  59           format = '4x3'
  60
  61         url = server + 'mp4:' + uuid + '_spiegeltv_0500_' + format + '.m4v'
  62
  63         return_dict = {
  64             'id': video_id,
  65             'title': title,
  66             'url': url,
  67             'ext': 'm4v',
  68             'description': description,
  69             'duration': duration,
  70             'thumbnails': thumbnails
  71         }
  72         return return_dict