_ 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         # TODO more code goes here, for example ...
  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_code = urllib.urlopen('%s/version.json' % apihost).read()
  33         version_json      = json.loads(version_json_code)
  34         version_name      = version_json['version_name']
  35
  36         slug_json_code    = urllib.urlopen('%s/%s/restapi/slugs/%s.json' % (apihost, version_name, video_id)).read()
  37         slug_json         = json.loads(slug_json_code)
  38         oid               = slug_json['object_id']
  39
  40         media_json_code   = urllib.urlopen('%s/%s/restapi/media/%s.json' % (apihost, version_name, oid)).read()
  41         media_json        = json.loads(media_json_code)
  42
  43         uuid              = media_json['uuid']
  44         is_wide           = media_json['is_wide']
  45
  46         server_json_code  = urllib.urlopen('http://www.spiegel.tv/streaming_servers/').read()
  47         server_json       = json.loads(server_json_code)
  48         server            = server_json[0]['endpoint']
  49
  50         thumbnails = []
  51         for image in media_json['images']:
  52           thumbnails.append({'url': image['url'], 'resolution': str(image['width']) + 'x' + str(image['height']) })
  53
  54         description = media_json['subtitle']
  55         duration = int(round(media_json['duration_in_ms'] / 1000))
  56
  57         if is_wide:
  58           format = '16x9'
  59         else:
  60           format = '4x3'
  61
  62         url = server + 'mp4:' + uuid + '_spiegeltv_0500_' + format + '.m4v'
  63
  64         return_dict = {
  65             'id': video_id,
  66             'title': title,
  67             'url': url,
  68             'ext': 'm4v',
  69             'description': description,
  70             'duration': duration,
  71             'thumbnails': thumbnails
  72         }
  73         return return_dict