yt_dlp/extractor/spiegel.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from .jwplatform import JWPlatformIE
   6
   7
   8 class SpiegelIE(InfoExtractor):
   9     _UUID_RE = r'[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12}'
  10     _VALID_URL = r'https?://(?:www\.)?(?:spiegel|manager-magazin)\.de(?:/[^/]+)+/[^/]*-(?P<id>[0-9]+|%s)(?:-embed|-iframe)?(?:\.html)?(?:#.*)?$' % _UUID_RE
  11     _TESTS = [{
  12         'url': 'http://www.spiegel.de/video/vulkan-tungurahua-in-ecuador-ist-wieder-aktiv-video-1259285.html',
  13         'md5': '50c7948883ec85a3e431a0a44b7ad1d6',
  14         'info_dict': {
  15             'id': 'II0BUyxY',
  16             'display_id': '1259285',
  17             'ext': 'mp4',
  18             'title': 'Vulkan Tungurahua in Ecuador ist wieder aktiv - DER SPIEGEL - Wissenschaft',
  19             'description': 'md5:8029d8310232196eb235d27575a8b9f4',
  20             'duration': 48.0,
  21             'upload_date': '20130311',
  22             'timestamp': 1362997920,
  23         },
  24     }, {
  25         'url': 'http://www.spiegel.de/video/schach-wm-videoanalyse-des-fuenften-spiels-video-1309159.html',
  26         'only_matching': True,
  27     }, {
  28         'url': 'https://www.spiegel.de/video/eifel-zoo-aufregung-um-ausgebrochene-raubtiere-video-99018031.html',
  29         'only_matching': True,
  30     }, {
  31         'url': 'https://www.spiegel.de/panorama/urteile-im-goldmuenzenprozess-haftstrafen-fuer-clanmitglieder-a-aae8df48-43c1-4c61-867d-23f0a2d254b7',
  32         'only_matching': True,
  33     }, {
  34         'url': 'http://www.spiegel.de/video/spiegel-tv-magazin-ueber-guellekrise-in-schleswig-holstein-video-99012776.html',
  35         'only_matching': True,
  36     }, {
  37         'url': 'http://www.spiegel.de/sport/sonst/badminton-wm-die-randsportart-soll-populaerer-werden-a-987092.html',
  38         'only_matching': True,
  39     }]
  40
  41     def _real_extract(self, url):
  42         video_id = self._match_id(url)
  43         webpage = self._download_webpage(url, video_id)
  44         media_id = self._html_search_regex(
  45             r'(&#34;|["\'])mediaId\1\s*:\s*(&#34;|["\'])(?P<id>(?:(?!\2).)+)\2',
  46             webpage, 'media id', group='id')
  47         return {
  48             '_type': 'url_transparent',
  49             'id': video_id,
  50             'display_id': video_id,
  51             'url': 'jwplatform:%s' % media_id,
  52             'title': self._og_search_title(webpage, default=None),
  53             'ie_key': JWPlatformIE.ie_key(),
  54         }