yt_dlp/extractor/spiegel.py

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