yt_dlp/extractor/gamestar.py

   1 from .common import InfoExtractor
   2 from ..utils import (
   3     int_or_none,
   4     remove_end,
   5 )
   6
   7
   8 class GameStarIE(InfoExtractor):
   9     _VALID_URL = r'https?://(?:www\.)?game(?P<site>pro|star)\.de/videos/.*,(?P<id>[0-9]+)\.html'
  10     _TESTS = [{
  11         'url': 'http://www.gamestar.de/videos/trailer,3/hobbit-3-die-schlacht-der-fuenf-heere,76110.html',
  12         'md5': 'ee782f1f8050448c95c5cacd63bc851c',
  13         'info_dict': {
  14             'id': '76110',
  15             'ext': 'mp4',
  16             'title': 'Hobbit 3: Die Schlacht der Fünf Heere - Teaser-Trailer zum dritten Teil',
  17             'description': 'Der Teaser-Trailer zu Hobbit 3: Die Schlacht der Fünf Heere zeigt einige Szenen aus dem dritten Teil der Saga und kündigt den...',
  18             'thumbnail': r're:^https?://.*\.jpg$',
  19             'timestamp': 1406542380,
  20             'upload_date': '20140728',
  21             'duration': 17,
  22         },
  23     }, {
  24         'url': 'http://www.gamepro.de/videos/top-10-indie-spiele-fuer-nintendo-switch-video-tolle-nindies-games-zum-download,95316.html',
  25         'only_matching': True,
  26     }, {
  27         'url': 'http://www.gamestar.de/videos/top-10-indie-spiele-fuer-nintendo-switch-video-tolle-nindies-games-zum-download,95316.html',
  28         'only_matching': True,
  29     }]
  30
  31     def _real_extract(self, url):
  32         mobj = self._match_valid_url(url)
  33         site = mobj.group('site')
  34         video_id = mobj.group('id')
  35
  36         webpage = self._download_webpage(url, video_id)
  37
  38         # TODO: there are multiple ld+json objects in the webpage,
  39         # while _search_json_ld finds only the first one
  40         json_ld = self._parse_json(self._search_regex(
  41             r'(?s)<script[^>]+type=(["\'])application/ld\+json\1[^>]*>(?P<json_ld>[^<]+VideoObject[^<]+)</script>',
  42             webpage, 'JSON-LD', group='json_ld'), video_id)
  43         info_dict = self._json_ld(json_ld, video_id)
  44         info_dict['title'] = remove_end(
  45             info_dict['title'], f' - Game{site.title()}')
  46
  47         view_count = int_or_none(json_ld.get('interactionCount'))
  48         comment_count = int_or_none(self._html_search_regex(
  49             r'<span>Kommentare</span>\s*<span[^>]+class=["\']count[^>]+>\s*\(\s*([0-9]+)',
  50             webpage, 'comment count', fatal=False))
  51
  52         info_dict.update({
  53             'id': video_id,
  54             'url': 'http://gamestar.de/_misc/videos/portal/getVideoUrl.cfm?premium=0&videoId=' + video_id,
  55             'ext': 'mp4',
  56             'view_count': view_count,
  57             'comment_count': comment_count,
  58         })
  59
  60         return info_dict