yt_dlp/extractor/gamespot.py

   1 from .once import OnceIE
   2 from ..compat import compat_urllib_parse_unquote
   3
   4
   5 class GameSpotIE(OnceIE):
   6     _VALID_URL = r'https?://(?:www\.)?gamespot\.com/(?:video|article|review)s/(?:[^/]+/\d+-|embed/)(?P<id>\d+)'
   7     _TESTS = [{
   8         'url': 'http://www.gamespot.com/videos/arma-3-community-guide-sitrep-i/2300-6410818/',
   9         'md5': 'b2a30deaa8654fcccd43713a6b6a4825',
  10         'info_dict': {
  11             'id': 'gs-2300-6410818',
  12             'ext': 'mp4',
  13             'title': 'Arma 3 - Community Guide: SITREP I',
  14             'description': 'Check out this video where some of the basics of Arma 3 is explained.',
  15         },
  16         'skip': 'manifest URL give HTTP Error 404: Not Found',
  17     }, {
  18         'url': 'http://www.gamespot.com/videos/the-witcher-3-wild-hunt-xbox-one-now-playing/2300-6424837/',
  19         'md5': '173ea87ad762cf5d3bf6163dceb255a6',
  20         'info_dict': {
  21             'id': 'gs-2300-6424837',
  22             'ext': 'mp4',
  23             'title': 'Now Playing - The Witcher 3: Wild Hunt',
  24             'description': 'Join us as we take a look at the early hours of The Witcher 3: Wild Hunt and more.',
  25         },
  26     }, {
  27         'url': 'https://www.gamespot.com/videos/embed/6439218/',
  28         'only_matching': True,
  29     }, {
  30         'url': 'https://www.gamespot.com/articles/the-last-of-us-2-receives-new-ps4-trailer/1100-6454469/',
  31         'only_matching': True,
  32     }, {
  33         'url': 'https://www.gamespot.com/reviews/gears-of-war-review/1900-6161188/',
  34         'only_matching': True,
  35     }]
  36
  37     def _real_extract(self, url):
  38         page_id = self._match_id(url)
  39         webpage = self._download_webpage(url, page_id)
  40         data_video = self._parse_json(self._html_search_regex(
  41             r'data-video=(["\'])({.*?})\1', webpage,
  42             'video data', group=2), page_id)
  43         title = compat_urllib_parse_unquote(data_video['title'])
  44         streams = data_video['videoStreams']
  45         formats = []
  46
  47         m3u8_url = streams.get('adaptive_stream')
  48         if m3u8_url:
  49             m3u8_formats = self._extract_m3u8_formats(
  50                 m3u8_url, page_id, 'mp4', 'm3u8_native',
  51                 m3u8_id='hls', fatal=False)
  52             for f in m3u8_formats:
  53                 formats.append(f)
  54                 http_f = f.copy()
  55                 del http_f['manifest_url']
  56                 http_f.update({
  57                     'format_id': f['format_id'].replace('hls-', 'http-'),
  58                     'protocol': 'http',
  59                     'url': f['url'].replace('.m3u8', '.mp4'),
  60                 })
  61                 formats.append(http_f)
  62
  63         mpd_url = streams.get('adaptive_dash')
  64         if mpd_url:
  65             formats.extend(self._extract_mpd_formats(
  66                 mpd_url, page_id, mpd_id='dash', fatal=False))
  67
  68         return {
  69             'id': data_video.get('guid') or page_id,
  70             'display_id': page_id,
  71             'title': title,
  72             'formats': formats,
  73             'description': self._html_search_meta('description', webpage),
  74             'thumbnail': self._og_search_thumbnail(webpage),
  75         }