yt_dlp/extractor/gamespot.py

   1 import urllib.parse
   2
   3 from .once import OnceIE
   4
   5
   6 class GameSpotIE(OnceIE):
   7     _VALID_URL = r'https?://(?:www\.)?gamespot\.com/(?:video|article|review)s/(?:[^/]+/\d+-|embed/)(?P<id>\d+)'
   8     _TESTS = [{
   9         'url': 'http://www.gamespot.com/videos/arma-3-community-guide-sitrep-i/2300-6410818/',
  10         'md5': 'b2a30deaa8654fcccd43713a6b6a4825',
  11         'info_dict': {
  12             'id': 'gs-2300-6410818',
  13             'ext': 'mp4',
  14             'title': 'Arma 3 - Community Guide: SITREP I',
  15             'description': 'Check out this video where some of the basics of Arma 3 is explained.',
  16         },
  17         'skip': 'manifest URL give HTTP Error 404: Not Found',
  18     }, {
  19         'url': 'http://www.gamespot.com/videos/the-witcher-3-wild-hunt-xbox-one-now-playing/2300-6424837/',
  20         'md5': '173ea87ad762cf5d3bf6163dceb255a6',
  21         'info_dict': {
  22             'id': 'gs-2300-6424837',
  23             'ext': 'mp4',
  24             'title': 'Now Playing - The Witcher 3: Wild Hunt',
  25             'description': 'Join us as we take a look at the early hours of The Witcher 3: Wild Hunt and more.',
  26         },
  27     }, {
  28         'url': 'https://www.gamespot.com/videos/embed/6439218/',
  29         'only_matching': True,
  30     }, {
  31         'url': 'https://www.gamespot.com/articles/the-last-of-us-2-receives-new-ps4-trailer/1100-6454469/',
  32         'only_matching': True,
  33     }, {
  34         'url': 'https://www.gamespot.com/reviews/gears-of-war-review/1900-6161188/',
  35         'only_matching': True,
  36     }]
  37
  38     def _real_extract(self, url):
  39         page_id = self._match_id(url)
  40         webpage = self._download_webpage(url, page_id)
  41         data_video = self._parse_json(self._html_search_regex(
  42             r'data-video=(["\'])({.*?})\1', webpage,
  43             'video data', group=2), page_id)
  44         title = urllib.parse.unquote(data_video['title'])
  45         streams = data_video['videoStreams']
  46         formats = []
  47
  48         m3u8_url = streams.get('adaptive_stream')
  49         if m3u8_url:
  50             m3u8_formats = self._extract_m3u8_formats(
  51                 m3u8_url, page_id, 'mp4', 'm3u8_native',
  52                 m3u8_id='hls', fatal=False)
  53             for f in m3u8_formats:
  54                 formats.append(f)
  55                 http_f = f.copy()
  56                 del http_f['manifest_url']
  57                 http_f.update({
  58                     'format_id': f['format_id'].replace('hls-', 'http-'),
  59                     'protocol': 'http',
  60                     'url': f['url'].replace('.m3u8', '.mp4'),
  61                 })
  62                 formats.append(http_f)
  63
  64         mpd_url = streams.get('adaptive_dash')
  65         if mpd_url:
  66             formats.extend(self._extract_mpd_formats(
  67                 mpd_url, page_id, mpd_id='dash', fatal=False))
  68
  69         return {
  70             'id': data_video.get('guid') or page_id,
  71             'display_id': page_id,
  72             'title': title,
  73             'formats': formats,
  74             'description': self._html_search_meta('description', webpage),
  75             'thumbnail': self._og_search_thumbnail(webpage),
  76         }