youtube_dlc/extractor/gamespot.py

   1 from __future__ import unicode_literals
   2
   3 from .once import OnceIE
   4 from ..compat import compat_urllib_parse_unquote
   5
   6
   7 class GameSpotIE(OnceIE):
   8     _VALID_URL = r'https?://(?:www\.)?gamespot\.com/(?:video|article|review)s/(?:[^/]+/\d+-|embed/)(?P<id>\d+)'
   9     _TESTS = [{
  10         'url': 'http://www.gamespot.com/videos/arma-3-community-guide-sitrep-i/2300-6410818/',
  11         'md5': 'b2a30deaa8654fcccd43713a6b6a4825',
  12         'info_dict': {
  13             'id': 'gs-2300-6410818',
  14             'ext': 'mp4',
  15             'title': 'Arma 3 - Community Guide: SITREP I',
  16             'description': 'Check out this video where some of the basics of Arma 3 is explained.',
  17         },
  18         'skip': 'manifest URL give HTTP Error 404: Not Found',
  19     }, {
  20         'url': 'http://www.gamespot.com/videos/the-witcher-3-wild-hunt-xbox-one-now-playing/2300-6424837/',
  21         'md5': '173ea87ad762cf5d3bf6163dceb255a6',
  22         'info_dict': {
  23             'id': 'gs-2300-6424837',
  24             'ext': 'mp4',
  25             'title': 'Now Playing - The Witcher 3: Wild Hunt',
  26             'description': 'Join us as we take a look at the early hours of The Witcher 3: Wild Hunt and more.',
  27         },
  28     }, {
  29         'url': 'https://www.gamespot.com/videos/embed/6439218/',
  30         'only_matching': True,
  31     }, {
  32         'url': 'https://www.gamespot.com/articles/the-last-of-us-2-receives-new-ps4-trailer/1100-6454469/',
  33         'only_matching': True,
  34     }, {
  35         'url': 'https://www.gamespot.com/reviews/gears-of-war-review/1900-6161188/',
  36         'only_matching': True,
  37     }]
  38
  39     def _real_extract(self, url):
  40         page_id = self._match_id(url)
  41         webpage = self._download_webpage(url, page_id)
  42         data_video = self._parse_json(self._html_search_regex(
  43             r'data-video=(["\'])({.*?})\1', webpage,
  44             'video data', group=2), page_id)
  45         title = compat_urllib_parse_unquote(data_video['title'])
  46         streams = data_video['videoStreams']
  47         formats = []
  48
  49         m3u8_url = streams.get('adaptive_stream')
  50         if m3u8_url:
  51             m3u8_formats = self._extract_m3u8_formats(
  52                 m3u8_url, page_id, 'mp4', 'm3u8_native',
  53                 m3u8_id='hls', fatal=False)
  54             for f in m3u8_formats:
  55                 formats.append(f)
  56                 http_f = f.copy()
  57                 del http_f['manifest_url']
  58                 http_f.update({
  59                     'format_id': f['format_id'].replace('hls-', 'http-'),
  60                     'protocol': 'http',
  61                     'url': f['url'].replace('.m3u8', '.mp4'),
  62                 })
  63                 formats.append(http_f)
  64
  65         mpd_url = streams.get('adaptive_dash')
  66         if mpd_url:
  67             formats.extend(self._extract_mpd_formats(
  68                 mpd_url, page_id, mpd_id='dash', fatal=False))
  69
  70         self._sort_formats(formats)
  71
  72         return {
  73             'id': data_video.get('guid') or page_id,
  74             'display_id': page_id,
  75             'title': title,
  76             'formats': formats,
  77             'description': self._html_search_meta('description', webpage),
  78             'thumbnail': self._og_search_thumbnail(webpage),
  79         }