1 from __future__ import unicode_literals
3 from .once import OnceIE
4 from ..compat import compat_urllib_parse_unquote
7 class GameSpotIE(OnceIE):
8 _VALID_URL = r'https?://(?:www\.)?gamespot\.com/(?:video|article|review)s/(?:[^/]+/\d+-|embed/)(?P<id>\d+)'
10 'url': 'http://www.gamespot.com/videos/arma-3-community-guide-sitrep-i/2300-6410818/',
11 'md5': 'b2a30deaa8654fcccd43713a6b6a4825',
13 'id': 'gs-2300-6410818',
15 'title': 'Arma 3 - Community Guide: SITREP I',
16 'description': 'Check out this video where some of the basics of Arma 3 is explained.',
18 'skip': 'manifest URL give HTTP Error 404: Not Found',
20 'url': 'http://www.gamespot.com/videos/the-witcher-3-wild-hunt-xbox-one-now-playing/2300-6424837/',
21 'md5': '173ea87ad762cf5d3bf6163dceb255a6',
23 'id': 'gs-2300-6424837',
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.',
29 'url': 'https://www.gamespot.com/videos/embed/6439218/',
30 'only_matching': True,
32 'url': 'https://www.gamespot.com/articles/the-last-of-us-2-receives-new-ps4-trailer/1100-6454469/',
33 'only_matching': True,
35 'url': 'https://www.gamespot.com/reviews/gears-of-war-review/1900-6161188/',
36 'only_matching': True,
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']
49 m3u8_url = streams.get('adaptive_stream')
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:
57 del http_f['manifest_url']
59 'format_id': f['format_id'].replace('hls-', 'http-'),
61 'url': f['url'].replace('.m3u8', '.mp4'),
63 formats.append(http_f)
65 mpd_url = streams.get('adaptive_dash')
67 formats.extend(self._extract_mpd_formats(
68 mpd_url, page_id, mpd_id='dash', fatal=False))
70 self._sort_formats(formats)
73 'id': data_video.get('guid') or page_id,
74 'display_id': page_id,
77 'description': self._html_search_meta('description', webpage),
78 'thumbnail': self._og_search_thumbnail(webpage),