1
0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-09 12:42:28 +01:00
yt-dlp/yt_dlp/extractor/gamespot.py

78 lines
3.0 KiB
Python
Raw Normal View History

2016-06-21 14:36:56 +02:00
from .once import OnceIE
2021-01-01 13:26:37 +01:00
from ..compat import compat_urllib_parse_unquote
2016-06-21 14:36:56 +02:00
class GameSpotIE(OnceIE):
2018-12-02 20:01:36 +01:00
_VALID_URL = r'https?://(?:www\.)?gamespot\.com/(?:video|article|review)s/(?:[^/]+/\d+-|embed/)(?P<id>\d+)'
_TESTS = [{
'url': 'http://www.gamespot.com/videos/arma-3-community-guide-sitrep-i/2300-6410818/',
'md5': 'b2a30deaa8654fcccd43713a6b6a4825',
'info_dict': {
'id': 'gs-2300-6410818',
'ext': 'mp4',
'title': 'Arma 3 - Community Guide: SITREP I',
2014-01-17 03:13:40 +01:00
'description': 'Check out this video where some of the basics of Arma 3 is explained.',
},
2021-01-01 13:26:37 +01:00
'skip': 'manifest URL give HTTP Error 404: Not Found',
}, {
'url': 'http://www.gamespot.com/videos/the-witcher-3-wild-hunt-xbox-one-now-playing/2300-6424837/',
2021-01-01 13:26:37 +01:00
'md5': '173ea87ad762cf5d3bf6163dceb255a6',
'info_dict': {
'id': 'gs-2300-6424837',
'ext': 'mp4',
'title': 'Now Playing - The Witcher 3: Wild Hunt',
'description': 'Join us as we take a look at the early hours of The Witcher 3: Wild Hunt and more.',
},
}, {
'url': 'https://www.gamespot.com/videos/embed/6439218/',
'only_matching': True,
2017-11-13 10:30:12 +01:00
}, {
'url': 'https://www.gamespot.com/articles/the-last-of-us-2-receives-new-ps4-trailer/1100-6454469/',
'only_matching': True,
2018-12-02 20:01:36 +01:00
}, {
'url': 'https://www.gamespot.com/reviews/gears-of-war-review/1900-6161188/',
'only_matching': True,
}]
def _real_extract(self, url):
2014-11-04 23:04:12 +01:00
page_id = self._match_id(url)
webpage = self._download_webpage(url, page_id)
2021-01-01 13:26:37 +01:00
data_video = self._parse_json(self._html_search_regex(
r'data-video=(["\'])({.*?})\1', webpage,
'video data', group=2), page_id)
title = compat_urllib_parse_unquote(data_video['title'])
streams = data_video['videoStreams']
formats = []
2021-01-01 13:26:37 +01:00
m3u8_url = streams.get('adaptive_stream')
2016-06-21 14:36:56 +02:00
if m3u8_url:
m3u8_formats = self._extract_m3u8_formats(
m3u8_url, page_id, 'mp4', 'm3u8_native',
m3u8_id='hls', fatal=False)
2021-01-01 13:26:37 +01:00
for f in m3u8_formats:
formats.append(f)
http_f = f.copy()
del http_f['manifest_url']
http_f.update({
'format_id': f['format_id'].replace('hls-', 'http-'),
'protocol': 'http',
'url': f['url'].replace('.m3u8', '.mp4'),
})
formats.append(http_f)
2016-06-21 14:36:56 +02:00
2021-01-01 13:26:37 +01:00
mpd_url = streams.get('adaptive_dash')
if mpd_url:
formats.extend(self._extract_mpd_formats(
mpd_url, page_id, mpd_id='dash', fatal=False))
2016-06-21 14:36:56 +02:00
self._sort_formats(formats)
return {
2021-01-01 13:26:37 +01:00
'id': data_video.get('guid') or page_id,
2014-11-04 23:04:12 +01:00
'display_id': page_id,
2021-01-01 13:26:37 +01:00
'title': title,
'formats': formats,
2014-11-04 23:04:12 +01:00
'description': self._html_search_meta('description', webpage),
'thumbnail': self._og_search_thumbnail(webpage),
}