aboutsummaryrefslogtreecommitdiff
path: root/yt_dlp/extractor/sovietscloset.py
blob: d35214aa840f7eec2f31b062aba212f562cdc3ba (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
from .bunnycdn import BunnyCdnIE
from .common import InfoExtractor
from ..utils import make_archive_id, try_get, unified_timestamp


class SovietsClosetBaseIE(InfoExtractor):
    MEDIADELIVERY_REFERER = {'Referer': 'https://iframe.mediadelivery.net/'}

    def parse_nuxt_jsonp(self, nuxt_jsonp_url, video_id, name):
        nuxt_jsonp = self._download_webpage(nuxt_jsonp_url, video_id, note=f'Downloading {name} __NUXT_JSONP__')
        return self._search_nuxt_data(nuxt_jsonp, video_id, '__NUXT_JSONP__')

    def video_meta(self, video_id, game_name, category_name, episode_number, stream_date):
        title = game_name
        if category_name and category_name != 'Misc':
            title += f' - {category_name}'
        if episode_number:
            title += f' #{episode_number}'

        timestamp = unified_timestamp(stream_date)

        return {
            'id': video_id,
            'title': title,
            'http_headers': self.MEDIADELIVERY_REFERER,
            'uploader': 'SovietWomble',
            'creator': 'SovietWomble',
            'release_timestamp': timestamp,
            'timestamp': timestamp,
            'uploader_id': 'SovietWomble',
            'uploader_url': 'https://www.twitch.tv/SovietWomble',
            'was_live': True,
            'availability': 'public',
            'series': game_name,
            'season': category_name,
            'episode_number': episode_number,
        }


class SovietsClosetIE(SovietsClosetBaseIE):
    _VALID_URL = r'https?://(?:www\.)?sovietscloset\.com/video/(?P<id>[0-9]+)/?'
    _TESTS = [
        {
            'url': 'https://sovietscloset.com/video/1337',
            'md5': 'bd012b04b261725510ca5383074cdd55',
            'info_dict': {
                'id': '2f0cfbf4-3588-43a9-a7d6-7c9ea3755e67',
                'ext': 'mp4',
                'title': 'The Witcher #13',
                'thumbnail': r're:^https?://.*\.b-cdn\.net/2f0cfbf4-3588-43a9-a7d6-7c9ea3755e67/thumbnail\.jpg$',
                'uploader': 'SovietWomble',
                'creator': 'SovietWomble',
                'release_timestamp': 1492091580,
                'release_date': '20170413',
                'timestamp': 1492091580,
                'upload_date': '20170413',
                'uploader_id': 'SovietWomble',
                'uploader_url': 'https://www.twitch.tv/SovietWomble',
                'duration': 7008,
                'was_live': True,
                'availability': 'public',
                'series': 'The Witcher',
                'season': 'Misc',
                'episode_number': 13,
                'episode': 'Episode 13',
                'creators': ['SovietWomble'],
                'description': '',
                '_old_archive_ids': ['sovietscloset 1337'],
            },
        },
        {
            'url': 'https://sovietscloset.com/video/1105',
            'md5': '89fa928f183893cb65a0b7be846d8a90',
            'info_dict': {
                'id': 'c0e5e76f-3a93-40b4-bf01-12343c2eec5d',
                'ext': 'mp4',
                'title': 'Arma 3 - Zeus Games #5',
                'uploader': 'SovietWomble',
                'thumbnail': r're:^https?://.*\.b-cdn\.net/c0e5e76f-3a93-40b4-bf01-12343c2eec5d/thumbnail\.jpg$',
                'creator': 'SovietWomble',
                'release_timestamp': 1461157200,
                'release_date': '20160420',
                'timestamp': 1461157200,
                'upload_date': '20160420',
                'uploader_id': 'SovietWomble',
                'uploader_url': 'https://www.twitch.tv/SovietWomble',
                'duration': 8805,
                'was_live': True,
                'availability': 'public',
                'series': 'Arma 3',
                'season': 'Zeus Games',
                'episode_number': 5,
                'episode': 'Episode 5',
                'creators': ['SovietWomble'],
                'description': '',
                '_old_archive_ids': ['sovietscloset 1105'],
            },
        },
    ]

    def _real_extract(self, url):
        video_id = self._match_id(url)
        webpage = self._download_webpage(url, video_id)

        static_assets_base = self._search_regex(r'(/_nuxt/static/\d+)', webpage, 'staticAssetsBase')
        static_assets_base = f'https://sovietscloset.com{static_assets_base}'

        stream = self.parse_nuxt_jsonp(f'{static_assets_base}/video/{video_id}/payload.js', video_id, 'video')['stream']

        return self.url_result(
            f'https://iframe.mediadelivery.net/embed/5105/{stream["bunnyId"]}', ie=BunnyCdnIE, url_transparent=True,
            **self.video_meta(
                video_id=video_id, game_name=stream['game']['name'],
                category_name=try_get(stream, lambda x: x['subcategory']['name'], str),
                episode_number=stream.get('number'), stream_date=stream.get('date')),
            _old_archive_ids=[make_archive_id(self, video_id)])


class SovietsClosetPlaylistIE(SovietsClosetBaseIE):
    _VALID_URL = r'https?://(?:www\.)?sovietscloset\.com/(?!video)(?P<id>[^#?]+)'
    _TESTS = [

        {
            'url': 'https://sovietscloset.com/The-Witcher',
            'info_dict': {
                'id': 'The-Witcher',
                'title': 'The Witcher',
            },
            'playlist_mincount': 31,
        },
        {
            'url': 'https://sovietscloset.com/Arma-3/Zeus-Games',
            'info_dict': {
                'id': 'Arma-3/Zeus-Games',
                'title': 'Arma 3 - Zeus Games',
            },
            'playlist_mincount': 3,
        },
        {
            'url': 'https://sovietscloset.com/arma-3/zeus-games/',
            'info_dict': {
                'id': 'arma-3/zeus-games',
                'title': 'Arma 3 - Zeus Games',
            },
            'playlist_mincount': 3,
        },
        {
            'url': 'https://sovietscloset.com/Total-War-Warhammer',
            'info_dict': {
                'id': 'Total-War-Warhammer',
                'title': 'Total War: Warhammer - Greenskins',
            },
            'playlist_mincount': 33,
        },
    ]

    def _real_extract(self, url):
        playlist_id = self._match_id(url)
        if playlist_id.endswith('/'):
            playlist_id = playlist_id[:-1]

        webpage = self._download_webpage(url, playlist_id)

        static_assets_base = self._search_regex(r'(/_nuxt/static/\d+)', webpage, 'staticAssetsBase')
        static_assets_base = f'https://sovietscloset.com{static_assets_base}'

        sovietscloset = self.parse_nuxt_jsonp(f'{static_assets_base}/payload.js', playlist_id, 'global')['games']

        if '/' in playlist_id:
            game_slug, category_slug = playlist_id.lower().split('/')
        else:
            game_slug = playlist_id.lower()
            category_slug = 'misc'

        game = next(game for game in sovietscloset if game['slug'].lower() == game_slug)
        category = next((cat for cat in game['subcategories'] if cat.get('slug', '').lower() == category_slug),
                        game['subcategories'][0])
        category_slug = category.get('slug', '').lower() or category_slug
        playlist_title = game.get('name') or game_slug
        if category_slug != 'misc':
            playlist_title += f' - {category.get("name") or category_slug}'
        entries = [{
            **self.url_result(f'https://sovietscloset.com/video/{stream["id"]}', ie=SovietsClosetIE.ie_key()),
            **self.video_meta(
                video_id=stream['id'], game_name=game['name'], category_name=category.get('name'),
                episode_number=i + 1, stream_date=stream.get('date')),
        } for i, stream in enumerate(category['streams'])]

        return self.playlist_result(entries, playlist_id, playlist_title)