yt_dlp/extractor/sovietscloset.py

   1 from .common import InfoExtractor
   2 from ..utils import try_get, unified_timestamp
   3
   4
   5 class SovietsClosetBaseIE(InfoExtractor):
   6     MEDIADELIVERY_REFERER = {'Referer': 'https://iframe.mediadelivery.net/'}
   7
   8     def parse_nuxt_jsonp(self, nuxt_jsonp_url, video_id, name):
   9         nuxt_jsonp = self._download_webpage(nuxt_jsonp_url, video_id, note=f'Downloading {name} __NUXT_JSONP__')
  10         return self._search_nuxt_data(nuxt_jsonp, video_id, '__NUXT_JSONP__')
  11
  12     def video_meta(self, video_id, game_name, category_name, episode_number, stream_date):
  13         title = game_name
  14         if category_name and category_name != 'Misc':
  15             title += f' - {category_name}'
  16         if episode_number:
  17             title += f' #{episode_number}'
  18
  19         timestamp = unified_timestamp(stream_date)
  20
  21         return {
  22             'id': video_id,
  23             'title': title,
  24             'http_headers': self.MEDIADELIVERY_REFERER,
  25             'uploader': 'SovietWomble',
  26             'creator': 'SovietWomble',
  27             'release_timestamp': timestamp,
  28             'timestamp': timestamp,
  29             'uploader_id': 'SovietWomble',
  30             'uploader_url': 'https://www.twitch.tv/SovietWomble',
  31             'was_live': True,
  32             'availability': 'public',
  33             'series': game_name,
  34             'season': category_name,
  35             'episode_number': episode_number,
  36         }
  37
  38
  39 class SovietsClosetIE(SovietsClosetBaseIE):
  40     _VALID_URL = r'https?://(?:www\.)?sovietscloset\.com/video/(?P<id>[0-9]+)/?'
  41     _TESTS = [
  42         {
  43             'url': 'https://sovietscloset.com/video/1337',
  44             'md5': 'bd012b04b261725510ca5383074cdd55',
  45             'info_dict': {
  46                 'id': '1337',
  47                 'ext': 'mp4',
  48                 'title': 'The Witcher #13',
  49                 'thumbnail': r're:^https?://.*\.b-cdn\.net/2f0cfbf4-3588-43a9-a7d6-7c9ea3755e67/thumbnail\.jpg$',
  50                 'uploader': 'SovietWomble',
  51                 'creator': 'SovietWomble',
  52                 'release_timestamp': 1492091580,
  53                 'release_date': '20170413',
  54                 'timestamp': 1492091580,
  55                 'upload_date': '20170413',
  56                 'uploader_id': 'SovietWomble',
  57                 'uploader_url': 'https://www.twitch.tv/SovietWomble',
  58                 'duration': 7007,
  59                 'was_live': True,
  60                 'availability': 'public',
  61                 'series': 'The Witcher',
  62                 'season': 'Misc',
  63                 'episode_number': 13,
  64                 'episode': 'Episode 13',
  65             },
  66         },
  67         {
  68             'url': 'https://sovietscloset.com/video/1105',
  69             'md5': '89fa928f183893cb65a0b7be846d8a90',
  70             'info_dict': {
  71                 'id': '1105',
  72                 'ext': 'mp4',
  73                 'title': 'Arma 3 - Zeus Games #5',
  74                 'uploader': 'SovietWomble',
  75                 'thumbnail': r're:^https?://.*\.b-cdn\.net/c0e5e76f-3a93-40b4-bf01-12343c2eec5d/thumbnail\.jpg$',
  76                 'creator': 'SovietWomble',
  77                 'release_timestamp': 1461157200,
  78                 'release_date': '20160420',
  79                 'timestamp': 1461157200,
  80                 'upload_date': '20160420',
  81                 'uploader_id': 'SovietWomble',
  82                 'uploader_url': 'https://www.twitch.tv/SovietWomble',
  83                 'duration': 8804,
  84                 'was_live': True,
  85                 'availability': 'public',
  86                 'series': 'Arma 3',
  87                 'season': 'Zeus Games',
  88                 'episode_number': 5,
  89                 'episode': 'Episode 5',
  90             },
  91         },
  92     ]
  93
  94     def _extract_bunnycdn_iframe(self, video_id, bunnycdn_id):
  95         iframe = self._download_webpage(
  96             f'https://iframe.mediadelivery.net/embed/5105/{bunnycdn_id}',
  97             video_id, note='Downloading BunnyCDN iframe', headers=self.MEDIADELIVERY_REFERER)
  98
  99         m3u8_url = self._search_regex(r'(https?://.*?\.m3u8)', iframe, 'm3u8 url')
 100         thumbnail_url = self._search_regex(r'(https?://.*?thumbnail\.jpg)', iframe, 'thumbnail url')
 101
 102         m3u8_formats = self._extract_m3u8_formats(m3u8_url, video_id, headers=self.MEDIADELIVERY_REFERER)
 103
 104         if not m3u8_formats:
 105             duration = None
 106         else:
 107             duration = self._extract_m3u8_vod_duration(
 108                 m3u8_formats[0]['url'], video_id, headers=self.MEDIADELIVERY_REFERER)
 109
 110         return {
 111             'formats': m3u8_formats,
 112             'thumbnail': thumbnail_url,
 113             'duration': duration,
 114         }
 115
 116     def _real_extract(self, url):
 117         video_id = self._match_id(url)
 118         webpage = self._download_webpage(url, video_id)
 119
 120         static_assets_base = self._search_regex(r'(/_nuxt/static/\d+)', webpage, 'staticAssetsBase')
 121         static_assets_base = f'https://sovietscloset.com{static_assets_base}'
 122
 123         stream = self.parse_nuxt_jsonp(f'{static_assets_base}/video/{video_id}/payload.js', video_id, 'video')['stream']
 124
 125         return {
 126             **self.video_meta(
 127                 video_id=video_id, game_name=stream['game']['name'],
 128                 category_name=try_get(stream, lambda x: x['subcategory']['name'], str),
 129                 episode_number=stream.get('number'), stream_date=stream.get('date')),
 130             **self._extract_bunnycdn_iframe(video_id, stream['bunnyId']),
 131         }
 132
 133
 134 class SovietsClosetPlaylistIE(SovietsClosetBaseIE):
 135     _VALID_URL = r'https?://(?:www\.)?sovietscloset\.com/(?!video)(?P<id>[^#?]+)'
 136     _TESTS = [
 137
 138         {
 139             'url': 'https://sovietscloset.com/The-Witcher',
 140             'info_dict': {
 141                 'id': 'The-Witcher',
 142                 'title': 'The Witcher',
 143             },
 144             'playlist_mincount': 31,
 145         },
 146         {
 147             'url': 'https://sovietscloset.com/Arma-3/Zeus-Games',
 148             'info_dict': {
 149                 'id': 'Arma-3/Zeus-Games',
 150                 'title': 'Arma 3 - Zeus Games',
 151             },
 152             'playlist_mincount': 3,
 153         },
 154         {
 155             'url': 'https://sovietscloset.com/arma-3/zeus-games/',
 156             'info_dict': {
 157                 'id': 'arma-3/zeus-games',
 158                 'title': 'Arma 3 - Zeus Games',
 159             },
 160             'playlist_mincount': 3,
 161         },
 162         {
 163             'url': 'https://sovietscloset.com/Total-War-Warhammer',
 164             'info_dict': {
 165                 'id': 'Total-War-Warhammer',
 166                 'title': 'Total War: Warhammer - Greenskins',
 167             },
 168             'playlist_mincount': 33,
 169         },
 170     ]
 171
 172     def _real_extract(self, url):
 173         playlist_id = self._match_id(url)
 174         if playlist_id.endswith('/'):
 175             playlist_id = playlist_id[:-1]
 176
 177         webpage = self._download_webpage(url, playlist_id)
 178
 179         static_assets_base = self._search_regex(r'(/_nuxt/static/\d+)', webpage, 'staticAssetsBase')
 180         static_assets_base = f'https://sovietscloset.com{static_assets_base}'
 181
 182         sovietscloset = self.parse_nuxt_jsonp(f'{static_assets_base}/payload.js', playlist_id, 'global')['games']
 183
 184         if '/' in playlist_id:
 185             game_slug, category_slug = playlist_id.lower().split('/')
 186         else:
 187             game_slug = playlist_id.lower()
 188             category_slug = 'misc'
 189
 190         game = next(game for game in sovietscloset if game['slug'].lower() == game_slug)
 191         category = next((cat for cat in game['subcategories'] if cat.get('slug', '').lower() == category_slug),
 192                         game['subcategories'][0])
 193         category_slug = category.get('slug', '').lower() or category_slug
 194         playlist_title = game.get('name') or game_slug
 195         if category_slug != 'misc':
 196             playlist_title += f' - {category.get("name") or category_slug}'
 197         entries = [{
 198             **self.url_result(f'https://sovietscloset.com/video/{stream["id"]}', ie=SovietsClosetIE.ie_key()),
 199             **self.video_meta(
 200                 video_id=stream['id'], game_name=game['name'], category_name=category.get('name'),
 201                 episode_number=i + 1, stream_date=stream.get('date')),
 202         } for i, stream in enumerate(category['streams'])]
 203
 204         return self.playlist_result(entries, playlist_id, playlist_title)