yt_dlp/extractor/sovietscloset.py

   1 from .common import InfoExtractor
   2 from ..utils import (
   3     try_get,
   4     unified_timestamp
   5 )
   6
   7
   8 class SovietsClosetBaseIE(InfoExtractor):
   9     MEDIADELIVERY_REFERER = {'Referer': 'https://iframe.mediadelivery.net/'}
  10
  11     def parse_nuxt_jsonp(self, nuxt_jsonp_url, video_id, name):
  12         nuxt_jsonp = self._download_webpage(nuxt_jsonp_url, video_id, note=f'Downloading {name} __NUXT_JSONP__')
  13         return self._search_nuxt_data(nuxt_jsonp, video_id, '__NUXT_JSONP__')
  14
  15     def video_meta(self, video_id, game_name, category_name, episode_number, stream_date):
  16         title = game_name
  17         if category_name and category_name != 'Misc':
  18             title += f' - {category_name}'
  19         if episode_number:
  20             title += f' #{episode_number}'
  21
  22         timestamp = unified_timestamp(stream_date)
  23
  24         return {
  25             'id': video_id,
  26             'title': title,
  27             'http_headers': self.MEDIADELIVERY_REFERER,
  28             'uploader': 'SovietWomble',
  29             'creator': 'SovietWomble',
  30             'release_timestamp': timestamp,
  31             'timestamp': timestamp,
  32             'uploader_id': 'SovietWomble',
  33             'uploader_url': 'https://www.twitch.tv/SovietWomble',
  34             'was_live': True,
  35             'availability': 'public',
  36             'series': game_name,
  37             'season': category_name,
  38             'episode_number': episode_number,
  39         }
  40
  41
  42 class SovietsClosetIE(SovietsClosetBaseIE):
  43     _VALID_URL = r'https?://(?:www\.)?sovietscloset\.com/video/(?P<id>[0-9]+)/?'
  44     _TESTS = [
  45         {
  46             'url': 'https://sovietscloset.com/video/1337',
  47             'md5': 'bd012b04b261725510ca5383074cdd55',
  48             'info_dict': {
  49                 'id': '1337',
  50                 'ext': 'mp4',
  51                 'title': 'The Witcher #13',
  52                 'thumbnail': r're:^https?://.*\.b-cdn\.net/2f0cfbf4-3588-43a9-a7d6-7c9ea3755e67/thumbnail\.jpg$',
  53                 'uploader': 'SovietWomble',
  54                 'creator': 'SovietWomble',
  55                 'release_timestamp': 1492091580,
  56                 'release_date': '20170413',
  57                 'timestamp': 1492091580,
  58                 'upload_date': '20170413',
  59                 'uploader_id': 'SovietWomble',
  60                 'uploader_url': 'https://www.twitch.tv/SovietWomble',
  61                 'duration': 7007,
  62                 'was_live': True,
  63                 'availability': 'public',
  64                 'series': 'The Witcher',
  65                 'season': 'Misc',
  66                 'episode_number': 13,
  67                 'episode': 'Episode 13',
  68             },
  69         },
  70         {
  71             'url': 'https://sovietscloset.com/video/1105',
  72             'md5': '89fa928f183893cb65a0b7be846d8a90',
  73             'info_dict': {
  74                 'id': '1105',
  75                 'ext': 'mp4',
  76                 'title': 'Arma 3 - Zeus Games #5',
  77                 'uploader': 'SovietWomble',
  78                 'thumbnail': r're:^https?://.*\.b-cdn\.net/c0e5e76f-3a93-40b4-bf01-12343c2eec5d/thumbnail\.jpg$',
  79                 'creator': 'SovietWomble',
  80                 'release_timestamp': 1461157200,
  81                 'release_date': '20160420',
  82                 'timestamp': 1461157200,
  83                 'upload_date': '20160420',
  84                 'uploader_id': 'SovietWomble',
  85                 'uploader_url': 'https://www.twitch.tv/SovietWomble',
  86                 'duration': 8804,
  87                 'was_live': True,
  88                 'availability': 'public',
  89                 'series': 'Arma 3',
  90                 'season': 'Zeus Games',
  91                 'episode_number': 5,
  92                 'episode': 'Episode 5',
  93             },
  94         },
  95     ]
  96
  97     def _extract_bunnycdn_iframe(self, video_id, bunnycdn_id):
  98         iframe = self._download_webpage(
  99             f'https://iframe.mediadelivery.net/embed/5105/{bunnycdn_id}',
 100             video_id, note='Downloading BunnyCDN iframe', headers=self.MEDIADELIVERY_REFERER)
 101
 102         m3u8_url = self._search_regex(r'(https?://.*?\.m3u8)', iframe, 'm3u8 url')
 103         thumbnail_url = self._search_regex(r'(https?://.*?thumbnail\.jpg)', iframe, 'thumbnail url')
 104
 105         m3u8_formats = self._extract_m3u8_formats(m3u8_url, video_id, headers=self.MEDIADELIVERY_REFERER)
 106
 107         if not m3u8_formats:
 108             duration = None
 109         else:
 110             duration = self._extract_m3u8_vod_duration(
 111                 m3u8_formats[0]['url'], video_id, headers=self.MEDIADELIVERY_REFERER)
 112
 113         return {
 114             'formats': m3u8_formats,
 115             'thumbnail': thumbnail_url,
 116             'duration': duration,
 117         }
 118
 119     def _real_extract(self, url):
 120         video_id = self._match_id(url)
 121         webpage = self._download_webpage(url, video_id)
 122
 123         static_assets_base = self._search_regex(r'(/_nuxt/static/\d+)', webpage, 'staticAssetsBase')
 124         static_assets_base = f'https://sovietscloset.com{static_assets_base}'
 125
 126         stream = self.parse_nuxt_jsonp(f'{static_assets_base}/video/{video_id}/payload.js', video_id, 'video')['stream']
 127
 128         return {
 129             **self.video_meta(
 130                 video_id=video_id, game_name=stream['game']['name'],
 131                 category_name=try_get(stream, lambda x: x['subcategory']['name'], str),
 132                 episode_number=stream.get('number'), stream_date=stream.get('date')),
 133             **self._extract_bunnycdn_iframe(video_id, stream['bunnyId']),
 134         }
 135
 136
 137 class SovietsClosetPlaylistIE(SovietsClosetBaseIE):
 138     _VALID_URL = r'https?://(?:www\.)?sovietscloset\.com/(?!video)(?P<id>[^#?]+)'
 139     _TESTS = [
 140
 141         {
 142             'url': 'https://sovietscloset.com/The-Witcher',
 143             'info_dict': {
 144                 'id': 'The-Witcher',
 145                 'title': 'The Witcher',
 146             },
 147             'playlist_mincount': 31,
 148         },
 149         {
 150             'url': 'https://sovietscloset.com/Arma-3/Zeus-Games',
 151             'info_dict': {
 152                 'id': 'Arma-3/Zeus-Games',
 153                 'title': 'Arma 3 - Zeus Games',
 154             },
 155             'playlist_mincount': 3,
 156         },
 157         {
 158             'url': 'https://sovietscloset.com/arma-3/zeus-games/',
 159             'info_dict': {
 160                 'id': 'arma-3/zeus-games',
 161                 'title': 'Arma 3 - Zeus Games',
 162             },
 163             'playlist_mincount': 3,
 164         },
 165         {
 166             'url': 'https://sovietscloset.com/Total-War-Warhammer',
 167             'info_dict': {
 168                 'id': 'Total-War-Warhammer',
 169                 'title': 'Total War: Warhammer - Greenskins',
 170             },
 171             'playlist_mincount': 33,
 172         },
 173     ]
 174
 175     def _real_extract(self, url):
 176         playlist_id = self._match_id(url)
 177         if playlist_id.endswith('/'):
 178             playlist_id = playlist_id[:-1]
 179
 180         webpage = self._download_webpage(url, playlist_id)
 181
 182         static_assets_base = self._search_regex(r'(/_nuxt/static/\d+)', webpage, 'staticAssetsBase')
 183         static_assets_base = f'https://sovietscloset.com{static_assets_base}'
 184
 185         sovietscloset = self.parse_nuxt_jsonp(f'{static_assets_base}/payload.js', playlist_id, 'global')['games']
 186
 187         if '/' in playlist_id:
 188             game_slug, category_slug = playlist_id.lower().split('/')
 189         else:
 190             game_slug = playlist_id.lower()
 191             category_slug = 'misc'
 192
 193         game = next(game for game in sovietscloset if game['slug'].lower() == game_slug)
 194         category = next((cat for cat in game['subcategories'] if cat.get('slug', '').lower() == category_slug),
 195                         game['subcategories'][0])
 196         category_slug = category.get('slug', '').lower() or category_slug
 197         playlist_title = game.get('name') or game_slug
 198         if category_slug != 'misc':
 199             playlist_title += f' - {category.get("name") or category_slug}'
 200         entries = [{
 201             **self.url_result(f'https://sovietscloset.com/video/{stream["id"]}', ie=SovietsClosetIE.ie_key()),
 202             **self.video_meta(
 203                 video_id=stream['id'], game_name=game['name'], category_name=category.get('name'),
 204                 episode_number=i + 1, stream_date=stream.get('date')),
 205         } for i, stream in enumerate(category['streams'])]
 206
 207         return self.playlist_result(entries, playlist_id, playlist_title)