yt_dlp/extractor/wasdtv.py

   1 from .common import InfoExtractor
   2 from ..utils import (
   3     ExtractorError,
   4     int_or_none,
   5     parse_iso8601,
   6     traverse_obj,
   7     try_get,
   8 )
   9
  10
  11 class WASDTVBaseIE(InfoExtractor):
  12
  13     def _fetch(self, path, video_id, description, query={}):
  14         response = self._download_json(
  15             f'https://wasd.tv/api/{path}', video_id, query=query,
  16             note=f'Downloading {description} metadata',
  17             errnote=f'Unable to download {description} metadata')
  18         error = response.get('error')
  19         if error:
  20             raise ExtractorError(f'{self.IE_NAME} returned error: {error}', expected=True)
  21         return response.get('result')
  22
  23     def _extract_thumbnails(self, thumbnails_dict):
  24         return [{
  25             'url': url,
  26             'preference': index,
  27         } for index, url in enumerate(
  28             traverse_obj(thumbnails_dict, (('small', 'medium', 'large'),))) if url]
  29
  30     def _real_extract(self, url):
  31         container = self._get_container(url)
  32         stream = traverse_obj(container, ('media_container_streams', 0))
  33         media = try_get(stream, lambda x: x['stream_media'][0])
  34         if not media:
  35             raise ExtractorError('Can not extract media data.', expected=True)
  36         media_meta = media.get('media_meta')
  37         media_url, is_live = self._get_media_url(media_meta)
  38         video_id = media.get('media_id') or container.get('media_container_id')
  39         formats, subtitles = self._extract_m3u8_formats_and_subtitles(media_url, video_id, 'mp4')
  40         return {
  41             'id': str(video_id),
  42             'title': container.get('media_container_name') or self._og_search_title(self._download_webpage(url, video_id)),
  43             'description': container.get('media_container_description'),
  44             'thumbnails': self._extract_thumbnails(media_meta.get('media_preview_images')),
  45             'timestamp': parse_iso8601(container.get('created_at')),
  46             'view_count': int_or_none(stream.get('stream_current_viewers' if is_live else 'stream_total_viewers')),
  47             'is_live': is_live,
  48             'formats': formats,
  49             'subtitles': subtitles,
  50         }
  51
  52     def _get_container(self, url):
  53         raise NotImplementedError('Subclass for get media container')
  54
  55     def _get_media_url(self, media_meta):
  56         raise NotImplementedError('Subclass for get media url')
  57
  58
  59 class WASDTVStreamIE(WASDTVBaseIE):
  60     IE_NAME = 'wasdtv:stream'
  61     _VALID_URL = r'https?://wasd\.tv/(?P<id>[^/#?]+)$'
  62     _TESTS = [{
  63         'url': 'https://wasd.tv/24_7',
  64         'info_dict': {
  65             'id': '559738',
  66             'ext': 'mp4',
  67             'title': 'Live 24/7 Music',
  68             'description': '24&#x2F;7 Music',
  69             'timestamp': int,
  70             'upload_date': r're:^\d{8}$',
  71             'is_live': True,
  72             'view_count': int,
  73         },
  74     }]
  75
  76     def _get_container(self, url):
  77         nickname = self._match_id(url)
  78         channel = self._fetch(f'channels/nicknames/{nickname}', video_id=nickname, description='channel')
  79         channel_id = channel.get('channel_id')
  80         containers = self._fetch(
  81             'v2/media-containers', channel_id, 'running media containers',
  82             query={
  83                 'channel_id': channel_id,
  84                 'media_container_type': 'SINGLE',
  85                 'media_container_status': 'RUNNING',
  86             })
  87         if not containers:
  88             raise ExtractorError(f'{nickname} is offline', expected=True)
  89         return containers[0]
  90
  91     def _get_media_url(self, media_meta):
  92         return media_meta['media_url'], True
  93
  94
  95 class WASDTVRecordIE(WASDTVBaseIE):
  96     IE_NAME = 'wasdtv:record'
  97     _VALID_URL = r'https?://wasd\.tv/[^/#?]+(?:/videos)?\?record=(?P<id>\d+)$'
  98     _TESTS = [{
  99         'url': 'https://wasd.tv/spacemita/videos?record=907755',
 100         'md5': 'c9899dd85be4cc997816ff9f9ca516ce',
 101         'info_dict': {
 102             'id': '906825',
 103             'ext': 'mp4',
 104             'title': 'Музыкальный',
 105             'description': 'md5:f510388d929ff60ae61d4c3cab3137cc',
 106             'timestamp': 1645812079,
 107             'upload_date': '20220225',
 108             'thumbnail': r're:^https?://.+\.jpg',
 109             'is_live': False,
 110             'view_count': int,
 111         },
 112     }, {
 113         'url': 'https://wasd.tv/spacemita?record=907755',
 114         'only_matching': True,
 115     }]
 116
 117     def _get_container(self, url):
 118         container_id = self._match_id(url)
 119         return self._fetch(
 120             f'v2/media-containers/{container_id}', container_id, 'media container')
 121
 122     def _get_media_url(self, media_meta):
 123         media_archive_url = media_meta.get('media_archive_url')
 124         if media_archive_url:
 125             return media_archive_url, False
 126         return media_meta['media_url'], True
 127
 128
 129 class WASDTVClipIE(WASDTVBaseIE):
 130     IE_NAME = 'wasdtv:clip'
 131     _VALID_URL = r'https?://wasd\.tv/[^/#?]+/clips\?clip=(?P<id>\d+)$'
 132     _TESTS = [{
 133         'url': 'https://wasd.tv/spacemita/clips?clip=26804',
 134         'md5': '818885e720143d7a4e776ff66fcff148',
 135         'info_dict': {
 136             'id': '26804',
 137             'ext': 'mp4',
 138             'title': 'Пуш флексит на голове стримера',
 139             'timestamp': 1646682908,
 140             'upload_date': '20220307',
 141             'thumbnail': r're:^https?://.+\.jpg',
 142             'view_count': int,
 143         },
 144     }]
 145
 146     def _real_extract(self, url):
 147         clip_id = self._match_id(url)
 148         clip = self._fetch(f'v2/clips/{clip_id}', video_id=clip_id, description='clip')
 149         clip_data = clip.get('clip_data')
 150         formats, subtitles = self._extract_m3u8_formats_and_subtitles(clip_data.get('url'), video_id=clip_id, ext='mp4')
 151         return {
 152             'id': clip_id,
 153             'title': clip.get('clip_title') or self._og_search_title(self._download_webpage(url, clip_id, fatal=False)),
 154             'thumbnails': self._extract_thumbnails(clip_data.get('preview')),
 155             'timestamp': parse_iso8601(clip.get('created_at')),
 156             'view_count': int_or_none(clip.get('clip_views_count')),
 157             'formats': formats,
 158             'subtitles': subtitles,
 159         }