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         self._sort_formats(formats)
  41         return {
  42             'id': str(video_id),
  43             'title': container.get('media_container_name') or self._og_search_title(self._download_webpage(url, video_id)),
  44             'description': container.get('media_container_description'),
  45             'thumbnails': self._extract_thumbnails(media_meta.get('media_preview_images')),
  46             'timestamp': parse_iso8601(container.get('created_at')),
  47             'view_count': int_or_none(stream.get('stream_current_viewers' if is_live else 'stream_total_viewers')),
  48             'is_live': is_live,
  49             'formats': formats,
  50             'subtitles': subtitles,
  51         }
  52
  53     def _get_container(self, url):
  54         raise NotImplementedError('Subclass for get media container')
  55
  56     def _get_media_url(self, media_meta):
  57         raise NotImplementedError('Subclass for get media url')
  58
  59
  60 class WASDTVStreamIE(WASDTVBaseIE):
  61     IE_NAME = 'wasdtv:stream'
  62     _VALID_URL = r'https?://wasd\.tv/(?P<id>[^/#?]+)$'
  63     _TESTS = [{
  64         'url': 'https://wasd.tv/24_7',
  65         'info_dict': {
  66             'id': '559738',
  67             'ext': 'mp4',
  68             'title': 'Live 24/7 Music',
  69             'description': '24&#x2F;7 Music',
  70             'timestamp': int,
  71             'upload_date': r're:^\d{8}$',
  72             'is_live': True,
  73             'view_count': int,
  74         },
  75     }]
  76
  77     def _get_container(self, url):
  78         nickname = self._match_id(url)
  79         channel = self._fetch(f'channels/nicknames/{nickname}', video_id=nickname, description='channel')
  80         channel_id = channel.get('channel_id')
  81         containers = self._fetch(
  82             'v2/media-containers', channel_id, 'running media containers',
  83             query={
  84                 'channel_id': channel_id,
  85                 'media_container_type': 'SINGLE',
  86                 'media_container_status': 'RUNNING',
  87             })
  88         if not containers:
  89             raise ExtractorError(f'{nickname} is offline', expected=True)
  90         return containers[0]
  91
  92     def _get_media_url(self, media_meta):
  93         return media_meta['media_url'], True
  94
  95
  96 class WASDTVRecordIE(WASDTVBaseIE):
  97     IE_NAME = 'wasdtv:record'
  98     _VALID_URL = r'https?://wasd\.tv/[^/#?]+/videos\?record=(?P<id>\d+)$'
  99     _TESTS = [{
 100         'url': 'https://wasd.tv/spacemita/videos?record=907755',
 101         'md5': 'c9899dd85be4cc997816ff9f9ca516ce',
 102         'info_dict': {
 103             'id': '906825',
 104             'ext': 'mp4',
 105             'title': 'Музыкальный',
 106             'description': 'md5:f510388d929ff60ae61d4c3cab3137cc',
 107             'timestamp': 1645812079,
 108             'upload_date': '20220225',
 109             'thumbnail': r're:^https?://.+\.jpg',
 110             'is_live': False,
 111             'view_count': int,
 112         },
 113     }]
 114
 115     def _get_container(self, url):
 116         container_id = self._match_id(url)
 117         return self._fetch(
 118             f'v2/media-containers/{container_id}', container_id, 'media container')
 119
 120     def _get_media_url(self, media_meta):
 121         media_archive_url = media_meta.get('media_archive_url')
 122         if media_archive_url:
 123             return media_archive_url, False
 124         return media_meta['media_url'], True
 125
 126
 127 class WASDTVClipIE(WASDTVBaseIE):
 128     IE_NAME = 'wasdtv:clip'
 129     _VALID_URL = r'https?://wasd\.tv/[^/#?]+/clips\?clip=(?P<id>\d+)$'
 130     _TESTS = [{
 131         'url': 'https://wasd.tv/spacemita/clips?clip=26804',
 132         'md5': '818885e720143d7a4e776ff66fcff148',
 133         'info_dict': {
 134             'id': '26804',
 135             'ext': 'mp4',
 136             'title': 'Пуш флексит на голове стримера',
 137             'timestamp': 1646682908,
 138             'upload_date': '20220307',
 139             'thumbnail': r're:^https?://.+\.jpg',
 140             'view_count': int,
 141         },
 142     }]
 143
 144     def _real_extract(self, url):
 145         clip_id = self._match_id(url)
 146         clip = self._fetch(f'v2/clips/{clip_id}', video_id=clip_id, description='clip')
 147         clip_data = clip.get('clip_data')
 148         formats, subtitles = self._extract_m3u8_formats_and_subtitles(clip_data.get('url'), video_id=clip_id, ext='mp4')
 149         self._sort_formats(formats)
 150         return {
 151             'id': clip_id,
 152             'title': clip.get('clip_title') or self._og_search_title(self._download_webpage(url, clip_id, fatal=False)),
 153             'thumbnails': self._extract_thumbnails(clip_data.get('preview')),
 154             'timestamp': parse_iso8601(clip.get('created_at')),
 155             'view_count': int_or_none(clip.get('clip_views_count')),
 156             'formats': formats,
 157             'subtitles': subtitles,
 158         }