yt_dlp/extractor/caffeinetv.py

   1 from .common import InfoExtractor
   2 from ..utils import (
   3     determine_ext,
   4     int_or_none,
   5     parse_iso8601,
   6     traverse_obj,
   7     urljoin,
   8 )
   9
  10
  11 class CaffeineTVIE(InfoExtractor):
  12     _VALID_URL = r'https?://(?:www\.)?caffeine\.tv/[^/?#]+/video/(?P<id>[\da-f-]+)'
  13     _TESTS = [{
  14         'url': 'https://www.caffeine.tv/TsuSurf/video/cffc0a00-e73f-11ec-8080-80017d29f26e',
  15         'info_dict': {
  16             'id': 'cffc0a00-e73f-11ec-8080-80017d29f26e',
  17             'ext': 'mp4',
  18             'title': 'GOOOOD MORNINNNNN #highlights',
  19             'timestamp': 1654702180,
  20             'upload_date': '20220608',
  21             'uploader': 'RahJON Wicc',
  22             'uploader_id': 'TsuSurf',
  23             'duration': 3145,
  24             'age_limit': 17,
  25             'thumbnail': 'https://www.caffeine.tv/broadcasts/776b6f84-9cd5-42e3-af1d-4a776eeed697/replay/lobby.jpg',
  26             'comment_count': int,
  27             'view_count': int,
  28             'like_count': int,
  29             'tags': ['highlights', 'battlerap'],
  30         },
  31         'params': {
  32             'skip_download': 'm3u8',
  33         },
  34     }]
  35
  36     def _real_extract(self, url):
  37         video_id = self._match_id(url)
  38         json_data = self._download_json(
  39             f'https://api.caffeine.tv/social/public/activity/{video_id}', video_id)
  40         broadcast_info = traverse_obj(json_data, ('broadcast_info', {dict})) or {}
  41
  42         video_url = broadcast_info['video_url']
  43         ext = determine_ext(video_url)
  44         if ext == 'm3u8':
  45             formats = self._extract_m3u8_formats(video_url, video_id, 'mp4')
  46         else:
  47             formats = [{'url': video_url}]
  48
  49         return {
  50             'id': video_id,
  51             'formats': formats,
  52             **traverse_obj(json_data, {
  53                 'like_count': ('like_count', {int_or_none}),
  54                 'view_count': ('view_count', {int_or_none}),
  55                 'comment_count': ('comment_count', {int_or_none}),
  56                 'tags': ('tags', ..., {str}, {lambda x: x or None}),
  57                 'uploader': ('user', 'name', {str}),
  58                 'uploader_id': (((None, 'user'), 'username'), {str}, any),
  59                 'is_live': ('is_live', {bool}),
  60             }),
  61             **traverse_obj(broadcast_info, {
  62                 'title': ('broadcast_title', {str}),
  63                 'duration': ('content_duration', {int_or_none}),
  64                 'timestamp': ('broadcast_start_time', {parse_iso8601}),
  65                 'thumbnail': ('preview_image_path', {lambda x: urljoin(url, x)}),
  66             }),
  67             'age_limit': {
  68                 # assume Apple Store ratings: https://en.wikipedia.org/wiki/Mobile_software_content_rating_system
  69                 'FOUR_PLUS': 0,
  70                 'NINE_PLUS': 9,
  71                 'TWELVE_PLUS': 12,
  72                 'SEVENTEEN_PLUS': 17,
  73             }.get(broadcast_info.get('content_rating'), 17),
  74         }