yt_dlp/extractor/mixch.py

   1 from .common import InfoExtractor
   2 from ..networking.exceptions import HTTPError
   3 from ..utils import (
   4     ExtractorError,
   5     UserNotLive,
   6     int_or_none,
   7     str_or_none,
   8     url_or_none,
   9 )
  10 from ..utils.traversal import traverse_obj
  11
  12
  13 class MixchIE(InfoExtractor):
  14     IE_NAME = 'mixch'
  15     _VALID_URL = r'https?://(?:www\.)?mixch\.tv/u/(?P<id>\d+)'
  16
  17     _TESTS = [{
  18         'url': 'https://mixch.tv/u/16943797/live',
  19         'skip': 'don\'t know if this live persists',
  20         'info_dict': {
  21             'id': '16943797',
  22             'ext': 'mp4',
  23             'title': '#EntView #カリナ #セブチ 2024-05-05 06:58',
  24             'comment_count': int,
  25             'view_count': int,
  26             'timestamp': 1714726805,
  27             'uploader': 'Ent.View K-news🎶💕',
  28             'uploader_id': '16943797',
  29             'live_status': 'is_live',
  30             'upload_date': '20240503',
  31         },
  32     }, {
  33         'url': 'https://mixch.tv/u/16137876/live',
  34         'only_matching': True,
  35     }]
  36
  37     def _real_extract(self, url):
  38         video_id = self._match_id(url)
  39         data = self._download_json(f'https://mixch.tv/api-web/users/{video_id}/live', video_id)
  40         if not traverse_obj(data, ('liveInfo', {dict})):
  41             raise UserNotLive(video_id=video_id)
  42
  43         return {
  44             'id': video_id,
  45             'uploader_id': video_id,
  46             **traverse_obj(data, {
  47                 'title': ('liveInfo', 'title', {str}),
  48                 'comment_count': ('liveInfo', 'comments', {int_or_none}),
  49                 'view_count': ('liveInfo', 'visitor', {int_or_none}),
  50                 'timestamp': ('liveInfo', 'created', {int_or_none}),
  51                 'uploader': ('broadcasterInfo', 'name', {str}),
  52             }),
  53             'formats': [{
  54                 'format_id': 'hls',
  55                 'url': data['liveInfo']['hls'],
  56                 'ext': 'mp4',
  57                 'protocol': 'm3u8',
  58             }],
  59             'is_live': True,
  60             '__post_extractor': self.extract_comments(video_id),
  61         }
  62
  63     def _get_comments(self, video_id):
  64         yield from traverse_obj(self._download_json(
  65             f'https://mixch.tv/api-web/lives/{video_id}/messages', video_id,
  66             note='Downloading comments', errnote='Failed to download comments'), (..., {
  67                 'author': ('name', {str}),
  68                 'author_id': ('user_id', {str_or_none}),
  69                 'id': ('message_id', {str}, {lambda x: x or None}),
  70                 'text': ('body', {str}),
  71                 'timestamp': ('created', {int}),
  72             }))
  73
  74
  75 class MixchArchiveIE(InfoExtractor):
  76     IE_NAME = 'mixch:archive'
  77     _VALID_URL = r'https?://(?:www\.)?mixch\.tv/archive/(?P<id>\d+)'
  78
  79     _TESTS = [{
  80         'url': 'https://mixch.tv/archive/421',
  81         'skip': 'paid video, no DRM. expires at Jan 23',
  82         'info_dict': {
  83             'id': '421',
  84             'ext': 'mp4',
  85             'title': '96NEKO SHOW TIME',
  86         }
  87     }, {
  88         'url': 'https://mixch.tv/archive/1213',
  89         'skip': 'paid video, no DRM. expires at Dec 31, 2023',
  90         'info_dict': {
  91             'id': '1213',
  92             'ext': 'mp4',
  93             'title': '【特別トーク番組アーカイブス】Merm4id×燐舞曲 2nd LIVE「VERSUS」',
  94             'release_date': '20231201',
  95             'thumbnail': str,
  96         }
  97     }, {
  98         'url': 'https://mixch.tv/archive/1214',
  99         'only_matching': True,
 100     }]
 101
 102     def _real_extract(self, url):
 103         video_id = self._match_id(url)
 104
 105         try:
 106             info_json = self._download_json(
 107                 f'https://mixch.tv/api-web/archive/{video_id}', video_id)['archive']
 108         except ExtractorError as e:
 109             if isinstance(e.cause, HTTPError) and e.cause.status == 401:
 110                 self.raise_login_required()
 111             raise
 112
 113         return {
 114             'id': video_id,
 115             'title': traverse_obj(info_json, ('title', {str})),
 116             'formats': self._extract_m3u8_formats(info_json['archiveURL'], video_id),
 117             'thumbnail': traverse_obj(info_json, ('thumbnailURL', {url_or_none})),
 118         }