yt_dlp/extractor/mixch.py

   1 from __future__ import unicode_literals
   2
   3 from .common import InfoExtractor
   4 from ..utils import (
   5     ExtractorError,
   6     traverse_obj,
   7 )
   8
   9
  10 class MixchIE(InfoExtractor):
  11     IE_NAME = 'mixch'
  12     _VALID_URL = r'https?://(?:www\.)?mixch\.tv/u/(?P<id>\d+)'
  13
  14     _TESTS = [{
  15         'url': 'https://mixch.tv/u/16236849/live',
  16         'skip': 'don\'t know if this live persists',
  17         'info_dict': {
  18             'id': '16236849',
  19             'title': '24配信シェア⭕️投票🙏💦',
  20             'comment_count': 13145,
  21             'view_count': 28348,
  22             'timestamp': 1636189377,
  23             'uploader': '🦥伊咲👶🏻#フレアワ',
  24             'uploader_id': '16236849',
  25         }
  26     }, {
  27         'url': 'https://mixch.tv/u/16137876/live',
  28         'only_matching': True,
  29     }]
  30
  31     def _real_extract(self, url):
  32         video_id = self._match_id(url)
  33         webpage = self._download_webpage(f'https://mixch.tv/u/{video_id}/live', video_id)
  34
  35         initial_js_state = self._parse_json(self._search_regex(
  36             r'(?m)^\s*window\.__INITIAL_JS_STATE__\s*=\s*(\{.+?\});\s*$', webpage, 'initial JS state'), video_id)
  37         if not initial_js_state.get('liveInfo'):
  38             raise ExtractorError('Livestream has ended.', expected=True)
  39
  40         return {
  41             'id': video_id,
  42             'title': traverse_obj(initial_js_state, ('liveInfo', 'title')),
  43             'comment_count': traverse_obj(initial_js_state, ('liveInfo', 'comments')),
  44             'view_count': traverse_obj(initial_js_state, ('liveInfo', 'visitor')),
  45             'timestamp': traverse_obj(initial_js_state, ('liveInfo', 'created')),
  46             'uploader': traverse_obj(initial_js_state, ('broadcasterInfo', 'name')),
  47             'uploader_id': video_id,
  48             'formats': [{
  49                 'format_id': 'hls',
  50                 'url': traverse_obj(initial_js_state, ('liveInfo', 'hls')) or 'https://d1hd0ww6piyb43.cloudfront.net/hls/torte_%s.m3u8' % video_id,
  51                 'ext': 'mp4',
  52                 'protocol': 'm3u8',
  53             }],
  54             'is_live': True,
  55         }
  56
  57
  58 class MixchArchiveIE(InfoExtractor):
  59     IE_NAME = 'mixch:archive'
  60     _VALID_URL = r'https?://(?:www\.)?mixch\.tv/archive/(?P<id>\d+)'
  61
  62     _TESTS = [{
  63         'url': 'https://mixch.tv/archive/421',
  64         'skip': 'paid video, no DRM. expires at Jan 23',
  65         'info_dict': {
  66             'id': '421',
  67             'title': '96NEKO SHOW TIME',
  68         }
  69     }]
  70
  71     def _real_extract(self, url):
  72         video_id = self._match_id(url)
  73         webpage = self._download_webpage(url, video_id)
  74
  75         html5_videos = self._parse_html5_media_entries(
  76             url, webpage.replace('video-js', 'video'), video_id, 'hls')
  77         if not html5_videos:
  78             self.raise_login_required(method='cookies')
  79         infodict = html5_videos[0]
  80         infodict.update({
  81             'id': video_id,
  82             'title': self._html_search_regex(r'class="archive-title">(.+?)</', webpage, 'title')
  83         })
  84
  85         return infodict