yt-dlp/yt_dlp/extractor/mixch.py
2022-12-27 03:01:22 +05:30

86 lines
3.0 KiB
Python
Raw Blame History

This file contains invisible Unicode characters

This file contains invisible Unicode characters that are indistinguishable to humans but may be processed differently by a computer. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

from .common import InfoExtractor
from ..utils import (
ExtractorError,
traverse_obj,
)
class MixchIE(InfoExtractor):
IE_NAME = 'mixch'
_VALID_URL = r'https?://(?:www\.)?mixch\.tv/u/(?P<id>\d+)'
_TESTS = [{
'url': 'https://mixch.tv/u/16236849/live',
'skip': 'don\'t know if this live persists',
'info_dict': {
'id': '16236849',
'title': '24配信シェア⭕投票🙏💦',
'comment_count': 13145,
'view_count': 28348,
'timestamp': 1636189377,
'uploader': '🦥伊咲👶🏻#フレアワ',
'uploader_id': '16236849',
}
}, {
'url': 'https://mixch.tv/u/16137876/live',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(f'https://mixch.tv/u/{video_id}/live', video_id)
initial_js_state = self._parse_json(self._search_regex(
r'(?m)^\s*window\.__INITIAL_JS_STATE__\s*=\s*(\{.+?\});\s*$', webpage, 'initial JS state'), video_id)
is_live = initial_js_state.get('liveInfo')
if not is_live:
self.raise_no_formats('Livestream has ended or has not started', expected=True)
return {
'id': video_id,
'title': traverse_obj(initial_js_state, ('liveInfo', 'title')),
'comment_count': traverse_obj(initial_js_state, ('liveInfo', 'comments')),
'view_count': traverse_obj(initial_js_state, ('liveInfo', 'visitor')),
'timestamp': traverse_obj(initial_js_state, ('liveInfo', 'created')),
'uploader': traverse_obj(initial_js_state, ('broadcasterInfo', 'name')),
'uploader_id': video_id,
'formats': [{
'format_id': 'hls',
'url': traverse_obj(initial_js_state, ('liveInfo', 'hls')) or 'https://d1hd0ww6piyb43.cloudfront.net/hls/torte_%s.m3u8' % video_id,
'ext': 'mp4',
'protocol': 'm3u8',
}] if is_live else [],
'live_status': 'is_live' if is_live else 'is_upcoming',
}
class MixchArchiveIE(InfoExtractor):
IE_NAME = 'mixch:archive'
_VALID_URL = r'https?://(?:www\.)?mixch\.tv/archive/(?P<id>\d+)'
_TESTS = [{
'url': 'https://mixch.tv/archive/421',
'skip': 'paid video, no DRM. expires at Jan 23',
'info_dict': {
'id': '421',
'title': '96NEKO SHOW TIME',
}
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
html5_videos = self._parse_html5_media_entries(
url, webpage.replace('video-js', 'video'), video_id, 'hls')
if not html5_videos:
self.raise_login_required(method='cookies')
infodict = html5_videos[0]
infodict.update({
'id': video_id,
'title': self._html_search_regex(r'class="archive-title">(.+?)</', webpage, 'title')
})
return infodict