import urllib.parse import re from datetime import datetime from yt_dlp.extractor.common import InfoExtractor class VidmolyIE(InfoExtractor): _valid_domains = r'|'.join([r'vidmoly\.biz']) _VALID_URL = r'https?://(?:' + _valid_domains + ')/embed-(?P\w+)\.html$' def _real_extract(self, url): video_id = urllib.parse.unquote_plus(self._match_id(url)) html = self._download_html(url) m3u8_url = re.findall("'(https\\:\\/\\/.*master\\.m3u.*)'", html.text)[0] formats = self._extract_m3u8_formats( m3u8_url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls') title = re.findall(r"(.*)<\/title>", html.text)[0] ret = { 'id': video_id, 'display_id': video_id, 'title': title, 'formats': formats, } return ret