yourupload_fix.py

gistfile1.txt

from urllib.parse import urljoin

from yt_dlp.extractor.common import InfoExtractor
from yt_dlp.utils import determine_ext


class YourUploadRevivedIE(InfoExtractor):
    IE_NAME = 'yourupload:revived'
    _VALID_URL = r'https?://(?:www\.)?(?:yourupload\.com/(?:watch|embed)|embed\.yourupload\.com)/(?P<id>[A-Za-z0-9]+)'
    _TESTS = [{
        'url': 'https://www.yourupload.com/embed/5ReRhH1JrQvG',
        'only_matching': True,
    }]

    def _real_extract(self, url):
        video_id = self._match_id(url)
        embed_url = f'https://www.yourupload.com/embed/{video_id}'

        webpage = self._download_webpage(
            embed_url, video_id,
            headers={'Referer': 'https://www.yourupload.com/'}
        )

        title = (
            self._html_search_meta(['og:title', 'twitter:title'], webpage, default=None)
            or self._search_regex(
                [r'<title>([^<]+)</title>',
                 r'''(?i)\btitle\s*:\s*["']([^"']+)'''],
                webpage, 'title', default=video_id)
        )

        thumbnail = self._html_search_meta(
            ['og:image', 'twitter:image'], webpage, default=None)

        video_url = (
            self._html_search_meta(
                ['og:video:url', 'og:video', 'twitter:player:stream'],
                webpage, default=None)
            or self._search_regex(
                [
                    r'''<source[^>]+src=["']([^"'?]+\.(?:mp4|m3u8)(?:\?[^"']*)?)["']''',
                    r'''(?i)\bfile\s*:\s*["']([^"']+)["']''',
                    r'''(?i)\bsrc\s*:\s*["']([^"']+\.(?:mp4|m3u8)(?:\?[^"']*)?)["']''',
                    r'''(?i)\bvideo_url\s*[:=]\s*["']([^"']+)["']''',
                ],
                webpage, 'video url')
        )

        video_url = urljoin(embed_url, video_url)
        thumbnail = urljoin(embed_url, thumbnail) if thumbnail else None
        ext = determine_ext(video_url, None)

        if ext == 'm3u8':
            formats = self._extract_m3u8_formats(
                video_url, video_id, 'mp4', fatal=False,
                headers={'Referer': embed_url}
            )
            for f in formats:
                f.setdefault('http_headers', {})['Referer'] = embed_url
            return {
                'id': video_id,
                'title': title,
                'thumbnail': thumbnail,
                'formats': formats,
                'http_headers': {'Referer': embed_url},
            }

        return {
            'id': video_id,
            'title': title,
            'url': video_url,
            'thumbnail': thumbnail,
            'http_headers': {'Referer': embed_url},
        }