# Allow traditional search engines
User-agent: Googlebot
Allow: /

User-agent: Bingbot
Allow: /

User-agent: Slurp
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: Baiduspider
Allow: /

User-agent: YandexBot
Allow: /

User-agent: facebookexternalhit
Allow: /

User-agent: Twitterbot
Allow: /

User-agent: LinkedInBot
Allow: /

# Block AI training crawlers
User-agent: GPTBot
Disallow: /

User-agent: ChatGPT-User
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: Claude-Web
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: Omgilibot
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: Meta-ExternalAgent
Disallow: /

User-agent: Meta-ExternalFetcher
Disallow: /


User-agent: Diffbot
Disallow: /

User-agent: PerplexityBot
Disallow: /

User-agent: YouBot
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Amazonbot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: ChatGPT
Disallow: /

User-agent: PiplBot
Disallow: /

User-agent: Scrapy
Disallow: /

User-agent: python-requests
Disallow: /

User-agent: SemrushBot
Disallow: /

User-agent: AhrefsBot
Disallow: /

User-agent: MJ12bot
Disallow: /

# Default rule for unlisted crawlers
User-agent: *
Crawl-delay: 1
Disallow: /admin/
Disallow: /.env
Disallow: /package.json
Disallow: /node_modules/

# Sitemap location
Sitemap: https://noscript.show/sitemap.xml