# Search engines — welcome
User-agent: Googlebot
Allow: /

User-agent: Bingbot
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: Yandex
Allow: /

# Claude (Anthropic) — welcome
User-agent: ClaudeBot
Allow: /

User-agent: anthropic-ai
Allow: /

# AI training scrapers — blocked
User-agent: GPTBot
Disallow: /

User-agent: ChatGPT-User
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: FacebookBot
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: Amazonbot
Disallow: /

User-agent: Cohere-ai
Disallow: /

User-agent: PerplexityBot
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: Omgilibot
Disallow: /

User-agent: Timpibot
Disallow: /

# Default — allow (search engines not listed above)
User-agent: *
Disallow: /admin/
Disallow: /analytics/
Disallow: /api/

Sitemap: https://organicchemistrydata.org/sitemap.xml