# robots.txt for theculturalatlas.org

# ---------------------------------------------------------------
# Default
# ---------------------------------------------------------------
User-agent: *
Allow: /
Disallow: /search
Disallow: /do-not-crawl/

# ---------------------------------------------------------------
# Search and answer engines - ALLOWED
# ---------------------------------------------------------------

User-agent: Googlebot
Allow: /

User-agent: Bingbot
Allow: /

User-agent: Applebot
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: Claude-SearchBot
Allow: /

User-agent: Claude-User
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

# ---------------------------------------------------------------
# Model training crawlers - BLOCKED
# ---------------------------------------------------------------

User-agent: GPTBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: meta-externalagent
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: Amazonbot
Disallow: /do-not-crawl/

# ---------------------------------------------------------------
Sitemap: https://theculturalatlas.org/sitemap.xml