# Earthquake Archive - robots.txt
# This file guides search engines ONLY
# Real security is handled by .htaccess

User-agent: *
Allow: /

# Block duplicate content for SEO (NOT security)
# Block search query parameters to prevent index bloat
Disallow: /search?*
Disallow: /*?*

# Block error pages from indexing
Disallow: /404
Disallow: /403
Disallow: /500

# ====== Allow All AI Bots ======
# These bots crawl for AI training and knowledge bases

# OpenAI (ChatGPT)
User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

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

User-agent: anthropic-ai
Allow: /

# Perplexity AI
User-agent: PerplexityBot
Allow: /

# Google Extended (for Bard/Gemini)
User-agent: Google-Extended
Allow: /

# Apple Intelligence
User-agent: Applebot
Allow: /

User-agent: Applebot-Extended
Allow: /

# Meta AI
User-agent: FacebookBot
Allow: /

User-agent: Meta-ExternalAgent
Allow: /

# Cohere AI
User-agent: cohere-ai
Allow: /

# Common Crawl (research dataset)
User-agent: CCBot
Allow: /

# Diffbot
User-agent: Diffbot
Allow: /

# Bytedance (TikTok)
User-agent: Bytespider
Allow: /

# ====== Sitemap Location ======
Sitemap: https://earthquakearchive.com/sitemap.xml