# PetFood Data Station - robots.txt (2026-07-17 SEO/AI-crawler optimized)
# Base: https://petforai.com

# ===== General crawlers =====
User-agent: *
Allow: /
Allow: /site/
Allow: /llm.txt
Allow: /llm-context.txt
Allow: /llms-full.txt
Allow: /sitemap.xml
Allow: /api/v1/topics
Allow: /api/v1/llm_context
Allow: /api/v1/nutrient
Allow: /api/v1/cross_compare
Disallow: /api/v1/all
Disallow: /api/v1/dump
Disallow: /api/v1/raw/
Disallow: /private/
Disallow: /admin
Disallow: /docs
Sitemap: https://petforai.com/sitemap.xml

# ===== AI Crawlers - explicitly allowed =====
# OpenAI (ChatGPT, GPTBot, SearchBot)
User-agent: GPTBot
Allow: /llm.txt
Allow: /llm-context.txt
Allow: /llms-full.txt
Allow: /sitemap.xml
Allow: /api/v1/topics
Allow: /api/v1/llm_context
Allow: /api/v1/nutrient
Allow: /api/v1/cross_compare
Crawl-delay: 10

User-agent: ChatGPT-User
Allow: /
Crawl-delay: 5

User-agent: OAI-SearchBot
Allow: /
Crawl-delay: 10

# Anthropic Claude
User-agent: ClaudeBot
Allow: /
Crawl-delay: 10

User-agent: Claude-Web
Allow: /
Crawl-delay: 5

User-agent: anthropic-ai
Allow: /
Crawl-delay: 10

# Google (Gemini, AI Overviews)
User-agent: Google-Extended
Allow: /
Crawl-delay: 10

User-agent: Googlebot
Allow: /
Crawl-delay: 5

# Microsoft (Bing + Copilot)
User-agent: Bingbot
Allow: /
Crawl-delay: 5

User-agent: MSNBot-Media
Allow: /
Crawl-delay: 10

# Perplexity
User-agent: PerplexityBot
Allow: /
Crawl-delay: 10

User-agent: Perplexity-User
Allow: /
Crawl-delay: 5

# Common Crawl (used by many AI training pipelines)
User-agent: CCBot
Allow: /
Crawl-delay: 30

# Apple Intelligence
User-agent: Applebot-Extended
Allow: /
Crawl-delay: 10

# Meta AI
User-agent: Meta-ExternalAgent
Allow: /
Crawl-delay: 10

# ===== Bad bots - block aggressive scrapers =====
User-agent: Bytespider
Disallow: /

User-agent: ImagesiftBot
Disallow: /