# Eat-A-Pita Robots.txt
# Main directives for all bots
User-agent: *
Allow: /
Disallow: /config/
Disallow: /search/
Disallow: /account/
Disallow: /api/
Allow: /api/ui-extensions/
Disallow: /static/
Disallow: /*?*author=*
Disallow: /*?*tag=*
Disallow: /*?*month=*
Disallow: /*?*view=*
Disallow: /*?*format=*

# Legal pages - disallow for all bots
Disallow: /privacy-policy.html
Disallow: /terms-of-use.html

# Prevent search engines from indexing llms.txt (but allow crawling)
# This keeps llms.txt accessible but not in search results
User-agent: Googlebot
Disallow: /llms.txt

User-agent: Bingbot
Disallow: /llms.txt

User-agent: Slurp
Disallow: /llms.txt

User-agent: DuckDuckBot
Disallow: /llms.txt

User-agent: Yandex
Disallow: /llms.txt

# AI Bot specific directives - Allow full access to llms.txt and main content
User-agent: GPTBot
User-agent: ChatGPT-User
User-agent: CCBot
User-agent: anthropic-ai
User-agent: Google-Extended
User-agent: FacebookBot
User-agent: Claude-Web
User-agent: cohere-ai
User-agent: PerplexityBot
User-agent: Applebot-Extended
Allow: /
Allow: /llms.txt
Disallow: /privacy-policy.html
Disallow: /terms-of-use.html

# Google Ads Bot
User-agent: AdsBot-Google
User-agent: AdsBot-Google-Mobile
User-agent: AdsBot-Google-Mobile-Apps
Allow: /

# Sitemap location
Sitemap: https://www.eat-a-pita.ca/sitemap.xml

# Crawl delay for heavy bots
User-agent: Baiduspider
Crawl-delay: 10