# Castelli Mercato — robots.txt
# https://www.castellimercato.com/

# Default rules for all crawlers
User-agent: *
Allow: /

# llms.txt is for AI assistants, not for search result pages.
# Keep it crawlable but out of the index.
Noindex: /llms.txt

# AI assistants and LLM crawlers: welcome to read the site and llms.txt,
# but skip the legal pages.
User-agent: GPTBot
User-agent: ChatGPT-User
User-agent: OAI-SearchBot
User-agent: ClaudeBot
User-agent: Claude-User
User-agent: Claude-SearchBot
User-agent: Claude-Web
User-agent: anthropic-ai
User-agent: PerplexityBot
User-agent: Perplexity-User
User-agent: Google-Extended
User-agent: Applebot-Extended
User-agent: CCBot
User-agent: cohere-ai
User-agent: FacebookBot
User-agent: meta-externalagent
User-agent: Amazonbot
User-agent: Bytespider
User-agent: DuckAssistBot
User-agent: MistralAI-User
Allow: /
Allow: /llms.txt
Allow: /menu.html
Allow: /tags/
Disallow: /privacy-policy.html
Disallow: /terms-of-use.html

# Google Ads bots
User-agent: AdsBot-Google
User-agent: AdsBot-Google-Mobile
Allow: /

# Image crawlers — our food photography should be indexable
User-agent: Googlebot-Image
Allow: /assets/

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

User-agent: YandexBot
Crawl-delay: 10

# Sitemap
Sitemap: https://www.castellimercato.com/sitemap.xml