# Akin's African Restaurant — robots.txt
# https://akinsrestaurant.ca

# ------------------------------------------------------------------
# llms.txt is intentionally allowed for AI agents to crawl, but it
# is served with the HTTP response header `X-Robots-Tag: noindex`
# (see /_headers) so search engines will not index it.
# ------------------------------------------------------------------

# Default — all search and social bots
User-agent: *
Allow: /
Disallow: /privacy-policy.html
Disallow: /terms-of-use.html

# Googlebot
User-agent: Googlebot
Allow: /
Disallow: /privacy-policy.html
Disallow: /terms-of-use.html

# Bingbot
User-agent: Bingbot
Allow: /
Disallow: /privacy-policy.html
Disallow: /terms-of-use.html

# AI crawlers — allow public content, block legal pages
User-agent: GPTBot
User-agent: ChatGPT-User
User-agent: OAI-SearchBot
User-agent: CCBot
User-agent: anthropic-ai
User-agent: Claude-Web
User-agent: ClaudeBot
User-agent: Google-Extended
User-agent: FacebookBot
User-agent: Meta-ExternalAgent
User-agent: cohere-ai
User-agent: PerplexityBot
user-agent: Perplexity-User
User-agent: YouBot
User-agent: Applebot-Extended
User-agent: Bytespider
User-agent: Amazonbot
User-agent: DuckAssistBot
User-agent: MistralAI-User
Allow: /
Allow: /llms.txt
Disallow: /privacy-policy.html
Disallow: /terms-of-use.html

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

# Heavy crawlers — rate limit
User-agent: Baiduspider
Crawl-delay: 10

User-agent: Yandex
Crawl-delay: 10

# Sitemap
Sitemap: https://akinsrestaurant.ca/sitemap.xml