# The Mango Tree Indian Food Restaurant — robots.txt
# https://themangotreealberta.ca
#
# llms.txt is intentionally excluded from search engine indexes.
# Standard crawlers must not crawl or index it (Disallow below).
# For a stronger guarantee on supporting servers, also configure an HTTP header:
#     X-Robots-Tag: noindex, nofollow
# on the /llms.txt response.

# ── General crawlers ────────────────────────────────────────────────────────
User-agent: *
Allow: /

# noindex — keep llms.txt out of standard web indexes
Disallow: /llms.txt

# Exclude legal pages
Disallow: /privacy-policy.html
Disallow: /terms-of-use.html

# ── AI / LLM crawlers ───────────────────────────────────────────────────────
# These agents are explicitly permitted to read llms.txt and all public content
User-agent: GPTBot
User-agent: ChatGPT-User
User-agent: OAI-SearchBot
User-agent: CCBot
User-agent: anthropic-ai
User-agent: ClaudeBot
User-agent: Claude-Web
User-agent: Claude-SearchBot
User-agent: Google-Extended
User-agent: PerplexityBot
User-agent: Perplexity-User
User-agent: cohere-ai
User-agent: Applebot-Extended
User-agent: FacebookBot
User-agent: Meta-ExternalAgent
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 crawlers ─────────────────────────────────────────────────────
User-agent: AdsBot-Google
User-agent: AdsBot-Google-Mobile
User-agent: AdsBot-Google-Mobile-Apps
Allow: /

# ── Rate-limited bots ───────────────────────────────────────────────────────
User-agent: Baiduspider
Crawl-delay: 10

User-agent: SemrushBot
Crawl-delay: 5

User-agent: AhrefsBot
Crawl-delay: 5

# ── Sitemap location ────────────────────────────────────────────────────────
Sitemap: https://themangotreealberta.ca/sitemap.xml