# My Spice N Rice — robots.txt
# https://www.myspicenrice.ca

# ── General crawlers ──────────────────────────────────────────
User-agent: *
Allow: /
Disallow: /privacy-policy.html
Disallow: /terms-of-use.html

# ── AI / LLM training crawlers ────────────────────────────────
# Allow full crawl; block legal pages from training data
User-agent: GPTBot
User-agent: ChatGPT-User
User-agent: CCBot
User-agent: anthropic-ai
User-agent: Google-Extended
User-agent: Claude-Web
User-agent: cohere-ai
User-agent: PerplexityBot
User-agent: YouBot
Allow: /
Disallow: /privacy-policy.html
Disallow: /terms-of-use.html

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

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

# ── Sitemap ───────────────────────────────────────────────────
Sitemap: https://www.myspicenrice.ca/sitemap.xml