# Chef's Indian Kitchen — robots.txt
# https://chefsindiankitchen.com

# ===== General crawl rules =====
User-agent: *
Allow: /
Disallow: /config/
Disallow: /search/
Disallow: /account/
Disallow: /api/
Allow: /api/ui-extensions/
Disallow: /static/
Disallow: /components/
Disallow: /*?*author=*
Disallow: /*?*tag=*
Disallow: /*?*month=*
Disallow: /*?*view=*
Disallow: /*?*format=*
Disallow: /privacy-policy.html
Disallow: /terms-of-use.html

# llms.txt should be discoverable by AI crawlers but NOT indexed in search results.
# Noindex is enforced via X-Robots-Tag in the _headers file (Netlify/Cloudflare Pages).
# The Noindex directive below is also honoured by Google as a fallback signal.
Noindex: /llms.txt

# ===== AI crawler directives =====
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: Applebot-Extended
User-agent: Bytespider
Allow: /
Allow: /llms.txt
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 heavy bots =====
User-agent: Baiduspider
Crawl-delay: 10

# ===== Sitemap =====
Sitemap: https://chefsindiankitchen.com/sitemap.xml