# Makkar Kitchen Indian Restaurant - Robots.txt
# https://makkarkitchen.ca

# ==========================================
# Main directives for all bots
# ==========================================
User-agent: *
Allow: /
Disallow: /components/
Disallow: /config/
Disallow: /search/
Disallow: /account/
Disallow: /api/
Disallow: /static/
Disallow: /*?*author=*
Disallow: /*?*tag=*
Disallow: /*?*month=*
Disallow: /*?*view=*
Disallow: /*?*format=*

# Block legal pages from all crawlers (kept out of sitemap.xml too)
Disallow: /privacy-policy.html
Disallow: /terms-of-use.html

# ==========================================
# Search Engines - block legal pages, noindex llms.txt
# (Noindex directive here is a best-effort convention honored by
# some engines; if the host supports custom response headers,
# prefer sending X-Robots-Tag: noindex on /llms.txt instead.)
# ==========================================
User-agent: Googlebot
User-agent: Bingbot
User-agent: Yandex
User-agent: DuckDuckBot
Disallow: /privacy-policy.html
Disallow: /terms-of-use.html
Noindex: /llms.txt

User-agent: Baiduspider
User-agent: Sogou
Disallow: /privacy-policy.html
Disallow: /terms-of-use.html
Noindex: /llms.txt
Crawl-delay: 10

# ==========================================
# AI Crawlers - full access to llms.txt and site content
# ==========================================
User-agent: GPTBot
User-agent: ChatGPT-User
User-agent: OAI-SearchBot
User-agent: CCBot
User-agent: anthropic-ai
User-agent: Claude-Web
User-agent: cohere-ai
User-agent: Google-Extended
User-agent: PerplexityBot
User-agent: Applebot-Extended
User-agent: meta-externalagent
User-agent: Amazonbot
Allow: /llms.txt
Allow: /
Disallow: /privacy-policy.html
Disallow: /terms-of-use.html
Disallow: /components/

# ==========================================
# Google Ads Bot
# ==========================================
User-agent: AdsBot-Google
User-agent: AdsBot-Google-Mobile
User-agent: AdsBot-Google-Mobile-Apps
Allow: /

# ==========================================
# Sitemap and LLMs.txt locations
# ==========================================
Sitemap: https://makkarkitchen.ca/sitemap.xml

# LLMs.txt location for AI agents
# https://makkarkitchen.ca/llms.txt