# Kerala Restaurant (Authentic South Indian, Indo-Chinese Cuisine) - Robots.txt
# Website: https://keralarestaurantyeg.ca
# Last Updated: June 2026

# ==========================================
# Default Rules for All Crawlers
# ==========================================
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=*

# ==========================================
# Search Engine Crawlers (Google, Bing, etc.)
# Block llms.txt and legal pages from search engine indexing
# ==========================================
User-agent: Googlebot
User-agent: Googlebot-Image
User-agent: Googlebot-News
User-agent: Googlebot-Video
User-agent: Bingbot
User-agent: Slurp
User-agent: DuckDuckBot
User-agent: YandexBot
User-agent: Baiduspider
Allow: /
Disallow: /llms.txt
Disallow: /components/
Disallow: /privacy-policy.html
Disallow: /terms-of-use.html

# ==========================================
# AI Bot Specific Rules
# Allow AI crawlers to access llms.txt
# ==========================================
User-agent: GPTBot
User-agent: ChatGPT-User
User-agent: CCBot
User-agent: anthropic-ai
User-agent: Claude-Web
User-agent: ClaudeBot
User-agent: Google-Extended
User-agent: FacebookBot
User-agent: cohere-ai
User-agent: PerplexityBot
User-agent: YouBot
Allow: /
Allow: /llms.txt
Disallow: /components/
Disallow: /privacy-policy.html
Disallow: /terms-of-use.html

# ==========================================
# Google Ads Bot
# ==========================================
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

User-agent: SemrushBot
Crawl-delay: 5

User-agent: AhrefsBot
Crawl-delay: 5

# ==========================================
# Noindex Directive for llms.txt
# Prevent llms.txt from appearing in search engine results
# ==========================================
Noindex: /llms.txt

# ==========================================
# Sitemap Location
# ==========================================
Sitemap: https://keralarestaurantyeg.ca/sitemap.xml