# Indian Authentic Cuisine Robots.txt
# Canonical host: https://indianauthenticcuisines.ca

# Default rules for all crawlers
User-agent: *
Allow: /
Disallow: /config/
Disallow: /search/
Disallow: /account/
Disallow: /api/
Disallow: /static/
Disallow: /components/
Disallow: /privacy-policy.html
Disallow: /terms-of-use.html
Disallow: /llms.txt
Disallow: /*?*author=*
Disallow: /*?*tag=*
Disallow: /*?*month=*
Disallow: /*?*view=*
Disallow: /*?*format=*

# AI crawlers — site is open to AI indexing of public content,
# legal pages excluded; llms.txt is explicitly allowed for AI consumption.
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: PerplexityBot
User-agent: Perplexity-User
User-agent: cohere-ai
User-agent: Applebot-Extended
User-agent: FacebookBot
Allow: /
Allow: /llms.txt
Disallow: /privacy-policy.html
Disallow: /terms-of-use.html

# Google ad crawlers
User-agent: AdsBot-Google
User-agent: AdsBot-Google-Mobile
User-agent: AdsBot-Google-Mobile-Apps
Allow: /

# Crawl delay for high-volume bots
User-agent: Baiduspider
Crawl-delay: 10

User-agent: Yandex
Crawl-delay: 10

# Sitemap location
Sitemap: https://indianauthenticcuisines.ca/sitemap.xml