# BINH Vietnamese Restaurant — robots.txt
# https://www.Binhvietnamese.ca

# =============================================
# General crawlers
# =============================================
User-agent: *
Allow: /

# Block component partials (not standalone pages)
Disallow: /components/

# Block internal/utility paths
Disallow: /config/
Disallow: /search/
Disallow: /account/
Disallow: /api/
Allow: /api/ui-extensions/
Disallow: /static/

# Block faceted/filtered URL patterns
Disallow: /*?*author=*
Disallow: /*?*tag=*
Disallow: /*?*month=*
Disallow: /*?*view=*
Disallow: /*?*format=*

# =============================================
# AI crawlers — allow content, block legal pages
# =============================================
User-agent: GPTBot
User-agent: ChatGPT-User
User-agent: CCBot
User-agent: anthropic-ai
User-agent: Google-Extended
User-agent: FacebookBot
User-agent: Claude-Web
User-agent: cohere-ai
User-agent: PerplexityBot
User-agent: Applebot-Extended
Allow: /
Disallow: /components/
Disallow: /privacy-policy.html
Disallow: /terms-of-use.html

# =============================================
# Google Ads crawlers — full access
# =============================================
User-agent: AdsBot-Google
User-agent: AdsBot-Google-Mobile
User-agent: AdsBot-Google-Mobile-Apps
Allow: /

# =============================================
# Rate-limiting for heavy crawlers
# =============================================
User-agent: Baiduspider
Crawl-delay: 10

# =============================================
# Sitemap
# =============================================
Sitemap: https://www.Binhvietnamese.ca/sitemap.xml