# robots.txt for https://emmauscentre.org
# Optimized for Emmaus Health Centre, a Vercel-hosted React SPA
# Generated on May 15, 2025

# Allow all user agents to access main content
User-agent: *
Allow: /
Allow: /contact
Allow: /about
Allow: /projects
Allow: /gallery
Allow: /get-involved
Allow: /donate
Allow: /hospital/services
Allow: /catechetical/services

# Disallow sensitive or non-essential areas
Disallow: /api/ # Block Vercel serverless function endpoints
Disallow: /_vercel/ # Block Vercel system files
Disallow: /*?* # Block URLs with query parameters to avoid duplicate content
Disallow: /preview/ # Block Vercel preview deployments
Disallow: /admin/ # Block potential admin panels
Disallow: /modal/ # Block dynamic modal states

# Specific rules for Googlebot to optimize JavaScript rendering
User-agent: Googlebot
Allow: /
Allow: /contact
Allow: /about
Allow: /projects
Allow: /gallery
Allow: /get-involved
Allow: /donate
Allow: /hospital/services
Allow: /catechetical/services
Disallow: /api/
Disallow: /_vercel/
Disallow: /*?*
Disallow: /preview/
Disallow: /admin/
Disallow: /modal/
Crawl-delay: 5 # Moderate crawl speed for Vercel serverless environment

# Block resource-heavy bots to reduce server load
User-agent: AhrefsBot
User-agent: SemrushBot
User-agent: MJ12bot
Disallow: /

# Reference sitemap for efficient crawling
Sitemap: https://emmauscentre.org/sitemap.xml