# https://www.robotstxt.org/robotstxt.html
# This is for any additional robots directives

# Allow all search engines to index everything
User-agent: *
Allow: /

# Specific rules for major search engines
User-agent: Googlebot
Allow: /
Crawl-delay: 0

User-agent: Bingbot
Allow: /
Crawl-delay: 1

User-agent: Slurp
Allow: /
Crawl-delay: 1

# Block problematic bots
User-agent: AhrefsBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: DotBot
Disallow: /

# Medical website specific - block scraping bots
User-agent: ia_archiver
Disallow: /

User-agent: ScrapyBot
Disallow: /

# Block access to development and system files
Disallow: /api/
Disallow: /_next/
Disallow: /out/
Disallow: /.next/
Disallow: /node_modules/
Disallow: /admin/
Disallow: /private/
Disallow: /*?*utm_*
Disallow: /*?*fbclid*
Disallow: /*?*gclid*
Disallow: /*?*ref=*
Disallow: /*?*source=*

# Allow important assets for SEO
Allow: /logo.webp
Allow: /doctors/
Allow: /building/
Allow: /*.css
Allow: /*.js
Allow: /*.webp
Allow: /*.jpg
Allow: /*.png
Allow: /*.svg
Allow: /manifest.json
Allow: /favicon.ico

# Crawl-delay for server health
Crawl-delay: 1

# Sitemap locations (multiple formats for better indexing)
Sitemap: https://eastgate.com.na/sitemap.xml

# Host directive (helps with canonicalization)
Host: https://eastgate.com.na

# Contact information for webmasters
# Contact: info@eastgate.com.na