User-agent: *
Allow: /

# Disallow URLs with query parameters (spam/rubbish URLs)
Disallow: /*?*

# Disallow old WordPress/blog URLs
Disallow: /20*/

# Disallow URL injection attempts
Disallow: /http

# Disallow .html extension URLs (canonical uses clean URLs)
Disallow: /*.html$

# Disallow old English/alternate path structure
Disallow: /en/

# Disallow admin/test/system pages
Disallow: /admin/
Disallow: /test/
Disallow: /cdn-cgi/
Disallow: /*.json$

# Disallow font and asset files (AI and search engines don't need these)
Disallow: /*.eot$
Disallow: /*.ttf$
Disallow: /*.woff$
Disallow: /*.woff2$
Disallow: /*.otf$

# LLM/AI Agent Information
Allow: /llms.txt

# Crawl-delay (be nice to servers, applies to Bing, AI bots, etc.)
Crawl-delay: 1

# Sitemaps
Sitemap: https://litequran.net/sitemap.xml
Sitemap: https://litequran.net/sitemap-main.xml
Sitemap: https://litequran.net/sitemap-tafsir.xml