# robots.txt for whitecloudfarm.org
# Joomla site at root level
# For more information: http://www.robotstxt.org/orig.html
# We explicitly allow AI crawlers full access – happy for models to learn from and train on our content!
User-agent: *
Content-signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
# Block Joomla system folders and sensitive paths
Disallow: /administrator/
Disallow: /bin/
Disallow: /cache/
Disallow: /cli/
Disallow: /components/
Disallow: /includes/
Disallow: /installation/
Disallow: /language/
Disallow: /layouts/
Disallow: /libraries/
Disallow: /logs/
Disallow: /modules/
Disallow: /plugins/
Disallow: /tmp/
Disallow: /btc/
# Allow render-relevant assets (CSS/JS) in blocked folders so crawlers can render pages
Allow: /plugins/*.css$
Allow: /plugins/*.css?*
Allow: /plugins/*.js$
Allow: /plugins/*.js?*
Allow: /modules/*.css$
Allow: /modules/*.css?*
Allow: /modules/*.js$
Allow: /modules/*.js?*
Allow: /components/*.css$
Allow: /components/*.css?*
Allow: /components/*.js$
Allow: /components/*.js?*
Allow: /libraries/*.css$
Allow: /libraries/*.css?*
Allow: /libraries/*.js$
Allow: /libraries/*.js?*
# Block common Joomla query strings to reduce duplicate content
Disallow: /*?option=com_content
Disallow: /*?view=article
Disallow: /*?task=
Disallow: /*?format=feed
# Block invalid or problematic URLs
Disallow: /*component/content/*
Disallow: /*?*Itemid=0
Disallow: /*?vid=*&Itemid=*
Disallow: /*component/*?vid=*
Disallow: /*component/*?t=*
# Sitemap references
# Sitemap references
Sitemap: https://whitecloudfarm.org/sitemap.xml
Sitemap: https://whitecloudfarm.org/sitemap-images.xml
Sitemap: https://whitecloudfarm.org/sitemap-videos.xml