# RefractOne Robots.txt
# Purpose: Optimise crawl efficiency, eliminate low-value paths, prioritise revenue pages

User-agent: *
Allow: /

# Ensure critical assets are crawlable for proper rendering
Allow: /wp-content/uploads/
Allow: /assets/
Allow: /static/
Allow: /*.css$
Allow: /*.js$

# Block admin and backend areas
Disallow: /wp-admin/
Allow: /wp-admin/admin-ajax.php
Disallow: /wp-login.php

# Block system, temporary, and sensitive directories
Disallow: /cgi-bin/
Disallow: /tmp/
Disallow: /private/
Disallow: /core/

# Block internal search and dynamically generated low-value pages
Disallow: /search/
Disallow: /*?s=
Disallow: /*?q=

# Block URL parameters that create duplicate content
Disallow: /*?utm_source=
Disallow: /*?utm_medium=
Disallow: /*?utm_campaign=
Disallow: /*?utm_term=
Disallow: /*?utm_content=
Disallow: /*&utm_
Disallow: /*?ref=
Disallow: /*?replytocom=
Disallow: /*?sessionid=

# Optional: prevent crawling of filtered or faceted URLs if implemented later
Disallow: /*?filter=
Disallow: /*?sort=

# Crawl rate control (kept conservative)
Crawl-delay: 10

# Sitemap location (critical for discovery and prioritisation)
Sitemap: https://refractone.com/sitemap.xml