# Global rules
# -----------------
User-agent: *
Disallow: /wp-admin/
Disallow: /wp-includes/
Disallow: /wp-content/plugins/
Disallow: /wp-content/themes/
Disallow: /cgi-bin/
Disallow: /trackback/
Disallow: /xmlrpc.php
Disallow: /wp-login.php
Disallow: /wp-signup.php
Disallow: /?s=*
Disallow: /search/
Disallow: /search/*
Disallow: /wp-json/
Disallow: /*/trackback/
Disallow: /*/comments/
Disallow: /*?add-to-cart=*
Disallow: /*?orderby=*
Disallow: /*?filter_*

# Prevent crawling CF challenge URLs
Disallow: /cdn-cgi/bm/cv/
Disallow: /cdn-cgi/challenge-platform/

# Allow access to necessary assets
Allow: /wp-content/uploads/
Allow: /wp-content/cache/

# Sitemap
# -----------------
Sitemap: https://www.accessart.org.uk/sitemap.xml

# Ban bots that don't benefit us.
# --------------------------------
User-agent: AhrefsBot
User-agent: SemrushBot
User-agent: MJ12bot
User-agent: DotBot
User-agent: Nuclei
User-agent: WikiDo
User-agent: Riddler
User-agent: PetalBot
User-agent: Zoominfobot
User-agent: Go-http-client
User-agent: Node/simplecrawler
User-agent: CazoodleBot
User-agent: dotbot/1.0
User-agent: Gigabot
User-agent: Barkrowler
User-agent: BLEXBot
User-agent: magpie-crawler
Disallow: /

# Block feeds for search engines to reduce server load
# -------------------------------
User-agent: Googlebot
Disallow: /*/feed/
User-agent: Bingbot
Disallow: /*/feed/
User-agent: Slurp
Disallow: /*/feed/

# Allow feeds for other user agents
# -----------------------------------
User-agent: *
Allow: /*/feed/