# FILE: Client sites (all except Hine and Elmwood)
# Rename to robots.txt when uploading.
# Before uploading: replace the Sitemap line with the site's own,
# and keep any extra rules the site already had.
 
# AI training crawlers
User-agent: GPTBot
User-agent: ClaudeBot
User-agent: meta-externalagent
User-agent: Amazonbot
User-agent: Applebot-Extended
User-agent: CCBot
User-agent: Bytespider
Disallow: /
 
# Small AI crawlers seen in our logs, and SEO crawlers we don't use
User-agent: ElevenlabsCrawler
User-agent: LinkupBot
User-agent: SofyaBot
User-agent: ExaSearchBot
User-agent: SeltzSitemapFetcher
User-agent: trendictionbot
User-agent: PipericBot
User-agent: InsightBaseBot
User-agent: MJ12bot
User-agent: DotBot
User-agent: BLEXBot
User-agent: DataForSeoBot
User-agent: serpstatbot
User-agent: Barkrowler
Disallow: /
 
# Everyone else: search engines, AI answer bots, Ahrefs, Semrush
User-agent: *
Disallow: /wp-admin/
Allow: /wp-admin/admin-ajax.php
Disallow: /?s=
Disallow: /search/

# LGM Image Shield
User-agent: Googlebot-Image
Allow: /wp-content/uploads/2022/03/favicon.png
Allow: /wp-content/uploads/2021/08/smlogo.png
Disallow: /wp-content/uploads/

User-agent: msnbot-media
Disallow: /wp-content/uploads/

Sitemap: https://kwschool.co.uk/wp-sitemap.xml