# Global base rules User-agent: * Allow: /wp-admin/admin-ajax.php Allow: /*/*.css Allow: /*/*.js Disallow: /wp-admin/ Disallow: /wp-includes/ Disallow: /readme.html Disallow: /license.txt Disallow: /xmlrpc.php Disallow: /wp-login.php Disallow: /wp-register.php Disallow: */disclaimer/* Disallow: *?attachment_id= Disallow: /*?filtering= # Search Engine Visibility User-agent: Googlebot Allow: / User-agent: bingbot Allow: / User-agent: DuckDuckBot Allow: / # AI Bot Restrictions User-agent: PerplexityBot Disallow: / User-agent: YouBot Disallow: / User-agent: ChatGPT-User Disallow: / User-agent: Amazonbot Disallow: / User-agent: OAI-SearchBot Disallow: / User-agent: AI2Bot Disallow: / User-agent: Applebot Disallow: / User-agent: PhindBot Disallow: / # Bot & Scraper Protection (Basic List) User-agent: python-requests Disallow: / User-agent: curl Disallow: / User-agent: wget Disallow: / User-agent: libwww-perl Disallow: / User-agent: Go-http-client Disallow: / User-agent: Apache-HttpClient Disallow: / User-agent: Scrapy Disallow: / User-agent: Java Disallow: / Disallow: *?replytocom= Disallow: *?replytocom # Allow CSS/JS User-agent: * Allow: /*.css$ User-agent: * Allow: /*.js$ # Allow Images User-agent: * Allow: /*.jpg$ User-agent: * Allow: /*.jpeg$ User-agent: * Allow: /*.png$ User-agent: * Allow: /*.gif$ User-agent: * Allow: /*.webp$ User-agent: * Allow: /*.bmp$ User-agent: * Allow: /*.ico$ User-agent: * Allow: /*.svg$ # Block Search & Pagination User-agent: * Disallow: /?s= Disallow: /*?s= Disallow: /search/ Disallow: /page/ Disallow: /*?p= Disallow: /*?paged= Disallow: /*?page= # Block common crawl trap parameters User-agent: * Disallow: /*?p=* Disallow: /*&p=* Disallow: /*?preview=* User-agent: * Allow: /ads.txt User-agent: * Allow: /app-ads.txt # Custom Rules User-agent: Mediapartners-Google Allow: / User-agent: AdsBot-Google Allow: / User-agent: AdsBot-Google-Mobile Allow: / User-agent: Msnbot Allow: / User-agent: msnbot-media Allow: /wp-content/uploads/ User-agent: Applebot Allow: / User-agent: Yandex Allow: / User-agent: YandexImages Disallow: /wp-content/uploads/ User-agent: Slurp Allow: / # Generated by Better Robots.txt # https://better-robots.com # Crawl governance based on the Interpretive Governance framework # Reference: https://interpretive-governance.org/