# ======================================== # General Bot Rules # ======================================== User-agent: * Crawl-delay: 10 # Allow essential static assets (for rendering) Allow: /misc/*.css Allow: /misc/*.js Allow: /misc/*.gif Allow: /misc/*.jpg Allow: /misc/*.jpeg Allow: /misc/*.png Allow: /modules/*.css Allow: /modules/*.js Allow: /modules/*.gif Allow: /modules/*.jpg Allow: /modules/*.jpeg Allow: /modules/*.png Allow: /profiles/*.css Allow: /profiles/*.js Allow: /profiles/*.gif Allow: /profiles/*.jpg Allow: /profiles/*.jpeg Allow: /profiles/*.png Allow: /themes/*.css Allow: /themes/*.js Allow: /themes/*.gif Allow: /themes/*.jpg Allow: /themes/*.jpeg Allow: /themes/*.png # Block sensitive or non-public directories Disallow: /hr/ Disallow: /includes/ Disallow: /misc/ Disallow: /modules/ Disallow: /profiles/ Disallow: /scripts/ Disallow: /themes/ Disallow: /newsletter/tag/ Disallow: /newsletter/author/ Disallow: /newsletter/category/ Disallow: /generate_sitemap/ Disallow: /generate_sitemap/* Disallow: /new-home-page-test/ Disallow: /new-home-page-test-2/ # Block specific files Disallow: /CHANGELOG.txt Disallow: /cron.php Disallow: /INSTALL.mysql.txt Disallow: /INSTALL.pgsql.txt Disallow: /INSTALL.sqlite.txt Disallow: /install.php Disallow: /INSTALL.txt Disallow: /LICENSE.txt Disallow: /MAINTAINERS.txt Disallow: /update.php Disallow: /UPGRADE.txt Disallow: /xmlrpc.php # Clean URLs Disallow: /admin/ Disallow: /comment/reply/ Disallow: /filter/tips/ Disallow: /node/add/ Disallow: /search/ Disallow: /user/register/ Disallow: /user/password/ Disallow: /user/login/ Disallow: /user/logout/ # Non-clean URLs Disallow: /?q=admin/ Disallow: /?q=comment/reply/ Disallow: /?q=filter/tips/ Disallow: /?q=node/add/ Disallow: /?q=search/ Disallow: /?q=user/password/ Disallow: /?q=user/register/ Disallow: /?q=user/login/ Disallow: /?q=user/logout/ # ======================================== # Sitemap # ======================================== Sitemap: https://flushinghospital.org/sitemap_index.xml # ======================================== # AI Search / Agent Bots (Allowed) # ======================================== User-agent: OAI-SearchBot User-agent: ChatGPT-User User-agent: PerplexityBot User-agent: FirecrawlAgent User-agent: AndiBot User-agent: ExaBot User-agent: PhindBot User-agent: YouBot Crawl-delay: 5 Allow: / # ======================================== # AI Training Bots (Blocked) # ======================================== User-agent: GPTBot Disallow: / User-agent: Google-Extended Disallow: / User-agent: CCBot Disallow: / User-agent: ClaudeBot Disallow: /