# =================================================== # 1. GENERAL CRAWL RULES, WOOCOMMERCE & WISHLIST CLEANUP # =================================================== User-agent: * Content-Signal: search=yes, ai-train=no Disallow: /wp-admin/ Allow: /wp-admin/admin-ajax.php # WooCommerce Core Sensitive Pages Disallow: /cart/ Disallow: /checkout/ Disallow: /my-account/ Disallow: /order-received/ Disallow: /checkout/order-received/ # Wishlist, Compare, Order Tracking & Archives Disallow: /wishlist/ Disallow: /wishlist/* Disallow: /compare/ Disallow: /track-order/ Disallow: /author/ # WooCommerce Parameters & Dynamic Action URLs Disallow: /add-to-cart= Disallow: /?remove_item= Disallow: /?add_to_cart= Disallow: /add_to_wishlist= Disallow: /remove_from_wishlist= Disallow: /?orderby= Disallow: /?filter_ Disallow: /?min_price= Disallow: /?max_price= # WordPress Internal Search & Dynamic Query Strings Disallow: /?s= Disallow: /search/ Disallow: /? # Private Uploads (Protected Downloads) Disallow: /wp-content/uploads/woocommerce_uploads/ # Allow Media & Static Assets Allow: /wp-content/uploads/ Allow: /wp-includes/js/ Allow: /wp-content/themes/ Allow: /wp-content/plugins/ # =================================================== # 2. TOP AI SEARCH ENGINES & AGENTIC BOT ALLOW RULES # =================================================== # OpenAI (ChatGPT, SearchGPT) User-agent: GPTBot Allow: / User-agent: ChatGPT-User Allow: / User-agent: OAI-SearchBot Allow: / # Google Gemini & Google AI Overviews User-agent: Google-Extended Allow: / User-agent: GoogleOther Allow: / # Perplexity AI User-agent: PerplexityBot Allow: / # Anthropic (Claude AI) User-agent: ClaudeBot Allow: / User-agent: anthropic-ai Allow: / # Apple Intelligence User-agent: Applebot-Extended Allow: / # Meta AI User-agent: Meta-ExternalAgent Allow: / # Cohere AI User-agent: cohere-ai Allow: / # Common Crawl (Open Data Index for AI Training) User-agent: CCBot Allow: / Content-Signal: search=yes, ai-input=yes, ai-train=no # =================================================== # 3. SITEMAP INDEX LOCATION # =================================================== Sitemap: https://printspk.com/sitemap_index.xml