# InstrumentHive robots.txt - 2026-09-17 # Public products, categories, brands, articles and pagination remain crawlable. # This is crawler guidance, not authentication or a rate limiter. User-agent: * # WordPress administration; preserve AJAX needed for frontend rendering. Disallow: /wp-admin$ Disallow: /wp-admin? Disallow: /wp-admin/ Allow: /wp-admin/admin-ajax.php Disallow: /wp-login.php Disallow: /xmlrpc.php Disallow: /wp-cron.php Disallow: /wp-comments-post.php Disallow: /wp-trackback.php # Background service worker and oEmbed endpoints observed in server logs. Disallow: /ih-pwa-worker.php Disallow: /wp-json/oembed$ Disallow: /wp-json/oembed? Disallow: /wp-json/oembed/ # WooCommerce private/generated files; keep public uploads crawlable. Disallow: /wp-content/uploads/wc-logs/ Disallow: /wp-content/uploads/woocommerce_transient_files/ Disallow: /wp-content/uploads/woocommerce_uploads/ # Transactional, account, vendor administration and internal search URLs. Disallow: /cart$ Disallow: /cart/ Disallow: /cart? Disallow: /checkout$ Disallow: /checkout/ Disallow: /checkout? Disallow: /my-account$ Disallow: /my-account/ Disallow: /my-account? Disallow: /dashboard$ Disallow: /dashboard/ Disallow: /dashboard? Disallow: /wc-api$ Disallow: /wc-api/ Disallow: /wc-api? Disallow: /search$ Disallow: /search/ Disallow: /search? # AJAX/API actions and cart mutations (first or later query parameter). Disallow: /*?wc-ajax= Disallow: /*?*&wc-ajax= Disallow: /*?wc-api= Disallow: /*?*&wc-api= Disallow: /*?add-to-cart= Disallow: /*?*&add-to-cart= Disallow: /*?remove_item= Disallow: /*?*&remove_item= Disallow: /*?undo_item= Disallow: /*?*&undo_item= # Internal search, sorting and faceted filters. Disallow: /*?s= Disallow: /*?*&s= Disallow: /*?dgwt_wcas= Disallow: /*?*&dgwt_wcas= Disallow: /*?orderby= Disallow: /*?*&orderby= Disallow: /*?min_price= Disallow: /*?*&min_price= Disallow: /*?max_price= Disallow: /*?*&max_price= Disallow: /*?rating_filter= Disallow: /*?*&rating_filter= Disallow: /*?filter_ Disallow: /*?*&filter_ Disallow: /*?query_type_ Disallow: /*?*&query_type_ # Previews, customization, signed actions and comment reply duplicates. Disallow: /*?preview= Disallow: /*?*&preview= Disallow: /*?preview_id= Disallow: /*?*&preview_id= Disallow: /*?preview_nonce= Disallow: /*?*&preview_nonce= Disallow: /*?_wpnonce= Disallow: /*?*&_wpnonce= Disallow: /*?customize_changeset_uuid= Disallow: /*?*&customize_changeset_uuid= Disallow: /*?customize_theme= Disallow: /*?*&customize_theme= Disallow: /*?doing_wp_cron= Disallow: /*?*&doing_wp_cron= Disallow: /*?download_file= Disallow: /*?*&download_file= Disallow: /*?replytocom= Disallow: /*?*&replytocom= # Query-form oEmbed only; do not block the entire WordPress REST API. Disallow: /*?rest_route=/oembed/ Disallow: /*?*&rest_route=/oembed/ Disallow: /*?rest_route=%2Foembed%2F Disallow: /*?*&rest_route=%2Foembed%2F Disallow: /*?rest_route=%2foembed%2f Disallow: /*?*&rest_route=%2foembed%2f # No blanket query-string ban. Keep p=, page=, paged= and storecategory= # available for public discovery. Do not add separate Allow:/ search-bot # groups: they would replace the generic dynamic-URL restrictions. # Selected training / dataset collection opt-outs. # Applebot-Extended is a usage-control token, not a separate HTTP crawler. User-agent: GPTBot User-agent: ClaudeBot User-agent: Amazonbot User-agent: CCBot User-agent: Applebot-Extended Disallow: / # Google-Extended intentionally has no opt-out here: it also controls # grounding in Gemini Apps and Vertex AI. This preserves that GEO route # but does NOT opt out of the associated Google model-training uses. Sitemap: https://www.instrumenthive.com/sitemap_index.xml