# ========================================== # robots.txt — WordPress + WooCommerce # Basado en la guia de Sered. Personalizado: # - Bots de ENTRENAMIENTO IA: bloqueados # - Bots de BUSQUEDA/CITACION IA: permitidos (para que te citen) # ========================================== # ========================================== # 1. REGLAS PARA MOTORES DE BUSQUEDA GENERALES # ========================================== User-agent: * Crawl-delay: 10 # Directorios internos y sensibles Disallow: /wp-admin/ Disallow: /wp-includes/ Disallow: /wp-content/plugins/ Disallow: /wp-content/themes/ Disallow: /wp-json/ Disallow: /trackback/ Disallow: /xmlrpc.php # Archivos sensibles Disallow: /.env Disallow: /.git/ Disallow: /wp-config.php Disallow: /wp-cron.php Disallow: /error_log Disallow: /debug.log # Feeds (evita contenido duplicado) Disallow: /feed/ Disallow: /comments/feed/ Disallow: /*/feed/ Disallow: /*/feed/$ Disallow: /*/comments/feed/ # Busquedas internas (grandes consumidoras de CPU: no cachean) Disallow: /?s= Disallow: /*?s= Disallow: /search/ # ========================================== # WOOCOMMERCE — PARAMETROS DE FILTROS Y FACETS # Cada combinacion de filtro genera una URL unica que NO se cachea # y ejecuta una consulta pesada a la BD. Es la causa nº1 de CPU en tiendas. # NO bloquees /shop/, /product-category/ ni /product/: son tu SEO. # ========================================== # --- ATAQUE DETECTADO 20/08/2026 ------------------------------------- # Cientos de IPs distintas rastreando combinaciones de marcas del tipo: # /tienda/?filter_marca=imera%2Cfairland%2Ccool-smart&query_type_marca=or # Son millones de URLs unicas, ninguna cacheable, cada una con una consulta # pesada a la BD. Aqui se declara, pero el bloqueo REAL esta en el .htaccess: # estos bots se hacen pasar por Chrome/Mac y NO respetan robots.txt. # --------------------------------------------------------------------- # Filtros de atributos (layered nav) - todas las variantes Disallow: /*?filter_ Disallow: /*&filter_ Disallow: /*filter_marca Disallow: /*filter_ Disallow: /tienda/*? Disallow: /tienda/page/ # Tipo de consulta del filtro (AND/OR). WooCommerce solo lo emite # con multiseleccion: es la firma exacta del ataque. Disallow: /*?query_type_ Disallow: /*&query_type_ Disallow: /*query_type_ # Filtros de plugins de facetas (WOOF / Berocket / FacetWP / SearchWP) Disallow: /*?swoof Disallow: /*&swoof Disallow: /*?woof_ Disallow: /*&woof_ Disallow: /*?really_curr_tax Disallow: /*?_bhfilter Disallow: /*&_bhfilter Disallow: /*?fwp_ Disallow: /*&fwp_ Disallow: /*?_sf_s Disallow: /*?product_filter # Filtro de precio Disallow: /*?min_price= Disallow: /*&min_price= Disallow: /*?max_price= Disallow: /*&max_price= # Filtro de valoracion Disallow: /*?rating_filter= Disallow: /*&rating_filter= # Ordenacion del catalogo Disallow: /*?orderby= Disallow: /*&orderby= # Paginacion (genera duplicados) Disallow: /*?paged= Disallow: /*&paged= Disallow: /*?page= Disallow: /*&page= # Paginacion de productos y AJAX de WooCommerce Disallow: /*?product-page= Disallow: /*&product-page= Disallow: /*?wc-ajax= Disallow: /*&wc-ajax= Disallow: /*?per_page= Disallow: /*?product_count= Disallow: /*?count= # Acciones de carrito y wishlist Disallow: /*?add-to-cart= Disallow: /*&add-to-cart= Disallow: /*?add_to_wishlist= Disallow: /*&add_to_wishlist= Disallow: /*?removed_item= Disallow: /*?wc-api= Disallow: /*?compare= # Paginas privadas del cliente Disallow: /cart/ Disallow: /checkout/ Disallow: /my-account/ Disallow: /wp-login.php # Recursos esenciales para rastreo y diseno Allow: /wp-admin/admin-ajax.php Allow: /wp-includes/*.js Allow: /wp-includes/*.css Allow: /wp-content/uploads/ Allow: /wp-content/plugins/*.js Allow: /wp-content/plugins/*.css Allow: /wp-content/themes/*.js Allow: /wp-content/themes/*.css # ========================================== # 2. BOTS DE IA — BLOQUEO SELECTIVO # Solo bots VERIFICADOS que respetan robots.txt. # Los que lo ignoran estan en el .htaccess. # # PERMITIDOS A PROPOSITO (no aparecen abajo, por eso pueden pasar): # Googlebot, Bingbot, Applebot -> buscadores clasicos # OAI-SearchBot, ChatGPT-User -> ChatGPT puede citarte # Claude-SearchBot, Claude-User -> Claude puede citarte # PerplexityBot, Perplexity-User -> Perplexity puede citarte # meta-webindexer -> Meta AI puede citarte # facebookexternalhit -> previews de enlaces FB/IG/WhatsApp # ========================================== # --- ANTHROPIC (entrenamiento) --- User-agent: ClaudeBot Disallow: / User-agent: Claude-Web Disallow: / User-agent: anthropic-ai Disallow: / # --- OPENAI (entrenamiento) --- User-agent: GPTBot Disallow: / # --- GOOGLE (entrenamiento / uso interno) --- User-agent: Google-Extended Disallow: / User-agent: GoogleOther Disallow: / User-agent: Google-CloudVertexBot Disallow: / # --- APPLE (entrenamiento) --- User-agent: Applebot-Extended Disallow: / # --- META (entrenamiento y publicidad) --- User-agent: meta-externalagent Disallow: / User-agent: meta-externalads Disallow: / User-agent: FacebookBot Disallow: / # --- COHERE --- User-agent: cohere-ai Disallow: / User-agent: cohere-training-data-crawler Disallow: / # --- AMAZON --- User-agent: Amazonbot Disallow: / # --- DUCKDUCKGO --- User-agent: DuckAssistBot Disallow: / # --- YOU.COM --- User-agent: YouBot Disallow: / # --- MISTRAL --- User-agent: MistralBot Disallow: / # --- xAI (GROK) --- User-agent: xAI-Bot Disallow: / # --- DEEPSEEK --- User-agent: DeepSeekBot Disallow: / # --- HUGGING FACE --- User-agent: HuggingFaceBot Disallow: / # --- ALLEN INSTITUTE FOR AI --- User-agent: Ai2Bot Disallow: / # --- HUAWEI PETAL SEARCH --- User-agent: PetalBot Disallow: / # --- COMMON CRAWL --- User-agent: CCBot Disallow: / # --- BYTESPIDER (tambien en .htaccess) --- User-agent: Bytespider Disallow: / # --- OTROS SCRAPERS Y HERRAMIENTAS SEO --- User-agent: DataForSeoBot Disallow: / User-agent: SemrushBot Disallow: / User-agent: SemrushBot-BA Disallow: / User-agent: SemrushBot-SI Disallow: / User-agent: SemrushBot-SWA Disallow: / User-agent: TurnitinBot Disallow: / User-agent: Omgili Disallow: / User-agent: omgilibot Disallow: / User-agent: magpie-crawler Disallow: / User-agent: img2dataset Disallow: / User-agent: FriendlyCrawler Disallow: / User-agent: Timpibot Disallow: / User-agent: PiplBot Disallow: / User-agent: YandexAdditional Disallow: / User-agent: Sidetrade Disallow: / User-agent: peer39_crawler Disallow: / User-agent: VelenPublicWebCrawler Disallow: / User-agent: ICC-Crawler Disallow: / User-agent: Awario Disallow: / User-agent: Cotoyogi Disallow: / User-agent: EchoboxBot Disallow: / User-agent: ExaBot Disallow: / User-agent: Factset_spyderbot Disallow: / User-agent: ImagesiftBot Disallow: / User-agent: LAIONDownloader Disallow: / # ========================================== # 3. SITEMAP — sustituye por tu dominio real # ========================================== # Sitemap: https://tudominio.com/sitemap_index.xml