# === Reglas generales para todos los bots (humanos crawlers respetuosos) === User-agent: * Allow: / Allow: /wp-admin/admin-ajax.php Disallow: /wp-admin/ Disallow: /wp-login.php # Bloquear páginas técnicas de WooCommerce Disallow: /cart/ Disallow: /checkout/ Disallow: /my-account/ Disallow: /wishlist/ Disallow: /thank-you/ Disallow: /track-order/ Disallow: /cdn-cgi/ # Bloquear feeds de comentarios Disallow: /comments/feed/ # Bloquear parámetros de carrito (sintaxis corregida) Disallow: /*?add-to-cart= Disallow: /*&add-to-cart= Disallow: /*?remove_item= Disallow: /*?wc-ajax= # Bloquear ordenamientos y filtros de WooCommerce (URLs costosas) Disallow: /*?orderby= Disallow: /*?filter_ Disallow: /*?min_price= Disallow: /*?max_price= # Bloquear búsqueda interna Disallow: /?s= Disallow: /search/ Crawl-delay: 5 # === Sitemap === Sitemap: https://cervezasalemanas.mx/sitemap_index.xml # === LLMs / Bots de búsqueda en tiempo real (PERMITIDOS - traen usuarios) === # Estos bots visitan tu sitio cuando un usuario le pregunta a la IA por tus productos # Anthropic - Claude visita cuando un usuario lo pide User-agent: Claude-User Allow: / Allow: /llms.txt Crawl-delay: 2 Disallow: /cart/ Disallow: /checkout/ Disallow: /my-account/ Disallow: /wishlist/ Disallow: /thank-you/ Disallow: /track-order/ Disallow: /*?add-to-cart= Disallow: /*&add-to-cart= Disallow: /*?wc-ajax= # Anthropic - búsqueda de Claude User-agent: Claude-SearchBot Allow: / Allow: /llms.txt Crawl-delay: 2 Disallow: /cart/ Disallow: /checkout/ Disallow: /my-account/ Disallow: /wishlist/ Disallow: /thank-you/ Disallow: /track-order/ Disallow: /*?add-to-cart= Disallow: /*&add-to-cart= Disallow: /*?wc-ajax= # OpenAI - ChatGPT visita cuando un usuario lo pide User-agent: ChatGPT-User Allow: / Allow: /llms.txt Crawl-delay: 2 Disallow: /cart/ Disallow: /checkout/ Disallow: /my-account/ Disallow: /wishlist/ Disallow: /thank-you/ Disallow: /track-order/ Disallow: /*?add-to-cart= Disallow: /*&add-to-cart= Disallow: /*?wc-ajax= # OpenAI - búsqueda de SearchGPT User-agent: OAI-SearchBot Allow: / Allow: /llms.txt Crawl-delay: 2 Disallow: /cart/ Disallow: /checkout/ Disallow: /my-account/ Disallow: /wishlist/ Disallow: /thank-you/ Disallow: /track-order/ Disallow: /*?add-to-cart= Disallow: /*&add-to-cart= Disallow: /*?wc-ajax= # Perplexity - búsqueda y respuestas en vivo User-agent: PerplexityBot Allow: / Allow: /llms.txt Crawl-delay: 2 Disallow: /cart/ Disallow: /checkout/ Disallow: /my-account/ Disallow: /wishlist/ Disallow: /thank-you/ Disallow: /track-order/ Disallow: /*?add-to-cart= Disallow: /*&add-to-cart= Disallow: /*?wc-ajax= User-agent: Perplexity-User Allow: / Allow: /llms.txt Crawl-delay: 2 Disallow: /cart/ Disallow: /checkout/ Disallow: /my-account/ Disallow: /wishlist/ Disallow: /thank-you/ Disallow: /track-order/ Disallow: /*?add-to-cart= Disallow: /*&add-to-cart= Disallow: /*?wc-ajax= # === LLMs / Bots de entrenamiento (PERMITIDOS con crawl-delay alto) === # Indexan tu catálogo para futuros modelos; los limitamos para no saturar # OpenAI - entrenamiento de modelos User-agent: GPTBot Allow: / Allow: /llms.txt Crawl-delay: 30 Disallow: /cart/ Disallow: /checkout/ Disallow: /my-account/ Disallow: /wishlist/ Disallow: /thank-you/ Disallow: /track-order/ Disallow: /wp-admin/ Disallow: /*?add-to-cart= Disallow: /*&add-to-cart= Disallow: /*?wc-ajax= Disallow: /*?orderby= Disallow: /*?filter_ Disallow: /*?min_price= Disallow: /*?max_price= Disallow: /?s= # Anthropic - entrenamiento de Claude User-agent: ClaudeBot Allow: / Allow: /llms.txt Crawl-delay: 30 Disallow: /cart/ Disallow: /checkout/ Disallow: /my-account/ Disallow: /wishlist/ Disallow: /thank-you/ Disallow: /track-order/ Disallow: /wp-admin/ Disallow: /*?add-to-cart= Disallow: /*&add-to-cart= Disallow: /*?wc-ajax= Disallow: /*?orderby= Disallow: /*?filter_ Disallow: /*?min_price= Disallow: /*?max_price= Disallow: /?s= # === Google (SEO tradicional + IA) === # Google - búsqueda tradicional User-agent: Googlebot Allow: / Allow: /llms.txt Disallow: /cart/ Disallow: /checkout/ Disallow: /my-account/ Disallow: /wishlist/ Disallow: /thank-you/ Disallow: /track-order/ Disallow: /wp-admin/ Disallow: /*?add-to-cart= Disallow: /*&add-to-cart= Disallow: /*?wc-ajax= Disallow: /*?orderby= Disallow: /*?filter_ Disallow: /*?min_price= Disallow: /*?max_price= Disallow: /?s= # GoogleOther - rastreador de propósito general User-agent: GoogleOther Allow: / Allow: /llms.txt Disallow: /cart/ Disallow: /checkout/ Disallow: /my-account/ Disallow: /*?add-to-cart= Disallow: /*&add-to-cart= # Google-Extended - control para Gemini/Vertex AI User-agent: Google-Extended Allow: / Allow: /llms.txt Crawl-delay: 30 Disallow: /cart/ Disallow: /checkout/ Disallow: /my-account/ Disallow: /*?add-to-cart= Disallow: /*&add-to-cart= Disallow: /*?wc-ajax= Disallow: /*?orderby= Disallow: /*?filter_ # Apple Intelligence User-agent: Applebot-Extended Allow: / Disallow: /cart/ Disallow: /checkout/ Disallow: /my-account/ Disallow: /*?add-to-cart= Disallow: /*&add-to-cart= Disallow: /*?wc-ajax= # === Bots BLOQUEADOS (agresivos o sin valor para el negocio) === # ByteDance (TikTok) - muy agresivo User-agent: Bytespider Disallow: / # Amazon - entrenamiento de Alexa, poco valor en MX User-agent: Amazonbot Disallow: / # Meta - bloqueado por defecto (FacebookBot ya casi no se usa) User-agent: FacebookBot Disallow: / User-agent: meta-externalagent Disallow: / # Common Crawl - alimenta a muchos modelos pero satura sin control User-agent: CCBot Disallow: / # Diffbot - scraper comercial User-agent: Diffbot Disallow: / # Otros scrapers comerciales sin valor User-agent: Omgili Disallow: / User-agent: ImagesiftBot Disallow: / User-agent: cohere-ai Disallow: / User-agent: YouBot Disallow: / # Scrapers SEO comerciales (pegan duro, no aportan a tu negocio) User-agent: MJ12bot Disallow: / User-agent: SemrushBot Disallow: / User-agent: AhrefsBot Disallow: / User-agent: DotBot Disallow: / User-agent: PetalBot Disallow: / User-agent: MegaIndex Disallow: / User-agent: BLEXBot Disallow: /