# robots.txt optimizado para WordPress + WooCommerce # Actualizado: Enero 2025 # Configuración general para todos los robots User-agent: \* Crawl-delay: 1 # === BLOQUEOS DE SEGURIDAD === # Directorios sensibles de WordPress Disallow: /wp-admin/ Disallow: /wp-includes/ Disallow: /wp-content/plugins/ Disallow: /wp-content/themes/ Disallow: /wp-content/cache/ Disallow: /wp-content/uploads/wpo-plugins-tables-list.json # Archivos de configuración y sensibles Disallow: /wp-config.php Disallow: /wp-config-sample.php Disallow: /readme.html Disallow: /license.txt Disallow: /wp-trackback.php Disallow: /xmlrpc.php Disallow: /.htaccess Disallow: /wp-cron.php # === BLOQUEOS DE WOOCOMMERCE === # Páginas de cuenta y checkout Disallow: /checkout/ Disallow: /cart/ Disallow: /my-account/ Disallow: /mi-cuenta/ Disallow: /carrito/ Disallow: /finalizar-compra/ # Parámetros de WooCommerce Disallow: /_?add-to-cart= Disallow: /_?removed*item= Disallow: /*?orderby= Disallow: /*?filter* Disallow: /_?min_price= Disallow: /_?max_price= Disallow: /product-tag/ Disallow: /shop/page/ # === BLOQUEOS DE WORDPRESS === # Páginas de búsqueda y parámetros Disallow: /?s= Disallow: /search/ Disallow: /_?s= Disallow: /_&s= # Feeds (opcional - descomenta si no quieres indexar feeds) # Disallow: /feed/ # Disallow: /\*/feed/ # Disallow: /comments/feed/ # Páginas de autor y fechas (si no quieres indexarlas) Disallow: /author/ Disallow: /_/trackback/ Disallow: /_/embed/ # Parámetros de paginación y filtros Disallow: /_?replytocom= Disallow: /_?attachment_id= Disallow: /page/ Disallow: /\*/page/ # Archivos de medios directos (opcional) Disallow: /wp-content/uploads/_.php$ Disallow: /wp-content/uploads/_.exe$ # === PERMITIR ACCESOS IMPORTANTES === # Permitir acceso a wp-admin para AJAX Allow: /wp-admin/admin-ajax.php Allow: /wp-includes/js/ Allow: /wp-includes/css/ # Permitir uploads de imágenes para indexación Allow: /wp-content/uploads/ # === CONFIGURACIÓN ESPECÍFICA DE BOTS === # Google User-agent: Googlebot Allow: /wp-content/uploads/ Disallow: /wp-admin/ Allow: /wp-admin/admin-ajax.php # Googlebot para imágenes User-agent: Googlebot-Image Allow: /wp-content/uploads/ # Bing User-agent: Bingbot Crawl-delay: 1 Allow: /wp-content/uploads/ # === BOTS DE IA (PERMITIDOS) === # Claude (Anthropic) User-agent: anthropic-ai User-agent: Claude-Web Crawl-delay: 2 Allow: / # ChatGPT (OpenAI) User-agent: GPTBot User-agent: ChatGPT-User Crawl-delay: 2 Allow: / # Google Gemini / Bard User-agent: Google-Extended Crawl-delay: 2 Allow: / # === HERRAMIENTAS SEO (PERMITIDAS) === # Semrush User-agent: SemrushBot Crawl-delay: 5 Allow: / # Ahrefs User-agent: AhrefsBot Crawl-delay: 5 Allow: / # Moz User-agent: rogerbot User-agent: dotbot Crawl-delay: 5 Allow: / # Majestic User-agent: MJ12bot Crawl-delay: 5 Allow: / # === BOTS MALICIOSOS (BLOQUEADOS) === # Scrapers y bots agresivos User-agent: HTTrack User-agent: Offline Explorer User-agent: Teleport User-agent: WebZIP User-agent: WebCopier User-agent: WebReaper User-agent: WebStripper User-agent: EmailCollector User-agent: EmailSiphon User-agent: EmailWolf User-agent: ExtractorPro User-agent: CherryPicker User-agent: WebBandit User-agent: NICErsPRO User-agent: WebmasterWorldForumBot User-agent: Indy Library User-agent: wget User-agent: libwww-perl User-agent: python-requests User-agent: MegaIndex.ru User-agent: BLEXBot User-agent: AhrefsBot/5.0 Disallow: / # === SITEMAP === # Reemplaza con la URL real de tu sitemap Sitemap: https://verges.com/sitemap_index.xml