# robots.txt automatically generated by PrestaShop e-commerce open-source solution # http://www.prestashop.com - http://www.prestashop.com/forums # This file is to prevent the crawling and indexing of certain parts # of your site by web crawlers and spiders run by sites like Yahoo! # and Google. By telling these "robots" where not to go on your site, # you save bandwidth and server resources. # For more information about the robots.txt standard, see: # http://www.robotstxt.org/robotstxt.html # --- SITEMAPS --- Sitemap: https://ferreidea.com/index.php?fc=module&module=lgsitemaps&controller=sitemap&name=sitemap_1 Sitemap: https://ferreidea.com/index.php?fc=module&module=lgsitemaps&controller=sitemap&name=product_1_1 Sitemap: https://ferreidea.com/index.php?fc=module&module=lgsitemaps&controller=sitemap&name=category_1_1 Sitemap: https://ferreidea.com/index.php?fc=module&module=lgsitemaps&controller=sitemap&name=cms_1_1 Sitemap: https://ferreidea.com/index.php?fc=module&module=lgsitemaps&controller=sitemap&name=manufacturer_1_1 Sitemap: https://ferreidea.com/module/ultimateimagetool/sitemap?token=8b40c32e203a16556cbd4bedeabd1da6 # ---------------------------------------------------------- # REGLAS GENERALES (todos los bots) # ---------------------------------------------------------- User-agent: * # Permitir recursos para renderizado (mejor comprensión de producto/contenido) Allow: /*.css$ Allow: /*.js$ Allow: /*.mjs$ Allow: /*.jpg$ Allow: /*.jpeg$ Allow: /*.png$ Allow: /*.gif$ Allow: /*.webp$ Allow: /*.svg$ Allow: /*.ico$ Allow: /*.woff$ Allow: /*.woff2$ Allow: /*.ttf$ Allow: /*.eot$ Allow: /themes/ Allow: /assets/ # Permitir assets dentro de módulos (pero bloqueamos el resto del árbol más abajo) Allow: /modules/*/views/css/ Allow: /modules/*/views/js/ Allow: /modules/*/views/img/ # --- ZONAS INTERNAS / DIRECTORIOS SISTEMA (PrestaShop 8.1) --- Disallow: /app/ Disallow: /cache/ Disallow: /classes/ Disallow: /config/ Disallow: /controllers/ Disallow: /download/ Disallow: /localization/ Disallow: /log/ Disallow: /mails/ Disallow: /override/ Disallow: /pdf/ Disallow: /src/ Disallow: /tools/ Disallow: /translations/ Disallow: /upload/ Disallow: /var/ Disallow: /vendor/ Disallow: /webservice/ # (Bloqueo general de módulos; arriba permitimos sus assets necesarios) Disallow: /modules/ # --- RUTAS PRIVADAS / SIN VALOR SEO (friendly URLs comunes) --- Disallow: /iniciar-sesion Disallow: /mi-cuenta Disallow: /carrito Disallow: /pedido Disallow: /confirmacion-pedido Disallow: /seguimiento-pedido Disallow: /seguimiento-pedido-invitado Disallow: /historial-compra Disallow: /datos-personales Disallow: /direccion Disallow: /direcciones Disallow: /descuento Disallow: /facturas-abono Disallow: /recuperar-contraseña Disallow: /busqueda # (Variantes EN por si existieran) Disallow: /login Disallow: /my-account Disallow: /cart Disallow: /order Disallow: /order-confirmation Disallow: /search # --- CONTROLADORES por parámetro (evitar indexación de flujos internos) --- Disallow: /*controller=addresses Disallow: /*controller=address Disallow: /*controller=authentication Disallow: /*controller=cart Disallow: /*controller=discount Disallow: /*controller=footer Disallow: /*controller=get-file Disallow: /*controller=header Disallow: /*controller=history Disallow: /*controller=identity Disallow: /*controller=images.inc Disallow: /*controller=init Disallow: /*controller=my-account Disallow: /*controller=order Disallow: /*controller=order-slip Disallow: /*controller=order-detail Disallow: /*controller=order-follow Disallow: /*controller=order-return Disallow: /*controller=order-confirmation Disallow: /*controller=pagination Disallow: /*controller=password Disallow: /*controller=pdf-invoice Disallow: /*controller=pdf-order-return Disallow: /*controller=pdf-order-slip Disallow: /*controller=product-sort Disallow: /*controller=search Disallow: /*controller=statistics Disallow: /*controller=attachment Disallow: /*controller=guest-tracking # --- PARÁMETROS que generan duplicados (ahorro de crawl budget) --- # Ordenación, paginaciones, búsquedas y tracking Disallow: /*?order= Disallow: /*&order= Disallow: /*?orderby= Disallow: /*&orderby= Disallow: /*?n= Disallow: /*&n= Disallow: /*?page= Disallow: /*&page= Disallow: /*?id_currency= Disallow: /*&id_currency= Disallow: /*?search_query= Disallow: /*&search_query= Disallow: /*?q= Disallow: /*&q= Disallow: /*?back= Disallow: /*&back= Disallow: /*?utm_ Disallow: /*&utm_ Disallow: /*?gclid= Disallow: /*&gclid= Disallow: /*?fbclid= Disallow: /*&fbclid= Disallow: /*?*token= Disallow: /*&*token= # ---------------------------------------------------------- # LLM & SEARCH BOTS — PERMITIDOS EXPLÍCITAMENTE # (No es requerido, pero lo dejamos claro y arriba ya quedó todo Allow por defecto) # ---------------------------------------------------------- User-agent: Googlebot Allow: / User-agent: Googlebot-Image Allow: / User-agent: Storebot-Google Allow: / User-agent: bingbot Allow: / User-agent: DuckDuckBot Allow: / User-agent: OAI-SearchBot Allow: / User-agent: ChatGPT-User Allow: / User-agent: GPTBot Allow: / User-agent: Claude-SearchBot Allow: / User-agent: Claude-User Allow: / User-agent: ClaudeBot Allow: / User-agent: PerplexityBot Allow: / User-agent: CCBot Allow: / # ---------------------------------------------------------- # BLOQUEO DE SCRAPERS / TRACKERS CONOCIDOS # (Lista viva; muchos respetan robots.txt, otros no. Complementa con WAF/CDN e IP rate-limits.) # ---------------------------------------------------------- User-agent: AhrefsBot Disallow: / User-agent: SemrushBot Disallow: / User-agent: SemrushBot-SA Disallow: / User-agent: MJ12bot Disallow: / User-agent: DotBot Disallow: / User-agent: BLEXBot Disallow: / User-agent: Barkrowler Disallow: / User-agent: MegaIndex.ru Disallow: / User-agent: MegaIndex Disallow: / User-agent: SEOkicks-Robot Disallow: / User-agent: AspiegelBot Disallow: / User-agent: MauiBot Disallow: / User-agent: ZoominfoBot Disallow: / User-agent: SISTRIX Disallow: / User-agent: SiteAuditBot Disallow: / User-agent: spbot Disallow: / User-agent: Exabot Disallow: / User-agent: Baiduspider Disallow: / User-agent: YandexBot Disallow: / User-agent: PetalBot Disallow: / User-agent: trendictionbot Disallow: / User-agent: SeobilityBot Disallow: / User-agent: Sergiobot Disallow: / User-agent: SMTBot Disallow: / User-agent: Cocolyzebot Disallow: / User-agent: Seekport Crawler Disallow: / User-agent: curl Disallow: / User-agent: Wget Disallow: / User-agent: Python-requests Disallow: / User-agent: python-urllib Disallow: / User-agent: Go-http-client Disallow: / User-agent: Java Disallow: / User-agent: Scrapy Disallow: / User-agent: HeadlessChrome Disallow: / User-agent: Bytespider Disallow: / User-agent: GPTBot-Image Disallow: /