Top Sites>La Casa de las Carcasas

# Robots.txt optimizado para lacasadelascarcasas.es
# Última actualización: Noviembre 2025

# === CONFIGURACIÓN GLOBAL ===

User-agent: *

#Generico Shopify
Disallow: /buscar/
Disallow: /admin/
Disallow: /cart/
Disallow: /orders
Disallow: /checkout/
Disallow: /account/
Disallow: /policies/
Disallow: /services/
Disallow: /application/
Disallow: /apps/


# Apps y funcionalidades específicas
Disallow: /discount/
Disallow: /zakeke/customize/

# APIs y endpoints internos
Disallow: /api/
Disallow: /.well-known/shopify/
Disallow: /wallets/
Disallow: /payments/
Disallow: /services/product_recommendations

# Control de búsqueda interna
Disallow: /search?
Disallow: /search/suggest
Disallow: /buscar?
Disallow: /m=and&q=

# Parámetros de sesión y tracking
Disallow: /*?*session_id=
Disallow: /*?*cart_sig=
Disallow: /*?*preview_theme_id=
Disallow: /*?*preview_script_id=
DisAllow: /*?*pbcid=

# Parámetros UTM (evitar contenido duplicado)
Disallow: /*?*utm_source=
Disallow: /*?*utm_medium=
Disallow: /*?*utm_campaign=
Disallow: /*?*utm_term=
Disallow: /*?*utm_content=
Disallow: /*?*fbclid=
Disallow: /*?*gclid=
Disallow: /*?*mc_cid=
Disallow: /*?*mc_eid=

# Permitir recursos estáticos para renderizado
Allow: /*.css
Allow: /*.js
Allow: /*.jpg
Allow: /*.jpeg
Allow: /*.png
Allow: /*.gif
Allow: /*.webp
Allow: /*.svg
Allow: /*.woff
Allow: /*.woff2
Allow: /*.ttf
Allow: /*.eot
Allow: /*.ico

# Permitir archivos CDN de Shopify
Allow: /cdn/
Allow: /cdn-cgi/

#Bloqueo de feeds para crawlers
User-agent: *
Allow: /feed/$ 
Disallow: /*feed*
Disallow: /feed/ 
Disallow: /comments/feed/
Disallow: /*/feed/$ 
Disallow: /*/feed/rss/$ 
Disallow: /*/trackback/$ 
Disallow: /*/*/feed/$ 
Disallow: /*/*/feed/rss/$ 
Disallow: /*/*/trackback/$ 
Disallow: /*/*/*/feed/$ 
Disallow: /*/*/*/feed/rss/$ 
Disallow: /*/*/*/trackback/$

#Control presupuesto rastreo
User-agent: AhrefsBot
User-agent: AhrefsSiteAudit
User-agent: Slurp
User-agent: Pinterest
Crawl-delay: 5
User-agent: noxtrumbot
Crawl-delay: 50

#Previene problemas de recursos bloqueados en CSS y JS
User-Agent: *
Allow: /*.css$
Allow: /*.js$

# === BUSCADORES TRADICIONALES ===
User-agent: Googlebot
Allow: /
Disallow: /admin
Disallow: /cart
Disallow: /checkouts/
Disallow: /orders

User-agent: Googlebot-Image
Allow: /

User-agent: Googlebot-Mobile
Allow: /

User-agent: Bingbot
Allow: /
Disallow: /admin
Disallow: /cart
Disallow: /checkouts/
Disallow: /orders

User-agent: Slurp
Allow: /
Crawl-delay: 1

User-agent: DuckDuckBot
Allow: /

User-agent: Yandex
Allow: /
Crawl-delay: 2

# === BOTS DE IA - BÚSQUEDA Y CHAT ===
# OpenAI / ChatGPT
User-agent: ChatGPT-User
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: GPTBot
Allow: /

# Anthropic / Claude
User-agent: Claude-Web
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: ClaudeBot
Allow: /

# Google AI
User-agent: Google-Extended
Allow: /

User-agent: Bard
Allow: /

# Microsoft / Bing AI
User-agent: Bingbot-AI
Allow: /

# Perplexity
User-agent: PerplexityBot
Allow: /

# Otros bots de IA importantes
User-agent: cohere-ai
Allow: /

User-agent: YouBot
Allow: /

User-agent: PhindBot
Allow: /

User-agent: FirecrawlAgent
Allow: /

User-agent: ExaBot
Allow: /

User-agent: AndiBot
Allow: /

User-agent: Timpibot
Allow: /

User-agent: applebot
Allow: /

User-agent: applebot-extended
Allow: /

# === SOCIAL MEDIA BOTS ===
User-agent: facebookexternalhit
Allow: /

User-agent: Twitterbot
Allow: /

User-agent: LinkedInBot
Allow: /

User-agent: WhatsApp
Allow: /

User-agent: Pinterestbot
Allow: /
Crawl-delay: 1

# === HERRAMIENTAS SEO (Control de presupuesto) ===
User-agent: AhrefsBot
Disallow: /

User-agent: AhrefsSiteAudit  
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: Screaming Frog SEO Spider
Disallow: /

User-agent: SEOkicks
Disallow: /

User-agent: SiteAnalyzerBot
Disallow: /

# === BLOQUEO DE BOTS MALICIOSOS Y SCRAPERS ===
User-agent: HTTrack
Disallow: /

User-agent: WebCopier
Disallow: /

User-agent: WebStripper
Disallow: /

User-agent: WebZIP
Disallow: /

User-agent: TeleportPro
Disallow: /

User-agent: Offline Explorer
Disallow: /

User-agent: SiteSnagger
Disallow: /

User-agent: WGet
Disallow: /

User-agent: WebReaper
Disallow: /

User-agent: WebSauger
Disallow: /

User-agent: Website eXtractor
Disallow: /

User-agent: NinjaBot
Disallow: /

User-agent: Download Ninja
Disallow: /

#Sitemaps
Sitemap: https://lacasadelascarcasas.es/sitemap.xml


# Bloque añadido solicitado — evita indexación de URLs con parámetros de cursor/direction/filters
User-agent: *
Disallow: /*?cursor=
Disallow: /*?direction=
Disallow: /*?filters=

Not stored for this site.