# As a condition of accessing this website, you agree to abide by the following
# content signals:

# (a)  If a Content-Signal = yes, you may collect content for the corresponding
#      use.
# (b)  If a Content-Signal = no, you may not collect content for the
#      corresponding use.
# (c)  If the website operator does not include a Content-Signal for a
#      corresponding use, the website operator neither grants nor restricts
#      permission via Content-Signal with respect to the corresponding use.

# The content signals and their meanings are:

# search:   building a search index and providing search results (e.g., returning
#           hyperlinks and short excerpts from your website's contents). Search does not
#           include providing AI-generated search summaries.
# ai-input: inputting content into one or more AI models (e.g., retrieval
#           augmented generation, grounding, or other real-time taking of content for
#           generative AI search answers).
# ai-train: training or fine-tuning AI models.

# ANY RESTRICTIONS EXPRESSED VIA CONTENT SIGNALS ARE EXPRESS RESERVATIONS OF
# RIGHTS UNDER ARTICLE 4 OF THE EUROPEAN UNION DIRECTIVE 2019/790 ON COPYRIGHT
# AND RELATED RIGHTS IN THE DIGITAL SINGLE MARKET.

# BEGIN Cloudflare Managed content

User-agent: *
Content-Signal: search=yes,ai-train=no
Allow: /

User-agent: Amazonbot
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: CloudflareBrowserRenderingCrawler
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: GPTBot
Disallow: /

User-agent: meta-externalagent
Disallow: /

# END Cloudflare Managed Content

# Robots.txt Optimizado para Antoniodemarketing
# Revisado: 25 de marzo de 2026

# 1. CONTROL DE IA Y AGENTES COMERCIALES
# Permitimos busqueda (RAG) pero bloqueamos entrenamiento
User-agent: GPTBot
User-agent: ChatGPT-User
User-agent: OAI-SearchBot
User-agent: Google-Extended
User-agent: PerplexityBot
User-agent: ClaudeBot
User-agent: anthropic-ai
User-agent: Amazonbot
User-agent: Applebot-Extended
User-agent: meta-externalagent
User-agent: FacebookBot
User-agent: AhrefsBot
User-agent: SemrushBot
Disallow: /wp-admin/
Disallow: /wp-includes/

# Senales de IA para maxima visibilidad
# Content-Signal: search=yes, ai-input=yes, ai-train=no

# 2. BLOQUEO TOTAL DE BOTS AGRESIVOS O SPAM
User-agent: Bytespider
User-agent: PetalBot
User-agent: BLEXBot
User-agent: MJ12bot
User-agent: DotBot
Disallow: /

# 3. REGLAS PARA BUSCADORES (Google, Bing, Yahoo)
User-agent: *

# Priorizar renderizado (Esencial para Core Web Vitals)
Allow: /wp-admin/admin-ajax.php
Allow: /wp-content/uploads/
Allow: /wp-content/plugins/*.js
Allow: /wp-content/plugins/*.css
Allow: /wp-content/themes/*.js
Allow: /wp-content/themes/*.css

# Bloqueos de administracion y sistema
Disallow: /wp-admin/
Disallow: /wp-includes/
Disallow: /wp-content/cache/
Disallow: /wp-login.php
Disallow: /xmlrpc.php

# Optimizacion de Crawl Budget (Evita contenido duplicado)
Disallow: /search/
Disallow: /?s=
Disallow: /*?
Disallow: /*?replytocom=
Disallow: /author/
Disallow: /tag/
Disallow: /comments/feed/
Disallow: /trackback/
# Bloqueo de paginacion si no es necesaria
Disallow: /page/

# Seguridad y Proteccion de Datos
Disallow: /wp-json/wp/v2/users
Disallow: /wp-config.php
Disallow: /readme.html
Disallow: /license.txt
Disallow: /*.sql$
Disallow: /*.log$
Disallow: /wp-load.php
Disallow: /wp-mail.php

# SITEMAPS
Sitemap: https://www.antoniodmarketing.es/robots.txt

# VigIA LLMs
# LLMs: https://www.antoniodmarketing.es/llms.txt
# LLMs-full: https://www.antoniodmarketing.es/llms-full.txt