# =======================================
# robots.txt – comidaschilenas.com
# Versión: S/GMC V2 - RECIPE AUTHORITY & SECURITY FIX
# Estrategia: Hardening Forense + Protección de Imágenes + GEO
# =======================================

User-agent: *

# --- 1. CORE RENDERIZADO, CACHÉ y SEGURIDAD ---
Allow: /wp-content/cache/
Allow: /wp-content/litespeed/
Allow: /wp-admin/admin-ajax.php

# Permitir Assets de Core, Plugins y Themes (CWV 100%)
Allow: /wp-admin/*.css$
Allow: /wp-admin/*.js$
Allow: /wp-includes/*.js$
Allow: /wp-includes/*.css$
Allow: /wp-content/plugins/*.css$
Allow: /wp-content/plugins/*.js$
Allow: /wp-content/themes/*.css$
Allow: /wp-content/themes/*.js$
Allow: /wp-content/themes/*.webp$
Allow: /wp-content/themes/*.svg$

# Bloqueo de PHP en directorios de assets
Disallow: /wp-includes/*.php
Disallow: /wp-content/plugins/*.php
Disallow: /wp-content/cache/*.php
Disallow: /wp-content/litespeed/*.php
Disallow: /wp-content/themes/*.php

# --- 2. HARDENING Y BLOQUEO FORENSE (Basado en tus Logs) ---
Disallow: /wp-admin/
Disallow: /wp-login.php
Disallow: /wp-config.php
Disallow: /xmlrpc.php
Disallow: /cgi-bin/
Disallow: /.env
Disallow: /.git/
# Tu lista forense optimizada
Disallow: /content.php
Disallow: /logo.php
Disallow: /home.php
Disallow: /vendor/
Disallow: /system/
Disallow: /backup/
Disallow: /admin/
Disallow: /wp-content/uploads/*.php$
Disallow: /wp-json/wp/v2/users

# --- 3. LIMPIEZA DE CRAWL BUDGET (Crítico para Recetas) ---
Disallow: /tag/
Disallow: /*/feed/
Disallow: /feed/
Disallow: /comments/feed/
Disallow: /search/
Disallow: /trackback/
Disallow: /cart/
Disallow: /checkout/
Disallow: /my-account/
Disallow: /*?s=
Disallow: /*?add-to-cart=
Disallow: /*?replytocom=
# Bloqueo de parámetros de tracking para evitar contenido duplicado
Disallow: /*?utm_*
Disallow: /*?gclid=
Disallow: /*?fbclid=

# Excepción para Discover (Feed raíz)
Allow: /feed$

# --- 4. GARANTÍA GLOBAL DE RENDERIZADO (Imágenes y Fuentes) ---
Allow: /wp-content/uploads/
Allow: /.well-known/
Allow: /*.css$
Allow: /*.js$
Allow: /*.jpg$
Allow: /*.jpeg$
Allow: /*.png$
Allow: /*.gif$
Allow: /*.svg$
Allow: /*.webp$
Allow: /*.avif$
Allow: /*.woff2$

# --- 5. CONTROL DE BOTS Y LLMs (GEO Ready) ---
# Heredan todas las prohibiciones anteriores. Solo aplicamos delay.

User-agent: AhrefsBot
Crawl-delay: 10

User-agent: SemrushBot
Crawl-delay: 10

User-agent: GPTBot
Crawl-delay: 5

User-agent: ClaudeBot
Crawl-delay: 5

User-agent: Google-Extended
Crawl-delay: 5

Sitemap: https://comidaschilenas.com/sitemap_index.xml

# VigIA LLMs
LLMs: https://comidaschilenas.com/llms.txt
LLMs-full: https://comidaschilenas.com/llms-full.txt

# BEGIN AI Content Signals
# Generated on 2026-05-30 16:48:05 UTC

# 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.

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

# END AI Content Signals

# VigIA - AI Crawler Rules
User-agent: Meta-ExternalAgent
Disallow: /

User-agent: Meta-WebIndexer
Disallow: /

User-agent: TimpiBot
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: Bytespider
Disallow: /