# ======================================================
# robots.txt — Optimizado para WordPress + SEO + IA + Multilingüe
# Sitio: https://www.arkoslight.com/
# Idiomas: español (principal), inglés /en, alemán /de, italiano /it, francés /fr
# Última revisión: 2025-11-07
# ======================================================

User-agent: *
# --- Permitir rastreo del contenido principal ---
Allow: /wp-content/uploads/
Allow: /wp-json/
Allow: /*.js$
Allow: /*.css$
Allow: /*.png$
Allow: /*.jpg$
Allow: /*.jpeg$
Allow: /*.gif$
Allow: /*.webp$
Allow: /*.svg$
Allow: /*.woff$
Allow: /*.woff2$

# --- Bloquear secciones internas de WordPress ---
Disallow: /wp-admin/
Disallow: /wp-includes/
Disallow: /wp-content/plugins/
Disallow: /wp-content/themes/
Disallow: /cgi-bin/
Disallow: /trackback/
Disallow: /comments/
Disallow: /xmlrpc.php

# --- Evitar contenido duplicado o irrelevante ---
Disallow: /?s=
Disallow: /*?s=
Disallow: /search
Disallow: /author/
Disallow: /archives/
Disallow: /*?replytocom=
Disallow: /*?share=
Disallow: /*?utm_*
Disallow: /*?fbclid=
Disallow: /cart/
Disallow: /checkout/
Disallow: /my-account/
Disallow: /private/
Disallow: /downloads/
Disallow: /catalog/

# --- Permitir rastreo de todas las versiones idiomáticas ---
Allow: /          # español (principal)
Allow: /en/       # inglés
Allow: /de/       # alemán
Allow: /it/       # italiano
Allow: /fr/       # francés

# --- Contenido público relevante ---
Allow: /productos/
Allow: /proyectos/
Allow: /journal/
Allow: /light-life-1984/
Allow: /contacto/

# --- Sitemaps multilingües ---
Sitemap: https://www.arkoslight.com/sitemap_index.xml
Sitemap: https://www.arkoslight.com/en/sitemap_index.xml
Sitemap: https://www.arkoslight.com/de/sitemap_index.xml
Sitemap: https://www.arkoslight.com/it/sitemap_index.xml
Sitemap: https://www.arkoslight.com/fr/sitemap_index.xml

# ======================================================
# Bots de búsqueda (SEO)
# ======================================================
User-agent: Googlebot
Allow: /
Crawl-delay: 2

User-agent: Bingbot
Allow: /
Crawl-delay: 5

User-agent: Yandex
Allow: /
Crawl-delay: 10

# ======================================================
# Bots de IA — visibilidad controlada y citación de marca
# ======================================================
User-agent: GPTBot
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: CCBot
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: FacebookBot
Allow: /

User-agent: cohere-ai
Allow: /

User-agent: MistralBot
Allow: /

User-agent: YouBot
Allow: /

# ======================================================
# Información adicional
# ======================================================
# 1. Maximiza la indexación internacional del contenido de Arkoslight.
# 2. Permite a los modelos de IA acceder con fines informativos y de citación.
# 3. Protege áreas internas y duplicadas del CMS WordPress.
# 4. Complementa el archivo llms.txt para control de uso por IA.
# ======================================================