# Robots.txt para Socovesa.cl - Optimizado Junio 2026

# ---------------------------------------------------
# 1. Reglas Generales y Limpieza SEO
# ---------------------------------------------------
User-agent: *
Disallow: /*.pdf$
Disallow: /*.PDF$
Disallow: /wp-admin/
Disallow: /wp-login.php
Disallow: /admin/
Disallow: /xmlrpc.php
Disallow: /?s=
Disallow: /search/
Disallow: /page/*/?s=
Disallow: /trackback/
Disallow: /comments/
Disallow: /feed/
# 🚨 BLOQUEO DE SPAM DETECTADO (Crítico)
Disallow: /category/pinup*
Disallow: /category/1win*
Disallow: /category/mostbet*
Disallow: /category/forex*
# ---------------------------------------------------
# 2. HABILITACIÓN DE LLMs y BOTS DE ENTRENAMIENTO 
# ---------------------------------------------------
# OpenAI (ChatGPT) - Solo entrenamiento, no búsqueda
User-agent: GPTBot
Allow: /
# Google -Gemini 
User-agent: Google-Extended
Allow: /
# Anthropic (Claude)
User-agent: Anthropic-ai
Allow: /
User-agent: ClaudeBot
Disallow: /
# Apple - Solo entrenamiento IA (Siri seguirá funcionando con Applebot normal)
User-agent: Applebot-Extended
Disallow: /
# Meta (Facebook/Llama) - Entrenamiento
User-agent: FacebookBot
Disallow: /
User-agent: Meta-ExternalAgent
Disallow: /
# Common Crawl (Base de datos masiva para entrenar muchas IAs)
User-agent: CCBot
Allow: /
User-agent: ChatGPT-User
Allow: /
# Perplexity (Motor de respuestas que reduce clics)
User-agent: PerplexityBot
Allow: /
# Amazon (Alexa/Training)
User-agent: Amazonbot
Disallow: /
# ByteDance (TikTok/ByteSpider - Crawler muy agresivo)
User-agent: Bytespider
Disallow: /
User-agent: Bytedance
Disallow: /
# ---------------------------------------------------
# 3. Permisos para Bots Comerciales (Tráfico Real)
# ---------------------------------------------------
User-agent: AdsBot-Google
Allow: /
User-agent: Googlebot
Allow: /
User-agent: Googlebot-Image
Allow: /
User-agent: bingbot
Allow: /
# ---------------------------------------------------
# 4. Sitemap
https://www.socovesa.cl/sitemap_index.xml