# =====================================================
# 1. BLOQUEO TOTAL DE BOTS DE IA Y SCRAPERS (ENTRENAMIENTO)
# =====================================================
User-agent: anthropic-ai
User-agent: Applebot-Extended
User-agent: Bytespider
User-agent: CCBot
User-agent: ChatGPT-User
User-agent: ClaudeBot
User-agent: Diffbot
User-agent: GPTBot
User-agent: Google-Extended
User-agent: ImagesiftBot
User-agent: PerplexityBot
User-agent: YouBot
Disallow: /

# Bloqueo de herramientas de SEO y Scrapers agresivos
User-agent: AhrefsBot
User-agent: Amazonbot
User-agent: amazon-kendra
User-agent: Applebot
User-agent: Dotbot
User-agent: HTTrack
User-agent: libwww-perl
User-agent: MJ12bot
User-agent: PetalBot
User-agent: python-requests
User-agent: SemrushBot
User-agent: wget
Disallow: /

# ==========================================
# 2. REGLAS PARA BUSCADORES (Google, Bing, Perplexity Search)
# ==========================================
User-agent: *

# Señal legal IA (Cloudflare/UE)
Content-Signal: search=yes, ai-input=no, ai-train=no

# Control de frecuencia para no saturar el servidor
Crawl-delay: 10

# Bloqueo de carpetas privadas o de gestión
Disallow: /ediciones-pendientes/

# Evitar indexación de búsquedas internas y filtros
Disallow: /search/
Disallow: /*?s=
Disallow: /*?search=
Disallow: /*&filter=
Disallow: /*&sort=

# Evitar feeds, trackbacks y comentarios
Disallow: /feed/
Disallow: /trackback/
Disallow: /comments/

# Bloqueo de archivos pesados/descargables
Disallow: /*.zip$
Disallow: /*.rar$
Disallow: /*.7z$
Disallow: /*.tar$
Disallow: /*.gz$

# ==========================================
# 3. RUTA DEL SITEMAP
# ==========================================
# Sitemap: https://www.gacetanautica.es/sitemap.xml