# ============================================================
# robots.txt — expedientecero.com.ar
# Propuesta agosto 2026 — R.NET
# ============================================================

# ---------- BLOQUE GENERICO (todos los bots) ----------
# Bingbot usa este bloque: Microsoft recomienda definir el
# crawl-delay aca y NO en un bloque propio de bingbot.
User-agent: *
Crawl-delay: 5

# Paginacion profunda de archivos (category, tag, author).
# Son las consultas mas caras del sitio y no aportan SEO.
Disallow: /*/page/

# Feeds de archivos (los feeds de notas siguen permitidos)
Disallow: /*/feed/

# URLs dinamicas y busquedas
Disallow: /*?
Disallow: /?s=
Disallow: /search

# Trackbacks
Disallow: /trackback
Disallow: /*trackback

# WordPress
Disallow: /xmlrpc.php
Disallow: /wp-admin/
Disallow: /wp-includes/
Disallow: /wp-content/plugins/
Disallow: /wp-content/cache/
Disallow: /wp-content/themes/

# Otros
Disallow: /cgi-bin/
Disallow: /*.sql$


# ---------- GOOGLEBOT ----------
# Google IGNORA crawl-delay: ajusta su ritmo solo, segun como
# responda el servidor. Por eso aca no se define.
# Necesita JS y CSS para renderizar correctamente.
User-agent: Googlebot
Allow: /*.js$
Allow: /*.css$
Disallow: /*/page/
Disallow: /*/feed/
Disallow: /*?
Disallow: /?s=
Disallow: /search
Disallow: /trackback
Disallow: /*trackback
Disallow: /xmlrpc.php
Disallow: /wp-admin/
Disallow: /wp-includes/
Disallow: /wp-content/plugins/
Disallow: /wp-content/cache/
Disallow: /cgi-bin/
Disallow: /*.sql$


# ---------- BOTS DE BUSQUEDA / CITA DE IA ----------
# Mantienen acceso al contenido (iniciativa GEO/AEO de julio 2026)
# pero con freno: en agosto se detectaron 18 peticiones en 51
# segundos desde 6 IPs distintas de OAI-SearchBot.

User-agent: OAI-SearchBot
Crawl-delay: 10
Disallow: /*/page/
Disallow: /*/feed/
Disallow: /*?
Disallow: /?s=
Disallow: /search
Disallow: /wp-admin/
Disallow: /wp-includes/
Disallow: /wp-content/plugins/
Disallow: /wp-content/cache/
Disallow: /wp-json/
Allow: /

User-agent: ChatGPT-User
Crawl-delay: 10
Disallow: /*/page/
Disallow: /*/feed/
Disallow: /*?
Disallow: /?s=
Disallow: /search
Disallow: /wp-admin/
Disallow: /wp-includes/
Disallow: /wp-content/plugins/
Disallow: /wp-content/cache/
Disallow: /wp-json/
Allow: /

User-agent: GPTBot
Crawl-delay: 10
Disallow: /*/page/
Disallow: /*/feed/
Disallow: /*?
Disallow: /?s=
Disallow: /search
Disallow: /wp-admin/
Disallow: /wp-includes/
Disallow: /wp-content/plugins/
Disallow: /wp-content/cache/
Disallow: /wp-json/
Allow: /

User-agent: ClaudeBot
Crawl-delay: 10
Disallow: /*/page/
Disallow: /*/feed/
Disallow: /*?
Disallow: /?s=
Disallow: /search
Disallow: /wp-admin/
Disallow: /wp-includes/
Disallow: /wp-content/plugins/
Disallow: /wp-content/cache/
Disallow: /wp-json/
Allow: /

User-agent: Claude-SearchBot
Crawl-delay: 10
Disallow: /*/page/
Disallow: /*/feed/
Disallow: /*?
Disallow: /?s=
Disallow: /search
Disallow: /wp-admin/
Disallow: /wp-includes/
Disallow: /wp-content/plugins/
Disallow: /wp-content/cache/
Disallow: /wp-json/
Allow: /

User-agent: PerplexityBot
Crawl-delay: 10
Disallow: /*/page/
Disallow: /*/feed/
Disallow: /*?
Disallow: /?s=
Disallow: /search
Disallow: /wp-admin/
Disallow: /wp-includes/
Disallow: /wp-content/plugins/
Disallow: /wp-content/cache/
Disallow: /wp-json/
Allow: /


# ---------- HERRAMIENTAS SEO ----------
# No aportan trafico. Se frenan fuerte.
User-agent: AhrefsBot
Crawl-delay: 30

User-agent: SemrushBot
Crawl-delay: 30

User-agent: MJ12bot
Crawl-delay: 30

User-agent: DotBot
Crawl-delay: 30


# ---------- SITEMAP ----------
Sitemap: https://expedientecero.com.ar/sitemap_index.xml