# ---------------------------------------------------------
# ROBOTS.TXT · PROFESIONALNET.NET
# Estrategia GEO 2026: queremos que la IA nos lea, nos indexe y nos cite.
# Revisado: 2026-07-20
# CORREGIDO 2026-09-08 (NEXARIA): en RFC 9309 un agente con grupo propio NO hereda
#   las reglas del grupo "*". Los grupos de IA solo traian "Allow: /" y "Disallow: /wp-admin/",
#   asi que GPTBot, ClaudeBot, PerplexityBot, CCBot, Applebot, OAI-SearchBot y Google-Extended
#   SI podian rastrear /wp-includes/, /xmlrpc.php, /wp-json/, la busqueda interna ?s= y las
#   URLs con ?utm_, ?gclid=, ?replytocom= ... Medido con parser RFC 9309 validado 6/6.
#   Se replican en cada grupo las mismas reglas tecnicas del grupo "*".
#   NO se restringe NADA de contenido: la estrategia GEO no cambia, solo deja de regalarles basura.
# ---------------------------------------------------------

# ================= 1. REGLA GENERAL =================
User-agent: *
Allow: /

# Rutas tecnicas sin valor de busqueda
Disallow: /wp-admin/
Allow: /wp-admin/admin-ajax.php
Disallow: /wp-includes/
Disallow: /wp-json/
Disallow: /xmlrpc.php
Disallow: /cgi-bin/
Disallow: /trackback/
Disallow: /comments/feed/
Disallow: /search/
Disallow: /*?s=

# Parametros que canibalizan y queman presupuesto de rastreo
Disallow: /*?utm_
Disallow: /*?fbclid=
Disallow: /*?gclid=
Disallow: /*?ref=
Disallow: /*?sort=
Disallow: /*?replytocom=

# Recursos necesarios para RENDERIZAR la pagina (Google debe verlos)
Allow: /wp-content/uploads/
Allow: /wp-content/themes/
Allow: /wp-content/plugins/
Allow: /*.css$
Allow: /*.js$
Allow: /*.webp$
Allow: /*.svg$

# ================= 2. IA: ACCESO TOTAL =================
# Decision de negocio (jul-2026): permitimos lectura, indexacion y
# entrenamiento. Queremos ser la FUENTE que citan los modelos.

# -- OpenAI / ChatGPT --
User-agent: GPTBot
User-agent: OAI-SearchBot
User-agent: ChatGPT-User
Allow: /
Disallow: /wp-admin/
Allow: /wp-admin/admin-ajax.php
Disallow: /wp-includes/
Disallow: /wp-json/
Disallow: /xmlrpc.php
Disallow: /cgi-bin/
Disallow: /trackback/
Disallow: /comments/feed/
Disallow: /search/
Disallow: /*?s=
Disallow: /*?utm_
Disallow: /*?fbclid=
Disallow: /*?gclid=
Disallow: /*?ref=
Disallow: /*?sort=
Disallow: /*?replytocom=

# -- Anthropic / Claude --
User-agent: ClaudeBot
User-agent: Claude-User
User-agent: Claude-SearchBot
User-agent: anthropic-ai
Allow: /
Disallow: /wp-admin/
Allow: /wp-admin/admin-ajax.php
Disallow: /wp-includes/
Disallow: /wp-json/
Disallow: /xmlrpc.php
Disallow: /cgi-bin/
Disallow: /trackback/
Disallow: /comments/feed/
Disallow: /search/
Disallow: /*?s=
Disallow: /*?utm_
Disallow: /*?fbclid=
Disallow: /*?gclid=
Disallow: /*?ref=
Disallow: /*?sort=
Disallow: /*?replytocom=

# -- Google (Gemini y AI Overviews) --
User-agent: Google-Extended
Allow: /
Disallow: /wp-admin/
Allow: /wp-admin/admin-ajax.php
Disallow: /wp-includes/
Disallow: /wp-json/
Disallow: /xmlrpc.php
Disallow: /cgi-bin/
Disallow: /trackback/
Disallow: /comments/feed/
Disallow: /search/
Disallow: /*?s=
Disallow: /*?utm_
Disallow: /*?fbclid=
Disallow: /*?gclid=
Disallow: /*?ref=
Disallow: /*?sort=
Disallow: /*?replytocom=

# -- Perplexity --
User-agent: PerplexityBot
User-agent: Perplexity-User
Allow: /
Disallow: /wp-admin/
Allow: /wp-admin/admin-ajax.php
Disallow: /wp-includes/
Disallow: /wp-json/
Disallow: /xmlrpc.php
Disallow: /cgi-bin/
Disallow: /trackback/
Disallow: /comments/feed/
Disallow: /search/
Disallow: /*?s=
Disallow: /*?utm_
Disallow: /*?fbclid=
Disallow: /*?gclid=
Disallow: /*?ref=
Disallow: /*?sort=
Disallow: /*?replytocom=

# -- Apple, Amazon, Meta, Mistral, Cohere, DuckDuckGo --
User-agent: Applebot
User-agent: Applebot-Extended
User-agent: Amazonbot
User-agent: Meta-ExternalAgent
User-agent: Meta-ExternalFetcher
User-agent: MistralAI-User
User-agent: cohere-ai
User-agent: DuckAssistBot
Allow: /
Disallow: /wp-admin/
Allow: /wp-admin/admin-ajax.php
Disallow: /wp-includes/
Disallow: /wp-json/
Disallow: /xmlrpc.php
Disallow: /cgi-bin/
Disallow: /trackback/
Disallow: /comments/feed/
Disallow: /search/
Disallow: /*?s=
Disallow: /*?utm_
Disallow: /*?fbclid=
Disallow: /*?gclid=
Disallow: /*?ref=
Disallow: /*?sort=
Disallow: /*?replytocom=

# -- Common Crawl: alimenta a media industria de la IA --
User-agent: CCBot
Allow: /
Disallow: /wp-admin/
Allow: /wp-admin/admin-ajax.php
Disallow: /wp-includes/
Disallow: /wp-json/
Disallow: /xmlrpc.php
Disallow: /cgi-bin/
Disallow: /trackback/
Disallow: /comments/feed/
Disallow: /search/
Disallow: /*?s=
Disallow: /*?utm_
Disallow: /*?fbclid=
Disallow: /*?gclid=
Disallow: /*?ref=
Disallow: /*?sort=
Disallow: /*?replytocom=

# ================= 3. BOTS NO DESEADOS =================
User-agent: AhrefsBot
User-agent: SemrushBot
User-agent: DotBot
User-agent: Rogerbot
User-agent: MJ12bot
User-agent: BLEXBot
User-agent: Zmeu
User-agent: Sucker
User-agent: Larbin
Disallow: /

# ================= 4. SITEMAP =================
Sitemap: https://www.profesionalnet.net/sitemap_index.xml