User-agent: *
Allow: /
Disallow: /inicio
Disallow: /admin
Disallow: /bienvenida
Disallow: /primera-alerta
Disallow: /alertas$
Disallow: /alertas/
Disallow: /alerta/
Disallow: /calendario
Disallow: /clientes
Disallow: /entradas
Disallow: /ajustes
Disallow: /pagos
Disallow: /invitacion
Disallow: /baja
Disallow: /login
Disallow: /oauth
Disallow: /promo
Disallow: /demo
# /empresas (plural) is the PRIVATE company explorer — distinct from the public
# /empresa/:nif ficha below.
Disallow: /empresas$
Disallow: /empresas/
# /categorias is the private "Licitaciones" product tab (ProtectedRoute). It
# rewrites to _spa-shell.html, which keeps the template's "index, follow" — the
# noindex only lands after React hydrates. Every other private route is listed
# here; this one was the gap.
Disallow: /categorias$
Disallow: /categorias/
# /empresa/:nif is crawlable: a curated whitelist (scripts/data/top-empresas.json)
# ships as prerendered, indexable static pages; every other /empresa URL is
# served a noindex shell (firebase.json → _spa-shell-empresa.html).

# AI crawlers: explicitly welcome
User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: Applebot-Extended
Allow: /

User-agent: CCBot
Allow: /

# Claude and Perplexity user/search agents. Without their own group they fall
# through to the wildcard (also allowed), but naming them keeps the policy
# explicit: ClaudeBot only covers training.
User-agent: Claude-SearchBot
Allow: /

User-agent: Claude-User
Allow: /

User-agent: Perplexity-User
Allow: /

Sitemap: https://boletinclaro.es/sitemap.xml