# corrigiendo.es - robots.txt
# Política: permitir búsqueda (incluida IA con citación), bloquear entrenamiento de modelos
# Fuente única: config/seo/bots.yaml
# Última actualización: 2026-05-15

# ========================================
# Crawlers de búsqueda (permitidos)
# ========================================

User-agent: Googlebot
Allow: /
Disallow: /admin/
Disallow: /scanner/
Disallow: /webhook/
Disallow: /dashboard/
Disallow: /manage/
Disallow: /examen/
Disallow: /examen-grupal/
Disallow: /subscription/
Disallow: /login
Disallow: /login-beta
Disallow: /register
Disallow: /password
Disallow: /connect/

User-agent: Googlebot-Image
Allow: /

User-agent: Bingbot
Allow: /
Disallow: /admin/
Disallow: /scanner/
Disallow: /webhook/
Disallow: /dashboard/
Disallow: /manage/
Disallow: /examen/
Disallow: /examen-grupal/
Disallow: /subscription/
Disallow: /login
Disallow: /login-beta
Disallow: /register
Disallow: /password
Disallow: /connect/

User-agent: DuckDuckBot
Allow: /
Disallow: /admin/
Disallow: /scanner/
Disallow: /webhook/
Disallow: /dashboard/
Disallow: /manage/
Disallow: /examen/

# Crawlers de búsqueda con IA (permitidos: indexan para citación, no para entrenamiento)
User-agent: OAI-SearchBot
Allow: /
Disallow: /admin/
Disallow: /scanner/
Disallow: /webhook/
Disallow: /dashboard/
Disallow: /manage/

User-agent: ChatGPT-User
Allow: /
Disallow: /admin/
Disallow: /scanner/
Disallow: /webhook/
Disallow: /dashboard/
Disallow: /manage/

User-agent: PerplexityBot
Allow: /
Disallow: /admin/
Disallow: /scanner/
Disallow: /webhook/
Disallow: /dashboard/
Disallow: /manage/

User-agent: ClaudeBot
Allow: /
Disallow: /admin/
Disallow: /scanner/
Disallow: /webhook/
Disallow: /dashboard/
Disallow: /manage/

User-agent: Applebot
Allow: /
Disallow: /admin/
Disallow: /scanner/
Disallow: /webhook/
Disallow: /dashboard/
Disallow: /manage/

User-agent: YandexBot
Allow: /
Disallow: /admin/
Disallow: /scanner/
Disallow: /webhook/
Disallow: /dashboard/
Disallow: /manage/

# ========================================
# Crawlers de entrenamiento (bloqueados)
# ========================================

User-agent: GPTBot
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: Amazonbot
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: cohere-ai
Disallow: /

User-agent: FacebookBot
Disallow: /

User-agent: Meta-ExternalAgent
Disallow: /

User-agent: Meta-ExternalFetcher
Disallow: /

User-agent: ImagesiftBot
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: Omgilibot
Disallow: /

User-agent: PetalBot
Disallow: /

# ========================================
# Resto de bots
# ========================================

User-agent: *
Allow: /
Disallow: /admin/
Disallow: /scanner/
Disallow: /webhook/
Disallow: /dashboard/
Disallow: /manage/
Disallow: /examen/
Disallow: /examen-grupal/
Disallow: /subscription/
Disallow: /_profiler/
Disallow: /login
Disallow: /login-beta
Disallow: /register
Disallow: /password
Disallow: /connect/
Disallow: /*?*utm_

# ========================================
# Sitemaps
# ========================================

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