# As a condition of accessing this website, you agree to abide by the following
# content signals:

# (a)  If a content-signal = yes, you may collect content for the corresponding
#      use.
# (b)  If a content-signal = no, you may not collect content for the
#      corresponding use.
# (c)  If the website operator does not include a content signal for a
#      corresponding use, the website operator neither grants nor restricts
#      permission via content signal with respect to the corresponding use.

# The content signals and their meanings are:

# search:   building a search index and providing search results (e.g., returning
#           hyperlinks and short excerpts from your website's contents). Search does not
#           include providing AI-generated search summaries.
# ai-input: inputting content into one or more AI models (e.g., retrieval
#           augmented generation, grounding, or other real-time taking of content for
#           generative AI search answers).
# ai-train: training or fine-tuning AI models.

# ANY RESTRICTIONS EXPRESSED VIA CONTENT SIGNALS ARE EXPRESS RESERVATIONS OF
# RIGHTS UNDER ARTICLE 4 OF THE EUROPEAN UNION DIRECTIVE 2019/790 ON COPYRIGHT
# AND RELATED RIGHTS IN THE DIGITAL SINGLE MARKET.

# BEGIN Cloudflare Managed content

User-Agent: *
Content-signal: search=yes,ai-train=no
Allow: /

User-agent: Amazonbot
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: GPTBot
Disallow: /

User-agent: meta-externalagent
Disallow: /

# END Cloudflare Managed Content

# robots.txt para Bienvenida - Asistente de Viaje con IA
# https://bienvenida.com/robots.txt

# Permitir a todos los bots de búsqueda acceso general
User-agent: *
Allow: /

# Bloquear páginas administrativas y privadas
Disallow: /login/
Disallow: /admin/
Disallow: /private/
Disallow: /cgi-bin/
Disallow: /.git/

# Bloquear páginas de búsqueda y filtros (contenido duplicado)
Disallow: /*?q=
Disallow: /*?search=
Disallow: /*?filter=
Disallow: /*?sort=
Disallow: /buscar?

# Bloquear páginas de carrito/checkout (si las añades en el futuro)
Disallow: /carrito
Disallow: /checkout
Disallow: /pago
Disallow: /cuenta/

# Bloquear archivos y directorios técnicos no necesarios para SEO
Disallow: /*.json$
Disallow: /*.xml$ # Excepto sitemaps específicamente permitidos
Disallow: /*.log$

# Reglas específicas para Google (permite todo el contenido importante)
User-agent: Googlebot
Allow: /
Disallow: /admin/
Disallow: /private/

# Reglas específicas para Google Images
User-agent: Googlebot-Image
Allow: /images/
Allow: /blog/images/
Disallow: /admin/

# Bloquear bots de IA que extraen contenido para entrenamiento
# (Opcional - comenta si quieres que usen tu contenido)
User-agent: GPTBot
Disallow: /

User-agent: ChatGPT-User
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: Claude-Web
Disallow: /

# Permitir bots de SEO y análisis comunes
User-agent: AhrefsBot
Allow: /

User-agent: SemrushBot
Allow: /

User-agent: MJ12bot
Allow: /

# Bloquear bots maliciosos conocidos y scrapers
User-agent: SemrushBot
Crawl-delay: 10

User-agent: AhrefsBot
Crawl-delay: 10

User-agent: MJ12bot
Crawl-delay: 10

# Especificar ubicación del sitemap XML (IMPORTANTE)
Sitemap: https://bienvenida.com/sitemap.xml
Sitemap: https://bienvenida.com/sitemap-blog.xml
Sitemap: https://bienvenida.com/sitemap-pages.xml

# Crawl-delay para bots más agresivos (opcional)
# User-agent: *
# Crawl-delay: 5