# robots.txt — manucontreras.com
# Buscadores: acceso permitido
# Rastreadores de IA: bloqueados

# -----------------------------------------------
# BUSCADORES PERMITIDOS
# -----------------------------------------------

User-agent: Googlebot
Allow: /

User-agent: Googlebot-Image
Allow: /

User-agent: Bingbot
Allow: /

User-agent: Slurp
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: Baiduspider
Allow: /

User-agent: YandexBot
Allow: /

User-agent: facebookexternalhit
Allow: /

User-agent: Twitterbot
Allow: /

User-agent: LinkedInBot
Allow: /

# -----------------------------------------------
# RASTREADORES DE IA — BLOQUEADOS
# -----------------------------------------------

# OpenAI / ChatGPT
User-agent: GPTBot
Disallow: /

User-agent: ChatGPT-User
Disallow: /

User-agent: OAI-SearchBot
Disallow: /

# Anthropic / Claude
User-agent: ClaudeBot
Disallow: /

User-agent: Claude-Web
Disallow: /

User-agent: anthropic-ai
Disallow: /

# Google AI (Gemini / Bard entrenamiento)
User-agent: Google-Extended
Disallow: /

# Meta AI
User-agent: FacebookBot
Disallow: /

User-agent: Meta-ExternalAgent
Disallow: /

User-agent: Meta-ExternalFetcher
Disallow: /

# Amazon Alexa / Alexa AI
User-agent: Amazonbot
Disallow: /

# Apple AI
User-agent: Applebot-Extended
Disallow: /

# Common Crawl (base de datos usada por muchos modelos)
User-agent: CCBot
Disallow: /

# Cohere
User-agent: cohere-ai
Disallow: /

# Perplexity
User-agent: PerplexityBot
Disallow: /

# You.com
User-agent: YouBot
Disallow: /

# Diffbot (extracción de datos para IA)
User-agent: Diffbot
Disallow: /

# Bytespider / TikTok (ByteDance)
User-agent: Bytespider
Disallow: /

# Omgili / Webz.io (datos para LLMs)
User-agent: omgili
Disallow: /

User-agent: omgilibot
Disallow: /

# DataForSEO
User-agent: DataForSeoBot
Disallow: /

# ImagesiftBot
User-agent: ImagesiftBot
Disallow: /

# Magpie-Crawler (Paragraph AI)
User-agent: Magpie-Crawler
Disallow: /

# PetalBot (Huawei AI)
User-agent: PetalBot
Disallow: /

# Scrapy (scraping genérico)
User-agent: Scrapy
Disallow: /

# Timpibot
User-agent: Timpibot
Disallow: /

# -----------------------------------------------
# SITEMAP
# -----------------------------------------------

Sitemap: https://manucontreras.com/sitemap.xml