# Misana - robots.txt
# Opt-in explicite pour les crawlers IA : on veut etre cite dans les
# reponses AI (ChatGPT, Claude, Perplexity, Gemini, etc.).

# Defaut : tout autorise sauf admin, API et endpoints techniques.
User-agent: *
Allow: /
Disallow: /admin/
Disallow: /admin
Disallow: /api/
Disallow: /studio
Disallow: /studio/
Disallow: /_nuxt/
Disallow: /request

# === Moteurs de recherche ===
User-agent: Googlebot
Allow: /

User-agent: Bingbot
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: Slurp
Allow: /

User-agent: YandexBot
Allow: /

User-agent: Baiduspider
Allow: /

# === Crawlers IA (entrainement + on-demand citation) ===

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

User-agent: ChatGPT-User
Allow: /

User-agent: OAI-SearchBot
Allow: /

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

User-agent: Claude-Web
Allow: /

User-agent: anthropic-ai
Allow: /

# Google - Gemini / Bard / AI Overviews
User-agent: Google-Extended
Allow: /

# Perplexity AI
User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

# Apple Intelligence
User-agent: Applebot
Allow: /

User-agent: Applebot-Extended
Allow: /

# Meta AI
User-agent: Meta-ExternalAgent
Allow: /

User-agent: meta-externalagent
Allow: /

User-agent: FacebookBot
Allow: /

# Amazon AI
User-agent: Amazonbot
Allow: /

# ByteDance / Doubao
User-agent: Bytespider
Allow: /

# DuckDuckGo AI
User-agent: DuckAssistBot
Allow: /

# You.com AI
User-agent: YouBot
Allow: /

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

User-agent: cohere-training-data-crawler
Allow: /

# Common Crawl (utilise par de nombreux LLMs pour l'entrainement)
User-agent: CCBot
Allow: /

# Diffbot (utilise par plusieurs IA)
User-agent: Diffbot
Allow: /

# Mistral AI
User-agent: MistralAI-User
Allow: /

Sitemap: https://misana-group.com/sitemap.xml