Sitemap: https://www.mazarine.com/sitemap.xml

User-agent: *
Disallow: /*?uuid=*&preview=*
Disallow: /*?*preview=*

# OpenAI — ChatGPT search & Browse
User-agent: GPTBota
Allow: /

# OpenAI — ChatGPT user-facing browsing
User-agent: ChatGPT-User
Allow: /

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

# Anthropic — Claude (legacy)
User-agent: anthropic-ai
Allow: /

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

# Perplexity
User-agent: PerplexityBot
Allow: /

# Apple — Siri / Apple Intelligence
User-agent: Applebot-Extended
Allow: /

# Meta — Meta AI
User-agent: FacebookBot
Allow: /

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

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

# Diffbot
User-agent: Diffbot
Allow: /

# Common Crawl — principale source des datasets d'entraînement LLM
User-agent: CCBot
Disallow: /

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

# Omgili / Webz.io — data reseller
User-agent: omgili
Disallow: /

User-agent: omgilibot
Disallow: /

# DataForSEO
User-agent: DataForSeoBot
Disallow: /