# robots.txt for medicum.fr
# Last updated: 2025-05-09

User-agent: Googlebot
Allow: /

User-agent: Googlebot-Image
Allow: /

User-agent: Googlebot-Mobile
Allow: /

User-agent: Googlebot-News
Allow: /

User-agent: Bingbot
Allow: /

User-agent: MSNBot
Allow: /

User-agent: BingPreview
Allow: /

User-agent: Slurp
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
User-agent: ChatGPT-User/2.0
Allow: /

User-agent: GPTBot
Disallow: /                    

# ——— ANTHROPIC (Claude) ———
User-agent: anthropic-ai      # bulk model training
Disallow: /
User-agent: ClaudeBot         # chat citation fetch
User-agent: claude-web        # web-focused crawl
Allow: /

# ——— PERPLEXITY ———
User-agent: PerplexityBot     # index builder
Allow: /
User-agent: Perplexity-User   # human-triggered visit
Allow: /

# ——— GOOGLE (Gemini) ———
User-agent: Google-Extended
Allow: /

# ——— MICROSOFT (Bing / Copilot) ———
User-agent: BingBot
Allow: /

# ——— AMAZON ———
User-agent: Amazonbot
Allow: /

# ——— APPLE ———
User-agent: Applebot
User-agent: Applebot-Extended
Allow: /

# ——— META ———
User-agent: FacebookBot
User-agent: meta-externalagent
Allow: /

# ——— LINKEDIN ———
User-agent: LinkedInBot
Allow: /

# ——— BYTEDANCE ———
User-agent: Bytespider
Allow: /

# ——— DUCKDUCKGO ———
User-agent: DuckAssistBot
Allow: /

# ——— COHERE ———
User-agent: cohere-ai
Allow: /

# ——— ALLEN INSTITUTE / COMMON CRAWL / OTHER RESEARCH ———
User-agent: AI2Bot
User-agent: CCBot
User-agent: Diffbot
User-agent: omgili
Disallow: /

# ——— EMERGING SEARCH START-UPS ———
User-agent: TimpiBot
User-agent: YouBot
Disallow: /

User-agent: Baiduspider
Disallow: /

User-agent: Yandex
Disallow: /

User-agent: YandexBot
Disallow: /

User-agent: SeznamBot
Disallow: /

User-agent: Exabot
Disallow: /

User-agent: ia_archiver
Disallow: /

User-agent: TurnitinBot
Disallow: /

User-agent: ZoominfoBot
Disallow: /

User-agent: 360Spider
Disallow: /

User-agent: ZmEu
Disallow: /

User-agent: Wget
Disallow: /

User-agent: EmailCollector
Disallow: /

User-agent: EmailSiphon
Disallow: /

User-agent: WebBandit
Disallow: /

User-agent: WebZIP
Disallow: /

User-agent: HTTrack
Disallow: /

User-agent: WebCopier
Disallow: /

User-agent: Download Ninja
Disallow: /

User-agent: Offline Explorer
Disallow: /

User-agent: Teleport Pro
Disallow: /

User-agent: WebStripper
Disallow: /

User-agent: Xaldon WebSpider
Disallow: /

User-agent: NetSpider
Disallow: /

User-agent: NetZip
Disallow: /

# Block all bots not specified above
User-agent: *
Allow: /

Sitemap: https://www.medicum.fr/sitemapindex.xml