# robots.txt for https://thenursingdirectory.com/
# Last updated: 2026-04-23

# ============================================================
# STANDARD SEARCH ENGINES — FULLY ALLOWED
# ============================================================

User-agent: Googlebot
Allow: /
Disallow: /rest/
Disallow: /api/
Disallow: /admin/
Disallow: /cdn-cgi/

User-agent: Googlebot-Image
Allow: /

# AdSense ad crawler — REQUIRED for ad serving after approval
User-agent: Mediapartners-Google
Allow: /

# Google site verification / AdsBot (display ads)
User-agent: AdsBot-Google
Allow: /

User-agent: AdsBot-Google-Mobile
Allow: /

User-agent: Bingbot
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: YandexBot
Allow: /

User-agent: Slurp
Allow: /

# ============================================================
# AI SEARCH & INDEXING CRAWLERS — ALLOWED FOR CITATIONS
# ============================================================

User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: cohere-ai
Allow: /

User-agent: Applebot
Allow: /

User-agent: Amazonbot
Allow: /

# ============================================================
# AI TRAINING DATA SCRAPERS — BLOCKED
# ============================================================

User-agent: CCBot
Disallow: /

User-agent: DataForSeoBot
Disallow: /

User-agent: PetalBot
Disallow: /

User-agent: SemrushBot
Disallow: /

User-agent: AhrefsBot
Disallow: /

User-agent: MJ12bot
Disallow: /

# ============================================================
# ALL BOTS — allow everything except private areas
# ============================================================

User-agent: *
Allow: /
Disallow: /admin/
Disallow: /api/
Disallow: /cdn-cgi/
Disallow: /rest/

Sitemap: https://thenursingdirectory.com/sitemap.xml
Sitemap: https://thenursingdirectory.com/sitemap-news.xml