# HealthBase robots.txt
# https://healthbase.io

# ── Allow all legitimate crawlers ──
User-agent: *
Allow: /

# Block query strings and non-content paths
Disallow: /*?*
Disallow: /*.json$

# ── Google ──
User-agent: Googlebot
Allow: /
Crawl-delay: 1

User-agent: Googlebot-Image
Allow: /

# ── Bing ──
User-agent: Bingbot
Allow: /
Crawl-delay: 2

# ── AI Answer Engines & Research Crawlers ──
# Explicitly allow AI/LLM crawlers for GEO (Generative Engine Optimization)

User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: cohere-ai
Allow: /

User-agent: YouBot
Allow: /

# ── Social & Preview Crawlers ──
User-agent: Twitterbot
Allow: /

User-agent: facebookexternalhit
Allow: /

User-agent: LinkedInBot
Allow: /

# ── Research & Academic Crawlers ──
User-agent: Semanticscholar
Allow: /

User-agent: ia_archiver
Allow: /

# ── Block Known Bad Actors / Scrapers ──
User-agent: AhrefsBot
Disallow: /

User-agent: SemrushBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: BLEXBot
Disallow: /

User-agent: PetalBot
Disallow: /

# ── Sitemaps ──
Sitemap: https://healthbase.io/sitemap.xml