# RealBizGrants Robots.txt
# Updated: May 2026 — block AI training & most AI search crawlers per ownership directive

# Allow major search engines (these still drive clicks)
User-agent: Googlebot
Allow: /
Crawl-delay: 1

User-agent: Bingbot
Allow: /
Crawl-delay: 1

User-agent: Slurp
Allow: /

User-agent: DuckDuckBot
Allow: /

# Baiduspider intentionally blocked below (Chinese scrapers section)

User-agent: YandexBot
Allow: /

User-agent: Applebot
Allow: /

# Social previews
User-agent: Twitterbot
Allow: /

User-agent: LinkedInBot
Allow: /

User-agent: Pinterest
Allow: /

# ─────────────────────────────────────────────
# AI ANSWER / RETRIEVAL crawlers — ALLOWED
# These power real-time citations in ChatGPT, Perplexity, Claude.
# Allowing them is required for GEO/AEO visibility.
# ─────────────────────────────────────────────
User-agent: ChatGPT-User
Allow: /
Disallow: /admin
Disallow: /dashboard
Disallow: /vault
Disallow: /review
Disallow: /copilot
Disallow: /reset-password
Disallow: /auth
Disallow: /onboarding

User-agent: OAI-SearchBot
Allow: /
Disallow: /admin
Disallow: /dashboard
Disallow: /vault
Disallow: /review
Disallow: /copilot
Disallow: /reset-password
Disallow: /auth
Disallow: /onboarding

User-agent: Perplexity-User
Allow: /
Disallow: /admin
Disallow: /dashboard
Disallow: /vault
Disallow: /review
Disallow: /copilot
Disallow: /reset-password
Disallow: /auth
Disallow: /onboarding

User-agent: Claude-Web
Allow: /
Disallow: /admin
Disallow: /dashboard
Disallow: /vault
Disallow: /review
Disallow: /copilot
Disallow: /reset-password
Disallow: /auth
Disallow: /onboarding

# ─────────────────────────────────────────────
# AI TRAINING crawlers — BLOCKED
# These ingest content for model training without compensation.
# ─────────────────────────────────────────────
User-agent: GPTBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: PerplexityBot
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: Amazonbot
Disallow: /

User-agent: FacebookBot
Disallow: /

User-agent: facebookexternalhit
Disallow: /

User-agent: Meta-ExternalAgent
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: ImagesiftBot
Disallow: /

User-agent: Omgilibot
Disallow: /

User-agent: cohere-ai
Disallow: /

User-agent: Timpibot
Disallow: /

# ─────────────────────────────────────────────
# Chinese scrapers — BLOCKED
# Aggressive crawlers with little SEO/citation value in our market.
# ─────────────────────────────────────────────
User-agent: Baiduspider
Disallow: /

User-agent: Baiduspider-render
Disallow: /

User-agent: Baiduspider-image
Disallow: /

User-agent: Baiduspider-news
Disallow: /

User-agent: Baiduspider-video
Disallow: /

User-agent: Sogou web spider
Disallow: /

User-agent: Sogou inst spider
Disallow: /

User-agent: Sogou Pic Spider
Disallow: /

User-agent: Sogou News Spider
Disallow: /

User-agent: Sogou Orion spider
Disallow: /

User-agent: Sosospider
Disallow: /

User-agent: 360Spider
Disallow: /

User-agent: 360Spider-Image
Disallow: /

User-agent: 360Spider-Video
Disallow: /

User-agent: HaoSouSpider
Disallow: /

User-agent: Yisouspider
Disallow: /

User-agent: EasouSpider
Disallow: /

User-agent: YoudaoBot
Disallow: /

User-agent: YodaoBot
Disallow: /

User-agent: ByteDance
Disallow: /

User-agent: TencentBot
Disallow: /

User-agent: Tencent_spider
Disallow: /

# Default rules — protect private routes
User-agent: *
Allow: /
Disallow: /dashboard
Disallow: /admin
Disallow: /vault
Disallow: /review
Disallow: /copilot
Disallow: /reset-password
Disallow: /auth
Disallow: /onboarding
Disallow: /confirm-newsletter
Disallow: /starter-pack
Disallow: /api/

# Sitemaps
Sitemap: https://www.realbizgrants.com/sitemap.xml
Sitemap: https://www.realbizgrants.com/sitemap-index.xml
Sitemap: https://ajwrvlzznouvvrdxgkmk.supabase.co/functions/v1/grant-profiles-sitemap