# robots.txt — Phase 115 (regenerated 2026-05-09)
User-agent: *
Allow: /
Disallow: /admin/
Disallow: /api/
Disallow: /*?utm_*
Disallow: /*?ref=


# AI engines — explicit allow, no crawl-delay
User-agent: GPTBot
Allow: /
User-agent: OAI-SearchBot
Allow: /
User-agent: ChatGPT-User
Allow: /
User-agent: PerplexityBot
Allow: /
User-agent: Perplexity-User
Allow: /
User-agent: ClaudeBot
Allow: /
User-agent: Claude-Web
Allow: /
User-agent: anthropic-ai
Allow: /
User-agent: Google-Extended
Allow: /
User-agent: GoogleOther
Allow: /
User-agent: Applebot-Extended
Allow: /
User-agent: Bytespider
Allow: /
User-agent: CCBot
Allow: /
User-agent: cohere-ai
Allow: /
User-agent: Meta-ExternalAgent
Allow: /
User-agent: FacebookBot
Allow: /
User-agent: Amazonbot
Allow: /
User-agent: DuckAssistBot
Allow: /
User-agent: YouBot
Allow: /
User-agent: Diffbot
Allow: /
User-agent: ImagesiftBot
Allow: /
User-agent: Mistral-AI
Allow: /
User-agent: xAI-Bot
Allow: /

Sitemap: https://thainotary.co.th/sitemap.xml

# HTML sitemap hubs (Phase 189/191) — crawler-friendly flat link corpus served
# as real static HTML (independent of SPA hydration). Discovery hints:
# https://thainotary.co.th/sitemap-hub.html      (1,500 curated hub URLs)
# https://thainotary.co.th/hub/index.html        (15 cluster sub-hubs → 100K+ deep URLs)

# Phase 192 — Top-1000 static snapshot discovery
# Snapshot Index: https://thainotary.co.th/snapshot/index.html