# SNL Painting Inc. — https://snlpainting.com
# robots.txt — intentional AI crawler policy
# Last updated: 2026-05-14

# ── Search engines: full crawl ────────────────────────────────
User-agent: Googlebot
Allow: /

User-agent: Bingbot
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: Applebot
Allow: /

# ── AI training & retrieval crawlers ──────────────────────────
# Strategy: ALLOW retrieval crawlers (live citation in AI answers)
#           BLOCK pure training crawlers (no SEO upside for us)
# Re-evaluate every 90 days; AI crawler behavior shifts fast.

# Google AI Overviews & Gemini retrieval — must remain ALLOWED
User-agent: Google-Extended
Allow: /

# OpenAI live web retrieval (ChatGPT browsing, ChatGPT Search) — ALLOW
User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

# OpenAI training crawler — BLOCK (no retrieval benefit, only training)
User-agent: GPTBot
Disallow: /

# Anthropic retrieval (Claude with web search) — ALLOW
User-agent: ClaudeBot
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: anthropic-ai
Disallow: /

# Perplexity retrieval — ALLOW
User-agent: PerplexityBot
Allow: /

# Microsoft Copilot / Bing Chat — ALLOW (Bingbot covers it)

# Common Crawl (feeds many AI training datasets) — BLOCK
User-agent: CCBot
Disallow: /

# Meta AI / FacebookBot training — BLOCK
User-agent: FacebookBot
Disallow: /

User-agent: Meta-ExternalAgent
Disallow: /

# Bytedance / TikTok training crawler — BLOCK
User-agent: Bytespider
Disallow: /

# Apple training crawler — BLOCK (Applebot above is retrieval)
User-agent: Applebot-Extended
Disallow: /

# ── Block bad bots / scrapers ─────────────────────────────────
User-agent: AhrefsBot
Crawl-delay: 10

User-agent: SemrushBot
Crawl-delay: 10

User-agent: MJ12bot
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: PetalBot
Disallow: /

# ── Standard WordPress hardening ──────────────────────────────
User-agent: *
Allow: /
Disallow: /wp-admin/
Disallow: /wp-includes/
Disallow: /wp-content/plugins/
Disallow: /wp-content/cache/
Disallow: /readme.html
Disallow: /license.txt
Disallow: /xmlrpc.php
Disallow: /?s=
Disallow: /search/
Disallow: /*?replytocom
Disallow: /*?p=
Disallow: /trackback/
Allow: /wp-admin/admin-ajax.php
Allow: /wp-content/uploads/

# ── Sitemaps ──────────────────────────────────────────────────
Sitemap: https://snlpainting.com/sitemap_index.xml
Sitemap: https://snlpainting.com/page-sitemap.xml
Sitemap: https://snlpainting.com/post-sitemap.xml
Sitemap: https://snlpainting.com/service-sitemap.xml
Sitemap: https://snlpainting.com/local-sitemap.xml