# robots.txt for www.heflintrees.com
# Last updated: 2026-05-10
# Generated for Heflin Tree Service LLC — Decatur, GA · (470) 937-9592

# ─── Default: allow all reputable search + AI crawlers ───────────────────────
User-agent: *
Allow: /
Disallow: /api/
Disallow: /admin/
Disallow: /*.json$
Disallow: /*?*

# ─── Major search engines (explicit allow for crawl efficiency) ──────────────
User-agent: Googlebot
Allow: /
Crawl-delay: 0

User-agent: Googlebot-Image
Allow: /

User-agent: Googlebot-News
Allow: /

User-agent: Bingbot
Allow: /
Crawl-delay: 0

User-agent: Slurp
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: Baiduspider
Allow: /

User-agent: YandexBot
Allow: /

User-agent: Applebot
Allow: /

# ─── AI / LLM search crawlers (allowed — we want to be cited) ────────────────
# OpenAI / ChatGPT
User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: OAI-SearchBot
Allow: /

# Anthropic / Claude
User-agent: ClaudeBot
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: Claude-Web
Allow: /

# Perplexity
User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

# Google AI (Gemini, AI Overviews)
User-agent: Google-Extended
Allow: /

# Common Crawl (used as training data + cited by many LLMs)
User-agent: CCBot
Allow: /

# Cohere
User-agent: cohere-ai
Allow: /

# You.com
User-agent: YouBot
Allow: /

# Apple Intelligence
User-agent: Applebot-Extended
Allow: /

# Bytespider (TikTok / Doubao)
User-agent: Bytespider
Allow: /

# Diffbot (used by Bing, Apple, others)
User-agent: Diffbot
Allow: /

# Meta AI
User-agent: Meta-ExternalAgent
Allow: /

User-agent: FacebookBot
Allow: /

# ─── Block known low-value / scraping bots ───────────────────────────────────
User-agent: AhrefsBot
Crawl-delay: 10

User-agent: SemrushBot
Crawl-delay: 10

User-agent: DotBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: BLEXBot
Disallow: /

User-agent: PetalBot
Crawl-delay: 10

# ─── Sitemap (canonical XML index, lists all 104 URLs) ───────────────────────
Sitemap: https://www.heflintrees.com/sitemap.xml