# PartFinder — robots.txt
# Policy: discoverable via search, not available for AI training.

Host: https://partfinder.dev

# === Default: allow search engines and AI search bots ===
User-agent: *
Allow: /
Disallow: /api/
Disallow: /_next/
Disallow: /onboarding
Disallow: /dashboard
Disallow: /settings
Disallow: /checkout
Crawl-delay: 1

# === Block AI model training crawlers ===

# OpenAI (training only; OAI-SearchBot and ChatGPT-User are allowed)
User-agent: GPTBot
Disallow: /

# Google AI training (Googlebot for search is allowed)
User-agent: Google-Extended
Disallow: /

# Anthropic
User-agent: ClaudeBot
Disallow: /
User-agent: anthropic-ai
Disallow: /

# Meta
User-agent: Meta-ExternalAgent
Disallow: /
User-agent: Meta-ExternalFetcher
Disallow: /
User-agent: FacebookBot
Disallow: /

# Common Crawl (feeds most open-source training sets)
User-agent: CCBot
Disallow: /

# ByteDance
User-agent: Bytespider
Disallow: /
User-agent: DoubaoBot
Disallow: /

# Baidu AI
User-agent: PetalBot
Disallow: /

# Cohere (training; cohere-ai search is allowed)
User-agent: cohere-training-data-crawler
Disallow: /

# Data extractors
User-agent: Diffbot
Disallow: /
User-agent: img2dataset
Disallow: /

# Scrapers / SEO tools (no value, just load)
User-agent: AhrefsBot
Disallow: /
User-agent: SemrushBot
Disallow: /
User-agent: DotBot
Disallow: /
User-agent: MJ12bot
Disallow: /

Sitemap: https://partfinder.dev/sitemap.xml