# ANA crawler policy, 2026-05-23.
# Mission: let search engines and LLM answer/citation systems find and cite ANA.
# Boundary: block bulk model-training crawlers and commercial scrapers that take
# the corpus without sending readers back to the source.

User-agent: *
Allow: /

# Search / citation AI.
User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: Googlebot
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: Claude-User
Allow: /

User-agent: Claude-SearchBot
Allow: /

User-agent: PerplexityBot
Allow: /

# Model-training or bulk AI crawlers.
User-agent: GPTBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: Claude-Web
Disallow: /

User-agent: Meta-ExternalAgent
Disallow: /

User-agent: FacebookBot
Disallow: /

User-agent: Amazonbot
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: cohere-ai
Disallow: /

User-agent: cohere-training-data-crawler
Disallow: /

# Aggressive bulk crawlers and commercial scrapers.
User-agent: CCBot
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: AhrefsBot
Disallow: /

User-agent: SemrushBot
Disallow: /

User-agent: DataForSeoBot
Disallow: /

User-agent: PetalBot
Disallow: /

User-agent: BLEXBot
Disallow: /

User-agent: dotbot
Disallow: /

User-agent: omgili
Disallow: /

User-agent: SeekportBot
Disallow: /

Sitemap: https://wisconsincontractorauthority.com/sitemap.xml