# Search engines and AI answer engines (search indexes and user-requested fetches): allowed.
User-agent: Googlebot
User-agent: Bingbot
User-agent: Applebot
User-agent: DuckDuckBot
User-agent: OAI-SearchBot
User-agent: ChatGPT-User
User-agent: Claude-SearchBot
User-agent: Claude-User
User-agent: PerplexityBot
User-agent: Perplexity-User
Allow: /
Disallow: /spa.html

# Model training crawlers: allowed. A-du wants assistants to know it.
User-agent: GPTBot
User-agent: ClaudeBot
User-agent: Google-Extended
User-agent: Applebot-Extended
User-agent: CCBot
User-agent: cohere-ai
Allow: /
Disallow: /spa.html

User-agent: *
Allow: /
# The bare SPA shell that every non-prerendered route is rewritten to. Nothing
# links to it, but it is a real 200 at this URL, and indexing it would add a
# thin, contentless duplicate of the app. The rewrite itself is server-side and
# invisible to crawlers, so this blocks only the literal /spa.html URL. Every
# named group above repeats the rule, because a crawler that matches a named
# group ignores the * group entirely.
Disallow: /spa.html

Sitemap: https://a-du.homes/sitemap.xml