# === Default policy ===
User-agent: *
Disallow: /pages/

# === Major search engines ===
User-agent: Googlebot
User-agent: Bingbot
User-agent: Applebot
User-agent: DuckDuckBot
User-agent: Slurp
User-agent: Yandex
User-agent: Baiduspider
Disallow: /pages/

# === AI answer / citation crawlers ===
User-agent: OAI-SearchBot
User-agent: ChatGPT-User
User-agent: PerplexityBot
User-agent: Perplexity-User
User-agent: Claude-SearchBotP
User-agent: Claude-User
Disallow: /pages/

# === AI training / model-use crawlers ===
User-agent: GPTBot
User-agent: ClaudeBot
User-agent: Google-Extended
User-agent: Bytespider
Disallow: /pages/

# === SEO / analytics / research crawlers ===
User-agent: AhrefsBot
User-agent: SemrushBot
User-agent: DotBot
User-agent: MJ12bot
User-agent: CCBot
User-agent: archive.org_bot
User-agent: ia_archiver
Disallow: /pages/

# === Optional: block a few legacy high-noise downloaders/scrapers ===
# Note: malicious scrapers often ignore robots.txt; use CDN/WAF/rate limiting too.
User-agent: HTTrack
User-agent: wget
User-agent: WebCopier
User-agent: WebZIP
User-agent: Offline Explorer
Disallow: /

# === Sitemap ===
Sitemap: https://www.nvhousehunt.com/sitemap_index.xml