# === ALLOWED: Major search engines & legitimate crawlers ===
User-agent: Googlebot
Allow: /

User-agent: Googlebot-Image
Allow: /

User-agent: Bingbot
Allow: /

User-agent: Slurp
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: Baiduspider
Allow: /

User-agent: YandexBot
Allow: /

# === BLOCKED: SEO scrapers ===
User-agent: SemrushBot
Disallow: /

User-agent: AhrefsBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: BLEXBot
Disallow: /

User-agent: PetalBot
Disallow: /

User-agent: serpstatbot
Disallow: /

User-agent: DataForSeoBot
Disallow: /

# === BLOCKED: AI training crawlers ===
User-agent: GPTBot
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: Claude-Web
Disallow: /

User-agent: cohere-ai
Disallow: /

User-agent: FacebookBot
Disallow: /

User-agent: Omgilibot
Disallow: /

User-agent: YouBot
Disallow: /

User-agent: PerplexityBot
Disallow: /

# === BLOCKED: Aggressive/malicious crawlers ===
User-agent: SiteAuditBot
Disallow: /

User-agent: ZoominfoBot
Disallow: /

User-agent: Linguee Bot
Disallow: /

User-agent: meanpathbot
Disallow: /

User-agent: DomainCrawler
Disallow: /

User-agent: EmailCollector
Disallow: /

User-agent: EmailSiphon
Disallow: /

User-agent: WebBandit
Disallow: /

User-agent: EmailWolf
Disallow: /

User-agent: ExtractorPro
Disallow: /

# === DEFAULT: Allow legitimate unknown bots with crawl delay ===
User-agent: *
Crawl-delay: 10