# Allow Google crawlers

User-agent: Googlebot
Allow: /

User-agent: Googlebot-Image
Allow: /

User-agent: Googlebot-News
Allow: /

User-agent: Googlebot-Video
Allow: /

User-agent: Google-Extended
Disallow: /

User-agent: facebookexternalhit
Allow: /


# Block Bing family

User-agent: bingbot
Allow: /

User-agent: BingPreview
Allow: /

User-agent: adidxbot
Disallow: /

User-agent: msnbot
Disallow: /

# Block OpenAI

User-agent: GPTBot
Disallow: /

User-agent: ChatGPT-User
Disallow: /

User-agent: OAI-SearchBot
Disallow: /

# Block Anthropic

User-agent: ClaudeBot
Disallow: /

User-agent: anthropic-ai
Disallow: /

# Block Perplexity

User-agent: PerplexityBot
Disallow: /

# Block Meta

User-agent: meta-externalagent
Disallow: /


# Block Amazon

User-agent: Amazonbot
Disallow: /

# Block Apple

User-agent: Applebot
Disallow: /

# Block ByteDance / TikTok

User-agent: Bytespider
Disallow: /

User-agent: TikTokBot
Disallow: /

# Block Common AI dataset crawlers

User-agent: CCBot
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: PetalBot
Disallow: /

User-agent: SemrushBot
Disallow: /

User-agent: AhrefsBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: DataForSeoBot
Disallow: /

User-agent: SeznamBot
Disallow: /

User-agent: YandexBot
Disallow: /

User-agent: YouBot
Disallow: /

User-agent: Baiduspider
Disallow: /

# Default rule

User-agent: *
Allow: /