# Allow major search engines
User-agent: Applebot
Allow: /
Crawl-delay: 10

User-agent: Baiduspider
Allow: /
Crawl-delay: 10

User-agent: Bingbot
Allow: /
Crawl-delay: 10

User-agent: BingPreview
Allow: /
Crawl-delay: 10

User-agent: DuckDuckBot
Allow: /
Crawl-delay: 10

User-agent: facebookexternalhit
Allow: /

User-agent: Googlebot
Allow: /

User-agent: Pinterestbot
Allow: /

User-agent: Twitterbot
Allow: /

User-agent: YandexBot
Allow: /
Crawl-delay: 10

User-agent: LinkedInBot
Allow: /

# Block specific crawlers
User-agent: Amazonbot
Disallow: /

User-agent: ImagesiftBot
Disallow: /

User-agent: crawler_eb_germany
Disallow: /

# Block all other crawlers
User-agent: *
Disallow: /

# Apple AI training
User-agent: Applebot-Extended
Disallow: /

# Google AI training
User-agent: Google-Extended
Disallow: /

# OpenAI training 
User-agent: GPTBot
Disallow: /

# Anthropic training
User-agent: ClaudeBot
Disallow: /
User-agent: anthropic-ai
Disallow: /

# Meta AI training
User-agent: Meta-ExternalAgent
Disallow: /

# Common Crawl
User-agent: CCBot
Disallow: /

# ByteDance / TikTok / Doubao training
User-agent: Bytespider
Disallow: /

# Cohere training
User-agent: cohere-ai
Disallow: /

# Diffbot
User-agent: Diffbot
Disallow: /