# Block AI Crawlers and LLM Training Bots
User-agent: GPTBot
User-agent: ChatGPT-User
User-agent: ClaudeBot
User-agent: Claude-Web
User-agent: Applebot-Extended
User-agent: Google-Extended
User-agent: PerplexityBot
User-agent: YouBot
User-agent: Meta-ExternalAgent
User-agent: Meta-ExternalFetcher
User-agent: Cohere-ai
User-agent: Amazonbot
User-agent: Omgilibot
User-agent: Omgimarketingbot
User-agent: Claude-User
User-agent: DeepSeekBot
User-agent: Gemini-Deep-Research
User-agent: GoogleOther
User-agent: Meta-WebIndexer
User-agent: PerplexityBot
User-agent: YouBot
User-agent: ai2bot
User-agent: Ai2Bot-Dolma
User-agent: iAskBot
User-agent: PhindBot
Disallow: /

# Block Known Commercial Scrapers and Data Aggregators
User-agent: CCBot
User-agent: Diffbot
User-agent: Bytespider
User-agent: PetalBot
User-agent: ImagesiftBot
User-agent: Scrapy
User-agent: DotBot
User-agent: SemrushBot
User-agent: AhrefsBot
Disallow: /

# Allow standard search engines to index your site normally
User-agent: Googlebot
User-agent: Bingbot
User-agent: Slurp
User-agent: DuckDuckBot
User-agent: Applebot
User-agent: Yandex
User-agent: Baiduspider
Allow: /