# robots.txt for blog - Allow search engines, block AI crawlers

# Allow major search engines
User-agent: Googlebot
Allow: /

User-agent: Bingbot
Allow: /

User-agent: Slurp
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: Baiduspider
Allow: /

User-agent: YandexBot
Allow: /

User-agent: facebookexternalhit
Allow: /

User-agent: Twitterbot
Allow: /

User-agent: LinkedInBot
Allow: /

# Block known AI crawlers and scrapers
User-agent: GPTBot
Disallow: /

User-agent: ChatGPT-User
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: Claude-Web
Disallow: /

User-agent: PerplexityBot
Disallow: /

User-agent: YouBot
Disallow: /

User-agent: Meta-ExternalAgent
Disallow: /

User-agent: Meta-ExternalFetcher
Disallow: /

User-agent: cohere-ai
Disallow: /

User-agent: Claude
Disallow: /

User-agent: AI2Bot
Disallow: /

User-agent: ChatGPT
Disallow: /

User-agent: OAI-SearchBot
Disallow: /

User-agent: ChatGPT-Bot
Disallow: /

User-agent: ChatGPT-crawler
Disallow: /

User-agent: ChatGPT-User-Bot
Disallow: /

User-agent: ChatGPT-GPT4
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: AdsBot-Google
Disallow: /

User-agent: ImageSift
Disallow: /

User-agent: Timpibot
Disallow: /

# Block generic scraping patterns
User-agent: *bot*
Disallow: /

User-agent: *crawler*
Disallow: /

User-agent: *scraper*
Disallow: /

User-agent: *spider*
Disallow: /

# Default rule for unspecified agents
User-agent: *
Disallow: /

# Sitemap location (optional - update with your actual sitemap URL)
# Sitemap: https://yourblog.com/sitemap.xml