# Block AI and data collection bots
User-agent: AdsBot-Google
User-agent: Amazonbot
User-agent: anthropic-ai
User-agent: Applebot-Extended
User-agent: AwarioRssBot
User-agent: AwarioSmartBot
User-agent: Bytespider
User-agent: ByteDanceSpider
User-agent: CCBot
User-agent: ChatGPT-User
User-agent: ClaudeBot
User-agent: Claude-Web
User-agent: cohere-ai
User-agent: DataForSeoBot
User-agent: Diffbot
User-agent: FacebookBot
User-agent: FriendlyCrawler
User-agent: Google-Extended
User-agent: GoogleOther
User-agent: GPTBot
User-agent: img2dataset
User-agent: ImagesiftBot
User-agent: magpie-crawler
User-agent: Meltwater
User-agent: omgili
User-agent: omgilibot
User-agent: peer39_crawler
User-agent: peer39_crawler/1.0
User-agent: PerplexityBot
User-agent: PiplBot
User-agent: scoop.it
User-agent: Seekr
User-agent: YouBot
Disallow: /

# Block aggressive SEO tools
User-agent: AhrefsBot
User-agent: SemrushBot
User-agent: MJ12bot
User-agent: DotBot
Disallow: /

# Main search engines and their bots
User-agent: Googlebot
User-agent: Googlebot-News
User-agent: Googlebot-Video
User-agent: Googlebot-Image
User-agent: Bingbot
User-agent: Bingbot-Image
User-agent: YandexBot
User-agent: YandexImages
User-agent: Baiduspider
User-agent: Baiduspider-image
User-agent: DuckDuckBot
User-agent: Pinterestbot
Disallow:

# All other crawlers
User-agent: *
Disallow:

# Sitemap location
Sitemap: https://simone.org/sitemap.xml