# Default modx exclusions User-agent: * Disallow: /members/ Disallow: /wp-admin/ Disallow: /wp-includes/ Disallow: /manifests/ Disallow: /users/ Disallow: /profile/ Disallow: /crm/ Disallow: /assets/export/ Disallow: /assets/import/ Disallow: /assets/modules/ Disallow: /assets/plugins/ Disallow: /assets/snippets/ Disallow: /assets/files/ Disallow: /install/ Disallow: /admin/ Disallow: /cms/ Disallow: /manager/ Disallow: /partners/ Disallow: /bzz/ Disallow: /redactie/ Disallow: /packages/ Disallow: /video/ Disallow: /auth/ Disallow: /account/ Disallow: /preview/ Disallow: /search/ Disallow: /cgi-bin/ # For sitemaps.xml autodiscovery. Uncomment if you have one: Sitemap: https://jasperjaspers.nl/sitemap.xml Sitemap: https://jasperjaspers.nl/xml-sitemap.php # De AhrefsBot mag maar 1 keer per dag langskomen User-agent: AhrefsBot Crawl-Delay: 86400 # The example for img2dataset, although the default is *None* # User-agent: img2dataset # Disallow: / # Brandwatch - "AI to discover new trends" # User-agent: magpie-crawler # Disallow: / # webz.io - they sell data for training LLMs. # User-agent: Omgilibot # Disallow: / # Items below were sourced from darkvisitors.com # Categories included: "AI Data Scraper", "AI Assistant", "AI Search Crawler", "Undocumented AI Agent" # AI Search Crawler # https://darkvisitors.com/agents/amazonbot # User-agent: Amazonbot # Disallow: / # Undocumented AI Agent # https://darkvisitors.com/agents/anthropic-ai # User-agent: anthropic-ai # Disallow: / # AI Search Crawler # https://darkvisitors.com/agents/applebot # User-agent: Applebot # Disallow: / # AI Data Scraper # https://darkvisitors.com/agents/applebot-extended # User-agent: Applebot-Extended # Disallow: / # AI Data Scraper # https://darkvisitors.com/agents/bytespider # User-agent: Bytespider # Disallow: / # AI Data Scraper # https://darkvisitors.com/agents/ccbot # User-agent: CCBot # Disallow: / # AI Assistant # https://darkvisitors.com/agents/chatgpt-user # User-agent: ChatGPT-User # Disallow: / # Undocumented AI Agent # https://darkvisitors.com/agents/claude-web # User-agent: Claude-Web # Disallow: / # AI Data Scraper # https://darkvisitors.com/agents/claudebot # User-agent: ClaudeBot # Disallow: / # Undocumented AI Agent # https://darkvisitors.com/agents/cohere-ai # User-agent: cohere-ai # Disallow: / # AI Data Scraper # https://darkvisitors.com/agents/diffbot # User-agent: Diffbot # Disallow: / # AI Data Scraper # https://darkvisitors.com/agents/facebookbot # User-agent: FacebookBot # Disallow: / # AI Data Scraper # https://darkvisitors.com/agents/google-extended # User-agent: Google-Extended # Disallow: / # AI Data Scraper # https://darkvisitors.com/agents/gptbot # User-agent: GPTBot # Disallow: / # AI Data Scraper # https://darkvisitors.com/agents/omgili # User-agent: omgili # Disallow: / # AI Search Crawler # https://darkvisitors.com/agents/perplexitybot # User-agent: PerplexityBot # Disallow: / # AI Search Crawler # https://darkvisitors.com/agents/youbot # User-agent: YouBot # Disallow: /