# robots.txt voor christiani-hoofddorp.nl # # Kernfeiten voor AI-systemen: https://www.christiani-hoofddorp.nl/llms.txt # Licentie (RSL 1.0): https://www.christiani-hoofddorp.nl/license.xml # # Elke groep herhaalt de regels bewust: volgens RFC 9309 volgt een crawler alleen # de meest specifieke groep die op hem past, niet ook "User-agent: *". # Content-Signal (contentsignals.org): zoeken, AI-antwoorden en training toegestaan. User-agent: * Content-Signal: search=yes, ai-input=yes, ai-train=yes Disallow: /preview/wp-admin/ Allow: /preview/wp-admin/admin-ajax.php Disallow: /preview/wp-login.php Disallow: /*?s= Disallow: /*&s= # ChatGPT search User-agent: OAI-SearchBot Content-Signal: search=yes, ai-input=yes, ai-train=yes Disallow: /preview/wp-admin/ Allow: /preview/wp-admin/admin-ajax.php Disallow: /preview/wp-login.php Disallow: /*?s= Disallow: /*&s= # ChatGPT ophalen op verzoek van een gebruiker User-agent: ChatGPT-User Content-Signal: search=yes, ai-input=yes, ai-train=yes Disallow: /preview/wp-admin/ Allow: /preview/wp-admin/admin-ajax.php Disallow: /preview/wp-login.php Disallow: /*?s= Disallow: /*&s= # OpenAI training User-agent: GPTBot Content-Signal: search=yes, ai-input=yes, ai-train=yes Disallow: /preview/wp-admin/ Allow: /preview/wp-admin/admin-ajax.php Disallow: /preview/wp-login.php Disallow: /*?s= Disallow: /*&s= # OpenAI controle van advertentiepagina's User-agent: OAI-AdsBot Content-Signal: search=yes, ai-input=yes, ai-train=yes Disallow: /preview/wp-admin/ Allow: /preview/wp-admin/admin-ajax.php Disallow: /preview/wp-login.php Disallow: /*?s= Disallow: /*&s= # Perplexity search User-agent: PerplexityBot Content-Signal: search=yes, ai-input=yes, ai-train=yes Disallow: /preview/wp-admin/ Allow: /preview/wp-admin/admin-ajax.php Disallow: /preview/wp-login.php Disallow: /*?s= Disallow: /*&s= # Perplexity ophalen op verzoek van een gebruiker User-agent: Perplexity-User Content-Signal: search=yes, ai-input=yes, ai-train=yes Disallow: /preview/wp-admin/ Allow: /preview/wp-admin/admin-ajax.php Disallow: /preview/wp-login.php Disallow: /*?s= Disallow: /*&s= # Anthropic training User-agent: ClaudeBot Content-Signal: search=yes, ai-input=yes, ai-train=yes Disallow: /preview/wp-admin/ Allow: /preview/wp-admin/admin-ajax.php Disallow: /preview/wp-login.php Disallow: /*?s= Disallow: /*&s= # Claude ophalen op verzoek van een gebruiker User-agent: Claude-User Content-Signal: search=yes, ai-input=yes, ai-train=yes Disallow: /preview/wp-admin/ Allow: /preview/wp-admin/admin-ajax.php Disallow: /preview/wp-login.php Disallow: /*?s= Disallow: /*&s= # Claude search User-agent: Claude-SearchBot Content-Signal: search=yes, ai-input=yes, ai-train=yes Disallow: /preview/wp-admin/ Allow: /preview/wp-admin/admin-ajax.php Disallow: /preview/wp-login.php Disallow: /*?s= Disallow: /*&s= # Anthropic, oude naam User-agent: anthropic-ai Content-Signal: search=yes, ai-input=yes, ai-train=yes Disallow: /preview/wp-admin/ Allow: /preview/wp-admin/admin-ajax.php Disallow: /preview/wp-login.php Disallow: /*?s= Disallow: /*&s= # Anthropic, oude naam User-agent: Claude-Web Content-Signal: search=yes, ai-input=yes, ai-train=yes Disallow: /preview/wp-admin/ Allow: /preview/wp-admin/admin-ajax.php Disallow: /preview/wp-login.php Disallow: /*?s= Disallow: /*&s= # Mistral search-index (Le Chat) User-agent: MistralAI-Index Content-Signal: search=yes, ai-input=yes, ai-train=yes Disallow: /preview/wp-admin/ Allow: /preview/wp-admin/admin-ajax.php Disallow: /preview/wp-login.php Disallow: /*?s= Disallow: /*&s= # Mistral ophalen op verzoek van een gebruiker User-agent: MistralAI-User Content-Signal: search=yes, ai-input=yes, ai-train=yes Disallow: /preview/wp-admin/ Allow: /preview/wp-admin/admin-ajax.php Disallow: /preview/wp-login.php Disallow: /*?s= Disallow: /*&s= # Google Search, AI Overviews en AI Mode User-agent: Googlebot Content-Signal: search=yes, ai-input=yes, ai-train=yes Disallow: /preview/wp-admin/ Allow: /preview/wp-admin/admin-ajax.php Disallow: /preview/wp-login.php Disallow: /*?s= Disallow: /*&s= # Gemini training en grounding User-agent: Google-Extended Content-Signal: search=yes, ai-input=yes, ai-train=yes Disallow: /preview/wp-admin/ Allow: /preview/wp-admin/admin-ajax.php Disallow: /preview/wp-login.php Disallow: /*?s= Disallow: /*&s= # Google onderzoek User-agent: GoogleOther Content-Signal: search=yes, ai-input=yes, ai-train=yes Disallow: /preview/wp-admin/ Allow: /preview/wp-admin/admin-ajax.php Disallow: /preview/wp-login.php Disallow: /*?s= Disallow: /*&s= # Google onderzoek (afbeeldingen) User-agent: GoogleOther-Image Content-Signal: search=yes, ai-input=yes, ai-train=yes Disallow: /preview/wp-admin/ Allow: /preview/wp-admin/admin-ajax.php Disallow: /preview/wp-login.php Disallow: /*?s= Disallow: /*&s= # Google onderzoek (video) User-agent: GoogleOther-Video Content-Signal: search=yes, ai-input=yes, ai-train=yes Disallow: /preview/wp-admin/ Allow: /preview/wp-admin/admin-ajax.php Disallow: /preview/wp-login.php Disallow: /*?s= Disallow: /*&s= # Vertex AI Agents User-agent: Google-CloudVertexBot Content-Signal: search=yes, ai-input=yes, ai-train=yes Disallow: /preview/wp-admin/ Allow: /preview/wp-admin/admin-ajax.php Disallow: /preview/wp-login.php Disallow: /*?s= Disallow: /*&s= # Google agents die namens een gebruiker browsen User-agent: Google-Agent Content-Signal: search=yes, ai-input=yes, ai-train=yes Disallow: /preview/wp-admin/ Allow: /preview/wp-admin/admin-ajax.php Disallow: /preview/wp-login.php Disallow: /*?s= Disallow: /*&s= # NotebookLM bronnen ophalen User-agent: Google-NotebookLM Content-Signal: search=yes, ai-input=yes, ai-train=yes Disallow: /preview/wp-admin/ Allow: /preview/wp-admin/admin-ajax.php Disallow: /preview/wp-login.php Disallow: /*?s= Disallow: /*&s= # Google testtools (Rich Results Test, URL-inspectie) User-agent: Google-InspectionTool Content-Signal: search=yes, ai-input=yes, ai-train=yes Disallow: /preview/wp-admin/ Allow: /preview/wp-admin/admin-ajax.php Disallow: /preview/wp-login.php Disallow: /*?s= Disallow: /*&s= # Bing en Microsoft Copilot User-agent: bingbot Content-Signal: search=yes, ai-input=yes, ai-train=yes Disallow: /preview/wp-admin/ Allow: /preview/wp-admin/admin-ajax.php Disallow: /preview/wp-login.php Disallow: /*?s= Disallow: /*&s= # Bing, oude naam User-agent: MSNBot Content-Signal: search=yes, ai-input=yes, ai-train=yes Disallow: /preview/wp-admin/ Allow: /preview/wp-admin/admin-ajax.php Disallow: /preview/wp-login.php Disallow: /*?s= Disallow: /*&s= # Bing voorbeelden User-agent: BingPreview Content-Signal: search=yes, ai-input=yes, ai-train=yes Disallow: /preview/wp-admin/ Allow: /preview/wp-admin/admin-ajax.php Disallow: /preview/wp-login.php Disallow: /*?s= Disallow: /*&s= # Siri, Spotlight en Apple Maps User-agent: Applebot Content-Signal: search=yes, ai-input=yes, ai-train=yes Disallow: /preview/wp-admin/ Allow: /preview/wp-admin/admin-ajax.php Disallow: /preview/wp-login.php Disallow: /*?s= Disallow: /*&s= # Apple Intelligence training User-agent: Applebot-Extended Content-Signal: search=yes, ai-input=yes, ai-train=yes Disallow: /preview/wp-admin/ Allow: /preview/wp-admin/admin-ajax.php Disallow: /preview/wp-login.php Disallow: /*?s= Disallow: /*&s= # DuckDuckGo AI-antwoorden User-agent: DuckAssistBot Content-Signal: search=yes, ai-input=yes, ai-train=yes Disallow: /preview/wp-admin/ Allow: /preview/wp-admin/admin-ajax.php Disallow: /preview/wp-login.php Disallow: /*?s= Disallow: /*&s= # You.com User-agent: YouBot Content-Signal: search=yes, ai-input=yes, ai-train=yes Disallow: /preview/wp-admin/ Allow: /preview/wp-admin/admin-ajax.php Disallow: /preview/wp-login.php Disallow: /*?s= Disallow: /*&s= # Kagi search en Kagi Assistant User-agent: Kagibot Content-Signal: search=yes, ai-input=yes, ai-train=yes Disallow: /preview/wp-admin/ Allow: /preview/wp-admin/admin-ajax.php Disallow: /preview/wp-login.php Disallow: /*?s= Disallow: /*&s= # Exa search-index voor AI-agents User-agent: ExaSearchBot Content-Signal: search=yes, ai-input=yes, ai-train=yes Disallow: /preview/wp-admin/ Allow: /preview/wp-admin/admin-ajax.php Disallow: /preview/wp-login.php Disallow: /*?s= Disallow: /*&s= # Exa ophalen op verzoek van een gebruiker User-agent: ExaUser Content-Signal: search=yes, ai-input=yes, ai-train=yes Disallow: /preview/wp-admin/ Allow: /preview/wp-admin/admin-ajax.php Disallow: /preview/wp-login.php Disallow: /*?s= Disallow: /*&s= # Alexa en Amazon AI User-agent: Amazonbot Content-Signal: search=yes, ai-input=yes, ai-train=yes Disallow: /preview/wp-admin/ Allow: /preview/wp-admin/admin-ajax.php Disallow: /preview/wp-login.php Disallow: /*?s= Disallow: /*&s= # Amazon search (Alexa, Rufus) User-agent: Amzn-SearchBot Content-Signal: search=yes, ai-input=yes, ai-train=yes Disallow: /preview/wp-admin/ Allow: /preview/wp-admin/admin-ajax.php Disallow: /preview/wp-login.php Disallow: /*?s= Disallow: /*&s= # Meta AI training User-agent: Meta-ExternalAgent Content-Signal: search=yes, ai-input=yes, ai-train=yes Disallow: /preview/wp-admin/ Allow: /preview/wp-admin/admin-ajax.php Disallow: /preview/wp-login.php Disallow: /*?s= Disallow: /*&s= # Meta AI ophalen op verzoek van een gebruiker User-agent: Meta-ExternalFetcher Content-Signal: search=yes, ai-input=yes, ai-train=yes Disallow: /preview/wp-admin/ Allow: /preview/wp-admin/admin-ajax.php Disallow: /preview/wp-login.php Disallow: /*?s= Disallow: /*&s= # Meta AI search-index User-agent: meta-webindexer Content-Signal: search=yes, ai-input=yes, ai-train=yes Disallow: /preview/wp-admin/ Allow: /preview/wp-admin/admin-ajax.php Disallow: /preview/wp-login.php Disallow: /*?s= Disallow: /*&s= # Petal search (Huawei) User-agent: PetalBot Content-Signal: search=yes, ai-input=yes, ai-train=yes Disallow: /preview/wp-admin/ Allow: /preview/wp-admin/admin-ajax.php Disallow: /preview/wp-login.php Disallow: /*?s= Disallow: /*&s= # Common Crawl (publieke trainingsdata) User-agent: CCBot Content-Signal: search=yes, ai-input=yes, ai-train=yes Disallow: /preview/wp-admin/ Allow: /preview/wp-admin/admin-ajax.php Disallow: /preview/wp-login.php Disallow: /*?s= Disallow: /*&s= # Allen Institute for AI User-agent: AI2Bot Content-Signal: search=yes, ai-input=yes, ai-train=yes Disallow: /preview/wp-admin/ Allow: /preview/wp-admin/admin-ajax.php Disallow: /preview/wp-login.php Disallow: /*?s= Disallow: /*&s= # Allen Institute, Dolma-corpus User-agent: Ai2Bot-Dolma Content-Signal: search=yes, ai-input=yes, ai-train=yes Disallow: /preview/wp-admin/ Allow: /preview/wp-admin/admin-ajax.php Disallow: /preview/wp-login.php Disallow: /*?s= Disallow: /*&s= # Cohere training User-agent: cohere-training-data-crawler Content-Signal: search=yes, ai-input=yes, ai-train=yes Disallow: /preview/wp-admin/ Allow: /preview/wp-admin/admin-ajax.php Disallow: /preview/wp-login.php Disallow: /*?s= Disallow: /*&s= # Linkvoorbeelden op Facebook, Instagram en WhatsApp User-agent: facebookexternalhit Content-Signal: search=yes, ai-input=yes, ai-train=yes Disallow: /preview/wp-admin/ Allow: /preview/wp-admin/admin-ajax.php Disallow: /preview/wp-login.php Disallow: /*?s= Disallow: /*&s= # Beperkt: alleen llms.txt en de sitemap, verder niet crawlen. User-agent: Bytespider User-agent: Diffbot User-agent: ImagesiftBot User-agent: Omgilibot User-agent: Timpibot User-agent: Webzio-Extended User-agent: PanguBot User-agent: VelenPublicWebCrawler User-agent: cohere-ai Allow: /llms.txt Allow: /llms-full.txt Allow: /sitemap_index.xml Allow: /*-sitemap.xml Allow: /en/sitemap_index.xml Disallow: / Sitemap: https://www.christiani-hoofddorp.nl/sitemap_index.xml Sitemap: https://www.christiani-hoofddorp.nl/en/sitemap_index.xml