# Utrechtkrant — robots.txt User-agent: * Allow: / # Admin / Filament Disallow: /admin Disallow: /admin/ # Account dashboards Disallow: /account/ Disallow: /inloggen Disallow: /registreren Disallow: /wachtwoord # PR / paid posting flows (transactional, not indexable) Disallow: /pr/checkout Disallow: /pr/return Disallow: /pr/cancel Disallow: /pr/article/ Disallow: /pr/paypal-webhook Disallow: /pr/upload-image Disallow: /pr/upload-image-token Disallow: /pr/email-check # Directory self-signup flow Disallow: /bedrijvengids/aanmelden/return/ Disallow: /bedrijvengids/aanmelden/cancel/ Disallow: /bedrijvengids/aanmelden/bedrijf/ Disallow: /bedrijvengids/aanmelden/klaar/ # Marktplaats wizard Disallow: /marktplaats/plaatsen/ Disallow: /marktplaats/upload-foto Disallow: /marktplaats/boost/ # Ads self-service Disallow: /adverteren/start Disallow: /adverteren/return/ Disallow: /adverteren/cancel/ Disallow: /adverteren/success/ Disallow: /adverteren/upload/ Disallow: /r/ # Search result pages (canonical noindex) Disallow: /zoek Disallow: /*?q= # Submission/verify flows (one-shot tokens) Disallow: /inzending/ Disallow: /nieuwsbrief/bevestigen/ Disallow: /nieuwsbrief/uitschrijven/ # Common crawler traps Disallow: /*?utm_ Disallow: /*&utm_ Disallow: /*?fbclid= Disallow: /*?gclid= Disallow: /*?ref= # Bad bots — soft-block (Allow our own paths) User-agent: SemrushBot Disallow: / User-agent: AhrefsBot Disallow: / User-agent: MJ12bot Disallow: / User-agent: DotBot Disallow: / User-agent: PetalBot Disallow: / # Sitemap index Sitemap: http://utrechtkrant.nl/sitemap.xml Sitemap: http://utrechtkrant.nl/sitemap-news.xml Sitemap: http://utrechtkrant.nl/agenda/organisatoren/sitemap.xml # Host hint Host: utrechtkrant.nl