User-agent: * Allow: / # On empêche l'indexation des dossiers sensibles Disallow: /wp-admin Disallow: /wp-includes Disallow: /wp-content/plugins Disallow: /wp-content/cache Disallow: /trackback Disallow: /feed Disallow: /comments Disallow: /category/*/* Disallow: */trackback Disallow: */feed Disallow: */comments Disallow: /*.pdf$ # On désindexe toutes les URL ayant des paramètres (duplication de contenu) Disallow: /*?* Disallow: /*? # On désindexe la page de connexion (contenu inutile) Disallow: /wp-login.php # On autorise l'indexation des images et fichiers css/js Allow: /wp-content/uploads Allow: /wp-content/*.css Allow: /wp-content/*.js User-agent: Googlebot # On empêche l'indexation des fichiers sensibles Disallow: /*.php$ Disallow: /*.inc$ Disallow: /*.gz$ Disallow: /*.pdf$ # Autoriser Google Image User-agent: Googlebot-Image Disallow: Allow: /* # Autoriser Google AdSense User-agent: Mediapartners-Google* Disallow: Allow: /* # Autoriser Ahrefs User-agent: AhrefsSiteAudit Allow: /* User-agent: AhrefsBot Allow: /* # === Bots AI (limiter la cadence) === User-agent: ClaudeBot Crawl-delay: 30 User-agent: anthropic-ai Crawl-delay: 30 User-agent: Claude-Web Crawl-delay: 30 User-agent: GPTBot Crawl-delay: 30 User-agent: PerplexityBot Crawl-delay: 30 User-agent: Google-Extended Crawl-delay: 30 # === Bots SEO tiers (limiter la cadence) === User-agent: DataForSeoBot Crawl-delay: 10 # On indique au spider le lien vers notre sitemap Sitemap: https://haut-segala.com/sitemap_index.xml