User-Agent: *
# On empêche l'indexation des dossiers sensibles
Disallow: /wp-admin/
Disallow: /wp-includes
Disallow: /wp-content/plugins
Disallow: /wp-content/cache
Disallow: */comments
Disallow: /*.pdf$
Disallow: /*?filter_by=*
Disallow: /*?id=*

# On désindexe toutes les URL ayant des paramètres (duplication de contenu)
Disallow: /*?*
Disallow: /*?
Disallow: /*?amp=1
Disallow: /*?noamp=mobile
Disallow: /*?fbclid=
Disallow: /*?attachment_id=
Disallow: /*?noam=*
Disallow: /?print=print
Disallow: /?print=print&noamp=available
Disallow: /?noamp=available

# On désindexe la page de connexion (contenu inutile)
Disallow: /wp-login.php
# On autorise l'indexation des images
Allow: /wp-content/uploads

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: /*

# === Allow AI / LLM crawlers & agents (2026) ===
User-agent: GPTBot
User-agent: OAI-SearchBot
User-agent: ChatGPT-User
User-agent: ClaudeBot
User-agent: Claude-Web
User-agent: Claude-User
User-agent: PerplexityBot
User-agent: Perplexity-User
User-agent: Google-Extended
User-agent: FirecrawlAgent
User-agent: ExaBot
User-agent: AndiBot
User-agent: PhindBot
User-agent: YouBot
User-agent: Applebot-Extended
Allow: /*

# On indique au spider le lien vers notre sitemap
Sitemap: https://toutbusiness.tg/sitemap_index.xml
Sitemap: https://toutbusiness.tg/news-sitemap.xml