# ============================================================
# robots.txt — WordPress (SEO friendly)
# ============================================================

User-agent: *

# --- Zones techniques à ne PAS indexer ---
Disallow: /wp-admin/
Disallow: /wp-includes/
Disallow: /wp-content/plugins/
Disallow: /wp-content/themes/
Disallow: /wp-content/upgrade/
Disallow: /wp-content/mu-plugins/
Disallow: /wp-json/
Disallow: /xmlrpc.php
Disallow: /readme.html
Disallow: /license.txt
Disallow: /wp-login.php
Disallow: /wp-config-sample.php

# --- Fichiers utiles à autoriser explicitement ---
Allow: /wp-admin/admin-ajax.php
Allow: /wp-content/uploads/
Allow: /wp-content/themes/*/style.css
Allow: /wp-content/themes/*/*.js
Allow: /wp-content/themes/*/*.css
Allow: /wp-content/plugins/*/assets/
Allow: /wp-content/plugins/*/public/

# --- Zones qui polluent l'index (URL paramétrées) ---
Disallow: /*?s=
Disallow: /*?p=
Disallow: /search/
Disallow: /?replytocom=
Disallow: /?attachment_id=
Disallow: /trackback/
Disallow: /feed/
Disallow: /comments/feed/

# --- Bloque paramètres de tracking (canonicalization) ---
Disallow: /*?utm_
Disallow: /*?fbclid=
Disallow: /*?gclid=

# ============================================================
# Bad bots (scrapers agressifs — bloqués globalement)
# ============================================================

User-agent: AhrefsBot
Disallow: /

User-agent: SemrushBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: PetalBot
Disallow: /

User-agent: DataForSeoBot
Disallow: /

User-agent: Bytespider
Disallow: /

# ============================================================
# Sitemap
# ============================================================

Sitemap: https://lamaisondegardanne.org/sitemap_index.xml