# ============================================================
# Added by Chad on 2026/04/16 at direction of Claude after analyzinf Retour 404 hits
# ============================================================
# robots.txt — Block rules for bad-bot crawlers
# ============================================================
# Instructions:
#   Add the Disallow lines below to your existing robots.txt,
#   or replace it entirely with this file.
#
#   NOTE: robots.txt is a courtesy signal, not a firewall.
#   Malicious bots IGNORE it. Use the .htaccess rules for hard
#   blocking. robots.txt is useful for well-behaved crawlers
#   (Googlebot, Bingbot) that might accidentally follow links
#   to these paths. Do NOT list secret paths here — doing so
#   actually tips off crawlers that they exist.
# ============================================================
 
User-agent: *
 
# WordPress paths (not present on this site)
Disallow: /wp-admin/
Disallow: /wp-includes/
Disallow: /wp-content/
Disallow: /wp-login.php
Disallow: /wp-signup.php
Disallow: /wp-config.php
Disallow: /wordpress/
Disallow: /wp/
Disallow: /xmlrpc.php
 
# Framework probe paths
Disallow: /_next/
Disallow: /_profiler/
Disallow: /_ignition/
Disallow: /laravel/
Disallow: /cgi-bin/
 
# PHP files (none should be directly accessible)
Disallow: /*.php$
 
# Backup, upload, and vendor directories
Disallow: /backup/
Disallow: /uploads/
Disallow: /vendor/
Disallow: /old/
Disallow: /cache/
Disallow: /cpresources/
 
# Joomla / Drupal paths
Disallow: /sites/
Disallow: /media/system/
 
# Stale/incorrect sitemap paths seen in your logs
# (keep only your real sitemap location)
Disallow: /sitemap.html
Disallow: /sitemap.txt
Disallow: /sitemap.xml/
Disallow: /sitemap/sitemap.xml
Disallow: /news_sitemap.xml
Disallow: /news-sitemap.xml
 
User-agent: CCBot
Allow: /

# ============================================================
# Point crawlers to your real sitemap
# ============================================================

Sitemap: https://www.612Mariposa.com/sitemap.xml