# robots.txt for rescuemytimecleaningservice.com
# Updated: 2026-08-14

User-agent: *

# --- WordPress core / system paths ---
Disallow: /wp-admin/
Allow: /wp-admin/admin-ajax.php
Disallow: /wp-login.php
Disallow: /xmlrpc.php
Disallow: /wp-json/
Disallow: /readme.html
Disallow: /license.txt
Disallow: /wp-content/plugins/
Disallow: /wp-content/uploads/wpcf7_uploads/

# --- Thin / duplicate URL patterns ---
Disallow: /*?s=
Disallow: /search/
Disallow: /*?replytocom=
Disallow: /comments/feed/
Disallow: /author/
Disallow: /*?attachment_id=

# --- Tracking parameters (no SEO value, create duplicates) ---
Disallow: /*?utm_
Disallow: /*?gclid=
Disallow: /*?fbclid=
Disallow: /*?msclkid=

# --- Let crawlers render the site properly ---
Allow: /wp-content/uploads/
Allow: /*.css$
Allow: /*.js$
Allow: /*.png$
Allow: /*.jpg$
Allow: /*.jpeg$
Allow: /*.gif$
Allow: /*.svg$
Allow: /*.webp$

# --- Aggressive SEO scrapers (optional - saves server resources) ---
User-agent: AhrefsBot
Crawl-delay: 10

User-agent: SemrushBot
Crawl-delay: 10

User-agent: MJ12bot
Disallow: /

User-agent: DotBot
Disallow: /

# --- AI crawlers: ALLOWED (do not block - drives AI referral traffic) ---
# GPTBot, ClaudeBot, PerplexityBot, Google-Extended are permitted by the rules above.

Sitemap: https://rescuemytimecleaningservice.com/sitemap_index.xml