# robots.txt for Idha Mindcare - www.idhamindcare.com
# Updated: 2025-10-19

# Allow all search engines to crawl everything
User-agent: *
Disallow:

# Block access to sensitive directories
Disallow: /cgi-bin/
Disallow: /tmp/
Disallow: /includes/
Disallow: /scripts/

# Block WordPress admin (if needed)
Disallow: /blog/wp-admin/
Allow: /blog/wp-admin/admin-ajax.php

# Block WordPress includes and plugins (reduce crawl waste)
Disallow: /blog/wp-includes/
Disallow: /blog/wp-content/plugins/
Disallow: /blog/wp-content/cache/
Disallow: /blog/wp-content/themes/

# Block common files that waste crawl budget
Disallow: /*.php$
Allow: /*.php
Disallow: /*?
Disallow: /*.js$
Disallow: /*.css$
Disallow: /*.inc$

# Allow CSS and JS for Google to render pages properly
User-agent: Googlebot
Allow: /*.js
Allow: /*.css
Disallow: /*?

# Sitemap location
Sitemap: https://www.idhamindcare.com/sitemap.xml

# Crawl delay for aggressive bots (optional)
User-agent: AhrefsBot
Crawl-delay: 10

User-agent: SemrushBot
Crawl-delay: 10

User-agent: DotBot
Crawl-delay: 10