# robots.txt for www.newhaven.edu
# Updated for modern search engine crawlers

User-agent: *
# Block backend files, code fragments, and template elements
Disallow: /_unpublished-save-for-later/
Disallow: /_qa/
Disallow: /_qa_faculty/
Disallow: /_showcase/
Disallow: /_training/
Disallow: /_unewhaven-training/
Disallow: /*.pcf$
Disallow: /*.inc$
Disallow: /*_nav.php$
Disallow: /includes/
Disallow: /be_ixf_client.php
Disallow: /config.php
Disallow: /info
Disallow: /_calendar

# Prevent crawling of internal search result parameters or session IDs if applicable
# Disallow: /*?*q=
# Disallow: /*?*query=

# Explicitly allow Googlebot-Image or general assets if previously restricted
Allow: /media/*.jpg
Allow: /media/*.png
Allow: /media/*.webp

# Primary XML Sitemap location
Sitemap: https://www.newhaven.edu/sitemap.xml