#
# robots.txt
#
# This file is to prevent the crawling and indexing of certain parts
# of your site by web crawlers and spiders run by sites like Yahoo!
# and Google. By telling these "robots" where not to go on your site,
# you save bandwidth and server resources.
#
# This file will be ignored unless it is at the root of your host:
# Used:    http://example.com/robots.txt
# Ignored: http://example.com/site/robots.txt
#
# For more information about the robots.txt standard, see:
# http://www.robotstxt.org/robotstxt.html

User-agent: *
# CSS, JS, Images
Allow: /core/*.css$
Allow: /core/*.css?
Allow: /core/*.js$
Allow: /core/*.js?
Allow: /core/*.gif
Allow: /core/*.jpg
Allow: /core/*.jpeg
Allow: /core/*.png
Allow: /core/*.svg
Allow: /profiles/*.css$
Allow: /profiles/*.css?
Allow: /profiles/*.js$
Allow: /profiles/*.js?
Allow: /profiles/*.gif
Allow: /profiles/*.jpg
Allow: /profiles/*.jpeg
Allow: /profiles/*.png
Allow: /profiles/*.svg
# Directories
Disallow: /core/
Disallow: /profiles/
# Files
Disallow: /README.md
Disallow: /composer/Metapackage/README.txt
Disallow: /composer/Plugin/ProjectMessage/README.md
Disallow: /composer/Plugin/Scaffold/README.md
Disallow: /composer/Plugin/VendorHardening/README.txt
Disallow: /composer/Template/README.txt
Disallow: /modules/README.txt
Disallow: /sites/README.txt
Disallow: /themes/README.txt
Disallow: /web.config
# Paths (clean URLs)
Disallow: /admin/
Disallow: /comment/reply/
Disallow: /filter/tips
Disallow: /node/add/
Disallow: /search/
Disallow: /user/register
Disallow: /user/password
Disallow: /user/login
Disallow: /user/logout
Disallow: /media/oembed
Disallow: /*/media/oembed
# Paths (no clean URLs)
Disallow: /index.php/admin/
Disallow: /index.php/comment/reply/
Disallow: /index.php/filter/tips
Disallow: /index.php/node/add/
Disallow: /index.php/search/
Disallow: /index.php/user/password
Disallow: /index.php/user/register
Disallow: /index.php/user/login
Disallow: /index.php/user/logout
Disallow: /index.php/media/oembed
Disallow: /index.php/*/media/oembed

# Don't crawl views with facets
# Updated 23 January 2024 DJL
Disallow: /academics/program-finder?f*
Disallow: /academics/schools/school-arts-and-sciences?f*
Disallow: /academics/schools/marshall-m-sloane-school-business-and-communication?f*
Disallow: /academics/schools/school-health-sciences?f*
Disallow: /academics/schools/richard-and-sheila-young-school-nursing?f*
Disallow: /academics/schools/theresa-wood-lavine-division-professional-studies?f*
Disallow: /about-regis/news?f*
Disallow: /about-regis/find-us/faculty-and-staff-directory?*
Disallow: /blog?f*
Disallow: /views/ajax?q=*

# Don't crawl calendar events or pages except for the current month
# Disabled 6 August 2020 DJL
#Disallow: /upcoming-events*
#Allow: /upcoming-events/month$

# Don't crawl calendar category views
# Added 6 January 2022 DJL
Disallow: /*?category=All

# Don't crawl search results
# Added 23 January 2024 DJL
# Updated 2 February 2024 DJL
Disallow: /search?search=*
Disallow: /search_api_autocomplete/*
Disallow: /search*
Disallow: /academics/program-finder?*
Disallow: /academics/schools/school-arts-and-sciences?*
Disallow: /academics/schools/marshall-m-sloane-school-business-and-communication?*
Disallow: /academics/schools/school-health-sciences?*
Disallow: /academics/schools/richard-and-sheila-young-school-nursing?*
Disallow: /academics/schools/theresa-wood-lavine-division-professional-studies?*
Disallow: /about-regis/news?*

# Don't crawl AJAX-generated calendar pages
# Added 14 February 2024 DJL
Disallow: /upcoming-events/day/*
Disallow: /upcoming-events/week/*
Disallow: /upcoming-events/year/*

# Explicitly list all sitemaps
# Added 20 February 2024 DJL
Sitemap: https://www.regiscollege.edu/sitemap.xml
Sitemap: https://www.regiscollege.edu/sitemaps/default/sitemap.xml
Sitemap: https://www.regiscollege.edu/marketplace/sitemap.xml