#
# robots.txt file for AMR Website
#
# This file prevents crawling and indexing of certain parts of your site
# by web crawlers and spiders run by Google, Bing, and other search engines.
# By telling these "robots" where not to go, you save bandwidth and server resources.
#
# This file must be at the root of your host:
# Used:    https://example.com/robots.txt
# Ignored: https://example.com/site/robots.txt
#
# For more information about the robots.txt standard, see:
# https://www.robotstxt.org/
#
# For syntax validation, see:
# https://www.seoptimer.com/robots-txt-checker

User-agent: *
Crawl-delay: 10

# Application internals and build artifacts
Disallow: /bin/
Disallow: /obj/
Disallow: /Properties/
Disallow: /App_Data/

# Admin and authentication areas
Disallow: /Admin/
Disallow: /admin/
Disallow: /utility/Admin/
Disallow: /utility/CTA/
Disallow: /login/
Disallow: /members/login.aspx

# Development, staging, and test environment subdomains
Disallow: /Dev_amr_net/
Disallow: /dev_emcare_com/
Disallow: /dev_evhc_net/
Disallow: /dev_evhealth_net/
Disallow: /Staging_amr_net/
Disallow: /staging_emcare_com/
Disallow: /staging_evolution_net/
Disallow: /Test_amr_net/
Disallow: /test_emcare_com/
Disallow: /test_evhc_net/
Disallow: /test_evhealth_net/

# Legacy paths
Disallow: /Error/404/
Disallow: /Reference-Page-Styling/
Disallow: /web.config

# File types to disallow
Disallow: *.xlsx$
Disallow: *.xls$

# Allow search engines to crawl CSS and JavaScript for rendering
User-agent: Googlebot
Allow: *.js
Allow: *.css

User-agent: Bingbot
Allow: *.js
Allow: *.css

# Allow social media bots for preview generation
User-agent: Twitterbot
Allow: /

User-agent: Facebookexternalhit
Allow: /

# Sitemap location
Sitemap: https://www.amr.net/sitemap.xml