#
# 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: *
# JS/CSS
Allow: /core/*.css$
Allow: /core/*.js$
# Directories
Disallow: /core/
Disallow: /profiles/
# Paths (clean URLs)
Disallow: /admin/
Disallow: /user/
# Paths (no clean URLs)
Disallow: /index.php/

# prevent AI from using the site for learning
User-agent: GPTBot
Disallow: /

# prevent search engines from the following directories
User-agent: baiduspider
User-agent: bingbot
User-agent: duckduckbot
User-agent: googlebot
User-agent: msnbot
User-agent: slurp
User-agent: yandexbot
Disallow: /uploads/manual/manuals/