#
# 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.txt
Disallow: /web.config
Disallow: /cdn-cgi/*
# Paths (clean URLs)
Disallow: /admin/
Disallow: /comment/reply/
Disallow: /filter/tips/
# Disallow: /node/*
# Disallow: /taxonomy/term/*
# Disallow: /blog/tag/*
Disallow: /search
Disallow: /user/register/
Disallow: /user/password/
Disallow: /user/login/
Disallow: /user/logout/
# Disallow: */taxonomy/*
# Disallow: */tag/*
# Disallow: */node/*

# Disallow: /fr/node/*
# Disallow: /fr/taxonomy/term/*
# Disallow: /de/node/*
# Disallow: /de/taxonomy/term/*
# Disallow: /ja/node/*
# Disallow: /ja/taxonomy/term/*
# Disallow: /es/node/*
# Disallow: /es/taxonomy/term/*
# Disallow: /ru/node/*
# Disallow: /ru/taxonomy/term/*
# Disallow: /pt-br/node/*
# Disallow: /pt-br/taxonomy/term/*
# Disallow: /nl/node/*
# Disallow: /nl/taxonomy/term/*
# Disallow: /pl/node/*
# Disallow: /pl/taxonomy/term/*

# June update
Disallow: */resources/thank-you*
Disallow: */fr/resources/merci-vous*
Disallow: */es/resources/gracias*
Disallow: */ja/resources/thank-you*
Disallow: */de/resources/danke*
Disallow: */pt-br/resources/obrigado*
Disallow: */ru/resources/blagodarstvennyevas*
Disallow: */nl/resources/thank-you*
Disallow: */it/resources/thank-you*

# Prevent crawling on NL/PL/RU resources/blogs URLs
Disallow: /nl/resources*
Disallow: /pl/resources*
Disallow: /ru/resources*
Disallow: /nl/blog*
Disallow: /pl/blog*
Disallow: /ru/blog*

# 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/

# Hreflang fix
Disallow: *?_wrapper_format=html&page=*

# index.php fix
Disallow: *index.php/*

# Parameterized URLs
Disallow: *?ad=*
Disallow: *?f0=*
Disallow: *?amp*
Disallow: *?p=*
Disallow: *?_wrapper*
Disallow: *?destination*
Disallow: *?search*
Disallow: *?utm*
Disallow: *?tv*
Disallow: *?type*

# ChatGPT/GPTBot block
User-agent: GPTBot
Disallow: /

User-agent: ChatGPT-User
Disallow: