#
# 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: *
Crawl-delay: 10
Disallow: /es/search
Disallow: /fr/search
Disallow: /zh-hans/search
Disallow: /apachesolr-search
Disallow: /solr-multilingual
Disallow: /search

# CSS, JS, Images
Allow: /core/*.css$
Allow: /core/*.css?
Allow: /core/*.js$
Allow: /core/*.js?
Allow: /core/*.avif
Allow: /core/*.gif
Allow: /core/*.jpg
Allow: /core/*.jpeg
Allow: /core/*.png
Allow: /core/*.svg
Allow: /core/*.webp
Allow: /profiles/*.css$
Allow: /profiles/*.css?
Allow: /profiles/*.js$
Allow: /profiles/*.js?
Allow: /profiles/*.avif
Allow: /profiles/*.gif
Allow: /profiles/*.jpg
Allow: /profiles/*.jpeg
Allow: /profiles/*.png
Allow: /profiles/*.svg
Allow: /profiles/*.webp
# 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
# Paths (clean URLs)
Disallow: /admin/
Disallow: /comment/reply/
Disallow: /filter/tips
Disallow: /node/add/
Disallow: /search/
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/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

# Extras on drupal.org
# no access for table sorting paths or any paths that have parameters.
Disallow: /*?sort*
Disallow: /*&sort*
Disallow: /*?solrsort*
Disallow: /*&solrsort*

# no access to profile listings, they are costly to generate and don't provide useful information.
Disallow: /profile
Disallow: /profile/*
Disallow: /?q=profile
Disallow: /?q=profile/*

# Blocks user "track" pages
Disallow: /*/track$
# Blocks common URL parameters created by the Views module on tables
Disallow: /*sort=
Disallow: /*size=

# Disallow bogus aggregator pages
Disallow: /aggregator/*

# Disallow project search
Disallow: /project/issues/search
Disallow: /project/issues/search/*
Disallow: /project/issues/*/search

# Disallow book export
Disallow: /book/export/*

# Disallow pift tests
Disallow: /pift/retest/*

# Disallow project subscription
Disallow: /project/issues/subscribe-mail/*

# Disallow URLs with destination parameter
Disallow: /user/login?destination=*
Disallow: /user/register?destination=*
Disallow: /user?destination=*

# Disallow individual user trackers
Disallow: /user/*/track
Disallow: /user/*/track?page=*

# Googlebot picked up strange homepage URLs somewhere
Disallow: /home/*

# Block AI crawlers
User-agent: GPTBot
Disallow: /

User-agent: ChatGPT-User
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: cohere-ai
Disallow: /

# Specifically disallow search for all crawlers

User-agent: tphotobot
Disallow: /