#
# 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
#
# Append to web/robots.txt
# https://pantheon.io/docs/bots-and-indexing#robotstxt-with-composer-and-drupal
#
# Disallowed crawlers
User-agent: Amazonbot
User-agent: anthropic-ai
User-agent: Applebot-Extended
User-agent: AwarioRssBot
User-agent: AwarioSmartBot
User-agent: AhrefsBot
User-agent: BLEXBot
User-agent: Bytespider
User-agent: CCBot
User-agent: ChatGPT-User
User-agent: ClaudeBot
User-agent: Claude-Web
User-agent: cohere-ai
User-agent: DataForSeoBot
User-agent: Diffbot
User-agent: DotBot
User-agent: FacebookBot
User-agent: FriendlyCrawler
User-agent: Google-Extended
User-agent: GPTBot
User-agent: heritrix
User-agent: ImagesiftBot
User-agent: magpie-crawler
User-agent: MegaIndex.ru
User-agent: Meta-ExternalAgent
User-agent: meta-externalagent
User-agent: MJ12bot
User-agent: NewsNow
User-agent: news-please
User-agent: OAI-SearchBot
User-agent: omgili
User-agent: omgilibot
User-agent: panscient
User-agent: panscient.com
User-agent: peer39_crawler
User-agent: peer39_crawler/1.0
User-agent: PerplexityBot
User-agent: PetalBot
User-agent: Quora-Bot
User-agent: Riddler
User-agent: Scrapy
User-agent: SemrushBot
User-agent: SemrushBot-BA
User-agent: SemrushBot-BM
User-agent: SiteimproveBot-Crawler
User-agent: Slurp
User-agent: Sogou
User-agent: Timpibot
User-agent: TurnitinBot
User-agent: ultimate_sitemap_parser
User-agent: viberbot
User-agent: Yandex*
User-agent: YaK
Disallow: /
User-agent: AppleBot
User-agent: Bingbot
Crawl-delay: 10
User-agent: *
# This specifically targets the URL parameter pattern seen in a typical Drupal Search (e.g. Solr facets).
Disallow: /*?f[*
Disallow: /*&f[*
Disallow: /*?f%5B0*
Disallow: /*&f%5B1*
# Paths (no clean URLs)
Disallow: /?q=admin/
Disallow: /?q=comment/reply/
Disallow: /?q=contact/
Disallow: /?q=logout/
Disallow: /?q=node/add/
Disallow: /?q=search/
Disallow: /?q=user/password/
Disallow: /?q=user/register/
Disallow: /?q=user/login/
# Paths (clean URLs) - fixed
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
# Paths (no clean URLs) - fixed
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
# Paths (no clean URLs) – fixed
Disallow: /?q=admin
Disallow: /?q=comment/reply
Disallow: /?q=contact
Disallow: /?q=logout
Disallow: /?q=node/add
Disallow: /?q=search
Disallow: /?q=user/password
Disallow: /?q=user/register
Disallow: /?q=user/login
Disallow: /home/*
Sitemap: https://www.aaas.org/sitemap.xml