Infrastructure

#
# 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

# Slow down aggressive SEO crawlers
User-agent: SemrushBot
Crawl-delay: 30

User-agent: AhrefsBot
Crawl-delay: 30

User-agent: MJ12bot
Crawl-delay: 30

# AI training crawlers — higher delay (or Disallow: / if preferred)
User-agent: GPTBot
Crawl-delay: 30

User-agent: Google-Extended
Crawl-delay: 30

User-agent: CCBot
Crawl-delay: 60

User-agent: anthropic-ai
Crawl-delay: 30

User-agent: ClaudeBot
Crawl-delay: 30

# Meta's social preview crawler ignores Crawl-delay, but document intent
User-agent: facebookexternalhit
Crawl-delay: 10

User-agent: *
Crawl-delay: 30
# CSS, JS, Images
Allow: /misc/*.css$
Allow: /misc/*.css?
Allow: /misc/*.js$
Allow: /misc/*.js?
Allow: /misc/*.gif
Allow: /misc/*.jpg
Allow: /misc/*.jpeg
Allow: /misc/*.png
Allow: /modules/*.css$
Allow: /modules/*.css?
Allow: /modules/*.js$
Allow: /modules/*.js?
Allow: /modules/*.gif
Allow: /modules/*.jpg
Allow: /modules/*.jpeg
Allow: /modules/*.png
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: /themes/*.css$
Allow: /themes/*.css?
Allow: /themes/*.js$
Allow: /themes/*.js?
Allow: /themes/*.gif
Allow: /themes/*.jpg
Allow: /themes/*.jpeg
Allow: /themes/*.png
# Directories
Disallow: /includes/
Disallow: /misc/
Disallow: /modules/
Disallow: /profiles/
Disallow: /scripts/
Disallow: /themes/
# Files
Disallow: /CHANGELOG.txt
Disallow: /cron.php
Disallow: /INSTALL.mysql.txt
Disallow: /INSTALL.pgsql.txt
Disallow: /INSTALL.sqlite.txt
Disallow: /install.php
Disallow: /INSTALL.txt
Disallow: /LICENSE.txt
Disallow: /MAINTAINERS.txt
Disallow: /update.php
Disallow: /UPGRADE.txt
Disallow: /xmlrpc.php
# 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/
# Paths (no clean URLs)
Disallow: /?q=admin/
Disallow: /?q=comment/reply/
Disallow: /?q=filter/tips/
Disallow: /?q=node/add/
Disallow: /?q=search/
Disallow: /?q=user/password/
Disallow: /?q=user/register/
Disallow: /?q=user/login/
Disallow: /?q=user/logout/

# EFF Stuff

# Don't crawl pages endlessly.
Disallow: /*?*page=
Allow: /updates?page=
Disallow: /documents?language=
Allow: /documents?page=

# Disallow language prefixes, these should be passed via the `language` param.
Disallow: /am/*
Disallow: /ar/*
Disallow: /de/*
Disallow: /el/*
Disallow: /en/*
Disallow: /es/*
Disallow: /fa/*
Disallow: /fr/*
Disallow: /hi/*
Disallow: /it/*
Disallow: /ja/*
Disallow: /ko/*
Disallow: /my/*
Disallow: /nb/*
Disallow: /nl/*
Disallow: /pl/*
Disallow: /pt/*
Disallow: /pt-br/*
Disallow: /ro/*
Disallow: /ru/*
Disallow: /sh/*
Disallow: /sv/*
Disallow: /th/*
Disallow: /tr/*
Disallow: /uk/*
Disallow: /vi/*
Disallow: /wp/*
Disallow: /zh/*
Disallow: /zh-hans/*
Disallow: /zh-hant/*