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

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
# 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

# Disallow query strings in URLs.
Disallow: /*?*

# Prevent bots from crawling SAML login redirects.
# Googlebot was generating ~1758 requests/2h to these URLs, causing
# unnecessary PHP-FPM load for authentication redirects.
# @see https://gitlab.studiopresent.com/k8s/drupal/elte/-/issues/266
Disallow: /saml/login

# Block aggressive crawlers that cause server overload.
# Scrapy bots: 27K+ requests/day, crawling entire site including SAML endpoints.
User-agent: Scrapy
Disallow: /

# GPTBot: OpenAI training crawler.
User-agent: GPTBot
Disallow: /

# CCBot: Common Crawl bot used for AI training.
User-agent: CCBot
Disallow: /

# SemrushBot: aggressive SEO crawler, 9K+ requests/day.
User-agent: SemrushBot
Crawl-delay: 10
Disallow: /saml/
Disallow: /node/
Disallow: /user/

# Baiduspider: 6K+ requests/day.
User-agent: Baiduspider
Crawl-delay: 10
Disallow: /saml/
Disallow: /node/
Disallow: /user/

# AhrefsBot: aggressive SEO crawler.
User-agent: AhrefsBot
Crawl-delay: 10
Disallow: /saml/
Disallow: /node/
Disallow: /user/

# ChatGPT: AI crawler, 4K+ requests/day.
User-agent: ChatGPT-User
Crawl-delay: 10
Disallow: /saml/
Disallow: /node/
Disallow: /user/