#
# 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


# custom:
#
# NOTE: to edit these lines, and ensure they will survive a composer install:
# look into [drupal-root]/custom-assets/[prod|dev]/web/robots.txt.append or robots.txt.replace
# Then run `composer install` to trigger a new composer scaffold and rebuilding of the file(s).
#

# --- AI model training: disallowed ---
# Policy: no crawling for model training; search engines and AI answer
# engines that cite the site keep access through "User-agent: *":
# Googlebot (AI Overviews, AI Mode), Bingbot (Copilot), Applebot, PetalBot,
# OAI-SearchBot, ChatGPT-User, Claude-SearchBot, Claude-User, PerplexityBot,
# Perplexity-User, YouBot, Amzn-SearchBot, Amzn-User, Meta-ExternalFetcher.
# Google-Extended also covers grounding in Gemini apps (not Google Search,
# AI Overviews or AI Mode); there is no token for grounding alone.
User-agent: GPTBot
User-agent: ClaudeBot
User-agent: CCBot
User-agent: Google-Extended
User-agent: Applebot-Extended
User-agent: Amazonbot
User-agent: Bytespider
User-agent: Meta-ExternalAgent
User-agent: Diffbot
User-agent: SASbot
Disallow: /

# Do not add a "User-agent: Googlebot" group: Googlebot then obeys only that
# group and ignores every "User-agent: *" rule above (/search/, /user/, /admin/).
# Google ignores Crawl-delay anyway.

Sitemap: https://www.fi-compass.eu/sitemap.xml