#
# 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.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 POLICE RULES
# ========================================

# Delay user agents
User-agent: *
Crawl-delay: 1

# AI Search Engine Bots
User-agent: GPTBot
Allow: /
Crawl-delay: 1
User-agent: ClaudeBot
Allow: /
Crawl-delay: 1
User-agent: PerplexityBot
Allow: /
Crawl-delay: 1

# Paths (clean URLs)
User-agent: *
Disallow: /nieuws$
Disallow: /news$
Disallow: /actualites$
Disallow: /nachrichten$
Disallow: /zoeken/
Disallow: /rechercher/
Disallow: /durchsuchen/
Disallow: /search/
Disallow: /contact/je-wijk$
Disallow: /contact/votre-quartier$
Disallow: /kontakt/ihr-revier$
Disallow: /contact/your-district$
Disallow: /*f%5B0%5D*