#
# 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: *
# Crawl-delay: 10

# Directories to avoid indexing
Disallow: /core/
Disallow: /modules/
Disallow: /profiles/
Disallow: /themes/
Disallow: /vendor/
Disallow: /sites/default/files/

# Drupal-specific paths
Disallow: /admin/
Disallow: /user/
Disallow: /node/add/
Disallow: /search*
Disallow: /comment/reply/
Disallow: /logout/
Disallow: /edit/
Disallow: /?f[0] 
Disallow: /?education_sector
Disallow: /node

# Avoid duplicate content
Disallow: /taxonomy/term/
Disallow: /node/*
Disallow: /node/*/edit

# Allow access to important assets
Allow: /sites/default/files/*.css
Allow: /sites/default/files/*.js
Allow: /sites/default/files/*.jpg
Allow: /sites/default/files/*.png
Allow: /sites/default/files/*.gif

# Sitemap reference
Sitemap: https://www.nuffic.nl/sitemap.xml