# robots.txt
#
# Dit bestand voorkomt dat crawlers en indexers bepaalde delen van jouw website kunnen benaderen.
# Hiermee geef je de robots aan wat er verboden is.
# Dit zal veel bandbreedte en server resources schelen.
#
# Dit bestand zal enkel werken als hij in de root van jouw site staat:
# Used: https://example.com/robots.txt
# Ignored: https://example.com/site/robots.txt
# For more information about the robots.txt standard, see:
# https://www.robotstxt.org/wc/robots.html
#
# For syntax checking, see:
# http://www.sxw.org.uk/computing/robots/check.html
# disallow all
User-agent: *
Disallow: /
Crawl-delay: 29
# but allow only important bots
User-agent: Googlebot
User-agent: Googlebot-Image
User-agent: Mediapartners-Google
User-agent: msnbot
User-agent: msnbot-media
User-agent: Slurp
User-agent: Yahoo-Blogs
User-agent: Yahoo-MMCrawler
User-agent: Rogerbot
# Directories
Disallow: /includes/
Disallow: /mail/
Disallow: /misc/
Disallow: /modules/
Disallow: /profiles/
Disallow: /scripts/
Disallow: /sites/
Disallow: /themes/
Disallow: /pcs/
Disallow: /img/
Disallow: /fix/
Disallow: /tnc/
Disallow: /signature/
Disallow: /signaturein/
Disallow: /signature_info/
# Files
Disallow: /CHANGELOG.txt
Disallow: /cron.php
Disallow: /INSTALL.mysql.txt
Disallow: /INSTALL.pgsql.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: /wp-admin/
Allow: /wp-admin/admin-ajax.php
Disallow: /comment/reply/
Disallow: /contact/
Disallow: /logout/
Disallow: /node/add/
Disallow: /search/
Disallow: /opensearch/
Disallow: /user/register/
Disallow: /user/password/
Disallow: /user/login/
# Paths (no clean URLs)
Disallow: /?q=admin/
Disallow: /?q=comment/reply/
Disallow: /?q=contact/
Disallow: /?q=logout/
Disallow: /?q=node/add/
Disallow: /?q=search/
Disallow: /?q=user/password/
Disallow: /?q=user/register/
Disallow: /?q=user/login/
Crawl-delay: 29