#
# 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/wc/robots.html
#
# For syntax checking, see:
# http://www.sxw.org.uk/computing/robots/check.html
User-agent: *
Crawl-delay: 10
# Directories
Disallow: /includes/
Disallow: /misc/
Disallow: /modules/
Disallow: /profiles/
Disallow: /scripts/
Disallow: /themes/
# 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: /comment/reply/
Disallow: /filter/tips/
Disallow: /logout/
Disallow: /node/add/
Disallow: /search/
Disallow: /user/register/
Disallow: /user/password/
Disallow: /user/login/
# Paths (no clean URLs)
Disallow: /?q=admin/
Disallow: /?q=comment/reply/
Disallow: /?q=filter/tips/
Disallow: /?q=logout/
Disallow: /?q=node/add/
Disallow: /?q=search/
Disallow: /?q=user/password/
Disallow: /?q=user/register/
Disallow: /?q=user/login/
############
# End of Drupal-generated robots.txt
############
############
# This list is taken from parts of http://www.pflanzenfreunde.com/robots.txt
##############
# Some bots are known to be trouble, particularly those designed to copy
# entire sites. Please obey robots.txt.
User-agent: sitecheck.internetseer.com
Disallow: /
User-agent: Zealbot
Disallow: /
User-agent: MSIECrawler
Disallow: /
User-agent: SiteSnagger
Disallow: /
User-agent: WebStripper
Disallow: /
User-agent: WebCopier
Disallow: /
User-agent: Fetch
Disallow: /
User-agent: Offline Explorer
Disallow: /
User-agent: Teleport
Disallow: /
User-agent: TeleportPro
Disallow: /
User-agent: WebZIP
Disallow: /
User-agent: linko
Disallow: /
User-agent: HTTrack
Disallow: /
User-agent: Microsoft.URL.Control
Disallow: /
User-agent: Xenu
Disallow: /
User-agent: larbin
Disallow: /
User-agent: libwww
Disallow: /
User-agent: ZyBORG
Disallow: /
User-agent: Download Ninja
Disallow: /
#
# Sorry, wget in its recursive mode is a frequent problem.
# Please read the man page and use it properly; there is a
# --wait option you can use to set the delay between hits,
# for instance.
#
User-agent: wget
Disallow: /
#
# The 'grub' distributed client has been *very* poorly behaved.
#
User-agent: grub-client
Disallow: /
#
# Doesn't follow robots.txt anyway, but...
#
User-agent: k2spider
Disallow: /
#
# Hits many times per second, not acceptable
# http://www.nameprotect.com/botinfo.html
User-agent: NPBot
Disallow: /
# A capture bot, downloads gazillions of pages with no public benefit
# http://www.webreaper.net/
User-agent: WebReaper
Disallow: /
############
# End of stuff from http://www.pflanzenfreunde.com/robots.txt
############
##########
# From here below is the stuff I created (cyjon.net)
###########
#"Mozilla/5.0 (compatible; SEOkicks-Robot +http://www.seokicks.de/robot.html)"
# This one just felt fishy to me
User-agent: SEOkicks
Disallow: /
User-agent: SEOkicks-Robot
Disallow: /
#Sistrix crawler, pulls WAY too many pages WAY too fast. Ignores robots.txt
User-agent:SISTRIX
Disallow: /
# Semi-legitimate bot, but the company CEO is a jackass on bot protection forums
User-agent: MJ12bot
Disallow: /