# $Id: robots.txt,v 1.7 2007/01/08 12:02:18 dries Exp $ # # 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: 90 # Directories Disallow: /database/ Disallow: /includes/ Disallow: /misc/ Disallow: /modules/ Disallow: /sites/ Disallow: /themes/ Disallow: /scripts/ Disallow: /updates/ Disallow: /profiles/ Disallow: /user/* Disallow: /taxonomy/term/* # Files Disallow: /xmlrpc.php Disallow: /cron.php Disallow: /update.php Disallow: /install.php Disallow: /INSTALL.mysql.txt Disallow: /INSTALL.pgsql.txt Disallow: /CHANGELOG.txt Disallow: /MAINTAINERS.txt Disallow: /LICENSE.txt Disallow: /UPGRADE.txt # Paths (clean URLs) Disallow: /admin/ Disallow: /aggregator/ Disallow: /comment/reply/ Disallow: /contact/ 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=aggregator/ 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/ RewriteEngine On RewriteCond %{HTTP_USER_AGENT} ^BlackWidow [OR] RewriteCond %{HTTP_USER_AGENT} ^Bot\ mailto:craftbot@yahoo.com [OR] RewriteCond %{HTTP_USER_AGENT} ^ChinaClaw [OR] RewriteCond %{HTTP_USER_AGENT} ^Custo [OR] RewriteCond %{HTTP_USER_AGENT} ^DISCo [OR] RewriteCond %{HTTP_USER_AGENT} ^Download\ Demon [OR] RewriteCond %{HTTP_USER_AGENT} ^eCatch [OR] RewriteCond %{HTTP_USER_AGENT} ^EirGrabber [OR] RewriteCond %{HTTP_USER_AGENT} ^EmailSiphon [OR] RewriteCond %{HTTP_USER_AGENT} ^EmailWolf [OR] RewriteCond %{HTTP_USER_AGENT} ^Express\ WebPictures [OR] RewriteCond %{HTTP_USER_AGENT} ^ExtractorPro [OR] RewriteCond %{HTTP_USER_AGENT} ^EyeNetIE [OR] RewriteCond %{HTTP_USER_AGENT} ^FlashGet [OR] RewriteCond %{HTTP_USER_AGENT} ^GetRight [OR] RewriteCond %{HTTP_USER_AGENT} ^GetWeb! [OR] RewriteCond %{HTTP_USER_AGENT} ^Go!Zilla [OR] RewriteCond %{HTTP_USER_AGENT} ^Go-Ahead-Got-It [OR] RewriteCond %{HTTP_USER_AGENT} ^GrabNet [OR] RewriteCond %{HTTP_USER_AGENT} ^Grafula [OR] RewriteCond %{HTTP_USER_AGENT} ^HMView [OR] RewriteCond %{HTTP_USER_AGENT} HTTrack [NC,OR] RewriteCond %{HTTP_USER_AGENT} ^Image\ Stripper [OR] RewriteCond %{HTTP_USER_AGENT} ^Image\ Sucker [OR] RewriteCond %{HTTP_USER_AGENT} Indy\ Library [NC,OR] RewriteCond %{HTTP_USER_AGENT} ^InterGET [OR] RewriteCond %{HTTP_USER_AGENT} ^Internet\ Ninja [OR] RewriteCond %{HTTP_USER_AGENT} ^JetCar [OR] RewriteCond %{HTTP_USER_AGENT} ^JOC\ Web\ Spider [OR] RewriteCond %{HTTP_USER_AGENT} ^larbin [OR] RewriteCond %{HTTP_USER_AGENT} ^LeechFTP [OR] RewriteCond %{HTTP_USER_AGENT} ^Mass\ Downloader [OR] RewriteCond %{HTTP_USER_AGENT} ^MIDown\ tool [OR] RewriteCond %{HTTP_USER_AGENT} ^Mister\ PiX [OR] RewriteCond %{HTTP_USER_AGENT} ^Navroad [OR] RewriteCond %{HTTP_USER_AGENT} ^NearSite [OR] RewriteCond %{HTTP_USER_AGENT} ^NetAnts [OR] RewriteCond %{HTTP_USER_AGENT} ^NetSpider [OR] RewriteCond %{HTTP_USER_AGENT} ^Net\ Vampire [OR] RewriteCond %{HTTP_USER_AGENT} ^NetZIP [OR] RewriteCond %{HTTP_USER_AGENT} ^Octopus [OR] RewriteCond %{HTTP_USER_AGENT} ^Offline\ Explorer [OR] RewriteCond %{HTTP_USER_AGENT} ^Offline\ Navigator [OR] RewriteCond %{HTTP_USER_AGENT} ^PageGrabber [OR] RewriteCond %{HTTP_USER_AGENT} ^Papa\ Foto [OR] RewriteCond %{HTTP_USER_AGENT} ^pavuk [OR] RewriteCond %{HTTP_USER_AGENT} ^pcBrowser [OR] RewriteCond %{HTTP_USER_AGENT} ^RealDownload [OR] RewriteCond %{HTTP_USER_AGENT} ^ReGet [OR] RewriteCond %{HTTP_USER_AGENT} ^SiteSnagger [OR] RewriteCond %{HTTP_USER_AGENT} ^SmartDownload [OR] RewriteCond %{HTTP_USER_AGENT} ^SuperBot [OR] RewriteCond %{HTTP_USER_AGENT} ^SuperHTTP [OR] RewriteCond %{HTTP_USER_AGENT} ^Surfbot [OR] RewriteCond %{HTTP_USER_AGENT} ^tAkeOut [OR] RewriteCond %{HTTP_USER_AGENT} ^Teleport\ Pro [OR] RewriteCond %{HTTP_USER_AGENT} ^VoidEYE [OR] RewriteCond %{HTTP_USER_AGENT} ^Web\ Image\ Collector [OR] RewriteCond %{HTTP_USER_AGENT} ^Web\ Sucker [OR] RewriteCond %{HTTP_USER_AGENT} ^WebAuto [OR] RewriteCond %{HTTP_USER_AGENT} ^WebCopier [OR] RewriteCond %{HTTP_USER_AGENT} ^WebFetch [OR] RewriteCond %{HTTP_USER_AGENT} ^WebGo\ IS [OR] RewriteCond %{HTTP_USER_AGENT} ^WebLeacher [OR] RewriteCond %{HTTP_USER_AGENT} ^WebReaper [OR] RewriteCond %{HTTP_USER_AGENT} ^WebSauger [OR] RewriteCond %{HTTP_USER_AGENT} ^Website\ eXtractor [OR] RewriteCond %{HTTP_USER_AGENT} ^Website\ Quester [OR] RewriteCond %{HTTP_USER_AGENT} ^WebStripper [OR] RewriteCond %{HTTP_USER_AGENT} ^WebWhacker [OR] RewriteCond %{HTTP_USER_AGENT} ^WebZIP [OR] RewriteCond %{HTTP_USER_AGENT} ^Wget [OR] RewriteCond %{HTTP_USER_AGENT} ^Widow [OR] RewriteCond %{HTTP_USER_AGENT} ^WWWOFFLE [OR] RewriteCond %{HTTP_USER_AGENT} ^Xaldon\ WebSpider [OR] RewriteCond %{HTTP_USER_AGENT} ^Zeus RewriteRule .* - [F]