#
# 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: WebAuto
User-agent: Octopus
User-agent: Papa Foto
User-agent: SemrushBot
User-agent: WebZIP
User-agent: ExtractorPro
User-agent: GrabNet
User-agent: Indy Library
User-agent: WebGo IS
User-agent: Image Sucker
User-agent: Rogerbot
User-agent: larbin
User-agent: Go!Zilla
User-agent: WebFetch
User-agent: HTTrack
User-agent: WWWOFFLE
User-agent: PageGrabber
User-agent: Zeus
User-agent: Offline Explorer
User-agent: Dotbot
User-agent: SemrushBot/1.1~bl
User-agent: Image Stripper
User-agent: Navroad
User-agent: HMView
User-agent: Net Vampire
User-agent: Wget
User-agent: MIDown tool
User-agent: Grafula
User-agent: pavuk
User-agent: WebCopier
User-agent: NetZIP
User-agent: Internet Ninja
User-agent: Download Demon
User-agent: Xaldon WebSpider
User-agent: EyeNetIE
User-agent: Express WebPictures
User-agent: EirGrabber
User-agent: Mister PiX
User-agent: Website eXtractor
User-agent: SiteSnagger
User-agent: SmartDownload
User-agent: Go-Ahead-Got-It
User-agent: Website Quester
User-agent: ReGet
User-agent: Widow
User-agent: RealDownload
User-agent: InterGET
User-agent: JOC Web Spider
User-agent: pcBrowser
User-agent: WebReaper
User-agent: Exabot
User-agent: LeechFTP
User-agent: AhrefsBot/5.1
User-agent: LinkpadBot
User-agent: BlackWidow
User-agent: WebWhacker
User-agent: FlashGet
User-agent: GetWeb!
User-agent: Surfbot
User-agent: Web Image Collector
User-agent: MJ12bot
User-agent: EmailSiphon
User-agent: tAkeOut
User-agent: Offline Navigator
User-agent: eCatch
User-agent: NetAnts
User-agent: SuperHTTP
User-agent: DISCo
User-agent: Gigabot
User-agent: SuperBot
User-agent: NetSpider
User-agent: JetCar
User-agent: WebSauger
User-agent: AhrefsBot
User-agent: Bot [EMAIL="[email protected]"]mailto:[email protected][/EMAIL]
User-agent: VoidEYE
User-agent: NearSite
User-agent: WebStripper
User-agent: Teleport Pro
User-agent: Web Sucker
User-agent: GetRight
User-agent: EmailWolf
User-agent: Mass Downloader
User-agent: ChinaClaw
User-agent: Custo
User-agent: WebLeacher
Disallow: /
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.sqlite.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: /node/add/
Disallow: /search/
Disallow: /user/register/
Disallow: /user/password/
Disallow: /user/login/
Disallow: /user/logout/
# Paths (no clean URLs)
Disallow: /?q=admin/
Disallow: /?q=comment/reply/
Disallow: /?q=filter/tips/
Disallow: /?q=node/add/
Disallow: /?q=search/
Disallow: /?q=user/password/
Disallow: /?q=user/register/
Disallow: /?q=user/login/
Disallow: /?q=user/logout/