# # 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: A6-Indexer User-agent: A6-Indexer/1.0 User-agent: ADmantX Platform Semantic Analyzer User-agent: AhrefsBot User-agent: aiHitBot User-agent: aiHitBot/2.8 User-agent: Aboundexbot User-agent: AlphaBot User-agent: AlphaBot/1.1.4 User-agent: BLEXBot User-agent: BLEXbot/1.0 User-agent: BOT/0.1 User-agent: BOT for JCE User-agent: ca-crawler User-agent: ca-crawler/1.0 User-agent: DBot/7.5.6 User-agent: DotBot User-agent: DotBot/1.1 User-agent: EasouSpider User-agent: Ezooms User-agent: FunWebProducts User-agent: fr-crawler User-agent: fr-crawler/1.1 User-agent: GrapeShotCrawler User-agent: GrapeShotCrawler/2.0 User-agent: jetsli.de User-agent: LSSRockerCrawler User-agent: LSSRockerCrawler/1.0 User-agent: NetSeer User-agent: NetSeer crawler/2.0 User-agent: MJ12bot User-agent: MJ12bot/v1.4.5 User-agent: Mail.RU User-agent: meanpathbot User-agent: meanpathbot/1.0 User-agent: nutch-1.4/Nutch-1.4 User-agent: oBot/2.3.1 User-agent: OpenWebSpider User-agent: proximic User-agent: QuerySeekerSpider ( http://queryseeker.com/bot.html ) User-agent: rBot User-agent: LSSRocketCrawler/1.0 LightSpeedSystems User-agent: SearchMetricsBot User-agent: semalt User-agent: SemrushBot User-agent: SemrushBot/0.98~b1 User-agent: SeznamBot User-agent: SeznamBot/3.2 User-agent: SISTRIX User-agent: SISTRIX Crawler: http://crawler.sistrix.net/ User-agent: SMTBot User-agent: SMTBot/1.0 User-agent: Sogou User-agent: Sogou web spider/4.0 User-agent: spbot User-agent: TurnitinBot User-agent: TurnitinBot/3.0 User-agent: WeSEE User-agent: WeSEE:Ads/PageBot User-agent: WebMasterAid/1.0 User-agent: Wotbox User-agent: Wotbox/2.01 User-agent: XoviBot User-agent: XoviBot/2.0 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/ Disallow: /user/ Disallow: /user/password?/ # 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/ #other Disallow: /node/ Disallow: /register-yourself/ Disallow: /register-yourself?