# If the Joomla site is installed within a folder # eg www.example.com/joomla/ then the robots.txt file # MUST be moved to the site root # eg www.example.com/robots.txt # AND the joomla folder name MUST be prefixed to all of the # paths. # eg the Disallow rule for the /administrator/ folder MUST # be changed to read # Disallow: /joomla/administrator/ # # For more information about the robots.txt standard, see: # http://www.robotstxt.org/orig.html # # For syntax checking, see: # http://tool.motoricerca.info/robots-checker.phtml User-agent: * Disallow: /administrator/ Disallow: /bin/ Disallow: /cache/ Disallow: /cli/ Disallow: /components/ Disallow: /includes/ Disallow: /installation/ Disallow: /language/ Disallow: /layouts/ Disallow: /libraries/ Disallow: /logs/ Disallow: /modules/ Disallow: /plugins/ Disallow: /tmp/ # cloudflare recommended block: Disallow: /cdn-cgi/ # Start of Bot Blocking User-agent: AlphaBot Disallow: / # Block Admantx Bot User-agent: ADmantX Disallow: / # Block Heritrix User-agent: Heritrix Disallow: / # Block Indy Library Bot User-agent: Mozilla/3.0 (compatible; Indy Library) Disallow: / # Block Indy Library Bot User-agent: Indy Library Disallow: / # Block Mail.Ru User-agent: Mail.Ru Disallow: / # Block Majestic-12 Bot User-agent: MJ12bot Disallow: / # Block Moz DotBot User-agent: dotbot Disallow: / # Block Moz Rogerbot User-agent: rogerbot Disallow: / # Block PHPCrawl Bot User-agent: PHPCrawl Disallow: / # Block BLEXBot User-agent: BLEXBot Disallow: / # Block Brandwatch's Magpie Crawler User-agent: magpie-crawler Disallow: / # Block SeznamBot User-agent: SeznamBot Disallow: / # Block this bot User-agent: seoscanners.net Disallow: / # Block SoftSearch Bot User-agent: SoftSearch.ru robot Disallow: / # Block Uptime Bot User-agent: Uptimebot Disallow: / User-agent: Python-urllib Disallow: / User-agent: python-requests Disallow: / User-agent: Python-httplib2 Disallow: / User-agent: expo9 Disallow: / User-agent: ZumBot Disallow: / User-agent: Yandex Disallow: / # blocks access to whole site for Yandex User-agent: EventMachine HttpClient Disallow: / User-agent: MaxPointCrawler Disallow: / User-agent: Nutch Disallow: / User-agent: MaxPointCrawler/Nutch-1.10 Disallow: / User-agent: Go-http-client Disallow: / User-agent: Go-http-client/1.1 Disallow: / User-agent: Go 1.1 package http Disallow: / User-Agent: Wget Disallow: / User-agent: uipbot Disallow: / User-agent: uipbot/1.0 (uipbot@semasio.net) Disallow: / User-agent: GetIntent Crawler Disallow: / User-Agent: panscient.com Disallow: / User-agent: BUbiNG Disallow: / # End of Bot Blocking # Good Bot Whitelisting: User-agent: Twitterbot Disallow: User-agent: Mediapartners-Google Disallow: