# Googlebot # User-agent: googlebot # disallow ALL bots from calling actions in DataFeed controller User-agent: * Disallow: /DataFeed/ # disallow Majestic12 bot from calling actions in Amazon controller User-agent: MJ12bot Disallow: /Amazon/ # disallow OpenLinkProfiler bot from calling actions in Amazon controller User-agent: spbot Disallow: /Amazon/ # disallow spray-can/1.3.3 bot from calling actions in Amazon controller User-agent: spray-can/1.3.3 Disallow: /Amazon/ # disallow Baiduspider bot from calling actions in Amazon controller User-agent: Baiduspider Disallow: /Amazon/ # disallow BLEXBot bot from calling actions in Amazon controller User-agent: BLEXBot Disallow: /Amazon/ # disallow AhrefsBot bot from calling actions in Amazon controller User-agent: AhrefsBot Disallow: /Amazon/ ###################################################################################################### # below is a comprehensive of bad bots to block # Disallow all crawlers access to certain pages. User-agent: * Disallow: /checkout.asp Disallow: /add_cart.asp Disallow: /view_cart.asp Disallow: /error.asp Disallow: /shipquote.asp Disallow: /rssfeed.asp Disallow: /mobile/ Disallow: /admin/ # Block Yandex from crawling site User-agent: Yandex Disallow: / # Block Yeti User-agent: Yeti Disallow: / # Block NextGenSearchBot User-agent: NextGenSearchBot Disallow: / # Block ia-archiver from crawling site User-agent: ia_archiver Disallow: / # Block Baiduspider from crawling site User-agent: Baiduspider Disallow: / # Block PicScout Crawler from crawling site User-agent: PicScout Disallow: / # Block MJ12bot from crawling site User-agent: MJ12bot Disallow: / # Block 008 from crawling site User-agent: 008 Disallow: / # Block AhrefsBot from crawling site User-agent: AhrefsBot Disallow: / # Block CCBot Crawler from crawling site User-agent: CCBot Disallow: / # Block BLEXBot Crawler from crawling site User-agent: BLEXBot Crawler Disallow: / # Block TinEye from crawling site User-agent: TinEye Disallow: / # Block Sogou Spider from crawling site User-agent: Sogou Spider Disallow: / # Block Exabot from crawling site User-agent: Exabot Disallow: / # Block Nutch from crawling site User-agent: Nutch Disallow: / # Block MJ12bot as it is just noise User-agent: MJ12bot Disallow: / # Block Python-urllib User-agent: Python-urllib Disallow: / # Block dotbot User-agent: dotbot Disallow: / # Block SEOkicks User-agent: SEOkicks-Robot Disallow: / # Block BlexBot User-agent: BLEXBot Disallow: / # Block SISTRIX User-agent: SISTRIX Crawler Disallow: / # Block Uptime robot User-agent: UptimeRobot/2.0 Disallow: / # Block Ezooms Robot User-agent: Ezooms Robot Disallow: / # Block Perl LWP User-agent: Perl LWP Disallow: / # Block netEstate NE Crawler (+http://www.website-datenbank.de/) User-agent: netEstate NE Crawler (+http://www.website-datenbank.de/) Disallow: / # Block WiseGuys Robot User-agent: WiseGuys Robot Disallow: / # Block Turnitin Robot User-agent: Turnitin Robot Disallow: / # Block Heritrix User-agent: Heritrix Disallow: / # Block pricepi User-agent: pimonster Disallow: / User-agent: Pimonster Disallow: / User-agent: Pi-Monster Disallow: / # Block Eniro User-agent: ECCP/1.0 (search@eniro.com) Disallow: / # Block YandexBot User-agent: Yandex Disallow: / # Block Baidu User-agent: Baiduspider User-agent: Baiduspider-video User-agent: Baiduspider-image Disallow: / # Block SoGou User-agent: Sogou Spider Disallow: / # Block Psbot User-agent: Psbot Disallow: / # Block Youdao User-agent: YoudaoBot Disallow: / # BLEXBot User-agent: BLEXBot Disallow: / # Block NaverBot User-agent: NaverBot User-agent: Yeti Disallow: / # Block Psbot User-agent: Psbot Disallow: / # Block Mediapartners-Google User-agent: Mediapartners-Google Disallow: / #Block Googlebot-Image User-agent: Googlebot-Image Disallow: / # Block ZBot User-agent: ZBot Disallow: / # Block Vagabondo User-agent: Vagabondo Disallow: / # Block LinkWalker User-agent: LinkWalker Disallow: / # Block Xenu Link Sleuth User-agent: Xenu Link Sleuth Disallow: / # Block SimplePie User-agent: SimplePie Disallow: / # Block Wget User-agent: Wget Disallow: / # Block Pixray-Seeker User-agent: Pixray-Seeker Disallow: / # Block BoardReader User-agent: BoardReader Disallow: / # Block Unknown Bot User-agent: Unknown Bot Disallow: /