User-agent: baiduspider archiver Baiduspider Blogbeat carleson cfetch compatible;Eolin Crawler DigExt DrecomBot EMPAS Exabot favicon FeedChecker feedfinder findlinks genieBot HMSE_Robot ichiro IP*Works! IRLbot Jigsaw kinjabot Labrador larbin lwp-trivial LWP::Simple MirrorChecking MissiguaLocator MJ12bot NG/2.0 NutchCVS PEARHTTP_Request Pingdom PostFavorites psbot SBIder ShopWiki sogou SurveyBot urllib/1.15 voyager W3C_Validator WISEbot Y!J-BSC ZyBorg Disallow: / # works BrowserMatchNoCase "Googlebot/" do_not_log is_a_robot BrowserMatchNoCase "naverbot" do_not_log is_a_robot BrowserMatchNoCase "Yahoo! Slurp" do_not_log is_a_robot BrowserMatchNoCase "msnbot/" do_not_log is_a_robot BrowserMatchNoCase "msnbot-media/" do_not_log is_a_robot BrowserMatchNoCase "Openmaru bot" do_not_log is_a_robot BrowserMatchNoCase "Twiceler" do_not_log is_a_robot BrowserMatchNoCase "Feedfetcher" do_not_log is_a_robot BrowserMatchNoCase "libwww-perl/" do_not_log is_a_robot # disco/Nutch-1.0-dev (experimental crawler; www.discoveryengine.com; disco-crawl@discoveryengine.com) BrowserMatchNoCase "disco/Nutch" do_not_log is_a_robot # Yahoo-MMCrawler/3.x (mms dash mmcrawler dash support at yahoo dash inc dot com) BrowserMatchNoCase "Yahoo-MMCrawler/" do_not_log is_a_robot # Teemer (NetSeer, Inc.; http://www.netseer.com/crawler.html; crawler@netseer.com) BrowserMatchNoCase "Teemer" do_not_log is_a_robot BrowserMatchNoCase "Python-urllib/" do_not_log is_a_robot BrowserMatchNoCase "EMPAS.ROBOT" do_not_log is_a_robot BrowserMatchNoCase "Allblog.net" do_not_log is_a_robot BrowserMatchNoCase "HanRSS/" do_not_log is_a_robot BrowserMatchNoCase "UniversalFeedParser/" do_not_log is_a_robot # test BrowserMatchNoCase "findlinks/" do_not_log is_a_robot BrowserMatchNoCase "Gigabot/" do_not_log is_a_robot # MJ12bot/v1.0.8 (http://majestic12.co.uk/bot.php?+) BrowserMatchNoCase "MJ12bot/" do_not_log is_a_robot # Speedy Spider (http://www.entireweb.com/about/search_tech/speedy_spider/) BrowserMatchNoCase "Speedy Spider" do_not_log is_a_robot BrowserMatchNoCase "Technoratibot/" do_not_log is_a_robot BrowserMatchNoCase "Yahoo! DE Slurp" do_not_log is_a_robot BrowserMatchNoCase "Googlebot-Mobile/" do_not_log is_a_robot BrowserMatchNoCase "Google-Sitemaps/" do_not_log is_a_robot BrowserMatchNoCase "Epson B68 Bluetooth WAP Browser" do_not_log is_a_robot BrowserMatchNoCase "woriobot" do_not_log is_a_robot YahooFeedSeeker/2.0 (compatible; Mozilla 4.0; MSIE 5.5; http://publisher.yahoo.com/rssguide) Mozilla/5.0 (compatible; LiteFinder/1.0; +http://www.litefinder.net/about.html) #block # Yeti/0.01 (nhn/1noon, yetibot@naver.com, check robots.txt daily and follow it) # BrowserMatchNoCase "Yeti/" do_not_log is_a_robot # Ƽ½ºÅ丮 ³»Àå ·Îº¿ ¸®½ºÆ® # 1Noonbot # Accoona-AI-Agent archiver Baiduspider Blogbeat carleson cfetch compatible;Eolin Crawler DigExt DrecomBot EMPAS Exabot favicon FeedChecker feedfinder findlinks genieBot HMSE_Robot ichiro IP*Works! IRLbot Jigsaw kinjabot Labrador larbin lwp-trivial LWP::Simple MirrorChecking MissiguaLocator MJ12bot NG/2.0 NutchCVS PEARHTTP_Request Pingdom PostFavorites psbot SBIder ShopWiki sogou SurveyBot urllib/1.15 voyager W3C_Validator WISEbot Y!J-BSC ZyBorg # dosen't work # BrowserMatchNoCase "ru-robot" do_not_log is_a_robot # BrowserMatchNoCase "Slurp/si" do_not_log is_a_robot # BrowserMatchNoCase "Mercator" do_not_log is_a_robot # BrowserMatchNoCase "Gulliver" do_not_log is_a_robot # BrowserMatchNoCase "SyncIT/" do_not_log is_a_robot # BrowserMatchNoCase "FAST-WebCrawler" do_not_log is_a_robot # BrowserMatchNoCase "Lycos_Spider" do_not_log is_a_robot # BrowserMatchNoCase "^ia_archive" do_not_log is_a_robot # BrowserMatchNoCase "^tv" do_not_log is_a_robot # BrowserMatchNoCase "Scooter" do_not_log is_a_robot # BrowserMatchNoCase "ZyBorg/" do_not_log is_a_robot # BrowserMatchNoCase "KIT-Fireball" do_not_log is_a_robot # BrowserMatchNoCase "DIIbot/" do_not_log is_a_robot # BrowserMatchNoCase "teoma_agent3" do_not_log is_a_robot # BrowserMatchNoCase "empas_robot" do_not_log is_a_robot