Skip to content

Instantly share code, notes, and snippets.

@2803media
Last active November 19, 2018 09:09
Show Gist options
  • Select an option

  • Save 2803media/0cf7d6644aeabe90d6d098e36bd39337 to your computer and use it in GitHub Desktop.

Select an option

Save 2803media/0cf7d6644aeabe90d6d098e36bd39337 to your computer and use it in GitHub Desktop.
# Fail2Ban configuration file
#
# Regexp to catch known spambots and software alike. Please verify
# that it is your intent to block IPs which were driven by
# above mentioned bots.
[Definition]
badbotscustom = \bQwantify\b|\bCFNetwork\b
badbots = \b173\.212soso\b|\b192\.comagent\b|\b1noonbot\b|\b1on1searchbot\b|\b360Spider\b|\b3de_search2\b|\b3d_search\b|\b3g bot\b|\b3gse\b|\b404checker\b|\b404enemy\b|\b50\.nu\b|\b80legs\b|\bA1 sitemap generator\b|\bA1 website download\b|\bA6-indexer\b|\bAasp\b|\bAbachobot\b|\bAbonti\b|\bAbotemailsearch\b|\bAboundex\b|\bAboutusbot\b|\bAccmonitor compliance server\b|\bAccoon\b|\bAchulkov\.net page walker\b|\bAcme\.spider\b|\bAcoonbot\b|\bAcquia-crawler\b|\bActivetouristbot\b|\bAcunetix\b|\bAdamm bot\b|\bAdbeat_bot\b|\bADmantX\b|\bAdminshop\.com\b|\bAd muncher\b|\bAdvanced email extractor\b|\bAesop_com_spiderman\b|\bAespider\b|\bAfD-Verbotsverfahren\b|\bAf knowledge now verity spider\b|\bAggregator\:vocus\b|\bAh-ha\.com crawler\b|\bAhrefs\b|\bAhrefsBot\b|\bAIBOT\b|\bAidu\b|\bAiHitBot\b|\bAipbot\b|\bAisiid\b|\bAitcsrobot/1\.1\b|\bAjsitemap\b|\bAkamai-sitesnapshot\b|\bAlexawebsearchplatform\b|\bAlexfdownload\b|\bAlexibot\b|\bAlkalinebot\b|\bAll acronyms bot\b|\bAlligator\b|\bAllSubmitter\b|\bAlphaBot\b|\bAlpha search agent\b|\bAmerla search bot\b|\bAmfibibot\b|\bAmpmppc\.com\b|\bAmznkassocbot\b|\bAnarchie\b|\bAnemone\b|\bAnonymous\b|\bAnotherbot\b|\bAnswerbot\b|\bAnswerbus\b|\bAnswerchase prove\b|\bAntbot\b|\bAntibot\b|\bAntisantyworm\b|\bAntro\.net\b|\bAonde-spider\b|\bApexoo\b|\bAport\b|\bAppengine-google\b|\bAppid\: s~stremor-crawler-\b|\bAqua_products\b|\bArabot\b|\bArachmo\b|\bArachnophilia\b|\bAria equalizer\b|\bArianna\.libero\.it\b|\bArikus_spider\b|\bArtavisbot\b|\bArtera\b|\bArt-online\.com\b|\bAsaha search engine turkey\b|\bAsk\b|\bAspider\b|\bASPSeek\b|\bAsterias\b|\bAstrofind\b|\bAthenusbot\b|\bAtlocalbot\b|\bAtomic_email_hunter\b|\bAttach\b|\bAttrakt\b|\bAttributor\b|\bAugurfind\b|\bAuresys\b|\bAutobaron crawler\b|\bAutoemailspider\b|\bAutowebdir\b|\bAvsearch-\b|\bAxfeedsbot\b|\bAxonize-bot\b|\bAyna\b|\bB2w\b|\bBackDoorBot\b|\bBacklink-Ceck\b|\bBacklink-check\b|\bBacklinkCrawler\b|\bBackrub\b|\bBackStreet\b|\bBackstreet browser\b|\bBackWeb\b|\bBadass\b|\bBandit\b|\bBarkrowler\b|\bBatchFTP\b|\bBattleztar Bazinga\b|\bBaypup\b|\bBBBike\b|\bBDCbot\b|\bBDFetch\b|\bBecomebot\b|\bBecomejpbot\b|\bBeetlebot\b|\bBender\b|\bBesserscheitern-crawl\b|\bBetaBot\b|\bBigado\.com\b|\bBig brother\b|\bBigcliquebot\b|\bBig data\b|\bBigfoot\b|\bBiglotron\b|\bBilbo\b|\bBilgibetabot\b|\bBilgibot\b|\bBintellibot\b|\bBitacle\b|\bBitlybot\b|\bBitvouseragent\b|\bBizbot\b|\bBizworks retriever\b|\bBlackbird\b|\bBlackboard\b|\bBlack\.hole\b|\bBlack Hole\b|\bBlackmask\.net search engine\b|\bBlackWidow\b|\bBladder fusion\b|\bBlaiz-bee\b|\bBlexbot\b|\bBlinkx\b|\bBlitzbot\b|\bBlog conversation project\b|\bBlogmyway\b|\bBlogpulselive\b|\bBlogrefsbot\b|\bBlogscope\b|\bBlogslive\b|\bBloobybot\b|\bBlow\b|\bBlowFish\b|\bBlt\b|\bBnf\.fr_bot\b|\bBoaconstrictor\b|\bBoardreader\b|\bBoia\.org\b|\bBoia-scan-agent\b|\bBoi_crawl_00\b|\bBoitho\b|\bBolt\b|\bBookmark buddy bookmark checker\b|\bBookmark search tool\b|\bBosug\b|\bBotALot\b|\bBot apoena\b|\bBotrighthere\b|\bBotswana\b|\bBottybot\b|\bBpbot\b|\bBraintime_search\b|\bBrandprotect\b|\bBrandwatch\b|\bBrokenlinkcheck\.com\b|\bBrowseremulator\b|\bBrowsermob\b|\bBruinbot\b|\bBsearchr&d\b|\bBspider\b|\bBtbot\b|\bBtsearch\b|\bBubing\b|\bBuddy\b|\bBuibui\b|\bBuildcms crawler\b|\bBuiltBotTough\b|\bBuiltWith\b|\bBullseye\b|\bBumblebee\b|\bBunnySlippers\b|\bBuscadorclarin\b|\bBuscaplus robi\b|\bButterfly\b|\bBuyhawaiibot\b|\bBuzzbot\b|\bBuzzSumo\b|\bByindia\b|\bByspider\b|\bByteserver\b|\bBzbot\b|\bCacheblaster\b|\bCaddbot\b|\bCafi\b|\bCalculon\b|\bCamcrawler\b|\bCamelstampede\b|\bCanon-webrecord\b|\bCareerbot\b|\bCataguru\b|\bCatchbot\b|\bCATExplorador\b|\bCazoodle\b|\bCCBot\b|\bCcgcrawl\b|\bCcubee\b|\bCd-preload\b|\bCegbfeieh\b|\bCe-preload\b|\bCerberian drtrs\b|\bCert figleafbot\b|\bCfetch\b|\bCfnetwork\b|\bChameleon\b|\bCharlotte\b|\bCheckbot\b|\bCheck&get\b|\bChecklinks\b|\bCheeseBot\b|\bChemiede-nodebot\b|\bCherryPicker\b|\bChilkat\b|\bChinaClaw\b|\bChlooe\b|\bChromeframe\b|\bCipinetbot\b|\bCis455crawler\b|\bCiteseerxbot\b|\bCizilla\b|\bClariabot\b|\bClaritybot\b|\bClimate ark\b|\bClimateark spider\b|\bCliqzbot\b|\bCloud mapping\b|\bClshttp\b|\bClushbot\b|\bCoast scan engine\b|\bCoast webmaster pro\b|\bCoccoc\b|\bCoccocbot-web\b|\bCogentbot\b|\bCognitiveseo\b|\bCollapsarweb\b|\bCollector\b|\bColocrossing\b|\bCombine\b|\bCom\.plumanalytics\b|\bConnectsearch\b|\bConpilot\b|\bContentsmartz\b|\bContextad bot\b|\bContype\b|\bCookienet\b|\bCoolbot\b|\bCoolcheck\b|\bCopernic\b|\bCopier\b|\bCopyRightCheck\b|\bCopyscape\b|\bCore-project\b|\bCosmos\b|\bCovario-ids\b|\bCowbot-\b|\bCowdog bot\b|\bCrabbybot\b|\bCraftbot\b|\bC r a w l 3 r\b|\bCrawl_application\b|\bCrawler@\b|\bCrawler43\.ejupiter\.com\b|\bCrawler4j\b|\bCrawler\.feedback\b|\bCrawler_for_infomine\b|\bCrawler\.kpricorn\.org\b|\bcrawl\.sogou\.com\b|\bCrawly\b|\bCrazyWebCrawler\b|\bCreativecommons\b|\bCrescent\b|\bCs-crawler\b|\bCse html validator\b|\bCSHttp\b|\bCshttpclient\b|\bCuasarbot\b|\bCulsearch\b|\bCurious\b|\bCusto\b|\bCvaulev\b|\bCyberdog\b|\bCybernavi_webget\b|\bCyberpatrol sitecat webbot\b|\bCyberspyder\b|\bCydralspider\b|\bD1garabicengine\b|\bDatabaseDriverMysqli\b|\bDataCha0s\b|\bDatafountains\b|\bDataparksearch\b|\bDataprovider\.com\b|\bDatascape robot\b|\bDataspearspiderbot\b|\bDataspider\b|\bDattatec\.com\b|\bDaumoa\b|\bDBLBot\b|\bDcpbot\b|\bDeclumbot\b|\bDeepindex\b|\bDeepnet crawler\b|\bDeeptrawl\b|\bDejan\b|\bDel\.icio\.us-thumbnails\b|\bDeltascan\b|\bDelvubot\b|\bDemandbase-bot\b|\bDemon\b|\bDer gro§e bildersauger\b|\bDer große bildersauger\b|\bDeusu\b|\bDevil\b|\bDfs-fetch\b|\bDiagem\b|\bDiamond\b|\bDibot\b|\bDidaxusbot\b|\bDigext\b|\bDigger\b|\bDigincore\b|\bDigi-rssbot\b|\bDigitalarchivesbot\b|\bDigitalPebble\b|\bDigout4u\b|\bDIIbot\b|\bDillo\b|\bDirbuster\b|\bDir_snatch\.exe\b|\bDisco\b|\bDiscobot\b|\bDiscoverybot\b|\bDistilled-reputation-monitor\b|\bDittoSpyder\b|\bDjangotraineebot\b|\bDkimrepbot\b|\bDmoz downloader\b|\bDnyzBot\b|\bDocomo\b|\bDof-verify\b|\bDomainAppender\b|\bDomainCrawler\b|\bDomainscan\b|\bDomainSigmaCrawler\b|\bDomainStatsBot\b|\bDomainwatcher bot\b|\bDotbot\b|\bDotspotsbot\b|\bDow jones searchbot\b|\bDownload\b|\bDownload Wonder\b|\bDoy\b|\bDragonfly\b|\bDrip\b|\bDrone\b|\bDtaagent\b|\bDTS Agent\b|\bDtsearchspider\b|\bDumbot\b|\bDwaar\b|\bDxseeker\b|\bEah\b|\bEarth platform indexer\b|\bEarth science educator robot\b|\bEasyDL\b|\bEbingbong\b|\bEc2linkfinder\b|\bEcairn-grabber\b|\bECatch\b|\bECCP/1\.0\b|\bEchoosebot\b|\bEcxi\b|\bEdisterbot\b|\bEdugovsearch\b|\bEgothor\b|\bEidetica\.com\b|\bEirGrabber\b|\bElblindo the blind bot\b|\bElisabot\b|\bEllerdalebot\b|\bEmailcollector\b|\bEmail extractor\b|\bEmailleach\b|\bEmailsiphon\b|\bEMail Siphon\b|\bEmailwolf\b|\bEMail Wolf\b|\bEmeraldshield\b|\bEmpas_robot\b|\bEnabot\b|\bEndeca\b|\bEnigmabot\b|\bEnswer neuro bot\b|\bEnter user-agent\b|\bEntitycubebot\b|\bEroCrawler\b|\bE-societyrobot\b|\bEstylesearch\b|\bEsyndicat bot\b|\bEurosoft-bot\b|\bEvaal\b|\bEvc-batch\b|\bEventware\b|\bEverest-vulcan inc\.\b|\bEvil\b|\bExabot\b|\bExactsearch\b|\bExactseek\b|\bExooba\b|\bExploder\b|\bExpress WebPictures\b|\bExtLinksBot\b|\bExtractor\b|\bExtractorPro\b|\bExtreme Picture Finder\b|\bEyenetie\b|\bEyeNetIE\b|\bEzooms\b|\bEz-robot\b|\bFactbot\b|\bFairad client\b|\bFalcon\b|\bFastbot crawler\b|\bFastbot\.de crawler\b|\bFast data search document retriever\b|\bFast esp\b|\bFast-search-engine\b|\bFatbot\b|\bFavcollector\b|\bFaviconizer\b|\bFavorites sweeper\b|\bF-bot test pilot\b|\bFDM\b|\bFdse robot\b|\bFedcontractorbot\b|\bFembot\b|\bFemtosearchBot\b|\bFetch api request\b|\bFetch_ici\b|\bFgcrawler\b|\bFHscan\b|\bFilangy\b|\bFilehound\b|\bFimap\b|\bFindanisp\.com_isp_finder\b|\bFindlinks\b|\bFindweb\b|\bFirebat\b|\bFirefox/7\.0\b|\bFirstgov\.gov search\b|\bFlaming attackbot\b|\bFlamingo_searchengine\b|\bFlashcapture\b|\bFlashGet\b|\bFlickysearchbot\b|\bFluffy the spider\b|\bFlunky\b|\bFocused_crawler\b|\bFollowsite\b|\bFoobot\b|\bFooooo_web_video_crawl\b|\bFopper\b|\bFormulafinderbot\b|\bForschungsportal\b|\bFrancis\b|\bFr_crawler\b|\bFreeuploader\b|\bFreewebmonitoring sitechecker\b|\bFreshcrawler\b|\bFreshdownload\b|\bFreshlinks\.exe\b|\bFriendfeedbot\b|\bFrodo\.at\b|\bFroggle\b|\bFrontPage\b|\bFroola bot\b|\bFull_breadth_crawler\b|\bFu-nbi\b|\bFunnelback\b|\bFurlbot\b|\bFyberSpider\b|\bFyrebot\b|\bG10-bot\b|\bGaisbot\b|\bGalaxyBot\b|\bGazz\b|\bGbplugin\b|\bGenerate_infomine_category_classifiers\b|\bGenevabot\b|\bGeniebot\b|\bGenieo\b|\bGeomaxenginebot\b|\bGeometabot\b|\bGeonabot\b|\bGeovisu\b|\bGermCrawler\b|\bGethtmlcontents\b|\bGetintent\b|\bGetleft\b|\bGetRight\b|\bGetsmart\b|\bGeturl\.rexx\b|\bGetWeb\b|\bGiant\b|\bGigablast\b|\bGigablastopensource\b|\bGigabot\b|\bG-i-g-a-b-o-t\b|\bGirafabot\b|\bGleamebot\b|\bGnome-vfs\b|\bGo-Ahead-Got-It\b|\bGoforitbot\b|\bGoforit\.com\b|\bGo-http-client\b|\bGold crawler\b|\bGoldfire server\b|\bGolem\b|\bGoodjelly\b|\bGordon-college-google-mini\b|\bGoroam\b|\bGoseebot\b|\bGotit\b|\bGovbot\b|\bGoZilla\b|\bGo\!Zilla\b|\bGpu p2p crawler\b|\bGrabber\b|\bGrabNet\b|\bGrafula\b|\bGrapeFX\b|\bGrapeshot\b|\bGrbot\b|\bGreenyogi\b|\bGridBot\b|\bGromit\b|\bGrub\b|\bGslfbot\b|\bGT\:\:WWW\b|\bGulliver\b|\bGulperbot\b|\bGurujibot\b|\bGvcbot\.com\b|\bGvc business crawler\b|\bGvc crawler\b|\bGvc search bot\b|\bGvc web crawler\b|\bGvc weblink crawler\b|\bGvc world links\b|\bHaansoft\b|\bHaosouSpider\b|\bHappyfunbot\b|\bHarvest\b|\bHatena antenna\b|\bHavij\b|\bHawler\b|\bHcat\b|\bHclsreport-crawler\b|\bHd nutch agent\b|\bHeader_test_client\b|\bHEADMasterSEO\b|\bHealia\b|\bHelix\b|\bHere will be link to crawler site\b|\bHeritrix\b|\bHiscan\b|\bHisoftware accmonitor server\b|\bHisoftware accverify\b|\bHitcrawler\b|\bHivabot\b|\bHloader\b|\bHmsebot\b|\bHMView\b|\bHoge\b|\bHolmes\b|\bHomepagesearch\b|\bHooblybot-image\b|\bHoowwwer\b|\bHostcrawler\b|\bHsft - link scanner\b|\bHsft - lvu scanner\b|\bHslide\b|\bHt\://check\b|\bHtdig\b|\bHtml link validator\b|\bHTMLparser\b|\bHttplib\b|\bHTTP\:\:Lite\b|\bHTTrack\b|\bHuaweisymantecspider\b|\bHul-wax\b|\bHumanlinks\b|\bHybridBot\b|\bHyperestraier\b|\bHyperix\b|\bIblog\b|\bIbuena\b|\bIcab\b|\bIcds-ingestion\b|\bIchiro\b|\bIcopyright conductor\b|\bIDBot\b|\bIDG/UK\b|\bId-search\b|\bIeautodiscovery\b|\bIecheck\b|\bIhwebchecker\b|\bIiitbot\b|\bIim_405\b|\bIlseBot\b|\bIltrovatore\b|\bImagebot\b|\bImage Fetch\b|\bImage-fetcher\b|\bImagefortress\b|\bImageshereimagesthereimageseverywhere\b|\bImage stripper\b|\bImage Sucker\b|\bImagevisu\b|\bImds_monitor\b|\bImo-google-robot-intelink\b|\bInagist\.com url crawler\b|\bIndeedBot\b|\bIndexer\b|\bIndustry cortex webcrawler\b|\bIndylabs_marius\b|\bIndy Library\b|\bInelabot\b|\bInet32 ctrl\b|\bInetbot\b|\bInfolink\b|\bInfomine\b|\bInfoNaviRobot\b|\bInformant\b|\bInfo seeker\b|\bInfoseek sidewinder\b|\bInfoTekies\b|\bInfousabot\b|\bIngrid\b|\bInktomi\b|\bInsightscollector\b|\bInsightsworksbot\b|\bInspirebot\b|\bInstabid\b|\bInsumascout\b|\bIntelix\b|\bIntelliseek\b|\bInterGET\b|\bInternetlinkagent\b|\bInternet Ninja\b|\bInternet radio crawler\b|\bInternetSeer\b|\bInternetVista monitor\b|\bInterseek\b|\bIoi\b|\bIpadd bot\b|\bIps-agent\b|\bIpselonbot\b|\bIp-web-crawler\.com\b|\bIria\b|\bIRLbot\b|\bIron33\b|\bIsara\b|\bIsearch\b|\bIsilox\b|\bIskanie\b|\bIstellaBot\b|\bIts-learning crawler\b|\bIu_csci_b659_class_crawler\b|\bIvia\b|\bJadynave\b|\bJamesBOT\b|\bJbot\b|\bJbrofuzz\b|\bJemmathetourist\b|\bJennyBot\b|\bJetbot\b|\bJetbrains omea pro\b|\bJetCar\b|\bJikeSpider\b|\bJim\b|\bJobo\b|\bJobspider_ba\b|\bJoc\b|\bJOC Web Spider\b|\bJoedog\b|\bJoomla\b|\bJorgee\b|\bJoyscapebot\b|\bJspyda\b|\bJunut bot\b|\bJustView\b|\bJyxobot\b|\bKakclebot\b|\bKalooga\b|\bKatatudo-spider\b|\bKbeta1\b|\bKeepni web site monitor\b|\bKenjin\.spider\b|\bKenjin Spider\b|\bKeybot translation-search-machine\b|\bKeywenbot\b|\bKeyword\.density\b|\bKeyword Density\b|\bKinjabot\b|\bKitenga-crawler-bot\b|\bKiwistatus\b|\bKmbot-\b|\bKmccrew bot search\b|\bKnight\b|\bKnowitall\b|\bKnowledge\.com\b|\bKnowledge engine\b|\bKoepabot\b|\bKoninklijke\b|\bKorniki\b|\bKozmosbot\b|\bKrowler\b|\bKsbot\b|\bK\.s\.bot\b|\bKuloko-bot\b|\bKulturarw3\b|\bKummhttp\b|\bKurzor\b|\bKyluka crawl\b|\bLabhoo\b|\bLabourunions411\b|\bLachesis\b|\bLament\b|\bLamerexterminator\b|\bLanshanbot\b|\bLapozzbot\b|\bLarbin\b|\bLbot\b|\bLeaptag\b|\bLeechFTP\b|\bLeechGet\b|\bLetscrawl\.com\b|\bLexiBot\b|\bLexxebot\b|\bLftp\b|\bLibcrawl\b|\bLibiviacore\b|\bLibw\b|\bLibWeb\b|\bLibwhisker\b|\bLightspeedsystems\b|\bLikse\b|\bLinguee bot\b|\bLinkalarm\b|\bLinkbot\b|\bLinkcheck by siteimprove\.com\b|\bLinkchecker\b|\bLink_checker\b|\bLink checker\b|\bLinkcheck scanner\b|\bLinkdexbot\b|\bLinkdex\.com\b|\bLinkextractorPro\b|\bLinklint\b|\bLinklooker\b|\bLinkman\b|\bLinkpadBot\b|\bLinkScan\b|\bLinksManager\b|\bLinksmanager\.com_bot\b|\bLinks sql\b|\bLinksweeper\b|\bLink validator\b|\bLinkWalker\b|\bLinqiaMetadataDownloaderBot\b|\bLinqiaRSSBot\b|\bLinqiaScrapeBot\b|\bLipperhey\b|\bLitefinder\b|\bLitemage_walker\b|\bLitlrbot\b|\bLittle grabber at skanktale\.com\b|\bLivelapbot\b|\bLm harvester\b|\bLmqueuebot\b|\bLmspider\b|\bLNSpiderguy\b|\bLoadtimebot\b|\bLocalcombot\b|\bLocust\b|\bLolongbot\b|\bLookbot\b|\bLsearch\b|\bLssbot\b|\bLt scotland checklink\b|\bLtx71\b|\bL\.webis\b|\bLWP\b|\bLWP\:\:Simple\b|\bLwp-trivial\b|\bLycos_spider\b|\bLydia entity spider\b|\bLynnbot\b|\bLytranslate\b|\bMagnet\b|\bMag-Net\b|\bMagpie-crawler\b|\bMagus bot\b|\bMail\.ru\b|\bMail\.RU_Bot\b|\bMainseek_bot\b|\bMajestic12\b|\bMammoth\b|\bMap robot\b|\bMarkMonitor\b|\bMarkWatch\b|\bMasagool\b|\bMasidani_bot_\b|\bMasscan\b|\bMass Downloader\b|\bMata\.hari\b|\bMata Hari\b|\bMatentzn at cs dot man dot ac dot uk\b|\bMauiBot\b|\bMaxamine\.com\b|\bMaxomobot\b|\bMcbot\b|\bMeanpathbot\b|\bMediawords\b|\bMedrabbit\b|\bMegaIndex\.ru\b|\bMegite\b|\bMemacbot\b|\bMemo\b|\bMendeleybot\b|\bMercator-\b|\bMercuryboard_user_agent_sql_injection\.nasl\b|\bMetacarta\b|\bMetaeuro web search\b|\bMetager2\b|\bMetagloss\b|\bMetal crawler\b|\bMetaquerier\b|\bMetaspider\b|\bMetaspinner\b|\bMetauri\b|\bMfcrawler\b|\bMFC_Tear_Sample\b|\bMfhttpscan\b|\bMicrosoft Data Access\b|\bMicrosoft URL Control\b|\bMIDown tool\b|\bMIIxpc\b|\bMinibot\b|\bMinirank\b|\bMini-robot\b|\bMirror\b|\bMissigua locator\b|\bMister\.pix\b|\bMister PiX\b|\bMiva\b|\bMJ12bot\b|\bMnogosearch\b|\bMod_accessibility\b|\bModuna\.com\b|\bMoget\b|\bMojeek\b|\bMonkeycrawl\b|\bMorfeus Fucking Scanner\b|\bMoses\b|\bMowserbot\b|\bMqbot\b|\bMr\.4x3\b|\bMse360\b|\bMSFrontPage\b|\bMSIECrawler\b|\bMsindianwebcrawl\b|\bMsmobot\b|\bMsnptc\b|\bMsrabot\b|\bMsrbot\b|\bMS Web Services Client Protocol\b|\bMt-soft\b|\bMuhstik-scan\b|\bMultitext\b|\bMusobot\b|\bMyapp\b|\bMycompanybot\b|\bMycrawler\b|\bMyengines-us-bot\b|\bMyfamilybot\b|\bMy-heritrix-crawler\b|\bMy_little_searchengine_project\b|\bMyra\b|\bNabot\b|\bNajdi\.si\b|\bNambu\b|\bName Intelligence\b|\bNameprotect\b|\bNasa search\b|\bNatchcvs\b|\bNatweb-bad-link-mailer\b|\bNaver\b|\bNavroad\b|\bNearSite\b|\bNec-meshexplorer\b|\bNeedle\b|\bNeosciocrawler\b|\bNerdbynature\.bot\b|\bNerdybot\b|\bNerima-crawl-\b|\bNessus\b|\bNestreader\b|\bNetAnts\b|\bNetcarta cyberpilot pro\b|\bNetcraft\b|\bNetEstate NE Crawler\b|\bNetexperts\b|\bNetid\.com bot\b|\bNetLyzer\b|\bNetMechanic\b|\bNetprospector\b|\bNetresearchserver\b|\bNetseer\b|\bNetshift\b|\bNetsongbot\b|\bNetsparker\b|\bNetSpider\b|\bNetsrcherp\b|\bNettrack\b|\bNet\:\:trackback\b|\bNet Vampire\b|\bNetvibes\b|\bNetZIP\b|\bNewmedhunt\b|\bNews bot\b|\bNewsgatherer\b|\bNewsgroupreporter\b|\bNews_search_app\b|\bNewstrovebot\b|\bNextGenSearchBot\b|\bNextthing\.org\b|\bNibbler\b|\bNicebot\b|\bNICErsPRO\b|\bNiki-bot\b|\bNikto\b|\bNimbleCrawler\b|\bNimbus-1\b|\bNinetowns\b|\bNinja\b|\bNjuicebot\b|\bNlese\b|\bNmap\b|\bNogate\b|\bNorbert the spider\b|\bNoteworthybot\b|\bNPbot\b|\bNrcan intranet crawler\b|\bNsdl_search_bot\b|\bNuggetize\.com bot\b|\bNusearch spider\b|\bNutch\b|\bNu_tch\b|\bNwspider\b|\bNymesis\b|\bNys-crawler\b|\bObjectssearch\b|\bOBot\b|\bObvius external linkcheck\b|\bOcelli\b|\bOctopus\b|\bOdp entries t_st\b|\bOegp\b|\bOffline\.explorer\b|\bOffline Explorer\b|\bOffline Navigator\b|\bOgspider\b|\bOmiexplorer_bot\b|\bOmniexplorer\b|\bOmnifind\b|\bOmniweb\b|\bOnetszukaj\b|\bOnline link validator\b|\bOozbot\b|\bOpenbot\b|\bOpenfind\b|\bOpenintelligencedata\b|\bOpenisearch\b|\bOpenLinkProfiler\b|\bOpenlink virtuoso rdf crawler\b|\bOpensearchserver_bot\b|\bOpenVAS\b|\bOpidig\b|\bOptidiscover\b|\bOracle secure enterprise search\b|\bOracle ultra search\b|\bOrangeBot\b|\bOrangeSpider\b|\bOrisbot\b|\bOrnl_crawler\b|\bOrnl_mercury\b|\bOsis-project\.jp\b|\bOso\b|\bOutclicksBot\b|\bOutfoxBot\b|\bOutfoxmelonbot\b|\bOwler-bot\b|\bOwsbot\b|\bOzelot\b|\bP3p client\b|\bPageAnalyzer\b|\bPage Analyzer\b|\bPagebiteshyperbot\b|\bPagebull\b|\bPagedown\b|\bPagefetcher\b|\bPageGrabber\b|\bPagepeeker\b|\bPagerank monitor\b|\bPage scorer\b|\bPageScorer\b|\bPage_verifier\b|\bPamsnbot\.htm\b|\bPanopy bot\b|\bPanscient\b|\bPansophica\b|\bPapa Foto\b|\bPaperlibot\b|\bParasite\b|\bParsijoo\b|\bPathtraq\b|\bPattern\b|\bPatwebbot\b|\bPavuk\b|\bPaxleframework\b|\bPbbot\b|\bPcBrowser\b|\bPcore-http\b|\bPd-crawler\b|\bPECL\:\:HTTP\b|\bPenthesila\b|\bPeoplePal\b|\bPerform_crawl\b|\bPerman\b|\bPersonal ultimate crawler\b|\bPHPCrawl\b|\bPhpdig\b|\bPhp version tracker\b|\bPicosearch\b|\bPicscout\b|\bPicsearch\b|\bPictureFinder\b|\bPieno robot\b|\bPimonster\b|\bPi-Monster\b|\bPipbot\b|\bPipeliner\b|\bPita\b|\bPixfinder\b|\bPixray\b|\bPiyushbot\b|\bPlanetwork bot search\b|\bPleaseCrawl\b|\bPlucker\b|\bPlukkie\b|\bPlumanalytics\b|\bPlumtree\b|\bPockey\b|\bPocohttp\b|\bPOE-Component-Client-HTTP\b|\bPogodak\.ba\b|\bPogodak\.co\.yu\b|\bPoirot\b|\bPolybot\b|\bPompos\b|\bPoodle predictor\b|\bPopscreenbot\b|\bPostpost\b|\bPrivacyfinder\b|\bProbethenet\b|\bProjectwf-java-test-crawler\b|\bProPowerBot\b|\bProWebWalker\b|\bProxem websearch\b|\bProximic\b|\bProxy crawler\b|\bPsbot\b|\bPss-bot\b|\bPsycheclone\b|\bPub-crawler\b|\bPucl\b|\bPulsebot\b|\bPump\b|\bPwebot\b|\bPxBroker\b|\bPyCurl\b|\bQeavis agent\b|\bQfkbot\b|\bQualidade\b|\bQualidator\.com bot\b|\bQuepasacreep\b|\bQueryn\.metasearch\b|\bQueryn metasearch\b|\bQueryN Metasearch\b|\bQuest\.durato\b|\bQuick-Crawler\b|\bQuintura-crw\b|\bQunarbot\b|\bQwantify\b|\bQweerybot\b|\bQweery_robot\.txt_checkbot\b|\bR2ibot\b|\bR6_commentreader\b|\bR6_feedfetcher\b|\bR6_votereader\b|\bRabot\b|\bRadian6\b|\bRadiation retriever\b|\bRampybot\b|\bRankActive\b|\bRankFlex\b|\bRankingBot\b|\bRankingBot2\b|\bRankivabot\b|\bRankur\b|\bRankurBot\b|\bRational sitecheck\b|\bRcstartbot\b|\bRealDownload\b|\bReaper\b|\bRebelMouse\b|\bRebi-shoveler\b|\bRecorder\b|\bRedbot\b|\bRedcarpet\b|\bRedesScrapy\b|\bReGet\b|\bRepoMonkey\b|\bResearch robot\b|\bRiddler\b|\bRiight\b|\bRipper\b|\bRisenetbot\b|\bRiverglassscanner\b|\bRobopal\b|\bRobosourcer\b|\bRobotek\b|\bRobozilla\b|\bRocketCrawler\b|\bRoger\b|\bRogerbot\b|\bRome client\b|\bRondello\b|\bRotondo\b|\bRoverbot\b|\bRpt-httpclient\b|\bRtgibot\b|\bRufusbot\b|\bRunnk online rss reader\b|\bRunnk rss aggregator\b|\bS2bot\b|\bSafaribookmarkchecker\b|\bSafednsbot\b|\bSafetynet robot\b|\bSaladspoon\b|\bSalesIntelligent\b|\bSapienti\b|\bSapphireweb\b|\bSBIder\b|\bSbl-bot\b|\bScanAlert\b|\bScanbot\b|\bScan\.lol\b|\bScfcrawler\b|\bScich\b|\bScientificcommons\.org\b|\bScollspider\b|\bScooperbot\b|\bScooter\b|\bScoutjet\b|\bScrapebox\b|\bScrapy\b|\bScrawltest\b|\bScreaming\b|\bScreenerBot\b|\bScrubby\b|\bScspider\b|\bScumbot\b|\bSearcharoo\.net\b|\bSearchblox\b|\bSearchbot\b|\bSearch-channel\b|\bSearchengine\b|\bSearch-engine-studio\b|\bSearchestate\b|\bSearchhippo\.com\b|\bSearchit-bot\b|\bSearch\.kumkie\.com\b|\bSearchmarking\b|\bSearchmarks\b|\bSearchmee\b|\bSearchmetricsBot\b|\bSearchmining\b|\bSearchnowbot\b|\bSearchpreview\b|\bSearch publisher\b|\bSearchspider\.com\b|\bSearch\.updated\.com\b|\bSearch\.usgs\.gov\b|\bSearch x-bot\b|\bSearqubot\b|\bSeb spider\b|\bSeekbot\b|\bSeeker\.lookseek\.com\b|\bSeeqbot\b|\bSeeqpod-vertical-crawler\b|\bSelflinkchecker\b|\bSemager\b|\bSemanticdiscovery\b|\bSemantifire\b|\bSemisearch\b|\bSemrush\b|\bSemrushBot\b|\bSeoengworldbot\b|\bSEOkicks\b|\bSEOlyticsCrawler\b|\bSeomoz\b|\bSEOprofiler\b|\bSeoscanners\b|\bSEOstats\b|\bSexsearcher\b|\bSeznam\b|\bSeznamBot\b|\bShablastbot\b|\bShadowwebanalyzer\b|\bShareaza\b|\bShelob\b|\bSherlock\b|\bShim-crawler\b|\bShodan\b|\bShopsalad\b|\bShopwiki\b|\bShowlinks\b|\bShowyoubot\b|\bSiclab\b|\bSilk\b|\bSimplepie\b|\bSiphon\b|\bSISTRIX\b|\bSitebeam\b|\bSitebot\b|\bSitecheck\b|\bSiteExplorer\b|\bSitefinder\b|\bSiteguardbot\b|\bSiteimprove\b|\bSiteLockSpider\b|\bSiteorbiter\b|\bSiteSnagger\b|\bSiteSucker\b|\bSite Sucker\b|\bSitesweeper\b|\bSitevigil\b|\bSitexpert\b|\bSkimbot\b|\bSkimwordsbot\b|\bSkreemrbot\b|\bSkywalker\b|\bSlackbot-LinkExpanding\b|\bSleipnir\b|\bSlow-crawler\b|\bSlySearch\b|\bSmart-crawler\b|\bSmartDownload\b|\bSmarte bot\b|\bSmartwit\.com\b|\bSMTBot\b|\bSnake\b|\bSnapbot\b|\bSnap\.com beta crawler\b|\bSnappreviewbot\b|\bSnappy\b|\bSnookit\b|\bSnooper\b|\bSnoopy\b|\bSocialRankIOBot\b|\bSocietyrobot\b|\bSocscibot\b|\bSoft411 directory\b|\bSogou\b|\bsogouspider\b|\bSogou web spider\b|\bSohu agent\b|\bSohu-search\b|\bSokitomi crawl\b|\bSolbot\b|\bSondeur\b|\bSootle\b|\bSosospider\b|\bSottopop\b|\bSpacebison\b|\bSpace bison\b|\bSpaceBison\b|\bSpace fung\b|\bSpammen\b|\bSpankBot\b|\bSpanner\b|\bSpatineo monitor controller\b|\bSpatineo serval controller\b|\bSpatineo serval getmapbot\b|\bSpbot\b|\bSpecial_archiver\b|\bSpeedy\b|\bSphere scout\b|\bSphider\b|\bSpiderengine\b|\bSpiderku\b|\bSpiderman\b|\bSpider\.terranautic\.net\b|\bSpinn3r\b|\bSpinne\b|\bSportcrew-bot\b|\bSproose\b|\bSputnikBot\b|\bSpyder3\.microsys\.com\b|\bSqlmap\b|\bSqlworm\b|\bSquidclamav_redirector\b|\bSquid-prefetch\b|\bSq webscanner\b|\bSqworm\b|\bSrevbot\b|\bSslbot\b|\bSsm agent\b|\bS~stremor-crawler\b|\bStackrambler\b|\bStardownloader\b|\bStatbot\b|\bStatcrawler\b|\bStatedept-crawler\b|\bSteeler\b|\bStegmann-bot\b|\bStero\b|\bStripper\b|\bStumbler\b|\bSuchclip\b|\bSucker\b|\bSucuri\b|\bSumeetbot\b|\bSumitbot\b|\bSummizebot\b|\bSummizefeedreader\b|\bSunrise xp\b|\bSuperBot\b|\bSuperHTTP\b|\bSuperlumin downloader\b|\bSuperpagesbot\b|\bSupremesearch\.net\b|\bSupybot\b|\bSurdotlybot\b|\bSurf\b|\bSurfbot\b|\bSurveyBot\b|\bSuzuran\b|\bSwebot\b|\bSwiftbot\b|\bSwish-e\b|\bSygolbot\b|\bSynapticwalker\b|\bSyntryx ant scout chassis pheromone\b|\bSysscan\b|\bSystemsearch-robot\b|\bSzukacz\b|\bT0PHackTeam\b|\bT8Abot\b|\bTailrank\b|\bTAkeOut\b|\bTalkro web-shot\b|\bTamu_crawler\b|\bTapuzbot\b|\bTarantula\b|\bTargetblaster\.com\b|\bTargetyournews\.com bot\b|\bTausdatabot\b|\bTaxinomiabot\b|\bTeamsoft wininet component\b|\bTecomi bot\b|\bTeezirbot\b|\bTeleport\b|\bTeleportPro\b|\bTelesoft\b|\bTelesphoreo\b|\bTelesphorep\b|\bTeradex mapper\b|\bTeragram_crawler\b|\bTerrawizbot\b|\bTestbot\b|\bTesting of bot\b|\bTextbot\b|\bThatrobotsite\.com\b|\bThe dyslexalizer\b|\bThe\.intraformant\b|\bThe Intraformant\b|\bTheNomad\b|\bTheophrastus\b|\bTheusefulbot\b|\bThumbbot\b|\bThumbnail\.cz robot\b|\bThumbshots-de-bot\b|\bT-h-u-n-d-e-r-s-t-o-n-e\b|\bTigerbot\b|\bTighttwatbot\b|\bTightTwatBot\b|\bTineye\b|\bTitan\b|\bToata\b|\bTocrawl\b|\bTo-dress_ru_bot_\b|\bTo-night-bot\b|\bTopicalizer\b|\bTopicblogs\b|\bToplistbot\b|\bTopserver php\b|\bTopyx-crawler\b|\bTouche\b|\bTourlentascanner\b|\bToweyabot\b|\bTpsystem\b|\bTraazi\b|\bTracemyfile\b|\bTransgenikbot\b|\bTravelbot\b|\bTravellazerbot\b|\bTravel-search\b|\bTreezy\b|\bTrendiction\b|\bTrendictionbot\b|\bTrendiction\.com\b|\bTrendiction\.de\b|\bTrex\b|\bTridentspider\b|\bTrovator\b|\bTrue_Robot\b|\bTscholarsbot\b|\bTsm translation-search-machine\b|\bTswebbot\b|\bTulipchain\b|\bTuringos\b|\bTurnitin\b|\bTurnitinBot\b|\bTutorgigbot\b|\bTweetedtimes bot\b|\bTweetmemebot\b|\bTwengaBot\b|\bTwice\b|\bTwikle\b|\bTwinuffbot\b|\bTwisted pagegetter\b|\bTwitturls\b|\bTwitturly\b|\bTygobot\b|\bTygoprowler\b|\bTyphoeus\b|\bUberbot\b|\bUcb-nutch\b|\bUdmsearch\b|\bUfam-crawler-\b|\bUltraseek\b|\bUnchaos\b|\bUnidentified\b|\bUnisterBot\b|\bUnitek uniengine\b|\bUniversalsearch\b|\bUnwindfetchor\b|\bUoftdb_experiment\b|\bUpdated\b|\bUrlappendbot\b|\bUrlblaze\b|\bUrlchecker\b|\bUrl-checker\b|\bUrlck\b|\bUrl control\b|\bUrldispatcher\b|\bUrl_gather\b|\bUrlspiderpro\b|\bURLy\.Warning\b|\bURLy Warning\b|\bUsaf afkn k2spider\b|\bUsasearch\b|\bU\.s\. government printing office\b|\bUss-cosmix\b|\bUsyd-nlp-spider\b|\bVacobot\b|\bVacuum\b|\bVadixbot\b|\bVagabondo\b|\bValidator\b|\bValkyrie\b|\bVB Project\b|\bVbseo\b|\bVCI\b|\bVci webviewer vci webviewer win32\b|\bVerbstarbot\b|\bVeriCiteCrawler\b|\bVerifactrola\b|\bVerity-url-gateway\b|\bVermut\b|\bVersus crawler\b|\bVersus\.integis\.ch\b|\bViasarchivinginformation\.html\b|\bVidibleScraper\b|\bVipr\b|\bVirus_detector\b|\bVirus-detector\b|\bVirusdie\b|\bVisbot\b|\bVishal for clia\b|\bVisweb\b|\bVital search'n urchin\b|\bVlad\b|\bVlsearch\b|\bVmbot\b|\bVocusbot\b|\bVoidEYE\b|\bVoil\b|\bVoilabot\b|\bVoltron\b|\bVortex\b|\bVoyager\b|\bVspider\b|\bW3c_unicorn\b|\bW3c-webcon\b|\bW3search\b|\bWacbot\b|\bWallpapers/3\.0\b|\bWallpapersHD\b|\bWanadoo\b|\bWASALive-Bot\b|\bWastrix\b|\bWater conserve portal\b|\bWater conserve spider\b|\bWatzbot\b|\bWauuu\b|\bWavefire\b|\bWaypath\b|\bWazzup\b|\bWbdbot\b|\bWBSearchBot\b|\bWeb-agent\b|\bWebalta\b|\bWebaltbot\b|\bWebAuto\b|\bWeb Auto\b|\bWebBandit\b|\bWebbot\b|\bWebbul-bot\b|\bWebcapture\b|\bWeb ceo online robot\b|\bWebcheck\b|\bWebclipping\.com\b|\bWebCollage\b|\bWeb Collage\b|\bWebCopier\b|\bWebcopy\b|\bWebcorp\b|\bWebcrawler\b|\bWeb crawler\b|\bWebcrawl\.net\b|\bWebdatacentrebot\b|\bWEBDAV\b|\bWeb downloader\b|\bWebdownloader for x\b|\bWebdup\b|\bWebemailextrac\b|\bWebEnhancer\b|\bWeb Enhancer\b|\bWebFetch\b|\bWeb Fetch\b|\bWebFuck\b|\bWeb Fuck\b|\bWebgather\b|\bWebgobbler\b|\bWebGo IS\b|\bWeb\.image\.collector\b|\bWeb image collector\b|\bWebImageCollector\b|\bWebimages\b|\bWebinator-search2\b|\bWebinator-wbi\b|\bWebindex\b|\bWeblayers\b|\bWebLeacher\b|\bWeblexbot\b|\bWeblinker\b|\bWeb link validator\b|\bWeblyzard\b|\bWeb magnet\b|\bWebmastercoffee\b|\bWebmasterworld extractor\b|\bWebmasterWorldForumBot\b|\bWebmeup-crawler\b|\bWebminer\b|\bWebmoose\b|\bWebot\b|\bWebPix\b|\bWeb Pix\b|\bWebReaper\b|\bWebripper\b|\bWebSauger\b|\bWeb Sauger\b|\bWebscan\b|\bWebsearchbench\b|\bWebshag\b|\bWebsite\b|\bWeb site downloader\b|\bWebsiteExtractor\b|\bWebsiteQuester\b|\bWebsite Quester\b|\bWeb-sniffer\b|\bWebspear\b|\bWebsphinx\b|\bWebspider\b|\bWebster\b|\bWebStripper\b|\bWebSucker\b|\bWeb Sucker\b|\bWebtrafficexpress\b|\bWebtrends link analyzer\b|\bWebvac\b|\bWebwalk\b|\bWebwasher\b|\bWebwatch\b|\bWebWhacker\b|\bWebxm\b|\bWebZIP\b|\bWeddings\.info\b|\bWenbin\b|\bWepa\b|\bWep search\b|\bWerelatebot\b|\bWeSEE\b|\bWhack\b|\bWhacker\b|\bWhatweb\b|\bWhirlpool web engine\b|\bWho\.is Bot\b|\bWhowhere robot\b|\bWidow\b|\bWikiabot\b|\bWikio\b|\bWikiwix-bot-\b|\bWinhttp\b|\bWinHTTrack\b|\bWire\b|\bWisebot\b|\bWiseGuys Robot\b|\bWISENutbot\b|\bWish-la\b|\bWish-project\b|\bWisponbot\b|\bWmcai-robot\b|\bWminer\b|\bWmsbot\b|\bWonderbot\b|\bWoobot\b|\bWoriobot\b|\bWorldshop\b|\bWorqmada\b|\bWotbox\b|\bWprecon\b|\bWPScan\b|\bWume_crawler\b|\bWww collector\b|\bWww-collector-e\b|\bWWW-Collector-E\b|\bWww-mechanize\b|\bWWW-Mechanize\b|\bWWW\:\:Mechanize\b|\bWWWOFFLE\b|\bWwwrobot\b|\bWwwster\b|\bWwwwanderer\b|\bWwwxref\b|\bWysigot\b|\bX09Mozilla\b|\bX22Mozilla\b|\bXaldon\b|\bXaldon_WebSpider\b|\bXaldon WebSpider\b|\bX-clawler\b|\bX-crawler\b|\bXenu\b|\bXerka metabot\b|\bXerka webbot\b|\bXget\b|\bXirq\b|\bXmarksfetch\b|\bXpymep1\.exe\b|\bXqrobot\b|\bYacybot\b|\bYacy\.net\b|\bYanga worldsearch bot\b|\bYarienavoir\.net\b|\bYasaklibot\b|\bYats crawler\b|\bYbot\b|\bYebolbot\b|\bYellowjacket\b|\bYeti\b|\bY\!j\b|\bYolinkbot\b|\bYooglifetchagent\b|\bYoono\b|\bYottacars_bot\b|\bYoudaoBot\b|\bYourls\b|\bZ-add link checker\b|\bZade\b|\bZagrebin\b|\bZao\b|\bZauba\b|\bZauba\.io\b|\bZedzo\.validate\b|\bZermelo\b|\bZeus\b|\bZgrab\b|\bZibber-v\b|\bZimeno\b|\bZing-bottabo\b|\bZipppbot\b|\bZitebot\b|\bZmEu\b|\bZongbot\b|\bZoomspider\b|\bZotag search\b|\bZsebot\b|\bZuibot\b|\bZumBot\b|\bZyBorg\b|\bZyte\b|\bapplebot\b|\barchive\.org_bot\b|\bBaidu\b|\bBaiduspider\b|\bCFNetwork\b|\bFirefox/21\.0\b|\bia_archiver\b|\bMozilla/4\.76\b|\bMSIE 5\.\b|\bMSIE 6\.0\b|\bQwantify\b|\bSafeDNSBot\b|\bUptimebot\b|\bYahoo\! Slurp\b|\bSeekport\b
failregex = (?i)<HOST> -.*"(GET|POST|HEAD|OPTIONS).*HTTP.*(?:%(badbotscustom)s|%(badbots)s).*"$
ignoreregex =
[badbots]
enabled = true
port = http,https
filter = badbots
logpath = /var/log/virtualmin/*_access_log
maxretry = 1
findtime = 3600
bantime = 300
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment