From: eldy <> Date: Fri, 25 Jan 2008 18:25:02 +0000 (+0000) Subject: Update robot X-Git-Tag: AWSTATS_6_8_BETA~33 X-Git-Url: http://git.ipfire.org/cgi-bin/gitweb.cgi?a=commitdiff_plain;h=fcf5a4045074f0295bd18ffda0bf06e3d7c513e8;p=thirdparty%2FAWStats.git Update robot --- diff --git a/wwwroot/cgi-bin/lib/robots.pm b/wwwroot/cgi-bin/lib/robots.pm index 72d9f6b8..962a9334 100644 --- a/wwwroot/cgi-bin/lib/robots.pm +++ b/wwwroot/cgi-bin/lib/robots.pm @@ -302,8 +302,8 @@ # added Z-Add Link Checker http://w3.z-add.co.uk/linkcheck/ # -- fix - some robots were reported with _ where _ should have been a space. # changed Xenu Link Sleuth -# changed microsoft\_url\_control -> microsoft\surl\scontrol -# changed favorites\ssweeper -> favorites\ssweeper +# changed microsoft\_url\_control -> microsoft_url_control +# changed favorites_sweeper -> favorites_sweeper # -- updates # updated AskJeeves to Ask @@ -341,7 +341,7 @@ 'contentmatch', 'ferret', 'googlebot', -'google-sitemaps', +'google\-sitemaps', 'gulliver', 'virus\_detector', # Must be before harvest 'harvest', @@ -354,7 +354,7 @@ 'myweb', 'nomad', 'scooter', -'yahoo!\sslurp\schina', # Must come before singluar slurp or yahoo +'yahoo!_slurp_china', # Must come before singluar slurp or yahoo 'slurp', '^voyager\/', 'weblayers', @@ -598,7 +598,7 @@ 'suntek', 'sven', 'tach_bw', -'tagyu\sagent', +'tagyu_agent', 'tailrank', 'tarantula', 'tarspider', @@ -653,14 +653,14 @@ 'wz101', 'xget', # Other robots reported by users -'1\-more\sscanner', +'1\-more_scanner', 'accoona\-ai\-agent', 'activebookmark', -'adamm\sbot', +'adamm_bot', 'almaden', 'aipbot', 'aleadsoftbot', -'alpha\ssearch\sagent', +'alpha_search_agent', 'aport', 'archive\.org_bot', 'argus', # Must be before nutch @@ -672,9 +672,9 @@ 'becomebot', 'bender', 'biglotron', -'bittorrent\sbot', -'biz360\sspider', -'blogbridge\sservice', +'bittorrent_bot', +'biz360_spider', +'blogbridge_service', 'bloglines', 'blogpulse', # added OpenWebSpider http://www.openwebspider.org/ @@ -714,20 +714,20 @@ 'bumblebee', 'candlelight\_favorites\_inspector', 'cbn00glebot', -'cerberian\sdrtrs', +'cerberian_drtrs', 'cfnetwork', 'cipinetbot', -'checkweb\slink\svalidator', +'checkweb_link_validator', 'commons\-httpclient', -'computer\sand\sautomation\sresearch\sinstitute\scrawler', +'computer_and_automation_research_institute_crawler', 'converamultimediacrawler', 'converacrawler', 'cscrawler', -'cse\shtml\svalidator\slite\sonline', +'cse_html_validator_lite_online', 'cuasarbot', 'cursor', 'custo', -'datafountains/dmoz\sdownloader', +'datafountains\/dmoz_downloader', 'daviesbot', 'daypopbot', 'deepindex', @@ -742,7 +742,7 @@ 'earthcom\.info', 'easydl', 'edgeio\-retriever', -'ets\sv', +'ets_v', 'exactseek', 'extreme\_picture\_finder', 'eventax', @@ -750,13 +750,13 @@ 'everest\-vulcan', 'ezresult', 'enteprise', -'fast\senterprise\scrawler.*crawleradmin\.t\-info@telekom\.de', -'fast\senterprise\scrawler.*t\-info_bi_cluster\scrawleradmin\.t\-info@telekom\.de', -'matrix\ss\.p\.a\.\s\-\sfast\senterprise\scrawler', # must come before fast enterprise crawler -'fast\senterprise\scrawler', +'fast_enterprise_crawler.*crawleradmin\.t\-info@telekom\.de', +'fast_enterprise_crawler.*t\-info_bi_cluster_crawleradmin\.t\-info@telekom\.de', +'matrix_s\.p\.a\._\-_fast_enterprise_crawler', # must come before fast enterprise crawler +'fast_enterprise_crawler', 'fast\-search\-engine', 'favorg', -'favorites\ssweeper', +'favorites_sweeper', 'feedburner', 'feedfetcher\-google', 'feedflow', @@ -765,19 +765,19 @@ 'feedvalidator', 'filmkamerabot', 'findlinks', -'findexa\scrawler', +'findexa_crawler', 'fooky\.com\/ScorpionBot', 'g2crawler', 'gaisbot', 'geniebot', 'gigabot', 'girafabot', -'global\sfetch', +'global_fetch', 'gnodspider', 'goforit\.com', 'goforitbot', 'grub', -'gpu\sp2p\scrawler', +'gpu_p2p_crawler', 'henrythemiragorobot', 'heritrix', 'holmes', @@ -803,7 +803,7 @@ 'jrtwine\_software\_check\_favorites\_utility', 'justview', 'kalambot', -'kamano\.de\snewsfeedverzeichnis', +'kamano\.de_newsfeedverzeichnis', 'kazoombot', 'kevin', 'keyoshid', # Must come before Y!J @@ -811,7 +811,7 @@ 'kinja\-imagebot', 'knowitall', 'knowledge\.com', -'kouaa\skrawler', +'kouaa_krawler', 'krugle', 'ksibot', 'kurzor', @@ -819,7 +819,7 @@ 'letscrawl\.com', 'libcrawl', 'linkbot', -'link\svalet\sonline', +'link_valet_online', 'metager\-linkchecker', # Must be before linkchecker 'linkchecker', 'livejournal\.com', @@ -831,22 +831,22 @@ 'mediapartners\-google', 'megite', 'metaspinner', -'microsoft\surl\scontrol', +'microsoft_url_control', 'mini\-reptile', 'minirank', -'missigua\slocator', +'missigua_locator', 'misterbot', 'miva', -'mizzu\slabs', +'mizzu_labs', 'mj12bot', 'mojeekbot', 'msiecrawler', -'ms\ssearch\s4\.0\srobot', +'ms_search_4\.0_robot', 'msrabot', 'msrbot', 'mt::telegraph::agent', 'nagios', -'nasa\ssearch', +'nasa_search', 'mydoyouhike', 'netluchs', 'netsprint', @@ -859,29 +859,29 @@ 'nutchosu\-vlib', 'nutch', # Must come after other nutch versions 'ocelli', -'octora\sbeta\sbot', +'octora_beta_bot', 'omniexplorer\_bot', 'onet\.pl\_sa', 'onfolio', 'opentaggerbot', 'openwebspider', -'oracle\sultra\ssearch', +'oracle_ultra_search', 'orbiter', 'yodaobot', 'qihoobot', 'passwordmaker\.org', -'pear\shttp\srequest\sclass', +'pear_http_request_class', 'peerbot', 'perman', 'php\_version\_tracker', -'php\sversion\stracker', +'php_version_tracker', 'pictureofinternet', 'ping\.blo\.gs', 'plinki', 'pluckfeedcrawler', 'pompos', 'popdexter', -'port\shuron\slabs', +'port_huron_labs', 'postfavorites', 'projectwf\-java\-test\-crawler', 'proodlebot', @@ -898,19 +898,19 @@ 'scumbot', 'searchguild\_dmoz\_experiment', 'seekbot', -'sensis\sweb\scrawler', +'sensis_web_crawler', 'seznambot', 'shim\-crawler', 'shoutcast', 'slysearch', -'snap\.com\sbeta\scrawler', +'snap\.com_beta_crawler', 'sohu\-search', 'sohu', # "sohu agent" 'snappy', -'sphere\sscout', -'sproose\scrawler', +'sphere_scout', +'sproose_crawler', 'steeler', -'steroid\s\sdownload', +'steroid__download', 'suchfin\-bot', 'superbot', 'surveybot', @@ -918,10 +918,10 @@ 'syndic8', 'syndicapi', 'synoobot', -'tcl\shttp\sclient\spackage', +'tcl_http_client_package', 'technoratibot', 'teragramcrawlersurf', -'test\scrawler', +'test_crawler', 'testbot', 't\-h\-u\-n\-d\-e\-r\-s\-t\-o\-n\-e', 'topicblogs', @@ -932,15 +932,15 @@ 'twiceler', 'ubicrawler', 'ultraseek', -'unchaos\sbot\shybrid\sweb\ssearch\sengine', +'unchaos_bot_hybrid_web_search_engine', 'unido\-bot', 'updated', 'ustc\-semantic\-group', 'vagabondo\-wap', 'vagabondo', 'vermut', -'versus\scrawler\sfrom\seda\.baykan@epfl\.ch', -'vespa\scrawler', +'versus_crawler_from_eda\.baykan@epfl\.ch', +'vespa_crawler', 'vortex', 'vse', 'w3c\-checklink', @@ -950,19 +950,19 @@ 'webclipping\.com', 'webcompass', 'webcrawl\.net', -'web\sdownloader', +'web_downloader', 'webdup', 'webfilter', 'webindexer', 'webminer', 'website\_monitoring\_bot', 'webvulncrawl', -'wells\ssearch', +'wells_search', 'wonderer', -'wume\scrawler', +'wume_crawler', 'wwweasel', -'xenu\'s\slink\ssleuth', -'xenu\slink\ssleuth', +'xenu\'s_link_sleuth', +'xenu_link_sleuth', 'xirq', 'y!j', # Must come after keyoshid Y!J 'yacy', @@ -972,10 +972,10 @@ 'yahooseeker\-testing', 'yahooseeker', 'yahoo\-mmcrawler', -'yahoo!\smindset', +'yahoo!_mindset', 'yandex', 'yooglifetchagent', -'z\-add\slink\schecker', +'z\-add_link_checker', 'zealbot', 'zhuaxia', 'zspider', @@ -1007,7 +1007,7 @@ 'ferret','Wild Ferret Web Hopper #1, #2, #3', 'contentmatch','Yahoo!China ContentMatch Crawler', 'googlebot','Googlebot', -'google-sitemaps', 'Google Sitemaps', +'google\-sitemaps', 'Google Sitemaps', 'gulliver','Northern Light Gulliver', 'virus\_detector','virus_detector', 'harvest','Harvest', @@ -1020,7 +1020,7 @@ 'myweb','Internet Shinchakubin', 'nomad','Nomad', 'scooter','Scooter', -'yahoo!\sslurp\schina','Yahoo! Slurp China', +'yahoo!_slurp_china','Yahoo! Slurp China', 'slurp','Yahoo Slurp', '^voyager\/','Voyager', 'weblayers','Weblayers', @@ -1264,7 +1264,7 @@ 'suntek','suntek search engine', 'sven','Sven', 'tach_bw','TACH Black Widow', -'tagyu\sagent','Tagyu Agent', +'tagyu_agent','Tagyu Agent', 'tarantula','Tarantula', 'tarspider','tarspider', 'tailrank','TailRank', @@ -1319,14 +1319,14 @@ 'wz101','WebZinger', 'xget','XGET', # Other robots reported by users -'1\-more\sscanner','1-More Scanner', +'1\-more_scanner','1-More Scanner', 'accoona\-ai\-agent','Accoona-AI-Agent', 'activebookmark','ActiveBookmark', -'adamm\sbot','AdamM Bot', +'adamm_bot','AdamM Bot', 'almaden','IBM Almaden Research Center WebFountain™', 'aipbot','aipbot', 'aleadsoftbot','ALeadSoftbot', -'alpha\ssearch\sagent','Alpha Search Agent', +'alpha_search_agent','Alpha Search Agent', 'aport', 'Aport', 'archive\.org_bot','archive.org bot', 'argus','Argus', @@ -1338,9 +1338,9 @@ 'becomebot', 'BecomeBot', 'bender','bender focused_crawler', 'biglotron','Biglotron', -'bittorrent\sbot','BitTorrent Bot', -'biz360\sspider','Biz360 spider', -'blogbridge\sservice','BlogBridge Service', +'bittorrent_bot','BitTorrent Bot', +'biz360_spider','Biz360 spider', +'blogbridge_service','BlogBridge Service', 'bloglines','Bloglines', 'blogpulse','BlogPulse ISSpider intelliseek.com', 'blogsearch','BlogSearch', @@ -1355,19 +1355,19 @@ 'bumblebee', 'Bumblebee (relevare.com)', 'candlelight\_favorites\_inspector','Candlelight_Favorites_Inspector', 'cbn00glebot','cbn00glebot', -'cerberian\sdrtrs','Cerberian Drtrs', +'cerberian_drtrs','Cerberian Drtrs', 'cfnetwork','CFNetwork', 'cipinetbot','CipinetBot', -'checkweb\slink\svalidator','CheckWeb link validator', +'checkweb_link_validator','CheckWeb link validator', 'commons\-httpclient','Jakarta commons-httpclient', -'computer\sand\sautomation\sresearch\sinstitute\scrawler','Computer and Automation Research Institute Crawler', +'computer_and_automation_research_institute_crawler','Computer and Automation Research Institute Crawler', 'converamultimediacrawler','ConveraMultiMediaCrawler', 'converacrawler','ConveraCrawler', 'cscrawler','CsCrawler', -'cse\shtml\svalidator\slite\sonline','CSE HTML Validator Lite Online','cuasarbot','Cuasarbot', +'cse_html_validator_lite_online','CSE HTML Validator Lite Online','cuasarbot','Cuasarbot', 'cursor','Cursor', 'custo','Custo', -'datafountains/dmoz\sdownloader','DataFountains/DMOZ Downloader', +'datafountains\/dmoz_downloader','DataFountains/DMOZ Downloader', 'daviesbot', 'DaviesBot', 'daypopbot', 'DayPop', 'deepindex','Deepindex', @@ -1382,7 +1382,7 @@ 'earthcom\.info','EARTHCOM.info', 'easydl','EasyDL', 'edgeio\-retriever','edgeio-retriever', -'ets\sv','ETS Enterprise Translation Server', +'ets_v','ETS Enterprise Translation Server', 'exactseek','ExactSeek Crawler', 'extreme\_picture\_finder','Extreme_Picture_Finder', 'eventax','eventax', @@ -1391,12 +1391,12 @@ 'ezresult', 'Ezresult', 'enteprise','Fast Enteprise Crawler', 'fast\-search\-engine','Fast-Search-Engine (not fastsearch.com)', -'fast\senterprise\scrawler','FAST Enterprise Crawler', -'fast\senterprise\scrawler.*scrawleradmin\.t\-info@telekom\.de','FAST Enterprise Crawler * crawleradmin.t-info@telekom.de', -'matrix\ss\.p\.a\.\s\-\sfast\senterprise\scrawler','Matrix S.p.A. - FAST Enterprise Crawler', -'fast\senterprise\scrawler.*t\-info_bi_cluster\scrawleradmin\.t\-info@telekom\.de','FAST Enterprise Crawler * T-Info_BI_cluster crawleradmin.t-info@telekom.de', +'fast_enterprise_crawler','FAST Enterprise Crawler', +'fast_enterprise_crawler.*scrawleradmin\.t\-info@telekom\.de','FAST Enterprise Crawler * crawleradmin.t-info@telekom.de', +'matrix_s\.p\.a\._\-_fast_enterprise_crawler','Matrix S.p.A. - FAST Enterprise Crawler', +'fast_enterprise_crawler.*t\-info_bi_cluster_crawleradmin\.t\-info@telekom\.de','FAST Enterprise Crawler * T-Info_BI_cluster crawleradmin.t-info@telekom.de', 'favorg','FavOrg', -'favorites\ssweeper','Favorites Sweeper', +'favorites_sweeper','Favorites Sweeper', 'feedburner', 'Feedburner', 'feedfetcher\-google','Feedfetcher-Google', 'feedflow','FeedFlow', @@ -1404,7 +1404,7 @@ 'feedsky','FeedSky', 'feedvalidator','FeedValidator', 'filmkamerabot','FilmkameraBot', -'findexa\scrawler','Findexa Crawler', +'findexa_crawler','Findexa Crawler', 'geniebot','Geniebot', 'findlinks','Findlinks', 'fooky\.com\/ScorpionBot','Fooky.com/ScorpionBot/ScoutOut', @@ -1412,11 +1412,11 @@ 'gaisbot','Gaisbot', 'gigabot','GigaBot', 'girafabot','Girafabot', -'global\sfetch','Global Fetch', +'global_fetch','Global Fetch', 'gnodspider','GNOD Spider', 'goforit\.com','GoForIt.com', 'goforitbot','GOFORITBOT', -'gpu\sp2p\scrawler','GPU p2p crawler', +'gpu_p2p_crawler','GPU p2p crawler', 'grub','Grub.org', 'henrythemiragorobot', 'Mirago', 'heritrix','Heritrix', @@ -1443,7 +1443,7 @@ 'jrtwine\_software\_check\_favorites\_utility','JRTwine_Software_Check_Favorites_Utility', 'justview', 'JustView', 'kalambot','KalamBot', -'kamano\.de\snewsfeedverzeichnis','kamano.de NewsFeedVerzeichnis', +'kamano\.de_newsfeedverzeichnis','kamano.de NewsFeedVerzeichnis', 'kazoombot','KazoomBot', 'kevin','Kevin', 'keyoshid','Yahoo! Japan keyoshid robot study', @@ -1451,14 +1451,14 @@ 'kinja\-imagebot', 'Kinja Imagebot', 'knowitall','KnowItAll', 'knowledge\.com','Knowledge.com', -'kouaa\skrawler','Kouaa Krawler', +'kouaa_krawler','Kouaa Krawler', 'krugle','Krugle', 'ksibot','ksibot', 'kurzor','Kurzor', 'lanshanbot','lanshanbot', 'letscrawl\.com','LetsCrawl.com', 'libcrawl','Crawl libcrawl', -'link\svalet\sonline','Link Valet Online', +'link_valet_online','Link Valet Online', 'linkbot','LinkBot', 'linkchecker','LinkChecker', 'livejournal\.com', 'LiveJournal.com', @@ -1468,23 +1468,23 @@ 'megite','Megite', 'metager\-linkchecker','MetaGer LinkChecker', 'metaspinner','Metaspinner', -'microsoft\surl\scontrol','Microsoft URL Control', +'microsoft_url_control','Microsoft URL Control', 'minirank','miniRank', 'mini\-reptile','Mini-reptile', -'missigua\slocator','Missigua_Locator', +'missigua_locator','Missigua_Locator', 'misterbot','Misterbot', 'miva','Miva', -'mizzu\slabs','Mizzu Labs', +'mizzu_labs','Mizzu Labs', 'mj12bot','MJ12bot', 'mojeekbot','MojeekBot', 'msiecrawler','MSIECrawler', -'ms\ssearch\s4\.0\srobot','MS SharePoint Portal Server - MS Search 4.0 Robot', +'ms_search_4\.0_robot','MS SharePoint Portal Server - MS Search 4.0 Robot', 'msrabot','msrabot', 'msrbot','MSRBOT', 'mt::telegraph::agent','MT::Telegraph::Agent', 'mydoyouhike','Mydoyouhike', 'nagios','Nagios', -'nasa\ssearch','NASA Search', +'nasa_search','NASA Search', 'netluchs','Netluchs', 'netsprint','NetSprint', 'newsgatoronline', 'NewsGator Online', @@ -1496,29 +1496,29 @@ 'nutchosu\-vlib','NutchOSU-VLIB', 'nutch','Nutch', 'ocelli','Ocelli', -'octora\sbeta\sbot','Octora Beta Bot', +'octora_beta_bot','Octora Beta Bot', 'omniexplorer\_bot','OmniExplorer Bot', 'onet\.pl\_sa','Onet.pl_SA', 'onfolio','Onfolio', 'opentaggerbot','OpenTaggerBot', 'openwebspider','OpenWebSpider', -'oracle\sultra\ssearch','Oracle Ultra Search', +'oracle_ultra_search','Oracle Ultra Search', 'orbiter','Orbiter', 'yodaobot','OutfoxBot/YodaoBot', 'qihoobot','QihooBot', 'passwordmaker\.org','passwordmaker.org', -'pear\shttp\srequest\sclass','PEAR HTTP Request class', +'pear_http_request_class','PEAR HTTP Request class', 'peerbot','PEERbot', 'perman', 'Perman surfer', 'php\_version\_tracker','PHP_version_tracker', -'php\sversion\stracker','PHP version tracker', +'php_version_tracker','PHP version tracker', 'pictureofinternet','PictureOfInternet', 'ping\.blo\.gs','ping.blo.gs', 'plinki','plinki', 'pluckfeedcrawler','PluckFeedCrawler', 'pompos','Pompos', 'popdexter','Popdexter', -'port\shuron\slabs','Port Huron Labs', +'port_huron_labs','Port Huron Labs', 'postfavorites','PostFavorites', 'projectwf\-java\-test\-crawler','ProjectWF-java-test-crawler', 'proodlebot','proodleBot', @@ -1536,18 +1536,18 @@ 'scumbot','Scumbot', 'searchguild\_dmoz\_experiment','SearchGuild_DMOZ_Experiment', 'seekbot','Seekbot', -'sensis\sweb\scrawler','Sensis Web Crawler', +'sensis_web_crawler','Sensis Web Crawler', 'seznambot','SeznamBot', 'shim\-crawler','Shim-Crawler', 'shoutcast','Shoutcast Directory Service', 'slysearch','SlySearch', -'snap\.com\sbeta\scrawler','snap.com beta crawler', +'snap\.com_beta_crawler','snap.com beta crawler', 'sohu\-search','sohu-search', 'sohu','sohu agent', 'snappy','Snappy', -'sphere\sscout','Sphere Scout', -'sproose\scrawler','sproose crawler', -'steroid\s\sdownload','STEROID Download', +'sphere_scout','Sphere Scout', +'sproose_crawler','sproose crawler', +'steroid__download','STEROID Download', 'steeler','Steeler', 'suchfin\-bot','Suchfin-Bot', 'superbot','SuperBot', @@ -1556,10 +1556,10 @@ 'syndic8','Syndic8', 'syndicapi','SyndicAPI', 'synoobot','SynooBot', -'tcl\shttp\sclient\spackage','Tcl http client package', +'tcl_http_client_package','Tcl http client package', 'technoratibot', 'Technoratibot', 'teragramcrawlersurf','TeragramCrawlerSURF', -'test\scrawler','Test Crawler', +'test_crawler','Test Crawler', 'testbot','TestBot', 't\-h\-u\-n\-d\-e\-r\-s\-t\-o\-n\-e','T-H-U-N-D-E-R-S-T-O-N-E', 'topicblogs', 'topicblogs', @@ -1570,15 +1570,15 @@ 'twiceler','twiceler', 'ubicrawler','UbiCrawler', 'ultraseek', 'Ultraseek', -'unchaos\sbot\shybrid\sweb\ssearch\sengine','UnChaos Bot Hybrid Web Search Engine', +'unchaos_bot_hybrid_web_search_engine','UnChaos Bot Hybrid Web Search Engine', 'unido\-bot','unido-bot', 'updated','updated', 'ustc\-semantic\-group','USTC-Semantic-Group', 'vagabondo\-wap','Vagabondo-WAP', 'vagabondo','Vagabondo', 'vermut','Vermut', -'versus\scrawler\sfrom\seda\.baykan@epfl\.ch','versus crawler from eda.baykan@epfl.ch', -'vespa\scrawler','Vespa Crawler', +'versus_crawler_from_eda\.baykan@epfl\.ch','versus crawler from eda.baykan@epfl.ch', +'vespa_crawler','Vespa Crawler', 'vortex','VORTEX', 'vse','VSE', 'w3c\-checklink','W3C Link Checker', @@ -1588,19 +1588,19 @@ 'webclipping\.com', 'WebClipping.com', 'webcompass', 'webcompass', 'webcrawl\.net','webcrawl.net', -'web\sdownloader','Web Downloader', +'web_downloader','Web Downloader', 'webdup','Webdup', 'webfilter','WebFilter', 'webindexer','WebIndexer', 'webminer','WebMiner', 'website\_monitoring\_bot','Website_Monitoring_Bot', 'webvulncrawl', 'WebVulnCrawl', -'wells\ssearch','Wells Search', +'wells_search','Wells Search', 'wonderer', 'Web Wombat Redback Spider', -'wume\scrawler','wume crawler', +'wume_crawler','wume crawler', 'wwweasel',,'WWWeasel', -'xenu\'s\slink\ssleuth','Xenu Link Sleuth', -'xenu\slink\ssleuth','Xenu Link Sleuth', +'xenu\'s_link_sleuth','Xenu Link Sleuth', +'xenu_link_sleuth','Xenu Link Sleuth', 'xirq','xirq', 'y!j', 'Y!J Yahoo Japan', 'yacy','yacy', @@ -1610,10 +1610,10 @@ 'yahooseeker\-testing', 'YahooSeeker-Testing', 'yahooseeker', 'YahooSeeker Yahoo! Blog crawler', 'yahoo\-mmcrawler', 'Yahoo-MMCrawler', -'yahoo!\smindset','Yahoo! Mindset', +'yahoo!_mindset','Yahoo! Mindset', 'yandex', 'Yandex bot', 'yooglifetchagent','yoogliFetchAgent', -'z\-add\slink\schecker','Z-Add Link Checker', +'z\-add_link_checker','Z-Add Link Checker', 'zealbot','ZealBot', 'zhuaxia','ZhuaXia', 'zspider','zspider',