From: eldy <> Date: Wed, 4 Sep 2013 09:08:03 +0000 (+0000) Subject: Update databases X-Git-Tag: AWSTATS_7_3~48 X-Git-Url: http://git.ipfire.org/cgi-bin/gitweb.cgi?a=commitdiff_plain;h=8fe90dedd23a03b3b991e283192c05db65bfa404;p=thirdparty%2FAWStats.git Update databases --- diff --git a/wwwroot/cgi-bin/lib/robots.pm b/wwwroot/cgi-bin/lib/robots.pm index 0ef9ea46..4b40f8f0 100644 --- a/wwwroot/cgi-bin/lib/robots.pm +++ b/wwwroot/cgi-bin/lib/robots.pm @@ -1256,11 +1256,13 @@ 'iaskspider','Sina Iask Spider', 'hl_ftien_spider','Hylanda', 'sogou','Sogou Spider', -'icjobs\.de', 'iCjobs Spider (only hits on robots.txt counted!)', -#The user agent string of the icjobs-spider seems to contain the -#identifying string only when it accesses the robots.txt file. -#When it accesses the actual content it does not identify itself as -#a spider. Thus traffic of this spider is counted as user traffic. +'icjobs\.de', 'iCjobs Spider', +#20130805 The user agent string of the icjobs-spider contained the +#identifying string only when it accessed the robots.txt file. +#When it accessed the actual content it did not identify itself as +#a spider. Thus traffic of this spider was counted as user traffic. +#The behavious seems to have changed now - the spider identifies itself +#when it accesses content pages. 'iconoclast','Popular Iconoclast', 'ilse','Ingrid', 'imagelock','Imagelock', diff --git a/wwwroot/cgi-bin/lib/search_engines.pm b/wwwroot/cgi-bin/lib/search_engines.pm index 9190ac0d..427f30cd 100644 --- a/wwwroot/cgi-bin/lib/search_engines.pm +++ b/wwwroot/cgi-bin/lib/search_engines.pm @@ -311,6 +311,8 @@ 'search\.certified-toolbar\.com', 'search\.sweetim\.com', 'search\.searchcompletion\.com', +'en\.eazel\.com', +'sr\.searchfunmoods\.com', # Chello Portals 'chello\.at', 'chello\.be', @@ -403,10 +405,12 @@ 'www\.vlips\.de', 'www\.metager\.de', 'search\.1und1\.de', +'sm\.de', # Minor Hungarian search engines 'heureka\.hu','vizsla\.origo\.hu','lapkereso\.hu','goliat\.hu','index\.hu','wahoo\.hu','webmania\.hu','search\.internetto\.hu', 'tango\.hu', 'keresolap\.hu', +'kereso\.startlap\.hu', 'polymeta\.hu', # Minor Indian search engines 'sify\.com', @@ -423,6 +427,7 @@ 'szukaj\.wp\.pl','szukaj\.onet\.pl','dodaj\.pl','gazeta\.pl','gery\.pl','hoga\.pl','netsprint\.pl','interia\.pl','katalog\.onet\.pl','o2\.pl','polska\.pl','szukacz\.pl','wow\.pl', # Minor russian search engines 'ya(ndex)?\.ru', 'aport\.ru', 'rambler\.ru', 'turtle\.ru', 'metabot\.ru', +'go\.mail\.ru', # Minor Swedish search engines 'evreka\.passagen\.se','eniro\.se', # Minor Slovak search engines @@ -562,6 +567,8 @@ 'search\.certified-toolbar\.com', 'certifiedtoolbarsearch', 'search\.sweetim\.com', 'sweetim', 'search\.searchcompletion\.com', 'searchcompletion', +'en\.eazel\.com','eazelsearch', +'sr\.searchfunmoods\.com', 'searchfunmoods', # Chello Portals 'chello\.at','chelloat', 'chello\.be','chellobe', @@ -693,6 +700,7 @@ 'www\.vlips\.de', 'vlips_de', 'www\.metager\.de', 'metager', 'search\.1und1\.de', 'search_1und1_de', +'sm\.de', 'smde', # Minor Hungarian search engines 'heureka\.hu','heureka', 'vizsla\.origo\.hu','origo', @@ -704,6 +712,7 @@ 'search\.internetto\.hu','internetto', 'tango\.hu','tango_hu', 'keresolap\.hu','keresolap_hu', +'kereso\.startlap\.hu', 'startlap_hu', 'polymeta\.hu','polymeta_hu', # Minor Indian search engines 'sify\.com','sify', @@ -746,6 +755,7 @@ 'rambler\.ru','rambler', 'turtle\.ru','turtle', 'metabot\.ru','metabot', +'go\.mail\.ru', 'mailru', # Minor Swedish search engines 'evreka\.passagen\.se','passagen', 'eniro\.se','enirose', @@ -866,6 +876,8 @@ 'certifiedtoolbarsearch', 'q=', 'sweetim', 'q=', 'searchcompletion', 'q=', +'eazelsearch', 'q=', +'searchfunmoods', 'q=', # Chello Portals 'chelloat','q1=', 'chellobe','q1=', @@ -960,9 +972,11 @@ 'vlips_de', 'q=', 'metager', 'eingabe=', 'search_1und1_de', 'q=', +'smde', 'q=', # Minor Hungarian search engines 'heureka','heureka=', 'origo','(q|search)=', 'goliat','KERESES=', 'wahoo','q=', 'internetto','searchstr=', 'keresolap_hu','q=', +'startlap_hu', 'q=', 'tango_hu','q=', 'polymeta_hu','', # Minor Indian search engines @@ -1002,6 +1016,7 @@ 'wowpl','q=', # Minor russian search engines 'yandex', 'text=', 'rambler','words=', 'aport', 'r=', 'metabot', 'st=', +'mailru', 'q=', # Minor swedish search engines 'passagen','q=', 'enirose','q=', @@ -1131,6 +1146,8 @@ 'certifiedtoolbarsearch', 'Certified-Toolbar Search', 'sweetim', 'SweetIM Search', 'searchcompletion', 'SearchCompletion Search', +'eazelsearch', 'Eazel Search', +'searchfunmoods', 'Funmoods', # Chello Portals 'chelloat','Chello Austria', 'chellobe','Chello Belgium', @@ -1227,10 +1244,12 @@ 'vlips_de', 'vlips.de', 'metager', 'MetaGer', 'search_1und1_de', '1&1 Suche', +'smde', 'SM.de - Die SuchMaschine', # Minor hungarian search engines 'heureka','Heureka', 'origo','Origo-Vizsla', 'lapkereso','Startlapkereso', 'goliat','Goliat', 'indexhu','Index', 'wahoo','Wahoo', 'webmania','webmania.hu', 'internetto','Internetto Kereso', 'tango_hu','Tango', 'keresolap_hu','Tango keresolap', +'startlap_hu','Startlab Kereso', 'polymeta_hu','Polymeta', # Minor Indian search engines 'sify','Sify', @@ -1269,6 +1288,7 @@ 'wowpl','Wow.pl', # Minor russian search engines 'yandex', 'Yandex', 'aport', 'Aport', 'rambler', 'Rambler', 'turtle', 'Turtle', 'metabot', 'MetaBot', +'mailru','Mail.Ru', # Minor Swedish search engines 'passagen','Evreka', 'enirose','Eniro Sverige',