search_engines.pm

awstats-6.6.zip tomcat日志分析包linux

# Minor Swedish search engines
'evreka\.passagen\.se','eniro\.se',
# Minor Slovak search engines
'zoznam\.sk',
# Minor Portuguese search engines
'sapo\.pt',
# Minor swiss search engines
'search\.ch', 'search\.bluewin\.ch'
);
@SearchEnginesSearchIDOrder_listgen=(
# Generic search engines
'search\..*\.\w+'
);


# NotSearchEnginesKeys
# If a search engine key is found, we check its exclude list to know if it's
# really a search engine
#------------------------------------------------------------------------------
%NotSearchEnginesKeys=(
'altavista\.'=>'babelfish\.altavista\.',
'google\.'=>'mail\.google\.',
'google\.'=>'translate\.google\.',
'msn\.'=>'hotmail\.msn\.',
'tiscali\.'=>'mail\.tiscali\.',
'yahoo\.'=>'mail\.yahoo\.',
'yandex\.'=>'direct\.yandex\.'
);


# SearchEnginesHashID
# Each Search Engine Search ID is associated to an AWStats id string
#------------------------------------------------------------------------------
%SearchEnginesHashID = (
# Major international search engines
'base\.google\.','google_base',
'froogle\.google\.','google_froogle',
'groups\.google\.','google_groups',
'images\.google\.','google_image',
'google\.','google',
'googlee\.','google',
'googlecom\.com','google',
'goggle\.co\.hu','google',
'216\.239\.(35|37|39|51)\.100','google_cache',
'216\.239\.(35|37|39|51)\.101','google_cache',
'216\.239\.5[0-9]\.104','google_cache',
'64\.233\.1[0-9]{2}\.104','google_cache',
'66\.102\.[1-9]\.104','google_cache',
'66\.249\.93\.104','google_cache',
'72\.14\.2[0-9]{2}\.104','google_cache',
'msn\.','msn',
'live\.com','live',
'voila\.','voila',
'mindset\.research\.yahoo','yahoo_mindset',
'yahoo\.','yahoo','(66\.218\.71\.225|216\.109\.117\.135|216\.109\.125\.130|66\.218\.69\.11)','yahoo',
'lycos\.','lycos',
'alexa\.com','alexa',
'alltheweb\.com','alltheweb',
'altavista\.','altavista',
'a9\.com','a9',
'dmoz\.org','dmoz',
'netscape\.','netscape',
'search\.terra\.','terra',
'www\.search\.com','search.com',
'tiscali\.','tiscali',
'search\.aol\.co','aol',
'search\.sli\.sympatico\.ca','sympatico',
'excite\.','excite',
# Minor international search engines
'4\-counter\.com','google4counter',
'att\.net','att',
'northernlight\.','northernlight',
'hotbot\.','hotbot',
'kvasir\.','kvasir',
'webcrawler\.','webcrawler',
'metacrawler\.','metacrawler',
'go2net\.com','go2net',
'(^|\.)go\.com','go',
'euroseek\.','euroseek',
'looksmart\.','looksmart',
'spray\.','spray',
'nbci\.com\/search','nbci',
'de\.ask.\com','askde', # break out Ask country specific engines.
'es\.ask.\com','askes',
'fr\.ask.\com','askfr',
'it\.ask.\com','askit',
'nl\.ask.\com','asknl',
'uk\.ask.\com','askuk',
'(^|\.)ask\.co\.uk','askuk',
'(^|\.)ask\.com','ask',
'atomz\.','atomz',
'overture\.com','overture',		# Replace 'goto\.com','Goto.com',
'teoma\.','teoma',
'findarticles\.com','findarticles',
'infospace\.com','infospace',
'mamma\.','mamma',
'dejanews\.','dejanews',
'dogpile\.com','dogpile',
'wisenut\.com','wisenut',
'ixquick\.com','ixquick',
'search\.earthlink\.net','earthlink',
'i-une\.com','iune',
'blingo\.com','blingo',
'centraldatabase\.org','centraldatabase',
'clusty\.com','clusty',
'mysearch\.','mysearch',
'vivisimo\.com','vivisimo',
'kartoo\.com','kartoo',
'icerocket\.com','icerocket',
'sphere\.com','sphere',
'ledix\.net','ledix',
'start\.shaw\.ca','shawca',
'searchalot\.com','searchalot',
'copernic\.com','copernic',
'avantfind\.com','avantfind',
'steadysearch\.com','steadysearch',
'steady-search\.com','steadysearch',
# Chello Portals
'chello\.at','chelloat',
'chello\.be','chellobe',
'chello\.cz','chellocz',
'chello\.fr','chellofr',
'chello\.hu','chellohu',
'chello\.nl','chellonl',
'chello\.no','chellono',
'chello\.pl','chellopl',
'chello\.se','chellose',
'chello\.sk','chellosk',
'chello','chellocom',
# Mirago 
'mirago\.be','miragobe',
'mirago\.ch','miragoch',
'mirago\.de','miragode',
'mirago\.dk','miragodk',
'es\.mirago\.com','miragoes',
'mirago\.fr','miragofr',
'mirago\.it','miragoit',
'mirago\.nl','miragonl',
'no\.mirago\.com','miragono',
'mirago\.se','miragose',
'mirago\.co\.uk','miragocouk',
'mirago','mirago', # required as catchall for new countries not yet known
'answerbus\.com','answerbus',
'icq\.com\/search','icq',
'nusearch\.com','nusearch',
'goodsearch\.com','goodsearch',
'scroogle\.org','scroogle',
'questionanswering\.com','questionanswering',
'mywebsearch\.com','mywebsearch',
'as\.starware\.com','comettoolbar',
# Social Bookmarking Services
'del\.icio\.us','delicious',
'digg\.com','digg',
'stumbleupon\.com','stumbleupon',
'swik\.net','swik',
'segnalo\.alice\.it','segnalo',
'ineffabile\.it','ineffabile',
# Minor Australian search engines
'anzwers\.com\.au','anzwers',
# Minor brazilian search engines
'engine\.exe','engine',
'miner\.bol\.com\.br','miner',
# Minor chinese search engines
'baidu\.com','baidu',
'search\.sina\.com','sina',
'search\.sohu\.com','sohu',
'sogou\.com','sogou',
# Minor czech search engines
'atlas\.cz','atlas',
'seznam\.cz','seznam',
'quick\.cz','quick',
'centrum\.cz','centrum',
'jyxo\.(cz|com)','jyxo',
'najdi\.to','najdi',
'redbox\.cz','redbox',
# Minor danish search-engines 
'opasia\.dk','opasia',
'danielsen\.com','danielsen',
'sol\.dk','sol',
'jubii\.dk','jubii',
'find\.dk','finddk',
'edderkoppen\.dk','edderkoppen',
'netstjernen\.dk','netstjernen',
'orbis\.dk','orbis',
'tyfon\.dk','tyfon',
'1klik\.dk','1klik',
'ofir\.dk','ofir',
# Minor dutch search engines
'ilse\.','ilse',
'vindex\.','vindex',
# Minor english search engines
'bbc\.co\.uk/cgi-bin/search','bbc',
'ifind\.freeserve','freeserve',
'looksmart\.co\.uk','looksmartuk',
'splut\.','splut',
'spotjockey\.','spotjockey',
'ukdirectory\.','ukdirectory',
'ukindex\.co\.uk','ukindex',
'ukplus\.','ukplus',
'searchy\.co\.uk','searchy',
# Minor finnish search engines
'haku\.www\.fi','haku',
# Minor french search engines
'recherche\.aol\.fr','aolfr',
'ctrouve\.','ctrouve',
'francite\.','francite',
'\.lbb\.org','lbb',
'rechercher\.libertysurf\.fr','libertysurf',
'search[\w\-]+\.free\.fr','free',
'recherche\.club-internet\.fr','clubinternet',
'toile\.com','toile',
'biglotron\.com', 'biglotron',
'mozbot\.fr', 'mozbot',
# Minor german search engines
'sucheaol\.aol\.de','aolde',
'fireball\.de','fireball',
'infoseek\.de','infoseek',
'suche\d?\.web\.de','webde',
'[a-z]serv\.rrzn\.uni-hannover\.de','meta',
'suchen\.abacho\.de','abacho',
'brisbane\.t-online\.de','t-online',
'allesklar\.de','allesklar',
'meinestadt\.de','meinestadt',
'212\.227\.33\.241','metaspinner',
'(161\.58\.227\.204|161\.58\.247\.101|212\.40\.165\.90|213\.133\.108\.202|217\.160\.108\.151|217\.160\.111\.99|217\.160\.131\.108|217\.160\.142\.227|217\.160\.176\.42)','metacrawler_de',
'wwweasel\.de','wwweasel',
'netluchs\.de','netluchs',
'schoenerbrausen\.de','schoenerbrausen',
# Minor Hungarian search engines
'heureka\.hu','heureka',
'vizsla\.origo\.hu','origo',
'lapkereso\.hu','lapkereso',
'goliat\.hu','goliat',
'index\.hu','indexhu',
'wahoo\.hu','wahoo',
'webmania\.hu','webmania',
'search\.internetto\.hu','internetto',
'tango\.hu','tango_hu',
'keresolap\.hu','keresolap_hu',
'polymeta\.hu','polymeta_hu',
# Minor Indian search engines
'sify\.com','sify',
# Minor Italian search engines
'virgilio\.it','virgilio',
'arianna\.libero\.it','arianna',
'supereva\.com','supereva',
'kataweb\.it','kataweb',
'search\.alice\.it\.master','aliceitmaster',
'search\.alice\.it','aliceit',
'gotuneed\.com','gotuneed',
'godado','godado',
'jumpy\.it','jumpy\.it',
'shinyseek\.it','shinyseek\.it',
'teecno\.it','teecnoit',
# Minor Japanese search engines
'ask\.jp','askjp',
'sagool\.jp','sagool',
# Minor Norwegian search engines
'sok\.start\.no','start', 'eniro\.no','eniro',
# Minor Polish search engines
'szukaj\.wp\.pl','wp',
'szukaj\.onet\.pl','onetpl',
'dodaj\.pl','dodajpl',
'gazeta\.pl','gazetapl',
'gery\.pl','gerypl',
'netsprint\.pl\/hoga\-search','hogapl',
'netsprint\.pl','netsprintpl',
'interia\.pl','interiapl',
'katalog\.onet\.pl','katalogonetpl',
'o2\.pl','o2pl',
'polska\.pl','polskapl',
'szukacz\.pl','szukaczpl',
'wow\.pl','wowpl',
# Minor russian search engines
'ya(ndex)?\.ru','yandex',
'aport\.ru','aport',
'rambler\.ru','rambler',
'turtle\.ru','turtle',
'metabot\.ru','metabot',
# Minor Swedish search engines
'evreka\.passagen\.se','passagen',
'eniro\.se','enirose',
# Minor Slovak search engines
'zoznam\.sk','zoznam',
# Minor Portuguese search engines
'sapo\.pt','sapo',
# Minor swiss search engines
'search\.ch','searchch',
'search\.bluewin\.ch','bluewin',
# Generic search engines
'search\..*\.\w+','search'
);


# SearchEnginesWithKeysNotInQuery
# List of search engines that store keyword as page instead of query parameter
#------------------------------------------------------------------------------
%SearchEnginesWithKeysNotInQuery=(
'a9',1    # www.a9.com/searckey1%20searchkey2
);

# SearchEnginesKnownUrl
# Known rules to extract keywords from a referrer search engine URL
#------------------------------------------------------------------------------
%SearchEnginesKnownUrl=(
# Most common search engines
'alexa','q=',
'alltheweb','q(|uery)=',
'altavista','q=',
'a9','a9\.com\/', 
'dmoz','search=',
'google_base','(p|q|as_p|as_q)=',
'google_froogle','(p|q|as_p|as_q)=',
'google_groups','group\/', # does not work
'google_image','(p|q|as_p|as_q)=',
'google_cache','(p|q|as_p|as_q)=cache:[0-9A-Za-z]{12}:',
'google','(p|q|as_p|as_q)=',
'lycos','query=',
'msn','q=',
'live','q=',
'netscape','search=',
'tiscali','key=',
'aol','query=',
'terra','query=',
'voila','(kw|rdata)=',
'search.com','q=',
'yahoo_mindset','p=',
'yahoo','p=',