search_engines.pm

awstats-6.6.zip tomcat日志分析包linux

'sympatico', 'query=', 
'excite','search=',
# Minor international search engines
'google4counter','(p|q|as_p|as_q)=',
'att','qry=',
'go','qt=',
'askde','(ask|q)=', # break out Ask country specific engines.
'askes','(ask|q)=',
'askfr','(ask|q)=',
'askit','(ask|q)=',
'asknl','(ask|q)=',
'ask','(ask|q)=',
'atomz','sp-q=',
'euroseek','query=',
'findarticles','key=',
'go2net','general=',
'hotbot','mt=',
'infospace','qkw=',
'kvasir', 'q=',
'looksmart','key=',
'mamma','query=',
'metacrawler','general=',
'nbci','keyword=',
'northernlight','qr=',
'overture','keywords=',
'dogpile', 'q(|kw)=',
'spray','string=',
'teoma','q=',
'webcrawler','searchText=',
'wisenut','query=', 
'ixquick', 'query=',
'earthlink', 'q=',
'iune','(keywords|q)=',
'blingo','q=',
'centraldatabase','query=',
'clusty','query=',
'mysearch','searchfor=',
'vivisimo','query=',
# kartoo: No keywords passed in referring URL.
'kartoo','',
'icerocket','q=',
'sphere','q=',
'ledix','q=',
'shawca','q=',
'searchalot','q=',
'copernic','web\/',
'avantfind','keywords=',
'steadysearch','w=',
# Chello Portals
'chelloat','q1=',
'chellobe','q1=',
'chellocz','q1=',
'chellofr','q1=',
'chellohu','q1=',
'chellonl','q1=',
'chellono','q1=',
'chellopl','q1=',
'chellose','q1=',
'chellosk','q1=',
'chellocom','q1=',
# Mirago
'miragobe','(txtsearch|qry)=',
'miragoch','(txtsearch|qry)=',
'miragode','(txtsearch|qry)=',
'miragodk','(txtsearch|qry)=',
'miragoes','(txtsearch|qry)=',
'miragofr','(txtsearch|qry)=',
'miragoit','(txtsearch|qry)=',
'miragonl','(txtsearch|qry)=',
'miragono','(txtsearch|qry)=',
'miragose','(txtsearch|qry)=',
'miragocouk','(txtsearch|qry)=',
'mirago','(txtsearch|qry)=',
'answerbus','', # Does not provide query parameters
'icq','q=',
'nusearch','nusearch_terms=',
'goodsearch','Keywords=',
'scroogle','Gw=', # Does not always provide query parameters
'questionanswering','',
'mywebsearch','searchfor=',
'comettoolbar','qry=',
# Social Bookmarking Services
'delicious','all=',
'digg','s=',
'stumbleupon','',
'swik','swik\.net/', # does not work. Keywords follow domain, e.g. http://swik.net/awstats+analytics
'segnalo','',
'ineffabile','',
# Minor Australian search engines
'anzwers','search=',
# Minor brazilian search engines
'engine','p1=', 'miner','q=',
# Minor chinese search engines
'baidu','word=', 'sina', 'word=', 'sohu','word=', 'sogou', 'query=',
# Minor czech search engines
'atlas','searchtext=', 'seznam','w=', 'quick','query=', 'centrum','q=', 'jyxo','s=', 'najdi','dotaz=', 'redbox','srch=',
# Minor danish search engines
'opasia','q=', 'danielsen','q=', 'sol','q=', 'jubii','soegeord=', 'finddk','words=', 'edderkoppen','query=', 'orbis','search_field=', '1klik','query=', 'ofir','querytext=',
# Minor dutch search engines
'ilse','search_for=', 'vindex','in=',
# Minor english search engines
'askuk','(ask|q)=', 'bbc','q=', 'freeserve','q=', 'looksmartuk','key=',
'splut','pattern=', 'spotjockey','Search_Keyword=', 'ukindex', 'stext=', 'ukdirectory','k=', 'ukplus','search=', 'searchy', 'search_term=',
# Minor finnish search engines
'haku','w=',
# Minor french search engines
'francite','name=', 'clubinternet', 'q=',
'toile', 'q=',
'biglotron','question=',
'mozbot','q=',
# Minor german search engines
'aolde','q=',
'fireball','q=', 'infoseek','qt=', 'webde','su=',
'abacho','q=', 't-online','q=', 
'metaspinner','qry=',
'metacrawler_de','qry=',
'wwweasel','q=',
'netluchs','query=',
'schoenerbrausen','q=',
# Minor Hungarian search engines
'heureka','heureka=', 'origo','(q|search)=', 'goliat','KERESES=', 'wahoo','q=', 'internetto','searchstr=',
'keresolap_hu','q=',
'tango_hu','q=',
'polymeta_hu','',
# Minor Indian search engines
'sify','keyword=',
# Minor Italian search engines
'virgilio','qs=',
'arianna','query=',
'supereva','q=',
'kataweb','q=',
'aliceitmaster','qs=',
'aliceit','qs=',
'gotuneed','', # Not yet known
'godado','Keywords=',
'jumpy\.it','searchWord=',
'shinyseek\.it','KEY=',
'teecnoit','q=',
# Minor Japanese search engines
'askjp','(ask|q)=',
'sagool','q=',
# Minor Norwegian search engines
'start','q=', 'eniro','q=',
# Minor Polish search engines
'wp','szukaj=',
'onetpl','qt=',
'dodajpl','keyword=',
'gazetapl','slowo=',
'gerypl','q=',
'hogapl','qt=',
'netsprintpl','q=',
'interiapl','q=',
'katalogonetpl','qt=',
'o2pl','qt=',
'polskapl','qt=',
'szukaczpl','q=',
'wowpl','q=',
# Minor russian search engines
'yandex', 'text=', 'rambler','words=', 'aport', 'r=', 'metabot', 'st=',
# Minor swedish search engines
'passagen','q=',
'enirose','q=',
# Minor swiss search engines
'searchch', 'q=', 'bluewin', 'qry='
);

# SearchEnginesKnownUrlNotFound
# Known rules to extract not found keywords from a referrer search engine URL
#------------------------------------------------------------------------------
%SearchEnginesKnownUrlNotFound=(
# Most common search engines
'msn','origq='
);

# If no rules are known, WordsToExtractSearchUrl will be used to search keyword parameter
# If no rules are known and search in WordsToExtractSearchUrl failed, this will be used to clean URL of not keyword parameters.
#------------------------------------------------------------------------------
@WordsToExtractSearchUrl= ('ask=','claus=','general=','key=','kw=','keyword=','keywords=','MT=','p=','q=','qr=','qt=','query=','s=','search=','searchText=','string=','su=','txtsearch=','w=');
@WordsToCleanSearchUrl= ('act=','annuaire=','btng=','cat=','categoria=','cfg=','cof=','cou=','count=','cp=','dd=','domain=','dt=','dw=','enc=','exec=','geo=','hc=','height=','hits=','hl=','hq=','hs=','id=','kl=','lang=','loc=','lr=','matchmode=','medor=','message=','meta=','mode=','order=','page=','par=','pays=','pg=','pos=','prg=','qc=','refer=','sa=','safe=','sc=','sort=','src=','start=','style=','stype=','sum=','tag=','temp=','theme=','type=','url=','user=','width=','what=','\\.x=','\\.y=','y=','look=');

# SearchEnginesKnownUTFCoding
# Known parameter that proves a search engine has coded its parameters in UTF-8
#------------------------------------------------------------------------------
%SearchEnginesKnownUTFCoding=(
# Most common search engines
'google','ie=utf-8',
'alltheweb','cs=utf-8'
);


# SearchEnginesHashLib
# List of search engines names
# 'search_engine_id', 'search_engine_name',
#------------------------------------------------------------------------------
%SearchEnginesHashLib=(
# Major international search engines
'alexa','<a href="http://www.alexa.com/" title="Search Engine Home Page [new window]" target="_blank">Alexa</a>',
'alltheweb','<a href="http://www.alltheweb.com/" title="Search Engine Home Page [new window]" target="_blank">AllTheWeb</a>',
'altavista','<a href="http://www.altavista.com/" title="Search Engine Home Page [new window]" target="_blank">AltaVista</a>',
'a9', '<a href="http://www.a9.com/" title="Search Engine Home Page [new window]" target="_blank">A9</a>',
'dmoz','<a href="http://dmoz.org/" title="Search Engine Home Page [new window]" target="_blank">DMOZ</a>',
'google_base','<a href="http://base.google.com/" title="Search Engine Home Page [new window]" target="_blank">Google (Base)</a>',
'google_froogle','<a href="http://froogle.google.com/" title="Search Engine Home Page [new window]" target="_blank">Froogle (Google)</a>',
'google_groups','<a href="http://groups.google.com/" title="Search Engine Home Page [new window]" target="_blank">Google (Groups)</a>',
'google_image','<a href="http://images.google.com/" title="Search Engine Home Page [new window]" target="_blank">Google (Images)</a>',
'google_cache','<a href="http://www.google.com/help/features.html#cached" title="Search Engine Home Page [new window]" target="_blank">Google (cache)</a>',
'google','<a href="http://www.google.com/" title="Search Engine Home Page [new window]" target="_blank">Google</a>',
'lycos','<a href="http://www.lycos.com/" title="Search Engine Home Page [new window]" target="_blank">Lycos</a>',
'msn','<a href="http://search.msn.com/" title="Search Engine Home Page [new window]" target="_blank">MSN Search</a>',
'live','<a href="http://www.live.com/" title="Search Engine Home Page [new window]" target="_blank">Windows Live</a>',
'netscape','<a href="http://www.netscape.com/" title="Search Engine Home Page [new window]" target="_blank">Netscape</a>',
'aol','<a href="http://www.aol.com/" title="Search Engine Home Page [new window]" target="_blank">AOL</a>',
'terra','<a href="http://www.terra.es/" title="Search Engine Home Page [new window]" target="_blank">Terra</a>',
'tiscali','<a href="http://search.tiscali.com/" title="Search Engine Home Page [new window]" target="_blank">Tiscali</a>',
'voila','<a href="http://www.voila.fr/" title="Search Engine Home Page [new window]" target="_blank">Voila</a>',
'search.com','<a href="http://www.search.com/" title="Search Engine Home Page [new window]" target="_blank">Search.com</a>',
'yahoo_mindset','<a href="http://mindset.research.yahoo.com/" title="Search Engine Home Page [new window]" target="_blank">Yahoo! Mindset</a>',
'yahoo','<a href="http://www.yahoo.com/" title="Search Engine Home Page [new window]" target="_blank">Yahoo!</a>',
'sympatico','<a href="http://sympatico.msn.ca/" title="Search Engine Home Page [new window]" target="_blank">Sympatico</a>',
'excite','<a href="http://www.excite.com/" title="Search Engine Home Page [new window]" target="_blank">Excite</a>',
# Minor international search engines
'google4counter','<a href="http://www.4-counter.com/" title="Search Engine Home Page [new window]" target="_blank">4-counter (Google)</a>',
'att','<a href="http://www.att.net/" title="Search Engine Home Page [new window]" target="_blank">AT&T search (powered by Google)</a>',
'go','Go.com',
'askde','<a href="http://de.ask.com/" title="Search Engine Home Page [new window]" target="_blank">Ask Deutschland</a>',
'askes','<a href="http://es.ask.com/" title="Search Engine Home Page [new window]" target="_blank">Ask Espa&ntilde;a</a>', # break out Ask country specific engines.
'askfr','<a href="http://fr.ask.com/" title="Search Engine Home Page [new window]" target="_blank">Ask France</a>',
'askit','<a href="http://it.ask.com/" title="Search Engine Home Page [new window]" target="_blank">Ask Italia</a>',
'asknl','<a href="http://nl.ask.com/" title="Search Engine Home Page [new window]" target="_blank">Ask Nederland</a>',
'ask','<a href="http://www.ask.com/" title="Search Engine Home Page [new window]" target="_blank">Ask</a>',
'atomz','Atomz',
'dejanews','DejaNews',
'euroseek','Euroseek',
'findarticles','Find Articles',
'go2net','Go2Net (Metamoteur)',
'hotbot','Hotbot',
'infospace','InfoSpace',
'kvasir','Kvasir',
'looksmart','Looksmart',
'mamma','Mamma',
'metacrawler','MetaCrawler (Metamoteur)',
'nbci','NBCI',
'northernlight','NorthernLight',
'overture','Overture',                 # Replace 'goto\.com','Goto.com',
'dogpile','<a href="http://www.dogpile.com/" title="Search Engine Home Page [new window]" target="_blank">Dogpile</a>',
'spray','Spray',
'teoma','<a href="http://search.ask.com/" title="Search Engine Home Page [new window]" target="_blank">Teoma</a>',							# Replace 'directhit\.com','DirectHit',
'webcrawler','<a href="http://www.webcrawler.com/" title="Search Engine Home Page [new window]" target="_blank">WebCrawler</a>',
'wisenut','WISENut', 
'ixquick','<a href="http://www.ixquick.com/" title="Search Engine Home Page [new window]" target="_blank">ix quick</a>', 
'earthlink', 'Earth Link',
'iune','<a href="http://www.i-une.com/" title="Search Engine Home Page [new window]" target="_blank">i-une</a>',
'blingo','<a href="http://www.blingo.com/" title="Search Engine Home Page [new window]" target="_blank">Blingo</a>',
'centraldatabase','<a href="http://search.centraldatabase.org/" title="Search Engine Home Page [new window]" target="_blank">GPU p2p search</a>',
'clusty','<a href="http://www.clusty.com/" title="Search Engine Home Page [new window]" target="_blank">Clusty</a>',
'mysearch','<a href="http://www.mysearch.com" title="Search Engine Home Page [new window]" target="_blank">My Search</a>',
'vivisimo','<a href="http://www.vivisimo.com/" title="Search Engine Home Page [new window]" target="_blank">Vivisimo</a>',
'kartoo','<a href="http://www.kartoo.com/" title="Search Engine Home Page [new window]" target="_blank">Kartoo</a>',
'icerocket','<a href="http://www.icerocket.com/" title="Search Engine Home Page [new window]" target="_blank">Icerocket (Blog)</a>',
'sphere','<a href="http://www.sphere.com/" title="Search Engine Home Page [new window]" target="_blank">Sphere (Blog)</a>',
'ledix','<a href="http://www.ledix.net/" title="Search Engine Home Page [new window]" target="_blank">Ledix</a>',
'shawca','<a href="http://start.shaw.ca/" title="Search Engine Home Page [new window]" target="_blank">Shaw.ca</a>',
'searchalot','<http://www.searchalot.com/" title="Search Engine Home Page [new window]" target="_blank">Searchalot</a>',
'copernic','<http://www.copernic.com/" title="Search Engine Home Page [new window]" target="_blank">Copernic</a>',
'avantfind','<http://www.avantfind.com/" title="Search Engine Home Page [new window]" target="_blank">Avantfind</a>',
'steadysearch','<http://www.avantfind.com/" title="Search Engine Home Page [new window]" target="_blank">Avantfind</a>',
# Chello Portals
'chelloat','<a href="http://www.chello.at/" title="Search Engine Home Page [new window]" target="_blank">Chello Austria</a>',
'chellobe','<a href="http://www.chello.be/" title="Search Engine Home Page [new window]" target="_blank">Chello Belgium</a>',
'chellocz','<a href="http://www.chello.cz/" title="Search Engine Home Page [new window]" target="_blank">Chello Czech Republic</a>',
'chellofr','<a href="http://www.chello.fr/" title="Search Engine Home Page [new window]" target="_blank">Chello France</a>',
'chellohu','<a href="http://www.chello.hu/" title="Search Engine Home Page [new window]" target="_blank">Chello Hungary</a>',
'chellonl','<a href="http://www.chello.nl/" title="Search Engine Home Page [new window]" target="_blank">Chello Netherlands</a>',
'chellono','<a href="http://www.chello.no/" title="Search Engine Home Page [new window]" target="_blank">Chello Norway</a>',
'chellopl','<a href="http://www.chello.pl/" title="Search Engine Home Page [new window]" target="_blank">Chello Poland</a>',
'chellose','<a href="http://www.chello.se/" title="Search Engine Home Page [new window]" target="_blank">Chello Sweden</a>',
'chellosk','<a href="http://www.chello.sk/" title="Search Engine Home Page [new window]" target="_blank">Chello Slovakia</a>',
'chellocom','<a href="http://www.chello.com/" title="Search Engine Home Page [new window]" target="_blank">Chello (Country not recognized)</a>',
# Mirago
'miragobe','<a href="http://www.mirago.be/" title="Search Engine Home Page [new window]" target="_blank">Mirago Belgium</a>',
'miragoch','<a href="http://www.mirago.ch/" title="Search Engine Home Page [new window]" target="_blank">Mirago Switzerland</a>',
'miragode','<a href="http://www.mirago.de/" title="Search Engine Home Page [new window]" target="_blank">Mirago Germany</a>',
'miragodk','<a href="http://www.mirago.dk/" title="Search Engine Home Page [new window]" target="_blank">Mirago Denmark</a>',
'miragoes','<a href="http://es.mirago.com/" title="Search Engine Home Page [new window]" target="_blank">Mirago Spain</a>',
'miragofr','<a href="http://www.mirago.fr/" title="Search Engine Home Page [new window]" target="_blank">Mirago France</a>',
'miragoit','<a href="http://www.mirago.it/" title="Search Engine Home Page [new window]" target="_blank">Mirago Italy</a>',
'miragonl','<a href="http://www.mirago.nl/" title="Search Engine Home Page [new window]" target="_blank">Mirago Netherlands</a>',
'miragono','<a href="http://no.mirago.com/" title="Search Engine Home Page [new window]" target="_blank">Mirago Norway</a>',
'miragose','<a href="http://www.mirago.se/" title="Search Engine Home Page [new window]" target="_blank">Mirago Sweden</a>',
'miragocouk','<a href="http://zone.mirago.co.uk/" title="Search Engine Home Page [new window]" target="_blank">Mirago UK</a>',
'mirago','<a href="http://www.mirago.com/" title="Search Engine Home Page [new window]" target="_blank">Mirago (country unknown)</a>',
'answerbus','<a href="http://www.answerbus.com/" title="Search Engine Home Page [new window]" target="_blank">Answerbus</a>',
'icq','<a href="http://www.icq.com/" title="Search Engine Home Page [new window]" target="_blank">icq</a>',
'nusearch','<a href="http://www.nusearch.com/" title="Search Engine Home Page [new window]" target="_blank">Nusearch</a>',
'goodsearch','<a href="http://www.goodsearch.com/" title="Search Engine Home Page [new window]" target="_blank">GoodSearch</a>',
'scroogle','<a href="http://www.scroogle.org/" title="Search Engine Home Page [new window]" target="_blank">Scroogle</a>',
'questionanswering','<a href="http://www.questionanswering.com/" title="Questionanswering home page [new window]" target="_blank">Questionanswering</a>',
'mywebsearch','<a href="http://search.mywebsearch.com/" title="MyWebSearch home page [new window]" target="_blank">MyWebSearch</a>',
'comettoolbar','<a href="http://as.starware.com/dp/search" title="Comet toolbar search home page [new window]" target="_blank">Comet toolbar search</a>',
# Social Bookmarking Services
'delicious','<a href="http://del.icio.us/" title="del.icio.us home page [new window]" target="_blank">del.icio.us</a> (Social Bookmark)',
'digg','<a href="http://www.digg.com/" title="Digg home page [new window]" target="_blank">Digg</a> (Social Bookmark)',
'stumbleupon','<a href="http://www.stumbleupon.com/" title="Stumbleupon home page [new window]" target="_blank">Stumbleupon</a> (Social Bookmark)',
'swik','<a href="http://swik.net/" title="Swik home page [new window]" target="_blank">Swik</a> (Social Bookmark)',
'segnalo','<a href="http://segnalo.alice.it/" title="Segnalo home page [new window]" target="_blank">Segnalo</a> (Social Bookmark)',
'ineffabile','<a href="http://www.ineffabile.it/" title="Ineffabile.it home page [new window]" target="_blank">Ineffabile.it</a> (Social Bookmark)',
# Minor Australian search engines
'anzwers','<a href="http://anzwers.com.au/" title="anzwers.com.au home page [new window]" target="_blank">anzwers.com.au</a>',
# Minor brazilian search engines
'engine','Cade', 'miner','Meta Miner',
# Minor chinese search engines
'baidu','Baidu', 'sina','Sina', 'sohu','Sohu', 'sogou','<a href="http://www.sogou.com/" title="Search Engine Home Page [new window]" target="_blank">Sogou</a>',
# Minor czech search engines
'atlas','Atlas.cz',	'seznam','Seznam', 'quick','Quick.cz', 'centrum','Centrum.cz', 'jyxo','Jyxo.cz', 'najdi','Najdi.to', 'redbox','RedBox.cz',
# Minor danish search-engines
'opasia','Opasia', 'danielsen','Thor (danielsen.com)', 'sol','SOL', 'jubii','Jubii', 'finddk','Find', 'edderkoppen','Edderkoppen', 'netstjernen','Netstjernen', 'orbis','Orbis', 'tyfon','Tyfon', '1klik','1Klik', 'ofir','Ofir',
# Minor dutch search engines
'ilse','Ilse','vindex','Vindex\.nl',						
# Minor english search engines
'askuk','<a href="http://uk.ask.com/" title="Search Engine Home Page [new window]" target="_blank">Ask UK</a>',
'bbc','BBC', 'freeserve','Freeserve', 'looksmartuk','Looksmart UK',
'splut','Splut', 'spotjockey','Spotjockey', 'ukdirectory','UK Directory', 'ukindex','UKIndex', 'ukplus','UK Plus', 'searchy','searchy.co.uk',
# Minor finnish search engines
'haku','Ihmemaa',										
# Minor french search engines
'aolfr','AOL (fr)', 'ctrouve','C\'est trouv