-# AWSTATS SEARCH ENGINES DATABASE
-#------------------------------------------------------------------------------
-# If you want to add a Search Engine to extend AWStats database detection capabilities,
-# you must add an entry in SearchEnginesSearchIDOrder, SearchEnginesHashID and in
-# SearchEnginesHashLib.
-# An entry if known in SearchEnginesKnownUrl is also welcome.
-#------------------------------------------------------------------------------
-# $Revision$ - $Author$ - $Date$
-
-# 2005-08-19 Sean Carlos http://www.antezeta.com/awstats.html
-# added minor italian search engines
-# arianna http://arianna.libero.it/
-# supereva http://search.supereva.com/
-# kataweb http://kataweb.it/
-# corrected uk looksmart
-# 'askuk','ask=', 'bbc','q=', 'freeserve','q=', 'looksmart','key=',
-# to
-# 'askuk','ask=', 'bbc','q=', 'freeserve','q=', 'looksmartuk','key=',
-# corrected spelling
-# internationnal -> international
-# added 'google\.'=>'mail\.google\.', to NotSearchEnginesKeys in order to
-# avoid counting gmail referrals as search engine traffic
-# 2005-08-21 Sean Carlos http://www.antezeta.com/awstats.html
-# avoid counting babelfish.altavista referrals as search engine traffic
-# avoid counting translate.google referrals as search engine traffic
-# 2005-11-20 Sean Carlos
-# added missing 'tiscali','key=', entry. Check order
-# 2005-11-22 Sean Carlos
-# added Google Base & Froogle. Froogle not tested.
-# 2006-04-18 Sean Carlos http://www.antezeta.com/awstats.html
-# added biglotron.com (France)
-# added blingo http://www.blingo.com/
-# added Clusty & Vivisimo
-# added eniro.no (Norway) [https://sourceforge.net/forum/message.php?msg_id=3134783]
-# added GPU p2p search http://search.centraldatabase.org/
-# added mail.tiscali to "not search engines list" [https://sourceforge.net/forum/message.php?msg_id=3166688]
-# added Ask group's "mysearch"
-# added sify.com (India)
-# added sogou.com (Cina) [https://sourceforge.net/forum/message.php?msg_id=3501603]
-# Ask changes:
-# - added Ask Japan (ask.jp)
-# - break out Ask new country level variants (DE, ES, FR, IT, NL)
-# - updated Ask name from Ask Jevees
-# - added Ask q= parameter - many recent searches probably not recognized; [https://sourceforge.net/forum/message.php?msg_id=3465444]
-# - updated Ask uk (new uk.ask.com added to older ask.co.uk)
-# updated voila kw|rdata parameter [https://sourceforge.net/forum/message.php?msg_id=3373912]
-# for each new engine, added link to Search Engine. This serves to document engine. Done for major & Italian engines as well. Requires patch
-# to AWStats to allow untranslated html. Otherwise html will appear instead of link.
-# reviewed mnoGoSearch (http://www.mnogosearch.org/); the search engined mentioned no longer
-# exists https://sourceforge.net/forum/message.php?msg_id=3025426
-# 2006-05-13 Sean Carlos http://www.antezeta.com/awstats.html
-# added 10 Chello European broadband portals (Austria, Belgium, Czech Republic, France, Hungary, The Netherlands, Norway, Poland, Slovakia, Sweden)
-# added Alice Internal Search (blends data with Google?) search.alice.it.master:10005
-# added detection of google cache views from IPs 66.249.93.104 72.14.203.104 72.14.207.104
-# To do: add more extensive IP list; keywords not yet detected.
-# added icerocket.com blog search http://www.icerocket.com/
-# added live.com (msn) http://www.live.com/
-# added Meta motor kartoo. Note: Kartoo does not provide search words in referrers, thus the engine will appear in the
-# search engine list but the actual search words are not available.
-# added netluchs.de http://www.netluchs.de/
-# added sphere.com blog search http://www.sphere.com/
-# added wwweasel.de http://wwweasel.de
-# added Yahoo Mindset! http://mindset.research.yahoo.com/
-# updated Mirago query parameter recognition (qry=); added breakout for each country (France, Germany, Spain, Italy, Norway, Sweden, Denmark, Netherlands, Belgium, Switzerland)
-# 2006-05-13
-# added Google cache IPs 64.233.183.104 & 66.102.7.104
-# 2006-05-20
-# anzwers.com.au
-# schoenerbrausen.de http://www.schoenerbrausen.de/
-# 216.239.59.104
-# answerbus http://www.answerbus.com/
-
-#package AWSSE;
-
-
-# SearchEnginesSearchIDOrder
-# It contains all matching criteria to search for in log fields. This list is
-# used to know in which order to search Search Engines IDs.
-# Most frequent one are in list1, used when LevelForSearchEnginesDetection is 1 or more
-# Minor robots are in list2, used when LevelForSearchEnginesDetection is 2 or more
-# Note: Regex IDs are in lower case and ' ' and '+' are changed into '_'
-#------------------------------------------------------------------------------
-@SearchEnginesSearchIDOrder_list1=(
-# Major international search engines
-'base\.google\.',
-'froogle\.google\.',
-'images\.google\.',
-'google\.','216\.239\.(35\.101|37\.101|39\.100|39\.101|51\.100|51\.101|35\.100|59\.104)',
-'64\.233\.183\.104',
-'66\.102\.7\.104',
-'66\.249\.93\.104',
-'72\.14\.(203\.104|207\.104)',
-'msn\.',
-'live\.com',
-'voila\.',
-'mindset\.research\.yahoo',
-'yahoo\.','(66\.218\.71\.225|216\.109\.117\.135)',
-'search\.aol\.co',
-'tiscali\.',
-'lycos\.',
-'alexa\.com',
-'alltheweb\.com',
-'altavista\.',
-'a9\.com',
-'dmoz\.org',
-'netscape\.',
-'search\.terra\.',
-'www\.search\.com',
-'search\.sli\.sympatico\.ca',
-'excite\.'
-);
-
-@SearchEnginesSearchIDOrder_list2=(
-# Minor international search engines
-'northernlight\.',
-'hotbot\.',
-'kvasir\.',
-'webcrawler\.',
-'metacrawler\.',
-'go2net\.com',
-'(^|\.)go\.com',
-'euroseek\.',
-'looksmart\.',
-'spray\.',
-'nbci\.com\/search',
-'de\.ask.\com', # break out Ask country specific engines. (.jp is in Japan section)
-'es\.ask.\com',
-'fr\.ask.\com',
-'it\.ask.\com',
-'nl\.ask.\com',
-'uk\.ask.\com',
-'(^|\.)ask\.com',
-'atomz\.',
-'overture\.com', # Replace 'goto\.com','Goto.com',
-'teoma\.',
-'findarticles\.com',
-'infospace\.com',
-'mamma\.',
-'dejanews\.',
-'dogpile\.com',
-'wisenut\.com',
-'ixquick\.com',
-'search\.earthlink\.net',
-'i-une\.com',
-'blingo\.com',
-'centraldatabase\.org',
-'clusty\.com',
-'mysearch\.',
-'vivisimo\.com',
-'kartoo\.com',
-'icerocket\.com',
-'sphere\.com',
-# Chello Portals
-'chello\.at',
-'chello\.be',
-'chello\.cz',
-'chello\.fr',
-'chello\.hu',
-'chello\.nl',
-'chello\.no',
-'chello\.pl',
-'chello\.se',
-'chello\.sk',
-'chello', # required as catchall for new countries not yet known
-# Mirago
-'mirago\.be',
-'mirago\.ch',
-'mirago\.de',
-'mirago\.dk',
-'es\.mirago\.com',
-'mirago\.fr',
-'mirago\.it',
-'mirago\.nl',
-'no\.mirago\.com',
-'mirago\.se',
-'mirago\.co\.uk',
-'mirago', # required as catchall for new countries not yet known
-'answerbus\.com',
-# Minor Australian search engines
-'anzwers\.com\.au',
-# Minor brazilian search engines
-'engine\.exe', 'miner\.bol\.com\.br',
-# Minor chinese search engines
-'baidu\.com','search\.sina\.com','search\.sohu\.com', 'sogou\.com',
-# Minor czech search engines
-'atlas\.cz','seznam\.cz','quick\.cz','centrum\.cz','jyxo\.(cz|com)','najdi\.to','redbox\.cz',
-# Minor danish search-engines
-'opasia\.dk', 'danielsen\.com', 'sol\.dk', 'jubii\.dk', 'find\.dk', 'edderkoppen\.dk', 'netstjernen\.dk', 'orbis\.dk', 'tyfon\.dk', '1klik\.dk', 'ofir\.dk',
-# Minor dutch search engines
-'ilse\.','vindex\.',
-# Minor english search engines
-'(^|\.)ask\.co\.uk','bbc\.co\.uk/cgi-bin/search','ifind\.freeserve','looksmart\.co\.uk','splut\.','spotjockey\.','ukdirectory\.','ukindex\.co\.uk','ukplus\.','searchy\.co\.uk',
-# Minor finnish search engines
-'haku\.www\.fi',
-# Minor french search engines
-'recherche\.aol\.fr','ctrouve\.','francite\.','\.lbb\.org','rechercher\.libertysurf\.fr', 'search[\w\-]+\.free\.fr', 'recherche\.club-internet\.fr',
-'toile\.com', 'biglotron\.com',
-# Minor german search engines
-'sucheaol\.aol\.de',
-'fireball\.de','infoseek\.de','suche\d?\.web\.de','[a-z]serv\.rrzn\.uni-hannover\.de',
-'suchen\.abacho\.de','brisbane\.t-online\.de','allesklar\.de','meinestadt\.de',
-'212\.227\.33\.241',
-'(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)',
-'wwweasel\.de',
-'netluchs\.de',
-'schoenerbrausen\.de',
-# Minor hungarian search engines
-'heureka\.hu','vizsla\.origo\.hu','lapkereso\.hu','goliat\.hu','index\.hu','wahoo\.hu','webmania\.hu','search\.internetto\.hu',
-# Minor Indian search engines
-'sify\.com',
-# Minor italian search engines
-'virgilio\.it','arianna\.libero\.it','supereva\.com','kataweb\.it','search\.alice\.it\.master',
-# Minor Japanese search engines
-'ask\.jp',
-# Minor Norwegian search engines
-'sok\.start\.no', 'eniro\.no',
-# Minor polish search engines
-'szukaj\.wp\.pl',
-# Minor russian search engines
-'ya(ndex)?\.ru', 'aport\.ru', 'rambler\.ru', 'turtle\.ru', 'metabot\.ru',
-# Minor swedish search engines
-'evreka\.passagen\.se',
-# 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\.',
-'yahoo\.'=>'groups\.yahoo\.'
-);
-
-
-# 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',
-'images\.google\.','google_image',
-'google\.','google','216\.239\.(35\.101|37\.101|39\.100|39\.101|51\.100|51\.101|35\.100|59\.104)','google',
-'64\.233\.183\.104','google_cache',
-'66\.102\.7\.104','google_cache',
-'66\.249\.93\.104','google_cache',
-'72\.14\.(203\.104|207\.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)','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
-'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',
-# 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',
-# 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',
-# 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',
-# 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',
-# Minor Japanese search engines
-'ask\.jp','askjp',
-# Minor Norwegian search engines
-'sok\.start\.no','start', 'eniro\.no','eniro',
-# Minor polish search engines
-'szukaj\.wp\.pl','wp',
-# 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',
-# 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_image','(p|q|as_p|as_q)=',
-'google_cache','(p|q|as_p|as_q)=cache:*.(?=\+)',
-'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=',
-'sympatico', 'query=',
-'excite','search=',
-# Minor international search engines
-'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=',
-# 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
-# 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=',
-# 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=',
-# Minor Indian search engines
-'sify','keyword=',
-# Minor Italian search engines
-'virgilio','qs=',
-'arianna','query=',
-'supereva','q=',
-'kataweb','q=',
-'aliceitmaster','qs=',
-# Minor Japanese search engines
-'askjp','(ask|q)=',
-# Minor Norwegian search engines
-'start','q=', 'eniro','q=',
-# Minor polish search engines
-'wp','szukaj=',
-# Minor russian search engines
-'yandex', 'text=', 'rambler','words=', 'aport', 'r=', 'metabot', 'st=',
-# Minor swedish search engines
-'passagen','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_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
-'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 España</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>',
-# 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>',
-# 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 trouvé', 'francite','Francité', 'lbb', 'LBB', 'libertysurf', 'Libertysurf', 'free', 'Free.fr', 'clubinternet', 'Club-internet',
-'toile', 'Toile du Québec',
-'biglotron','<a href="http://www.biglotron.com/" title="Search Engine Home Page [new window]" target="_blank">Biglotron</a>',
-# Minor German search engines
-'aolde','AOL (de)',
-'fireball','Fireball', 'infoseek','Infoseek', 'webde','Web.de',
-'abacho','Abacho', 't-online','T-Online',
-'allesklar','allesklar.de', 'meinestadt','meinestadt.de',
-'metaspinner','metaspinner',
-'metacrawler_de','metacrawler.de',
-'wwweasel','<a href="http://wwweasel.de/" title="Search Engine Home Page [new window]" target="_blank">WWWeasel</a>',
-'netluchs','<a href="http://www.netluchs.de/" title="Search Engine Home Page [new window]" target="_blank">Netluchs</a>',
-'schoenerbrausen','<a href="http://www.schoenerbrausen.de/" title="Search Engine Home Page [new window]" target="_blank">Schoenerbrausen/</a>',
-# Minor hungarian search engines
-'heureka','Heureka', 'origo','Origo-Vizsla', 'lapkereso','Startlapkeresõ', 'goliat','Góliát', 'indexhu','Index', 'wahoo','Wahoo', 'webmania','webmania.hu', 'internetto','Internetto Keresõ',
-# Minor Indian search engines
-'sify','<a href="http://search.sify.com/" title="Search Engine Home Page [new window]" target="_blank">Sify</a>',
-# Minor italian search engines
-'virgilio','<a href="http://www.virgilio.it/" title="Search Engine Home Page [new window]" target="_blank">Virgilio</a>',
-'arianna','<a href="http://arianna.libero.it/" title="Search Engine Home Page [new window]" target="_blank">Arianna</a>',
-'supereva','<a href="http://search.supereva.com/" title="Search Engine Home Page [new window]" target="_blank">Supereva</a>',
-'kataweb','<a href="http://www.kataweb.it/ricerca/" title="Search Engine Home Page [new window]" target="_blank">Kataweb</a>',
-'aliceitmaster','<a href="http://www.alice.it/" title="Search Engine Home Page [new window]" target="_blank">search.alice.it.master</a>',
-# Minor Japanese search engines
-'askjp','<a href="http://www.ask.jp/" title="Search Engine Home Page [new window]" target="_blank">Ask Japan</a>',
-# Minor Norwegian search engines
-'start','start.no', 'eniro','<a href="http://www.eniro.no/" title="Search Engine Home Page [new window]" target="_blank">Eniro</a>',
-# Minor polish search engines
-'wp','Szukaj',
-# Minor russian search engines
-'yandex', 'Yandex', 'aport', 'Aport', 'rambler', 'Rambler', 'turtle', 'Turtle', 'metabot', 'MetaBot',
-# Minor swedish search engines
-'passagen','Evreka',
-# Minor Swiss search engines
-'searchch', 'search.ch', 'bluewin', 'search.bluewin.ch',
-# Generic search engines
-'search','Unknown search engines'
-);
-
-
-# Sanity check.
-# Enable this code and run perl search_engines.pm to check file entries are ok
-#-----------------------------------------------------------------------------
-#foreach my $key (@SearchEnginesSearchIDOrder_list1) {
-# if (! $SearchEnginesHashID{$key}) { error("Entry '$key' has been found in SearchEnginesSearchIDOrder_list1 with no value in SearchEnginesHashID");
-# foreach my $key2 (@SearchEnginesSearchIDOrder_list2) { if ($key2 eq $key) { error("$key is in 1 and 2\n"); } }
-# foreach my $key2 (@SearchEnginesSearchIDOrder_listgen) { if ($key2 eq $key) { error("$key is in 1 and gen\n"); } }
-#} }
-#foreach my $key (@SearchEnginesSearchIDOrder_list2) {
-# if (! $SearchEnginesHashID{$key}) { error("Entry '$key' has been found in SearchEnginesSearchIDOrder_list1 with no value in SearchEnginesHashID");
-# foreach my $key2 (@SearchEnginesSearchIDOrder_list1) { if ($key2 eq $key) { error("$key is in 2 and 1\n"); } }
-# foreach my $key2 (@SearchEnginesSearchIDOrder_listgen) { if ($key2 eq $key) { error("$key is in 2 and gen\n"); } }
-#} }
-#foreach my $key (@SearchEnginesSearchIDOrder_listgen) { if (! $SearchEnginesHashID{$key}) { error("Entry '$key' has been found in SearchEnginesSearchIDOrder_listgen with no value in SearchEnginesHashID"); } }
-#foreach my $key (keys %NotSearchEnginesKeys) { if (! $SearchEnginesHashID{$key}) { error("Entry '$key' has been found in NotSearchEnginesKeys with no value in SearchEnginesHashID"); } }
-#foreach my $key (keys %SearchEnginesKnownUrl) {
-# my $found=0;
-# foreach my $key2 (values %SearchEnginesHashID) {
-# if ($key eq $key2) { $found=1; last; }
-# }
-# if (! $found) { die "Entry '$key' has been found in SearchEnginesKnownUrl with no value in SearchEnginesHashID"; }
-#}
-#foreach my $key (keys %SearchEnginesHashLib) {
-# my $found=0;
-# foreach my $key2 (values %SearchEnginesHashID) {
-# if ($key eq $key2) { $found=1; last; }
-# }
-# if (! $found) { die "Entry '$key' has been found in SearchEnginesHashLib with no value in SearchEnginesHashID"; }
-#}
-#print @SearchEnginesSearchIDOrder_list1." ".@SearchEnginesSearchIDOrder_list2." ".@SearchEnginesSearchIDOrder_listgen;
-
-1;
+# AWSTATS SEARCH ENGINES DATABASE\r
+#------------------------------------------------------------------------------\r
+# If you want to add a Search Engine to extend AWStats database detection capabilities,\r
+# you must add an entry in SearchEnginesSearchIDOrder, SearchEnginesHashID and in\r
+# SearchEnginesHashLib.\r
+# An entry if known in SearchEnginesKnownUrl is also welcome.\r
+#------------------------------------------------------------------------------\r
+# $Revision$ - $Author$ - $Date$\r
+\r
+# 2005-08-19 Sean Carlos http://www.antezeta.com/awstats.html\r
+# added minor italian search engines\r
+# arianna http://arianna.libero.it/\r
+# supereva http://search.supereva.com/\r
+# kataweb http://kataweb.it/\r
+# corrected uk looksmart\r
+# 'askuk','ask=', 'bbc','q=', 'freeserve','q=', 'looksmart','key=',\r
+# to \r
+# 'askuk','ask=', 'bbc','q=', 'freeserve','q=', 'looksmartuk','key=',\r
+# corrected spelling\r
+# internationnal -> international\r
+# added 'google\.'=>'mail\.google\.', to NotSearchEnginesKeys in order to\r
+# avoid counting gmail referrals as search engine traffic\r
+# 2005-08-21 Sean Carlos http://www.antezeta.com/awstats.html\r
+# avoid counting babelfish.altavista referrals as search engine traffic\r
+# avoid counting translate.google referrals as search engine traffic\r
+# 2005-11-20 Sean Carlos\r
+# added missing 'tiscali','key=', entry. Check order\r
+# 2005-11-22 Sean Carlos\r
+# added Google Base & Froogle. Froogle not tested.\r
+# 2006-04-18 Sean Carlos http://www.antezeta.com/awstats.html\r
+# added biglotron.com (France)\r
+# added blingo http://www.blingo.com/\r
+# added Clusty & Vivisimo\r
+# added eniro.no (Norway) [https://sourceforge.net/forum/message.php?msg_id=3134783]\r
+# added GPU p2p search http://search.centraldatabase.org/\r
+# added mail.tiscali to "not search engines list" [https://sourceforge.net/forum/message.php?msg_id=3166688]\r
+# added Ask group's "mysearch"\r
+# added sify.com (India)\r
+# added sogou.com (Cina) [https://sourceforge.net/forum/message.php?msg_id=3501603]\r
+# Ask changes:\r
+# - added Ask Japan (ask.jp) \r
+# - break out Ask new country level variants (DE, ES, FR, IT, NL)\r
+# - updated Ask name from Ask Jevees\r
+# - added Ask q= parameter - many recent searches probably not recognized; [https://sourceforge.net/forum/message.php?msg_id=3465444]\r
+# - updated Ask uk (new uk.ask.com added to older ask.co.uk)\r
+# updated voila kw|rdata parameter [https://sourceforge.net/forum/message.php?msg_id=3373912]\r
+# for each new engine, added link to Search Engine. This serves to document engine. Done for major & Italian engines as well. Requires patch\r
+# to AWStats to allow untranslated html. Otherwise html will appear instead of link.\r
+# reviewed mnoGoSearch (http://www.mnogosearch.org/); the search engined mentioned no longer\r
+# exists https://sourceforge.net/forum/message.php?msg_id=3025426\r
+# 2006-05-13 Sean Carlos http://www.antezeta.com/awstats.html\r
+# added 10 Chello European broadband portals (Austria, Belgium, Czech Republic, France, Hungary, The Netherlands, Norway, Poland, Slovakia, Sweden)\r
+# added Alice Internal Search (blends data with Google?) search.alice.it.master:10005\r
+# added detection of google cache views from IPs 66.249.93.104 72.14.203.104 72.14.207.104\r
+# To do: add more extensive IP list; keywords not yet detected.\r
+# added icerocket.com blog search http://www.icerocket.com/\r
+# added live.com (msn) http://www.live.com/\r
+# added Meta motor kartoo. Note: Kartoo does not provide search words in referrers, thus the engine will appear in the\r
+# search engine list but the actual search words are not available.\r
+# added netluchs.de http://www.netluchs.de/\r
+# added sphere.com blog search http://www.sphere.com/\r
+# added wwweasel.de http://wwweasel.de\r
+# added Yahoo Mindset! http://mindset.research.yahoo.com/\r
+# updated Mirago query parameter recognition (qry=); added breakout for each country (France, Germany, Spain, Italy, Norway, Sweden, Denmark, Netherlands, Belgium, Switzerland)\r
+# 2006-05-13 Sean Carlos http://www.antezeta.com/awstats.html \r
+# added Google cache IPs 64.233.183.104 & 66.102.7.104\r
+# 2006-05-20 Sean Carlos http://www.antezeta.com/awstats.html \r
+# anzwers.com.au\r
+# schoenerbrausen.de http://www.schoenerbrausen.de/\r
+# added Google cache IP 216.239.59.104\r
+# answerbus http://www.answerbus.com/ (does not provide keywords)\r
+# 2006-05-23 Sean Carlos http://www.antezeta.com/awstats.html\r
+# added Google cache IP 66.102.9.104, 64.233.161.104\r
+# 2006-06-23 Sean Carlos http://www.antezeta.com/awstats.html \r
+# added Alice Search search.alice.it\r
+# added GoodSearch http://www.goodsearch.com/ (does not provide keywords) "a Yahoo-powered search engine that donates money to your favorite charity or school each time you search the web"\r
+# added googlee.com, variant of Google\r
+# added gotuneed http://www.gotuneed.com/ Italian search engine, in beta\r
+# added icq.com\r
+# added logic to parse Google Cache search keywords. Seems to work for alpha but not numeric cache IDs, i.e. search?q=cache:lWVLmnuGJswJ: is recognized but q=cache:Yv5qxeJNuhgJ: is not recognized. The URL triggering the keywords will also appear. The URLs are probably too varied to parse out?\r
+# added Nusearch http://www.nusearch.com/\r
+# added Polymeta www.polymeta.hu (does not provide keywords)\r
+# added scroogle http://www.scroogle.org/ (does not always provide keywords)\r
+# added Tango http://tango.hu/search.php?st=0&q=jeles+napok\r
+# Changed Google Cache notation 64\.233\.(161|167|179|183|187)\.104 to 64\.233\.1[0-9]{2}\.104\r
+# 72\.14\.(203|205|207|209|221)\.104 to 72\.14\.2[0-9]{2}\.104\r
+# 216\.239\.(51|59)\.104 to 216\.239\.5[0-9]\.104\r
+# 66\.102\.(7|9)\.104 to 66\.102\.[1-9]\.104\r
+# 2006-06-27 Sean Carlos http://www.antezeta.com/awstats.html\r
+# added Onet.pl http://szukaj.onet.pl/ \r
+# corrected name "Wirtualna Polska" from "Szukaj" (search); added link http://szukaj.wp.pl/ \r
+# 2006-06-30 Sean Carlos http://www.antezeta.com/awstats.html\r
+# Additional Polish Search Engines:\r
+# added Dodaj.pl http://www.dodaj.pl/\r
+# added Gazeta.pl http://szukaj.gazeta.pl/\r
+# added Gery.pl http://szukaj.gery.pl/\r
+# added Hoga.pl http://www.hoga.pl/\r
+# added Interia.pl http://www.google.interia.pl/\r
+# added Katalog.Onet.pl http://katalog.onet.pl/\r
+# added NetSprint.pl http://www.netsprint.pl/\r
+# added o2.pl http://szukaj2.o2.pl/\r
+# added Polska http://szukaj.polska.pl/\r
+# added Szukacz http://www.szukacz.pl/\r
+# added Wow.pl http://szukaj.wow.pl/\r
+# added Sagool http://sagool.jp/\r
+\r
+# 2006-08-25 Social Bookmarks\r
+# International\r
+# added del.icio.us/search - for now, just search referrer. To do: consider /tag/(tagname) referrer?\r
+# added stumbleupon.com - No keywords supplied.\r
+# added swik.net\r
+# added digg. Keywords sometimes supplied.\r
+# Italy\r
+# added segnalo.alice.it - No keywords supplied.\r
+# added ineffabile.it - No keywords supplied.\r
+\r
+# added filter for google groups. Attempt to parse group name as keyword.\r
+\r
+# 2006-09-14 \r
+# added Eniro Sverige http://www.eniro.se/\r
+# added MyWebSearch http://search.mywebsearch.com/ \r
+# added Teecno http://www.teecno.it/ Italian Open Source Search Engine\r
+\r
+#package AWSSE;\r
+\r
+# 2006-09-25 (Gabor Moizes)\r
+# added 4-counter (Google alternative) http://4-counter.com/\r
+# added Googlecom (Google alternative) http://googlecom.com/\r
+# added Goggle (Google alternative) http://goggle.co.hu/\r
+# added Comet toolbar http://as.starware.com\r
+# added new IP for Yahoo: 216.109.125.130\r
+# added Ledix http://ledix.net/\r
+# added AT&T search (powered by Google) http://www.att.net/\r
+# added Keresolap (Hungarian search engine) http://www.keresolap.hu/\r
+# added Mozbot (French search engine) http://www.mozbot.fr/\r
+# added Zoznam (Slovak search engine) http://www.zoznam.sk/\r
+# added sapo.pt (Portuguese search engine) http://www.sapo.pt/\r
+# added shaw.ca (powered by Google) http://start.shaw.ca/\r
+# added Searchalot http://www.searchalot.com/\r
+# added Copernic http://www.copernic.com/\r
+# added 216.109.125.130 to Yahoo\r
+# added 66.218.69.11 to Yahoo\r
+# added Avantfind http://www.avantfind.com/\r
+# added Steadysearch http://www.steadysearch.com/\r
+# added Steadysearch http://www.steady-search.com/\r
+# modified 216\.239\.5[0-9]\.104/search to 216\.239\.5[0-9]\.104\r
+\r
+\r
+# SearchEnginesSearchIDOrder\r
+# It contains all matching criteria to search for in log fields. This list is\r
+# used to know in which order to search Search Engines IDs.\r
+# Most frequent one are in list1, used when LevelForSearchEnginesDetection is 1 or more\r
+# Minor robots are in list2, used when LevelForSearchEnginesDetection is 2 or more\r
+# Note: Regex IDs are in lower case and ' ' and '+' are changed into '_'\r
+#------------------------------------------------------------------------------\r
+@SearchEnginesSearchIDOrder_list1=(\r
+# Major international search engines\r
+'base\.google\.',\r
+'froogle\.google\.',\r
+'groups\.google\.',\r
+'images\.google\.',\r
+'google\.',\r
+'googlee\.',\r
+'googlecom\.com',\r
+'goggle\.co\.hu',\r
+'216\.239\.(35|37|39|51)\.100',\r
+'216\.239\.(35|37|39|51)\.101', \r
+'216\.239\.5[0-9]\.104', \r
+'64\.233\.1[0-9]{2}\.104',\r
+'66\.102\.[1-9]\.104',\r
+'66\.249\.93\.104',\r
+'72\.14\.2[0-9]{2}\.104',\r
+'msn\.',\r
+'live\.com',\r
+'voila\.',\r
+'mindset\.research\.yahoo',\r
+'yahoo\.','(66\.218\.71\.225|216\.109\.117\.135|216\.109\.125\.130|66\.218\.69\.11)',\r
+'search\.aol\.co',\r
+'tiscali\.',\r
+'lycos\.',\r
+'alexa\.com',\r
+'alltheweb\.com',\r
+'altavista\.',\r
+'a9\.com',\r
+'dmoz\.org',\r
+'netscape\.',\r
+'search\.terra\.',\r
+'www\.search\.com',\r
+'search\.sli\.sympatico\.ca', \r
+'excite\.'\r
+);\r
+\r
+@SearchEnginesSearchIDOrder_list2=(\r
+# Minor international search engines\r
+'4\-counter\.com',\r
+'att\.net',\r
+'northernlight\.',\r
+'hotbot\.',\r
+'kvasir\.',\r
+'webcrawler\.',\r
+'metacrawler\.',\r
+'go2net\.com',\r
+'(^|\.)go\.com',\r
+'euroseek\.',\r
+'looksmart\.',\r
+'spray\.',\r
+'nbci\.com\/search',\r
+'de\.ask.\com', # break out Ask country specific engines. (.jp is in Japan section)\r
+'es\.ask.\com',\r
+'fr\.ask.\com',\r
+'it\.ask.\com',\r
+'nl\.ask.\com',\r
+'uk\.ask.\com',\r
+'(^|\.)ask\.com',\r
+'atomz\.',\r
+'overture\.com', # Replace 'goto\.com','Goto.com',\r
+'teoma\.',\r
+'findarticles\.com',\r
+'infospace\.com',\r
+'mamma\.',\r
+'dejanews\.',\r
+'dogpile\.com',\r
+'wisenut\.com',\r
+'ixquick\.com',\r
+'search\.earthlink\.net', \r
+'i-une\.com',\r
+'blingo\.com',\r
+'centraldatabase\.org',\r
+'clusty\.com',\r
+'mysearch\.',\r
+'vivisimo\.com',\r
+'kartoo\.com',\r
+'icerocket\.com',\r
+'sphere\.com',\r
+'ledix\.net',\r
+'start\.shaw\.ca',\r
+'searchalot\.com',\r
+'copernic\.com',\r
+'avantfind\.com',\r
+'steadysearch\.com',\r
+'steady-search\.com',\r
+# Chello Portals\r
+'chello\.at',\r
+'chello\.be',\r
+'chello\.cz',\r
+'chello\.fr',\r
+'chello\.hu',\r
+'chello\.nl',\r
+'chello\.no',\r
+'chello\.pl',\r
+'chello\.se',\r
+'chello\.sk',\r
+'chello', # required as catchall for new countries not yet known\r
+# Mirago \r
+'mirago\.be',\r
+'mirago\.ch',\r
+'mirago\.de',\r
+'mirago\.dk',\r
+'es\.mirago\.com',\r
+'mirago\.fr',\r
+'mirago\.it',\r
+'mirago\.nl',\r
+'no\.mirago\.com',\r
+'mirago\.se',\r
+'mirago\.co\.uk',\r
+'mirago', # required as catchall for new countries not yet known\r
+'answerbus\.com',\r
+'icq\.com\/search',\r
+'nusearch\.com',\r
+'goodsearch\.com',\r
+'scroogle\.org',\r
+'questionanswering\.com',\r
+'mywebsearch\.com',\r
+'as\.starware\.com',\r
+# Social Bookmarking Services\r
+'del\.icio\.us',\r
+'digg\.com',\r
+'stumbleupon\.com',\r
+'swik\.net',\r
+'segnalo\.alice\.it',\r
+'ineffabile\.it',\r
+# Minor Australian search engines\r
+'anzwers\.com\.au',\r
+# Minor brazilian search engines\r
+'engine\.exe', 'miner\.bol\.com\.br',\r
+# Minor chinese search engines\r
+'baidu\.com','search\.sina\.com','search\.sohu\.com', 'sogou\.com',\r
+# Minor czech search engines\r
+'atlas\.cz','seznam\.cz','quick\.cz','centrum\.cz','jyxo\.(cz|com)','najdi\.to','redbox\.cz',\r
+# Minor danish search-engines \r
+'opasia\.dk', 'danielsen\.com', 'sol\.dk', 'jubii\.dk', 'find\.dk', 'edderkoppen\.dk', 'netstjernen\.dk', 'orbis\.dk', 'tyfon\.dk', '1klik\.dk', 'ofir\.dk',\r
+# Minor dutch search engines\r
+'ilse\.','vindex\.',\r
+# Minor english search engines\r
+'(^|\.)ask\.co\.uk','bbc\.co\.uk/cgi-bin/search','ifind\.freeserve','looksmart\.co\.uk','splut\.','spotjockey\.','ukdirectory\.','ukindex\.co\.uk','ukplus\.','searchy\.co\.uk',\r
+# Minor finnish search engines\r
+'haku\.www\.fi',\r
+# Minor french search engines\r
+'recherche\.aol\.fr','ctrouve\.','francite\.','\.lbb\.org','rechercher\.libertysurf\.fr', 'search[\w\-]+\.free\.fr', 'recherche\.club-internet\.fr',\r
+'toile\.com', 'biglotron\.com', \r
+'mozbot\.fr', \r
+# Minor german search engines\r
+'sucheaol\.aol\.de',\r
+'fireball\.de','infoseek\.de','suche\d?\.web\.de','[a-z]serv\.rrzn\.uni-hannover\.de',\r
+'suchen\.abacho\.de','brisbane\.t-online\.de','allesklar\.de','meinestadt\.de',\r
+'212\.227\.33\.241',\r
+'(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)',\r
+'wwweasel\.de',\r
+'netluchs\.de',\r
+'schoenerbrausen\.de',\r
+# Minor Hungarian search engines\r
+'heureka\.hu','vizsla\.origo\.hu','lapkereso\.hu','goliat\.hu','index\.hu','wahoo\.hu','webmania\.hu','search\.internetto\.hu',\r
+'tango\.hu',\r
+'keresolap\.hu',\r
+'polymeta\.hu',\r
+# Minor Indian search engines\r
+'sify\.com',\r
+# Minor Italian search engines\r
+'virgilio\.it','arianna\.libero\.it','supereva\.com','kataweb\.it','search\.alice\.it\.master','search\.alice\.it','gotuneed\.com',\r
+'godado','jumpy\.it','shinyseek\.it','teecno\.it',\r
+# Minor Japanese search engines\r
+'ask\.jp','sagool\.jp',\r
+# Minor Norwegian search engines\r
+'sok\.start\.no', 'eniro\.no',\r
+# Minor Polish search engines\r
+'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',\r
+# Minor russian search engines\r
+'ya(ndex)?\.ru', 'aport\.ru', 'rambler\.ru', 'turtle\.ru', 'metabot\.ru',\r
+# Minor Swedish search engines\r
+'evreka\.passagen\.se','eniro\.se',\r
+# Minor Slovak search engines\r
+'zoznam\.sk',\r
+# Minor Portuguese search engines\r
+'sapo\.pt',\r
+# Minor swiss search engines\r
+'search\.ch', 'search\.bluewin\.ch'\r
+);\r
+@SearchEnginesSearchIDOrder_listgen=(\r
+# Generic search engines\r
+'search\..*\.\w+'\r
+);\r
+\r
+\r
+# NotSearchEnginesKeys\r
+# If a search engine key is found, we check its exclude list to know if it's\r
+# really a search engine\r
+#------------------------------------------------------------------------------\r
+%NotSearchEnginesKeys=(\r
+'altavista\.'=>'babelfish\.altavista\.',\r
+'google\.'=>'mail\.google\.',\r
+'google\.'=>'translate\.google\.',\r
+'msn\.'=>'hotmail\.msn\.',\r
+'tiscali\.'=>'mail\.tiscali\.',\r
+'yahoo\.'=>'mail\.yahoo\.'\r
+);\r
+\r
+\r
+# SearchEnginesHashID\r
+# Each Search Engine Search ID is associated to an AWStats id string\r
+#------------------------------------------------------------------------------\r
+%SearchEnginesHashID = (\r
+# Major international search engines\r
+'base\.google\.','google_base',\r
+'froogle\.google\.','google_froogle',\r
+'groups\.google\.','google_groups',\r
+'images\.google\.','google_image',\r
+'google\.','google',\r
+'googlee\.','google',\r
+'googlecom\.com','google',\r
+'goggle\.co\.hu','google',\r
+'216\.239\.(35|37|39|51)\.100','google_cache',\r
+'216\.239\.(35|37|39|51)\.101','google_cache',\r
+'216\.239\.5[0-9]\.104','google_cache',\r
+'64\.233\.1[0-9]{2}\.104','google_cache',\r
+'66\.102\.[1-9]\.104','google_cache',\r
+'66\.249\.93\.104','google_cache',\r
+'72\.14\.2[0-9]{2}\.104','google_cache',\r
+'msn\.','msn',\r
+'live\.com','live',\r
+'voila\.','voila',\r
+'mindset\.research\.yahoo','yahoo_mindset',\r
+'yahoo\.','yahoo','(66\.218\.71\.225|216\.109\.117\.135|216\.109\.125\.130|66\.218\.69\.11)','yahoo',\r
+'lycos\.','lycos',\r
+'alexa\.com','alexa',\r
+'alltheweb\.com','alltheweb',\r
+'altavista\.','altavista',\r
+'a9\.com','a9',\r
+'dmoz\.org','dmoz',\r
+'netscape\.','netscape',\r
+'search\.terra\.','terra',\r
+'www\.search\.com','search.com',\r
+'tiscali\.','tiscali',\r
+'search\.aol\.co','aol',\r
+'search\.sli\.sympatico\.ca','sympatico',\r
+'excite\.','excite',\r
+# Minor international search engines\r
+'4\-counter\.com','google4counter',\r
+'att\.net','att',\r
+'northernlight\.','northernlight',\r
+'hotbot\.','hotbot',\r
+'kvasir\.','kvasir',\r
+'webcrawler\.','webcrawler',\r
+'metacrawler\.','metacrawler',\r
+'go2net\.com','go2net',\r
+'(^|\.)go\.com','go',\r
+'euroseek\.','euroseek',\r
+'looksmart\.','looksmart',\r
+'spray\.','spray',\r
+'nbci\.com\/search','nbci',\r
+'de\.ask.\com','askde', # break out Ask country specific engines.\r
+'es\.ask.\com','askes',\r
+'fr\.ask.\com','askfr',\r
+'it\.ask.\com','askit',\r
+'nl\.ask.\com','asknl',\r
+'uk\.ask.\com','askuk',\r
+'(^|\.)ask\.co\.uk','askuk',\r
+'(^|\.)ask\.com','ask',\r
+'atomz\.','atomz',\r
+'overture\.com','overture', # Replace 'goto\.com','Goto.com',\r
+'teoma\.','teoma',\r
+'findarticles\.com','findarticles',\r
+'infospace\.com','infospace',\r
+'mamma\.','mamma',\r
+'dejanews\.','dejanews',\r
+'dogpile\.com','dogpile',\r
+'wisenut\.com','wisenut',\r
+'ixquick\.com','ixquick',\r
+'search\.earthlink\.net','earthlink',\r
+'i-une\.com','iune',\r
+'blingo\.com','blingo',\r
+'centraldatabase\.org','centraldatabase',\r
+'clusty\.com','clusty',\r
+'mysearch\.','mysearch',\r
+'vivisimo\.com','vivisimo',\r
+'kartoo\.com','kartoo',\r
+'icerocket\.com','icerocket',\r
+'sphere\.com','sphere',\r
+'ledix\.net','ledix',\r
+'start\.shaw\.ca','shawca',\r
+'searchalot\.com','searchalot',\r
+'copernic\.com','copernic',\r
+'avantfind\.com','avantfind',\r
+'steadysearch\.com','steadysearch',\r
+'steady-search\.com','steadysearch',\r
+# Chello Portals\r
+'chello\.at','chelloat',\r
+'chello\.be','chellobe',\r
+'chello\.cz','chellocz',\r
+'chello\.fr','chellofr',\r
+'chello\.hu','chellohu',\r
+'chello\.nl','chellonl',\r
+'chello\.no','chellono',\r
+'chello\.pl','chellopl',\r
+'chello\.se','chellose',\r
+'chello\.sk','chellosk',\r
+'chello','chellocom',\r
+# Mirago \r
+'mirago\.be','miragobe',\r
+'mirago\.ch','miragoch',\r
+'mirago\.de','miragode',\r
+'mirago\.dk','miragodk',\r
+'es\.mirago\.com','miragoes',\r
+'mirago\.fr','miragofr',\r
+'mirago\.it','miragoit',\r
+'mirago\.nl','miragonl',\r
+'no\.mirago\.com','miragono',\r
+'mirago\.se','miragose',\r
+'mirago\.co\.uk','miragocouk',\r
+'mirago','mirago', # required as catchall for new countries not yet known\r
+'answerbus\.com','answerbus',\r
+'icq\.com\/search','icq',\r
+'nusearch\.com','nusearch',\r
+'goodsearch\.com','goodsearch',\r
+'scroogle\.org','scroogle',\r
+'questionanswering\.com','questionanswering',\r
+'mywebsearch\.com','mywebsearch',\r
+'as\.starware\.com','comettoolbar',\r
+# Social Bookmarking Services\r
+'del\.icio\.us','delicious',\r
+'digg\.com','digg',\r
+'stumbleupon\.com','stumbleupon',\r
+'swik\.net','swik',\r
+'segnalo\.alice\.it','segnalo',\r
+'ineffabile\.it','ineffabile',\r
+# Minor Australian search engines\r
+'anzwers\.com\.au','anzwers',\r
+# Minor brazilian search engines\r
+'engine\.exe','engine',\r
+'miner\.bol\.com\.br','miner',\r
+# Minor chinese search engines\r
+'baidu\.com','baidu',\r
+'search\.sina\.com','sina',\r
+'search\.sohu\.com','sohu',\r
+'sogou\.com','sogou',\r
+# Minor czech search engines\r
+'atlas\.cz','atlas',\r
+'seznam\.cz','seznam',\r
+'quick\.cz','quick',\r
+'centrum\.cz','centrum',\r
+'jyxo\.(cz|com)','jyxo',\r
+'najdi\.to','najdi',\r
+'redbox\.cz','redbox',\r
+# Minor danish search-engines \r
+'opasia\.dk','opasia',\r
+'danielsen\.com','danielsen',\r
+'sol\.dk','sol',\r
+'jubii\.dk','jubii',\r
+'find\.dk','finddk',\r
+'edderkoppen\.dk','edderkoppen',\r
+'netstjernen\.dk','netstjernen',\r
+'orbis\.dk','orbis',\r
+'tyfon\.dk','tyfon',\r
+'1klik\.dk','1klik',\r
+'ofir\.dk','ofir',\r
+# Minor dutch search engines\r
+'ilse\.','ilse',\r
+'vindex\.','vindex',\r
+# Minor english search engines\r
+'bbc\.co\.uk/cgi-bin/search','bbc',\r
+'ifind\.freeserve','freeserve',\r
+'looksmart\.co\.uk','looksmartuk',\r
+'splut\.','splut',\r
+'spotjockey\.','spotjockey',\r
+'ukdirectory\.','ukdirectory',\r
+'ukindex\.co\.uk','ukindex',\r
+'ukplus\.','ukplus',\r
+'searchy\.co\.uk','searchy',\r
+# Minor finnish search engines\r
+'haku\.www\.fi','haku',\r
+# Minor french search engines\r
+'recherche\.aol\.fr','aolfr',\r
+'ctrouve\.','ctrouve',\r
+'francite\.','francite',\r
+'\.lbb\.org','lbb',\r
+'rechercher\.libertysurf\.fr','libertysurf',\r
+'search[\w\-]+\.free\.fr','free',\r
+'recherche\.club-internet\.fr','clubinternet',\r
+'toile\.com','toile',\r
+'biglotron\.com', 'biglotron',\r
+'mozbot\.fr', 'mozbot',\r
+# Minor german search engines\r
+'sucheaol\.aol\.de','aolde',\r
+'fireball\.de','fireball',\r
+'infoseek\.de','infoseek',\r
+'suche\d?\.web\.de','webde',\r
+'[a-z]serv\.rrzn\.uni-hannover\.de','meta',\r
+'suchen\.abacho\.de','abacho',\r
+'brisbane\.t-online\.de','t-online',\r
+'allesklar\.de','allesklar',\r
+'meinestadt\.de','meinestadt',\r
+'212\.227\.33\.241','metaspinner',\r
+'(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',\r
+'wwweasel\.de','wwweasel',\r
+'netluchs\.de','netluchs',\r
+'schoenerbrausen\.de','schoenerbrausen',\r
+# Minor Hungarian search engines\r
+'heureka\.hu','heureka',\r
+'vizsla\.origo\.hu','origo',\r
+'lapkereso\.hu','lapkereso',\r
+'goliat\.hu','goliat',\r
+'index\.hu','indexhu',\r
+'wahoo\.hu','wahoo',\r
+'webmania\.hu','webmania',\r
+'search\.internetto\.hu','internetto',\r
+'tango\.hu','tango_hu',\r
+'keresolap\.hu','keresolap_hu',\r
+'polymeta\.hu','polymeta_hu',\r
+# Minor Indian search engines\r
+'sify\.com','sify',\r
+# Minor Italian search engines\r
+'virgilio\.it','virgilio',\r
+'arianna\.libero\.it','arianna',\r
+'supereva\.com','supereva',\r
+'kataweb\.it','kataweb',\r
+'search\.alice\.it\.master','aliceitmaster',\r
+'search\.alice\.it','aliceit',\r
+'gotuneed\.com','gotuneed',\r
+'godado','godado',\r
+'jumpy\.it','jumpy\.it',\r
+'shinyseek\.it','shinyseek\.it',\r
+'teecno\.it','teecnoit',\r
+# Minor Japanese search engines\r
+'ask\.jp','askjp',\r
+'sagool\.jp','sagool',\r
+# Minor Norwegian search engines\r
+'sok\.start\.no','start', 'eniro\.no','eniro',\r
+# Minor Polish search engines\r
+'szukaj\.wp\.pl','wp',\r
+'szukaj\.onet\.pl','onetpl',\r
+'dodaj\.pl','dodajpl',\r
+'gazeta\.pl','gazetapl',\r
+'gery\.pl','gerypl',\r
+'netsprint\.pl\/hoga\-search','hogapl',\r
+'netsprint\.pl','netsprintpl',\r
+'interia\.pl','interiapl',\r
+'katalog\.onet\.pl','katalogonetpl',\r
+'o2\.pl','o2pl',\r
+'polska\.pl','polskapl',\r
+'szukacz\.pl','szukaczpl',\r
+'wow\.pl','wowpl',\r
+# Minor russian search engines\r
+'ya(ndex)?\.ru','yandex',\r
+'aport\.ru','aport',\r
+'rambler\.ru','rambler',\r
+'turtle\.ru','turtle',\r
+'metabot\.ru','metabot',\r
+# Minor Swedish search engines\r
+'evreka\.passagen\.se','passagen',\r
+'eniro\.se','enirose',\r
+# Minor Slovak search engines\r
+'zoznam\.sk','zoznam',\r
+# Minor Portuguese search engines\r
+'sapo\.pt','sapo',\r
+# Minor swiss search engines\r
+'search\.ch','searchch',\r
+'search\.bluewin\.ch','bluewin',\r
+# Generic search engines\r
+'search\..*\.\w+','search'\r
+);\r
+\r
+\r
+# SearchEnginesWithKeysNotInQuery\r
+# List of search engines that store keyword as page instead of query parameter\r
+#------------------------------------------------------------------------------\r
+%SearchEnginesWithKeysNotInQuery=(\r
+'a9',1 # www.a9.com/searckey1%20searchkey2\r
+);\r
+\r
+# SearchEnginesKnownUrl\r
+# Known rules to extract keywords from a referrer search engine URL\r
+#------------------------------------------------------------------------------\r
+%SearchEnginesKnownUrl=(\r
+# Most common search engines\r
+'alexa','q=',\r
+'alltheweb','q(|uery)=',\r
+'altavista','q=',\r
+'a9','a9\.com\/', \r
+'dmoz','search=',\r
+'google_base','(p|q|as_p|as_q)=',\r
+'google_froogle','(p|q|as_p|as_q)=',\r
+'google_groups','group\/', # does not work\r
+'google_image','(p|q|as_p|as_q)=',\r
+'google_cache','(p|q|as_p|as_q)=cache:[0-9A-Za-z]{12}:',\r
+'google','(p|q|as_p|as_q)=',\r
+'lycos','query=',\r
+'msn','q=',\r
+'live','q=',\r
+'netscape','search=',\r
+'tiscali','key=',\r
+'aol','query=',\r
+'terra','query=',\r
+'voila','(kw|rdata)=',\r
+'search.com','q=',\r
+'yahoo_mindset','p=',\r
+'yahoo','p=',\r
+'sympatico', 'query=', \r
+'excite','search=',\r
+# Minor international search engines\r
+'google4counter','(p|q|as_p|as_q)=',\r
+'att','qry=',\r
+'go','qt=',\r
+'askde','(ask|q)=', # break out Ask country specific engines.\r
+'askes','(ask|q)=',\r
+'askfr','(ask|q)=',\r
+'askit','(ask|q)=',\r
+'asknl','(ask|q)=',\r
+'ask','(ask|q)=',\r
+'atomz','sp-q=',\r
+'euroseek','query=',\r
+'findarticles','key=',\r
+'go2net','general=',\r
+'hotbot','mt=',\r
+'infospace','qkw=',\r
+'kvasir', 'q=',\r
+'looksmart','key=',\r
+'mamma','query=',\r
+'metacrawler','general=',\r
+'nbci','keyword=',\r
+'northernlight','qr=',\r
+'overture','keywords=',\r
+'dogpile', 'q(|kw)=',\r
+'spray','string=',\r
+'teoma','q=',\r
+'webcrawler','searchText=',\r
+'wisenut','query=', \r
+'ixquick', 'query=',\r
+'earthlink', 'q=',\r
+'iune','(keywords|q)=',\r
+'blingo','q=',\r
+'centraldatabase','query=',\r
+'clusty','query=',\r
+'mysearch','searchfor=',\r
+'vivisimo','query=',\r
+# kartoo: No keywords passed in referring URL.\r
+'kartoo',,\r
+'icerocket','q=',\r
+'sphere','q=',\r
+'ledix','q=',\r
+'shawca','q=',\r
+'searchalot','q=',\r
+'copernic','web\/',\r
+'avantfind','keywords=',\r
+'steadysearch','w=',\r
+# Chello Portals\r
+'chelloat','q1=',\r
+'chellobe','q1=',\r
+'chellocz','q1=',\r
+'chellofr','q1=',\r
+'chellohu','q1=',\r
+'chellonl','q1=',\r
+'chellono','q1=',\r
+'chellopl','q1=',\r
+'chellose','q1=',\r
+'chellosk','q1=',\r
+'chellocom','q1=',\r
+# Mirago\r
+'miragobe','(txtsearch|qry)=',\r
+'miragoch','(txtsearch|qry)=',\r
+'miragode','(txtsearch|qry)=',\r
+'miragodk','(txtsearch|qry)=',\r
+'miragoes','(txtsearch|qry)=',\r
+'miragofr','(txtsearch|qry)=',\r
+'miragoit','(txtsearch|qry)=',\r
+'miragonl','(txtsearch|qry)=',\r
+'miragono','(txtsearch|qry)=',\r
+'miragose','(txtsearch|qry)=',\r
+'miragocouk','(txtsearch|qry)=',\r
+'mirago','(txtsearch|qry)=',\r
+'answerbus','', # Does not provide query parameters\r
+'icq','q=',\r
+'nusearch','nusearch_terms=',\r
+'goodsearch','Keywords=',\r
+'scroogle','Gw=', # Does not always provide query parameters\r
+'questionanswering','',\r
+'mywebsearch','searchfor=',\r
+'comettoolbar','qry=',\r
+# Social Bookmarking Services\r
+'delicious','all=',\r
+'digg','s=',\r
+'stumbleupon','',\r
+'swik','swik\.net/', # does not work. Keywords follow domain, e.g. http://swik.net/awstats+analytics\r
+'segnalo','',\r
+'ineffabile','',\r
+# Minor Australian search engines\r
+'anzwers','search=',\r
+# Minor brazilian search engines\r
+'engine','p1=', 'miner','q=',\r
+# Minor chinese search engines\r
+'baidu','word=', 'sina', 'word=', 'sohu','word=', 'sogou', 'query=',\r
+# Minor czech search engines\r
+'atlas','searchtext=', 'seznam','w=', 'quick','query=', 'centrum','q=', 'jyxo','s=', 'najdi','dotaz=', 'redbox','srch=',\r
+# Minor danish search engines\r
+'opasia','q=', 'danielsen','q=', 'sol','q=', 'jubii','soegeord=', 'finddk','words=', 'edderkoppen','query=', 'orbis','search_field=', '1klik','query=', 'ofir','querytext=',\r
+# Minor dutch search engines\r
+'ilse','search_for=', 'vindex','in=',\r
+# Minor english search engines\r
+'askuk','(ask|q)=', 'bbc','q=', 'freeserve','q=', 'looksmartuk','key=',\r
+'splut','pattern=', 'spotjockey','Search_Keyword=', 'ukindex', 'stext=', 'ukdirectory','k=', 'ukplus','search=', 'searchy', 'search_term=',\r
+# Minor finnish search engines\r
+'haku','w=',\r
+# Minor french search engines\r
+'francite','name=', 'clubinternet', 'q=',\r
+'toile', 'q=',\r
+'biglotron','question=',\r
+'mozbot','q=',\r
+# Minor german search engines\r
+'aolde','q=',\r
+'fireball','q=', 'infoseek','qt=', 'webde','su=',\r
+'abacho','q=', 't-online','q=', \r
+'metaspinner','qry=',\r
+'metacrawler_de','qry=',\r
+'wwweasel','q=',\r
+'netluchs','query=',\r
+'schoenerbrausen','q=',\r
+# Minor Hungarian search engines\r
+'heureka','heureka=', 'origo','(q|search)=', 'goliat','KERESES=', 'wahoo','q=', 'internetto','searchstr=',\r
+'keresolap_hu','q=',\r
+'tango_hu','q=',\r
+'polymeta_hu','',\r
+# Minor Indian search engines\r
+'sify','keyword=',\r
+# Minor Italian search engines\r
+'virgilio','qs=',\r
+'arianna','query=',\r
+'supereva','q=',\r
+'kataweb','q=',\r
+'aliceitmaster','qs=',\r
+'aliceit','qs=',\r
+'gotuneed','', # Not yet known\r
+'godado','Keywords=',\r
+'jumpy\.it','searchWord=',\r
+'shinyseek\.it','KEY=',\r
+'teecnoit','q=',\r
+# Minor Japanese search engines\r
+'askjp','(ask|q)=',\r
+'sagool','q=',\r
+# Minor Norwegian search engines\r
+'start','q=', 'eniro','q=',\r
+# Minor Polish search engines\r
+'wp','szukaj=',\r
+'onetpl','qt=',\r
+'dodajpl','keyword=',\r
+'gazetapl','slowo=',\r
+'gerypl','q=',\r
+'hogapl','qt=',\r
+'netsprintpl','q=',\r
+'interiapl','q=',\r
+'katalogonetpl','qt=',\r
+'o2pl','qt=',\r
+'polskapl','qt=',\r
+'szukaczpl','q=',\r
+'wowpl','q=',\r
+# Minor russian search engines\r
+'yandex', 'text=', 'rambler','words=', 'aport', 'r=', 'metabot', 'st=',\r
+# Minor swedish search engines\r
+'passagen','q=',\r
+'enirose','q=',\r
+# Minor swiss search engines\r
+'searchch', 'q=', 'bluewin', 'qry='\r
+);\r
+\r
+# SearchEnginesKnownUrlNotFound\r
+# Known rules to extract not found keywords from a referrer search engine URL\r
+#------------------------------------------------------------------------------\r
+%SearchEnginesKnownUrlNotFound=(\r
+# Most common search engines\r
+'msn','origq='\r
+);\r
+\r
+# If no rules are known, WordsToExtractSearchUrl will be used to search keyword parameter\r
+# If no rules are known and search in WordsToExtractSearchUrl failed, this will be used to clean URL of not keyword parameters.\r
+#------------------------------------------------------------------------------\r
+@WordsToExtractSearchUrl= ('ask=','claus=','general=','key=','kw=','keyword=','keywords=','MT=','p=','q=','qr=','qt=','query=','s=','search=','searchText=','string=','su=','txtsearch=','w=');\r
+@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=');\r
+\r
+# SearchEnginesKnownUTFCoding\r
+# Known parameter that proves a search engine has coded its parameters in UTF-8\r
+#------------------------------------------------------------------------------\r
+%SearchEnginesKnownUTFCoding=(\r
+# Most common search engines\r
+'google','ie=utf-8',\r
+'alltheweb','cs=utf-8'\r
+);\r
+\r
+\r
+# SearchEnginesHashLib\r
+# List of search engines names\r
+# 'search_engine_id', 'search_engine_name',\r
+#------------------------------------------------------------------------------\r
+%SearchEnginesHashLib=(\r
+# Major international search engines\r
+'alexa','<a href="http://www.alexa.com/" title="Search Engine Home Page [new window]" target="_blank">Alexa</a>',\r
+'alltheweb','<a href="http://www.alltheweb.com/" title="Search Engine Home Page [new window]" target="_blank">AllTheWeb</a>',\r
+'altavista','<a href="http://www.altavista.com/" title="Search Engine Home Page [new window]" target="_blank">AltaVista</a>',\r
+'a9', '<a href="http://www.a9.com/" title="Search Engine Home Page [new window]" target="_blank">A9</a>',\r
+'dmoz','<a href="http://dmoz.org/" title="Search Engine Home Page [new window]" target="_blank">DMOZ</a>',\r
+'google_base','<a href="http://base.google.com/" title="Search Engine Home Page [new window]" target="_blank">Google (Base)</a>',\r
+'google_froogle','<a href="http://froogle.google.com/" title="Search Engine Home Page [new window]" target="_blank">Froogle (Google)</a>',\r
+'google_groups','<a href="http://groups.google.com/" title="Search Engine Home Page [new window]" target="_blank">Google (Groups)</a>',\r
+'google_image','<a href="http://images.google.com/" title="Search Engine Home Page [new window]" target="_blank">Google (Images)</a>',\r
+'google_cache','<a href="http://www.google.com/help/features.html#cached" title="Search Engine Home Page [new window]" target="_blank">Google (cache)</a>',\r
+'google','<a href="http://www.google.com/" title="Search Engine Home Page [new window]" target="_blank">Google</a>',\r
+'lycos','<a href="http://www.lycos.com/" title="Search Engine Home Page [new window]" target="_blank">Lycos</a>',\r
+'msn','<a href="http://search.msn.com/" title="Search Engine Home Page [new window]" target="_blank">MSN Search</a>',\r
+'live','<a href="http://www.live.com/" title="Search Engine Home Page [new window]" target="_blank">Windows Live</a>',\r
+'netscape','<a href="http://www.netscape.com/" title="Search Engine Home Page [new window]" target="_blank">Netscape</a>',\r
+'aol','<a href="http://www.aol.com/" title="Search Engine Home Page [new window]" target="_blank">AOL</a>',\r
+'terra','<a href="http://www.terra.es/" title="Search Engine Home Page [new window]" target="_blank">Terra</a>',\r
+'tiscali','<a href="http://search.tiscali.com/" title="Search Engine Home Page [new window]" target="_blank">Tiscali</a>',\r
+'voila','<a href="http://www.voila.fr/" title="Search Engine Home Page [new window]" target="_blank">Voila</a>',\r
+'search.com','<a href="http://www.search.com/" title="Search Engine Home Page [new window]" target="_blank">Search.com</a>',\r
+'yahoo_mindset','<a href="http://mindset.research.yahoo.com/" title="Search Engine Home Page [new window]" target="_blank">Yahoo! Mindset</a>',\r
+'yahoo','<a href="http://www.yahoo.com/" title="Search Engine Home Page [new window]" target="_blank">Yahoo!</a>',\r
+'sympatico','<a href="http://sympatico.msn.ca/" title="Search Engine Home Page [new window]" target="_blank">Sympatico</a>',\r
+'excite','<a href="http://www.excite.com/" title="Search Engine Home Page [new window]" target="_blank">Excite</a>',\r
+# Minor international search engines\r
+'google4counter','<a href="http://www.4-counter.com/" title="Search Engine Home Page [new window]" target="_blank">4-counter (Google)</a>',\r
+'att','<a href="http://www.att.net/" title="Search Engine Home Page [new window]" target="_blank">AT&T search (powered by Google)</a>',\r
+'go','Go.com',\r
+'askde','<a href="http://de.ask.com/" title="Search Engine Home Page [new window]" target="_blank">Ask Deutschland</a>',\r
+'askes','<a href="http://es.ask.com/" title="Search Engine Home Page [new window]" target="_blank">Ask España</a>', # break out Ask country specific engines.\r
+'askfr','<a href="http://fr.ask.com/" title="Search Engine Home Page [new window]" target="_blank">Ask France</a>',\r
+'askit','<a href="http://it.ask.com/" title="Search Engine Home Page [new window]" target="_blank">Ask Italia</a>',\r
+'asknl','<a href="http://nl.ask.com/" title="Search Engine Home Page [new window]" target="_blank">Ask Nederland</a>',\r
+'ask','<a href="http://www.ask.com/" title="Search Engine Home Page [new window]" target="_blank">Ask</a>',\r
+'atomz','Atomz',\r
+'dejanews','DejaNews',\r
+'euroseek','Euroseek',\r
+'findarticles','Find Articles',\r
+'go2net','Go2Net (Metamoteur)',\r
+'hotbot','Hotbot',\r
+'infospace','InfoSpace',\r
+'kvasir','Kvasir',\r
+'looksmart','Looksmart',\r
+'mamma','Mamma',\r
+'metacrawler','MetaCrawler (Metamoteur)',\r
+'nbci','NBCI',\r
+'northernlight','NorthernLight',\r
+'overture','Overture', # Replace 'goto\.com','Goto.com',\r
+'dogpile','<a href="http://www.dogpile.com/" title="Search Engine Home Page [new window]" target="_blank">Dogpile</a>',\r
+'spray','Spray',\r
+'teoma','<a href="http://search.ask.com/" title="Search Engine Home Page [new window]" target="_blank">Teoma</a>', # Replace 'directhit\.com','DirectHit',\r
+'webcrawler','<a href="http://www.webcrawler.com/" title="Search Engine Home Page [new window]" target="_blank">WebCrawler</a>',\r
+'wisenut','WISENut', \r
+'ixquick','<a href="http://www.ixquick.com/" title="Search Engine Home Page [new window]" target="_blank">ix quick</a>', \r
+'earthlink', 'Earth Link',\r
+'iune','<a href="http://www.i-une.com/" title="Search Engine Home Page [new window]" target="_blank">i-une</a>',\r
+'blingo','<a href="http://www.blingo.com/" title="Search Engine Home Page [new window]" target="_blank">Blingo</a>',\r
+'centraldatabase','<a href="http://search.centraldatabase.org/" title="Search Engine Home Page [new window]" target="_blank">GPU p2p search</a>',\r
+'clusty','<a href="http://www.clusty.com/" title="Search Engine Home Page [new window]" target="_blank">Clusty</a>',\r
+'mysearch','<a href="http://www.mysearch.com" title="Search Engine Home Page [new window]" target="_blank">My Search</a>',\r
+'vivisimo','<a href="http://www.vivisimo.com/" title="Search Engine Home Page [new window]" target="_blank">Vivisimo</a>',\r
+'kartoo','<a href="http://www.kartoo.com/" title="Search Engine Home Page [new window]" target="_blank">Kartoo</a>',\r
+'icerocket','<a href="http://www.icerocket.com/" title="Search Engine Home Page [new window]" target="_blank">Icerocket (Blog)</a>',\r
+'sphere','<a href="http://www.sphere.com/" title="Search Engine Home Page [new window]" target="_blank">Sphere (Blog)</a>',\r
+'ledix','<a href="http://www.ledix.net/" title="Search Engine Home Page [new window]" target="_blank">Ledix</a>',\r
+'shawca','<a href="http://start.shaw.ca/" title="Search Engine Home Page [new window]" target="_blank">Shaw.ca</a>',\r
+'searchalot','<http://www.searchalot.com/" title="Search Engine Home Page [new window]" target="_blank">Searchalot</a>',\r
+'copernic','<http://www.copernic.com/" title="Search Engine Home Page [new window]" target="_blank">Copernic</a>',\r
+'avantfind','<http://www.avantfind.com/" title="Search Engine Home Page [new window]" target="_blank">Avantfind</a>',\r
+'steadysearch','<http://www.avantfind.com/" title="Search Engine Home Page [new window]" target="_blank">Avantfind</a>',\r
+# Chello Portals\r
+'chelloat','<a href="http://www.chello.at/" title="Search Engine Home Page [new window]" target="_blank">Chello Austria</a>',\r
+'chellobe','<a href="http://www.chello.be/" title="Search Engine Home Page [new window]" target="_blank">Chello Belgium</a>',\r
+'chellocz','<a href="http://www.chello.cz/" title="Search Engine Home Page [new window]" target="_blank">Chello Czech Republic</a>',\r
+'chellofr','<a href="http://www.chello.fr/" title="Search Engine Home Page [new window]" target="_blank">Chello France</a>',\r
+'chellohu','<a href="http://www.chello.hu/" title="Search Engine Home Page [new window]" target="_blank">Chello Hungary</a>',\r
+'chellonl','<a href="http://www.chello.nl/" title="Search Engine Home Page [new window]" target="_blank">Chello Netherlands</a>',\r
+'chellono','<a href="http://www.chello.no/" title="Search Engine Home Page [new window]" target="_blank">Chello Norway</a>',\r
+'chellopl','<a href="http://www.chello.pl/" title="Search Engine Home Page [new window]" target="_blank">Chello Poland</a>',\r
+'chellose','<a href="http://www.chello.se/" title="Search Engine Home Page [new window]" target="_blank">Chello Sweden</a>',\r
+'chellosk','<a href="http://www.chello.sk/" title="Search Engine Home Page [new window]" target="_blank">Chello Slovakia</a>',\r
+'chellocom','<a href="http://www.chello.com/" title="Search Engine Home Page [new window]" target="_blank">Chello (Country not recognized)</a>',\r
+# Mirago\r
+'miragobe','<a href="http://www.mirago.be/" title="Search Engine Home Page [new window]" target="_blank">Mirago Belgium</a>',\r
+'miragoch','<a href="http://www.mirago.ch/" title="Search Engine Home Page [new window]" target="_blank">Mirago Switzerland</a>',\r
+'miragode','<a href="http://www.mirago.de/" title="Search Engine Home Page [new window]" target="_blank">Mirago Germany</a>',\r
+'miragodk','<a href="http://www.mirago.dk/" title="Search Engine Home Page [new window]" target="_blank">Mirago Denmark</a>',\r
+'miragoes','<a href="http://es.mirago.com/" title="Search Engine Home Page [new window]" target="_blank">Mirago Spain</a>',\r
+'miragofr','<a href="http://www.mirago.fr/" title="Search Engine Home Page [new window]" target="_blank">Mirago France</a>',\r
+'miragoit','<a href="http://www.mirago.it/" title="Search Engine Home Page [new window]" target="_blank">Mirago Italy</a>',\r
+'miragonl','<a href="http://www.mirago.nl/" title="Search Engine Home Page [new window]" target="_blank">Mirago Netherlands</a>',\r
+'miragono','<a href="http://no.mirago.com/" title="Search Engine Home Page [new window]" target="_blank">Mirago Norway</a>',\r
+'miragose','<a href="http://www.mirago.se/" title="Search Engine Home Page [new window]" target="_blank">Mirago Sweden</a>',\r
+'miragocouk','<a href="http://zone.mirago.co.uk/" title="Search Engine Home Page [new window]" target="_blank">Mirago UK</a>',\r
+'mirago','<a href="http://www.mirago.com/" title="Search Engine Home Page [new window]" target="_blank">Mirago (country unknown)</a>',\r
+'answerbus','<a href="http://www.answerbus.com/" title="Search Engine Home Page [new window]" target="_blank">Answerbus</a>',\r
+'icq','<a href="http://www.icq.com/" title="Search Engine Home Page [new window]" target="_blank">icq</a>',\r
+'nusearch','<a href="http://www.nusearch.com/" title="Search Engine Home Page [new window]" target="_blank">Nusearch</a>',\r
+'goodsearch','<a href="http://www.goodsearch.com/" title="Search Engine Home Page [new window]" target="_blank">GoodSearch</a>',\r
+'scroogle','<a href="http://www.scroogle.org/" title="Search Engine Home Page [new window]" target="_blank">Scroogle</a>',\r
+'questionanswering','<a href="http://www.questionanswering.com/" title="Questionanswering home page [new window]" target="_blank">Questionanswering</a>',\r
+'mywebsearch','<a href="http://search.mywebsearch.com/" title="MyWebSearch home page [new window]" target="_blank">MyWebSearch</a>',\r
+'comettoolbar','<a href="http://as.starware.com/dp/search" title="Comet toolbar search home page [new window]" target="_blank">Comet toolbar search</a>',\r
+# Social Bookmarking Services\r
+'delicious','<a href="http://del.icio.us/" title="del.icio.us home page [new window]" target="_blank">del.icio.us</a> (Social Bookmark)',\r
+'digg','<a href="http://www.digg.com/" title="Digg home page [new window]" target="_blank">Digg</a> (Social Bookmark)',\r
+'stumbleupon','<a href="http://www.stumbleupon.com/" title="Stumbleupon home page [new window]" target="_blank">Stumbleupon</a> (Social Bookmark)',\r
+'swik','<a href="http://swik.net/" title="Swik home page [new window]" target="_blank">Swik</a> (Social Bookmark)',\r
+'segnalo','<a href="http://segnalo.alice.it/" title="Segnalo home page [new window]" target="_blank">Segnalo</a> (Social Bookmark)',\r
+'ineffabile','<a href="http://www.ineffabile.it/" title="Ineffabile.it home page [new window]" target="_blank">Ineffabile.it</a> (Social Bookmark)',\r
+# Minor Australian search engines\r
+'anzwers','<a href="http://anzwers.com.au/" title="anzwers.com.au home page [new window]" target="_blank">anzwers.com.au</a>',\r
+# Minor brazilian search engines\r
+'engine','Cade', 'miner','Meta Miner',\r
+# Minor chinese search engines\r
+'baidu','Baidu', 'sina','Sina', 'sohu','Sohu', 'sogou','<a href="http://www.sogou.com/" title="Search Engine Home Page [new window]" target="_blank">Sogou</a>',\r
+# Minor czech search engines\r
+'atlas','Atlas.cz', 'seznam','Seznam', 'quick','Quick.cz', 'centrum','Centrum.cz', 'jyxo','Jyxo.cz', 'najdi','Najdi.to', 'redbox','RedBox.cz',\r
+# Minor danish search-engines\r
+'opasia','Opasia', 'danielsen','Thor (danielsen.com)', 'sol','SOL', 'jubii','Jubii', 'finddk','Find', 'edderkoppen','Edderkoppen', 'netstjernen','Netstjernen', 'orbis','Orbis', 'tyfon','Tyfon', '1klik','1Klik', 'ofir','Ofir',\r
+# Minor dutch search engines\r
+'ilse','Ilse','vindex','Vindex\.nl', \r
+# Minor english search engines\r
+'askuk','<a href="http://uk.ask.com/" title="Search Engine Home Page [new window]" target="_blank">Ask UK</a>',\r
+'bbc','BBC', 'freeserve','Freeserve', 'looksmartuk','Looksmart UK',\r
+'splut','Splut', 'spotjockey','Spotjockey', 'ukdirectory','UK Directory', 'ukindex','UKIndex', 'ukplus','UK Plus', 'searchy','searchy.co.uk',\r
+# Minor finnish search engines\r
+'haku','Ihmemaa', \r
+# Minor french search engines\r
+'aolfr','AOL (fr)', 'ctrouve','C\'est trouvé', 'francite','Francité', 'lbb', 'LBB', 'libertysurf', 'Libertysurf', 'free', 'Free.fr', 'clubinternet', 'Club-internet',\r
+'toile', 'Toile du Québec',\r
+'biglotron','<a href="http://www.biglotron.com/" title="Search Engine Home Page [new window]" target="_blank">Biglotron</a>',\r
+'mozbot','<a href="http://www.mozbot.fr/" title="Search Engine Home Page [new window]" target="_blank">Mozbot</a>',\r
+# Minor German search engines\r
+'aolde','AOL (de)',\r
+'fireball','Fireball', 'infoseek','Infoseek', 'webde','Web.de',\r
+'abacho','Abacho', 't-online','T-Online', \r
+'allesklar','allesklar.de', 'meinestadt','meinestadt.de', \r
+'metaspinner','metaspinner',\r
+'metacrawler_de','metacrawler.de',\r
+'wwweasel','<a href="http://wwweasel.de/" title="Search Engine Home Page [new window]" target="_blank">WWWeasel</a>',\r
+'netluchs','<a href="http://www.netluchs.de/" title="Search Engine Home Page [new window]" target="_blank">Netluchs</a>',\r
+'schoenerbrausen','<a href="http://www.schoenerbrausen.de/" title="Search Engine Home Page [new window]" target="_blank">Schoenerbrausen/</a>',\r
+# Minor hungarian search engines\r
+'heureka','Heureka', 'origo','Origo-Vizsla', 'lapkereso','Startlapkeresõ', 'goliat','Góliát', 'indexhu','Index', 'wahoo','Wahoo', 'webmania','webmania.hu', 'internetto','Internetto Keresõ',\r
+'tango_hu','<a href="http://tango.hu/" title="Search Engine Home Page [new window]" target="_blank">Tango</a>',\r
+'keresolap_hu','<a href="http://keresolap.hu/" title="Search Engine Home Page [new window]" target="_blank">Tango keresolap</a>',\r
+'polymeta_hu','<a href="http://www.polymeta.hu/" title="Search Engine Home Page [new window]" target="_blank">Polymeta</a>',\r
+# Minor Indian search engines\r
+'sify','<a href="http://search.sify.com/" title="Search Engine Home Page [new window]" target="_blank">Sify</a>',\r
+# Minor Italian search engines\r
+'virgilio','<a href="http://www.virgilio.it/" title="Search Engine Home Page [new window]" target="_blank">Virgilio</a>',\r
+'arianna','<a href="http://arianna.libero.it/" title="Search Engine Home Page [new window]" target="_blank">Arianna</a>',\r
+'supereva','<a href="http://search.supereva.com/" title="Search Engine Home Page [new window]" target="_blank">Supereva</a>',\r
+'kataweb','<a href="http://www.kataweb.it/ricerca/" title="Search Engine Home Page [new window]" target="_blank">Kataweb</a>',\r
+'aliceitmaster','<a href="http://www.alice.it/" title="Search Engine Home Page [new window]" target="_blank">search.alice.it.master</a>',\r
+'aliceit','<a href="http://www.alice.it/" title="Search Engine Home Page [new window]" target="_blank">alice.it</a>',\r
+'gotuneed','<a href="http://www.gotuneed.com/" title="Search Engine Home Page [new window]" target="_blank">got u need</a>',\r
+'godado','Godado.it',\r
+'jumpy\.it','Jumpy.it',\r
+'shinyseek\.it','Shinyseek.it',\r
+'teecnoit','<a href="http://www.teecno.it/" title="Teecno home page [new window]" target="_blank">Teecno</a>',\r
+# Minor Japanese search engines\r
+'askjp','<a href="http://www.ask.jp/" title="Search E@SearchEngngine Home Page [new window]" target="_blank">Ask Japan</a>',\r
+'sagool','<a href="http://sagool.jp/" title="Sagool home page [new window]" target="_blank">Sagool</a>',\r
+# Minor Norwegian search engines\r
+'start','start.no', 'eniro','<a href="http://www.eniro.no/" title="Search Engine Home Page [new window]" target="_blank">Eniro</a>', \r
+# Minor polish search engines\r
+'wp','<a href="http://szukaj.wp.pl/" title="Wirtualna Polska home page [new window]" target="_blank">Wirtualna Polska</a>',\r
+'onetpl','<a href="http://szukaj.onet.pl/" title="Onet.pl home page [new window]" target="_blank">Onet.pl</a>',\r
+'dodajpl','<a href="http://www.dodaj.pl/" title="Dodaj.pl home page [new window]" target="_blank">Dodaj.pl</a>',\r
+'gazetapl','<a href="http://szukaj.gazeta.pl/" title="Gazeta.pl home page [new window]" target="_blank">Gazeta.pl</a>',\r
+'gerypl','<a href="http://szukaj.gery.pl/" title="Gery.pl home page [new window]" target="_blank">Gery.pl</a>',\r
+'hogapl','<a href="http://www.hoga.pl/" title="Hoga.pl home page [new window]" target="_blank">Hoga.pl</a>',\r
+'netsprintpl','<a href="http://www.netsprint.pl/" title="NetSprint.pl home page [new window]" target="_blank">NetSprint.pl</a>',\r
+'interiapl','<a href="http://www.google.interia.pl/" title="Interia.pl home page [new window]" target="_blank">Interia.pl</a>',\r
+'katalogonetpl','<a href="http://katalog.onet.pl/" ti@SearchEngtle="Katalog.Onet.pl home page [new window]" target="_blank">Katalog.Onet.pl</a>',\r
+'o2pl','<a href="http://szukaj2.o2.pl/" title="o2.pl home page [new window]" target="_blank">o2.pl</a>',\r
+'polskapl','<a href="http://szukaj.polska.pl/" title="Polska home page [new window]" target="_blank">Polska</a>',\r
+'szukaczpl','<a href="http://www.szukacz.pl/" title="Szukacz home page [new window]" target="_blank">Szukacz</a>',\r
+'wowpl','<a href="http://szukaj.wow.pl/" title="Wow.pl home page [new window]" target="_blank">Wow.pl</a>',\r
+# Minor russian search engines\r
+'yandex', 'Yandex', 'aport', 'Aport', 'rambler', 'Rambler', 'turtle', 'Turtle', 'metabot', 'MetaBot',\r
+# Minor Swedish search engines\r
+'passagen','Evreka',\r
+'enirose','<a href="http://www.eniro.se/" title="Eniro Sverige home page [new window]" target="_blank">Eniro Sverige</a>',\r
+# Minor Slovak search engines\r
+'zoznam','<a href="http://www.zoznam.sk/" Searc Engine home page [new window]" target="_blank">Zoznam</a>',\r
+# Minor Portuguese search engines\r
+'sapo','<a href="http://www.sapo.pt/" Searc Engine home page [new window]" target="_blank">Sapo</a>',\r
+# Minor Swiss search engines\r
+'searchch', 'search.ch', 'bluewin', 'search.bluewin.ch', \r
+# Generic search engines\r
+'search','Unknown search engines'\r
+);\r
+\r
+\r
+# Sanity check.\r
+# Enable this code and run perl search_engines.pm to check file entries are ok\r
+#-----------------------------------------------------------------------------\r
+#foreach my $key (@SearchEnginesSearchIDOrder_list1) {\r
+# if (! $SearchEnginesHashID{$key}) { error("Entry '$key' has been found in SearchEnginesSearchIDOrder_list1 with no value in SearchEnginesHashID");\r
+# foreach my $key2 (@SearchEnginesSearchIDOrder_list2) { if ($key2 eq $key) { error("$key is in 1 and 2\n"); } }\r
+# foreach my $key2 (@SearchEnginesSearchIDOrder_listgen) { if ($key2 eq $key) { error("$key is in 1 and gen\n"); } }\r
+#} }\r
+#foreach my $key (@SearchEnginesSearchIDOrder_list2) {\r
+# if (! $SearchEnginesHashID{$key}) { error("Entry '$key' has been found in SearchEnginesSearchIDOrder_list1 with no value in SearchEnginesHashID");\r
+# foreach my $key2 (@SearchEnginesSearchIDOrder_list1) { if ($key2 eq $key) { error("$key is in 2 and 1\n"); } }\r
+# foreach my $key2 (@SearchEnginesSearchIDOrder_listgen) { if ($key2 eq $key) { error("$key is in 2 and gen\n"); } }\r
+#} }\r
+#foreach my $key (@SearchEnginesSearchIDOrder_listgen) { if (! $SearchEnginesHashID{$key}) { error("Entry '$key' has been found in SearchEnginesSearchIDOrder_listgen with no value in SearchEnginesHashID"); } }\r
+#foreach my $key (keys %NotSearchEnginesKeys) { if (! $SearchEnginesHashID{$key}) { error("Entry '$key' has been found in NotSearchEnginesKeys with no value in SearchEnginesHashID"); } }\r
+#foreach my $key (keys %SearchEnginesKnownUrl) {\r
+# my $found=0;\r
+# foreach my $key2 (values %SearchEnginesHashID) {\r
+# if ($key eq $key2) { $found=1; last; }\r
+# }\r
+# if (! $found) { die "Entry '$key' has been found in SearchEnginesKnownUrl with no value in SearchEnginesHashID"; }\r
+#}\r
+#foreach my $key (keys %SearchEnginesHashLib) {\r
+# my $found=0;\r
+# foreach my $key2 (values %SearchEnginesHashID) {\r
+# if ($key eq $key2) { $found=1; last; }\r
+# }\r
+# if (! $found) { die "Entry '$key' has been found in SearchEnginesHashLib with no value in SearchEnginesHashID"; }\r
+#}\r
+#print @SearchEnginesSearchIDOrder_list1." ".@SearchEnginesSearchIDOrder_list2." ".@SearchEnginesSearchIDOrder_listgen;\r
+\r
+1;\r