]> git.ipfire.org Git - thirdparty/AWStats.git/commitdiff
added some missing parts to search_egines.pm 38/head
authorvisualperception <github@litody.net>
Sun, 4 Sep 2016 00:42:18 +0000 (01:42 +0100)
committerGitHub <noreply@github.com>
Sun, 4 Sep 2016 00:42:18 +0000 (01:42 +0100)
added some missing parts to search_egines.pm to bring it inline with live release of awstats 7.5 ( plus my additions of google countries and others)

wwwroot/cgi-bin/lib/search_engines.pm

index 501d286092c2cc291e5043db5b6683cc6d8434cf..c1e3c24353b225b2c93d40e452ffa4a5b444bb78 100644 (file)
 '^images\.google\.pl$',\r
 '^translate\.google\.pl$',\r
 'google\.pl$',\r
+\r
 '^www\.google\.ac$',\r
 '^images\.google\.ac$',\r
 '^translate\.google\.ac$',\r
 'altavista\.'=>'babelfish\.altavista\.',\r
 'google\.'=>'mail\.google\.',\r
 'google\.'=>'translate\.google\.',\r
+'google\.'=>'code\.google\.',\r
+'google\.'=>'groups\.google\.',\r
 'msn\.'=>'hotmail\.msn\.',\r
 'tiscali\.'=>'mail\.tiscali\.',\r
-'yahoo\.'=>'mail\.yahoo\.',\r
+'yahoo\.'=>'(?:picks|mail)\.yahoo\.|yahoo\.[^/]+/picks',\r
 'yandex\.'=>'direct\.yandex\.'\r
 );\r
 \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
+'a9',1,    # www.a9.com/searchkey1%20searchkey2\r
+'iminent',1, #http://start.iminent.com/StartWeb/1031/toolbox/#q=searchkey1%20searchkey2&additional_arguments\r
+'de_wiki_gov_cn',1, #http://de.wiki.gov.cn/s_searchkey1%20searchkey2\r
+'umuwa_de', 1, #http://umuwa.de/searchkey or http://umuwa.de/searchkey/Images\r
+'amazonsearch', 1 #http://www.amazon.de/gp/bit/apps/web/SERP/search/ref=bit_bds-p24_serp_cr_de?ie=UTF8tagbase=bds-p24&query=deutsch+8.+klasse+gymnasium+protokoll\r
 );\r
 \r
 # SearchEnginesKnownUrl\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= ('all=','as_q=','ask=','claus=','dotaz=','find=','general=','Gw=','heureka=','highlight=','ie=','image keys=','imgurl=','in=','iu=','k=','KERESES=','key=','keyword=','keywords=','kw=','mt=','name=','nusearch_terms=','OVKEY=','p=','p1=','pattern=','q=','q1=','qkw=','qpvt=','qr=','qr=','qry=','qs=','qt=','query=','querytext=','question=','r=','rdata=','req=','s=','search=','search_field=','search_for=','Search_Keyword=','search_term=','searchfor=','searchstr=','searchtext=','searchWord=','Serbian=','slowo=','soegeord=','sp-q=','srch=','st=','stext=','string=','su=','szukaj=','term=','text=','tn=','txtsearch=','uery=','w=','wd=','word=','words=');\r
+# old and not required @WordsToExtractSearchUrl= ('all=','as_q=','ask=','claus=','dotaz=','find=','general=','Gw=','heureka=','highlight=','ie=','image keys=','imgurl=','in=','iu=','k=','KERESES=','key=','keyword=','keywords=','kw=','mt=','name=','nusearch_terms=','OVKEY=','p=','p1=','pattern=','q=','q1=','qkw=','qpvt=','qr=','qr=','qry=','qs=','qt=','query=','querytext=','question=','r=','rdata=','req=','s=','search=','search_field=','search_for=','Search_Keyword=','search_term=','searchfor=','searchstr=','searchtext=','searchWord=','Serbian=','slowo=','soegeord=','sp-q=','srch=','st=','stext=','string=','su=','szukaj=','term=','text=','tn=','txtsearch=','uery=','w=','wd=','word=','words=');\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
 'yahoo_catchall','Yahoo : ( catchall )',\r
 \r
 'yandex','yandex ( catchall )',\r
-'yandexcom','<a href="http://yandex.com/" rel="nofollow" title="Search Engine Home Page [new window]" target="_blank">Ynndex .com</a>',\r
-'yandexcomtr','<a href="http://yandex.com.tr/" rel="nofollow" title="Search Engine Home Page [new window]" target="_blank">Ynndex .com.tr</a>',\r
-'yandexkz','<a href="http://yandex.kz/" rel="nofollow" title="Search Engine Home Page [new window]" target="_blank">Ynndex .kz</a>',\r
-'yandexru','<a href="http://yandex.ru/" rel="nofollow" title="Search Engine Home Page [new window]" target="_blank">Ynndex .ru</a>',\r
-'yandexua','<a href="http://yandex.ua/" rel="nofollow" title="Search Engine Home Page [new window]" target="_blank">Ynndex .ua</a>',\r
+'yandexcom','<a href="http://yandex.com/" rel="nofollow" title="Search Engine Home Page [new window]" target="_blank">Yandex .com</a>',\r
+'yandexcomtr','<a href="http://yandex.com.tr/" rel="nofollow" title="Search Engine Home Page [new window]" target="_blank">Yandex .com.tr</a>',\r
+'yandexkz','<a href="http://yandex.kz/" rel="nofollow" title="Search Engine Home Page [new window]" target="_blank">Yandex .kz</a>',\r
+'yandexru','<a href="http://yandex.ru/" rel="nofollow" title="Search Engine Home Page [new window]" target="_blank">Yandex .ru</a>',\r
+'yandexua','<a href="http://yandex.ua/" rel="nofollow" title="Search Engine Home Page [new window]" target="_blank">Yandex .ua</a>',\r
 'yell','<a href="http://www.yell.com/" title="Yell Home Page [new window]" rel="nofollow" target="_blank">Yell</a>',\r
 'yourbestsearch','<a href="http://yourbestsearch.net/" title="Home Page [new window]" rel="nofollow" target="_blank">YourBest Search</a>',\r
 'youtube','youtube',\r