From: Laurent Destailleur Date: Sat, 9 Nov 2013 13:23:06 +0000 (+0100) Subject: Update databases. X-Git-Tag: AWSTATS_7_3~35^2 X-Git-Url: http://git.ipfire.org/cgi-bin/gitweb.cgi?a=commitdiff_plain;h=213e436f1ebdc1ad3e0d494d4fa21926b4ca11eb;p=thirdparty%2FAWStats.git Update databases. Moved source version control on sourceforge Git. CVS is still opened as a mirror of GIT. --- diff --git a/docs/awstats_changelog.txt b/docs/awstats_changelog.txt index 8369de9c..e17ab9cf 100644 --- a/docs/awstats_changelog.txt +++ b/docs/awstats_changelog.txt @@ -15,6 +15,9 @@ Fixes: static link is wrong. - Restore detection of Opera browsers versions. +Other: +- Move version system to sourceforge Git instead of CVS. + ***** 7.2 ***** diff --git a/wwwroot/cgi-bin/lib/browsers.pm b/wwwroot/cgi-bin/lib/browsers.pm index 732b755a..dd50e9ef 100644 --- a/wwwroot/cgi-bin/lib/browsers.pm +++ b/wwwroot/cgi-bin/lib/browsers.pm @@ -3,7 +3,6 @@ # If you want to add a Browser to extend AWStats database detection capabilities, # you must add an entry in BrowsersSearchIDOrder and in BrowsersHashIDLib. #------------------------------------------------------- -# $Revision$ - $Author$ - $Date$ # 2006-05-15 Sean Carlos http://www.antezeta.com/awstats.html # akregator (rss) diff --git a/wwwroot/cgi-bin/lib/browsers_phone.pm b/wwwroot/cgi-bin/lib/browsers_phone.pm index 32e25afe..60918216 100644 --- a/wwwroot/cgi-bin/lib/browsers_phone.pm +++ b/wwwroot/cgi-bin/lib/browsers_phone.pm @@ -3,7 +3,6 @@ # If you want to add a Browser to extend AWStats database detection capabilities, # you must add an entry in BrowsersSearchIDOrder and in BrowsersHashIDLib. #------------------------------------------------------- -# $Revision$ - $Author$ - $Date$ # Originale version by malu # 2006-05-15 Sean Carlos http://www.antezeta.com/awstats.html diff --git a/wwwroot/cgi-bin/lib/domains.pm b/wwwroot/cgi-bin/lib/domains.pm index 36c3a19d..d190683c 100644 --- a/wwwroot/cgi-bin/lib/domains.pm +++ b/wwwroot/cgi-bin/lib/domains.pm @@ -3,7 +3,6 @@ # If you want to add a new domain to extend AWStats database detection capabilities, # you must add an entry in DomainsHashIDLib. #------------------------------------------------------- -# $Revision$ - $Author$ - $Date$ #package AWSDOM; diff --git a/wwwroot/cgi-bin/lib/mime.pm b/wwwroot/cgi-bin/lib/mime.pm index 882f53b9..ba186ae2 100644 --- a/wwwroot/cgi-bin/lib/mime.pm +++ b/wwwroot/cgi-bin/lib/mime.pm @@ -3,7 +3,6 @@ # If you want to add MIME types, # you must add an entry in MimeHashLib and assign it to a family #------------------------------------------------------- -# $Revision$ - $Author$ - $Date$ #package AWSMIME; diff --git a/wwwroot/cgi-bin/lib/operating_systems.pm b/wwwroot/cgi-bin/lib/operating_systems.pm index f3bbb898..8837e781 100644 --- a/wwwroot/cgi-bin/lib/operating_systems.pm +++ b/wwwroot/cgi-bin/lib/operating_systems.pm @@ -3,7 +3,6 @@ # If you want to add an OS to extend AWStats database detection capabilities, # you must add an entry in OSSearchIDOrder, in OSHashID and in OSHashLib. #------------------------------------------------------- -# $Revision$ - $Author$ - $Date$ # 2005-08-19 Sean Carlos http://www.antezeta.com/awstats.html # - added specific Linux distributions in addition to diff --git a/wwwroot/cgi-bin/lib/referer_spam.pm b/wwwroot/cgi-bin/lib/referer_spam.pm index 0b76cbfe..db4f67ff 100644 --- a/wwwroot/cgi-bin/lib/referer_spam.pm +++ b/wwwroot/cgi-bin/lib/referer_spam.pm @@ -3,7 +3,6 @@ # If you want to extend AWStats detection capabilities, # you must add an entry in RefererSpamKeys #------------------------------------------------------- -# $Revision$ - $Author$ - $Date$ #package AWSREFSPAMMERS; diff --git a/wwwroot/cgi-bin/lib/robots.pm b/wwwroot/cgi-bin/lib/robots.pm index 9b1ee0ee..877204b3 100644 --- a/wwwroot/cgi-bin/lib/robots.pm +++ b/wwwroot/cgi-bin/lib/robots.pm @@ -2,8 +2,24 @@ #------------------------------------------------------- # If you want to add robots to extend AWStats database detection capabilities, # you must add an entry in RobotsSearchIDOrder_listx and RobotsHashIDLib. + +# The entry in RobotsSearchIDOrder_listx is a Perl regular expression +# (see http://perldoc.perl.org/perlreref.html). AWSTats applies these +# expressions to the user agent string in the order given by the lists. The +# first match specifies the robot. +# +# The corresponding entry in RobotsHashIDLib contains the regular expression +# as key, followed by a string containing HTML-text. AWStats inserts this +# text into reports to describe the bot. If possible the text should contain +# a link to the bot home page. This make it easier for systadmins to find +# the information necessary e.g. to adapt the robots.txt file. +# +# An entry in the RobotsAffiliateLib is not necessary. An entry in this list +# contains as first part the regular expression specifying the bot. The +# second part is a string that gives the Company or product managing the bot. +# This information is not used yet. + #------------------------------------------------------- -# $Revision$ - $Author$ - $Date$ # 2005-08-19 Sean Carlos http://www.antezeta.com/awstats.html # added dipsie (not tested with real data). @@ -672,6 +688,7 @@ 'accoona\-ai\-agent', 'activebookmark', 'adamm_bot', +'adsbot-google', 'almaden', 'aipbot', 'aleadsoftbot', @@ -704,6 +721,7 @@ 'boitho\.com\-dc', 'bookmark\-manager', 'boris', +'bubing', 'bumblebee', 'candlelight[_+ ]favorites[_+ ]inspector', 'cbn00glebot', @@ -722,6 +740,7 @@ 'custo', 'datafountains\/dmoz_downloader', 'dataprovider\.com', +'daumoa', 'daviesbot', 'daypopbot', 'deepindex', @@ -734,6 +753,7 @@ 'dumm\.de\-bot', 'earthcom\.info', 'easydl', +'eccp', 'edgeio\-retriever', 'ets_v', 'exactseek', @@ -759,8 +779,11 @@ 'feedsky', 'feedvalidator', 'filmkamerabot', +'filterdb\.iss\.net', 'findlinks', 'findexa_crawler', +'firmilybot', +'foaf-search\.net', 'fooky\.com\/ScorpionBot', 'g2crawler', 'gaisbot', @@ -772,6 +795,7 @@ 'goforit\.com', 'goforitbot', 'gonzo', +'grapeshot', 'grub', 'gpu_p2p_crawler', 'henrythemiragorobot', @@ -825,6 +849,7 @@ 'linkchecker', 'livejournal\.com', 'lmspider', +'ltbot', 'lwp\-request', 'lwp\-trivial', 'magpierss', @@ -942,6 +967,7 @@ 'ultraseek', 'unchaos_bot_hybrid_web_search_engine', 'unido\-bot', +'unisterbot', 'updated', 'ustc\-semantic\-group', 'vagabondo\-wap', @@ -967,6 +993,7 @@ 'website[_+ ]monitoring[_+ ]bot', 'webvulncrawl', 'wells_search', +'wesee:search', 'wonderer', 'wume_crawler', 'wwweasel', @@ -1095,7 +1122,7 @@ 'yahoo! searchmonkey', 'yahooysmcm', 'yammer', -'yandexbot', +# 'yandexbot', #already covered by 'yandex' 'yeti', 'yie8', 'youdao', @@ -1472,6 +1499,7 @@ 'accoona\-ai\-agent','Accoona-AI-Agent', 'activebookmark','ActiveBookmark', 'adamm_bot','AdamM Bot', +'adsbot-google', 'AdsBot-Google', 'almaden','IBM Almaden Research Center WebFountain™', 'aipbot','aipbot', 'aleadsoftbot','ALeadSoftbot', @@ -1504,6 +1532,7 @@ 'boitho\.com\-dc','boitho.com-dc', 'bookmark\-manager','Bookmark-Manager', 'boris', 'Boris', +'bubing', 'BUbiNG', 'bumblebee', 'Bumblebee (relevare.com)', 'candlelight[_+ ]favorites[_+ ]inspector','Candlelight_Favorites_Inspector', 'cbn00glebot','cbn00glebot', @@ -1521,6 +1550,7 @@ 'custo','Custo', 'datafountains\/dmoz_downloader','DataFountains/DMOZ Downloader', 'dataprovider\.com', 'Dataprovider Site Explorer', +'daumoa', 'Daum', 'daviesbot', 'DaviesBot', 'daypopbot', 'DayPop', 'deepindex','Deepindex', @@ -1533,6 +1563,7 @@ 'dumm\.de\-bot','dumm.de-Bot', 'earthcom\.info','EARTHCOM.info', 'easydl','EasyDL', +'eccp', 'Eniro Sverige, email: search (at) eniro.com', 'edgeio\-retriever','edgeio-retriever', 'ets_v','ETS Enterprise Translation Server', 'exactseek','ExactSeek Crawler', @@ -1558,12 +1589,15 @@ 'feedsky','FeedSky', 'feedvalidator','FeedValidator', 'filmkamerabot','FilmkameraBot', +'filterdb\.iss\.net', 'oBot', 'findexa_crawler','Findexa Crawler', -'geniebot','Geniebot', +'firmilybot', 'Firmily Bot Home page (Website was hacked on Oct. 19, 2013)', 'findlinks','Findlinks', +'foaf-search\.net', 'Friend of a friend (FOAF) search engine', 'fooky\.com\/ScorpionBot','Fooky.com/ScorpionBot/ScoutOut', 'g2crawler','G2Crawler', 'gaisbot','Gaisbot', +'geniebot','Geniebot', 'gigabot','GigaBot', 'girafabot','Girafabot', 'global_fetch','Global Fetch', @@ -1572,6 +1606,7 @@ 'goforitbot','GOFORITBOT', 'gonzo','suchen.de', 'gpu_p2p_crawler','GPU p2p crawler', +'grapeshot', 'Grapeshot Crawler', 'grub','Grub.org', 'henrythemiragorobot', 'Mirago', 'heritrix','Heritrix', @@ -1621,8 +1656,9 @@ 'linkdex\.com', 'Linkdex', 'linkchecker','LinkChecker', 'livejournal\.com', 'LiveJournal.com', +'ltbot', 'Language Tools Bot (ltbot)', 'magpierss', 'MagpieRSS', -'mail\.ru', 'Mail.ru bot', +'mail\.ru', 'Mail.ru bot', 'mapoftheinternet\.com','MapoftheInternet.com', 'mediapartners\-google','Google AdSense', 'megite','Megite', @@ -1737,6 +1773,7 @@ 'ultraseek', 'Ultraseek', 'unchaos_bot_hybrid_web_search_engine','UnChaos Bot Hybrid Web Search Engine', 'unido\-bot','unido-bot', +'unisterbot', 'UnisterBot; E-Mail only: crawler (at) unister.de', 'updated','updated', 'ustc\-semantic\-group','USTC-Semantic-Group', 'vagabondo\-wap','Vagabondo-WAP', @@ -1762,6 +1799,7 @@ 'website[_+ ]monitoring[_+ ]bot','Website_Monitoring_Bot', 'webvulncrawl', 'WebVulnCrawl', 'wells_search','Wells Search', +'wesee:search', 'WeSEE Bot', 'wonderer', 'Web Wombat Redback Spider', 'wume_crawler','wume crawler', 'wwweasel',,'WWWeasel', @@ -1777,7 +1815,7 @@ 'yahooseeker', 'YahooSeeker Yahoo! Blog crawler', 'yahoo\-mmcrawler', 'Yahoo-MMCrawler', 'yahoo!_mindset','Yahoo! Mindset', -'yandex', 'Yandex bot', +'yandex', 'Yandex Bot', 'flexum', 'Flexum Search Engine', 'yanga', 'Yanga WorldSearch Bot', 'yet-another-spider','Yet-Another-Spider', @@ -1814,7 +1852,7 @@ 'alltop', 'alltop', 'applesyndication', 'applesyndication', 'asynchttpclient', 'asynchttpclient', -'bingbot', 'bingbot', +'bingbot', 'Bingbot', 'blogged_crawl', 'blogged_crawl', 'bloglovin', 'bloglovin', 'butterfly', 'butterfly', @@ -1907,7 +1945,7 @@ 'yahoo! searchmonkey', 'Additional Yahoo bots.', 'yahooysmcm', 'Additional Yahoo bots.', 'yammer', 'yammer', -'yandexbot', 'yandexbot', +#'yandexbot', 'yandexbot', #already covered by 'yandex' 'yeti', 'yeti', 'yie8', 'yie8', 'youdao', 'youdao', diff --git a/wwwroot/cgi-bin/lib/search_engines.pm b/wwwroot/cgi-bin/lib/search_engines.pm index 480d7b81..215a5422 100644 --- a/wwwroot/cgi-bin/lib/search_engines.pm +++ b/wwwroot/cgi-bin/lib/search_engines.pm @@ -57,7 +57,6 @@ # - If the HTML-Fragment (d) is syntactically incorrect. # #------------------------------------------------------------------------------ -# $Revision$ - $Author$ - $Date$ # 2005-08-19 Sean Carlos http://www.antezeta.com/awstats.html # added minor italian search engines @@ -317,6 +316,9 @@ 'dalesearch\.com', 'sweetpacks-search\.com', 'searchgol\.com', +'duckduckgo\.com', +'sr\.facemoods\.com', +'shoppstop\.com', # Chello Portals 'chello\.at', 'chello\.be', @@ -409,11 +411,12 @@ 'www\.amazon\.de.*search', #Just as a reminder, probably will not work as AWstats seem to consider the host part of an URL only 'de\.wow\.com', 'www\.vlips\.de', -'www\.metager\.de', +'metager\.de', 'search\.1und1\.de', 'sm\.de', 'sumaja\.de', 'navigationshilfe\.t-online\.de', +'umfis\.de', # Minor Hungarian search engines 'heureka\.hu','vizsla\.origo\.hu','lapkereso\.hu','goliat\.hu','index\.hu','wahoo\.hu','webmania\.hu','search\.internetto\.hu', 'tango\.hu', @@ -582,6 +585,9 @@ 'dalesearch\.com', 'dalesearch', 'sweetpacks-search\.com', 'sweetpacks', 'searchgol\.com', 'searchgol', +'duckduckgo\.com', 'duckduckgo', +'sr\.facemoods\.com', 'facemoods', +'shoppstop\.com', 'shoppstop', # Chello Portals 'chello\.at','chelloat', 'chello\.be','chellobe', @@ -713,11 +719,12 @@ 'www\.amazon\.de.*search', 'amazonsearch', #Not clear if this matches amazon searches only 'de\.wow\.com', 'wowsearch', 'www\.vlips\.de', 'vlips_de', -'www\.metager\.de', 'metager', +'metager\.de', 'metager', 'search\.1und1\.de', 'search_1und1_de', 'sm\.de', 'smde', 'sumaja\.de', 'sumaja', 'navigationshilfe\.t-online\.de', 'navigationshilfe', +'umfis\.de', 'umfis', # Minor Hungarian search engines 'heureka\.hu','heureka', 'vizsla\.origo\.hu','origo', @@ -899,6 +906,9 @@ 'dalesearch', 'q=', 'sweetpacks', 'q=', 'searchgol', 'q=', +'duckduckgo', 'uddg=', +'facemoods', 'q=', +'shoppstop', 'keywords=', # Chello Portals 'chelloat','q1=', 'chellobe','q1=', @@ -998,6 +1008,7 @@ 'smde', 'q=', #'sumaja', 'no query string available', #There is no query string in the referrer url 'navigationshilfe', 'q=', +'umfis', 'suchbegriff=', # Minor Hungarian search engines 'heureka','heureka=', 'origo','(q|search)=', 'goliat','KERESES=', 'wahoo','q=', 'internetto','searchstr=', 'keresolap_hu','q=', @@ -1044,7 +1055,7 @@ 'mailru', 'q=', # Minor swedish search engines 'passagen','q=', -'enirose','q=', +'enirose', 'hitta:', #Not sure if this works, as the keywords are part of the URL, and therefore the URL does not contain a question mark. # Minor swiss search engines 'searchch', 'q=', 'bluewin', 'qry=', # Minor Croatian, Serbian, Macedonian, Bosnian and Herzegovinian search engines @@ -1177,6 +1188,9 @@ 'dalesearch', 'Dale Search', 'sweetpacks', 'Sweetpacks', 'searchgol', 'Search-Gol', +'duckduckgo', 'DuckDuckGo (Does not provide search keyphrases, using found page instead)', +'facemoods', 'Facemoods Search', +'shoppstop', 'ShoppStop', # Chello Portals 'chelloat','Chello Austria', 'chellobe','Chello Belgium', @@ -1264,7 +1278,7 @@ 'netluchs','Netluchs', 'schoenerbrausen','Schoenerbrausen/', 'gmxsuche', 'GMX Suche', -'gmxsuche_at', 'GMX Suche Österreich', +'gmxsuche_at', 'GMX Suche �sterreich', 'ecosiasearch', 'Ecosia Search', 'aolsearch', 'AOL Search', 'aolsuche', 'AOL Suche', @@ -1278,6 +1292,7 @@ 'smde', 'SM.de - Die SuchMaschine', 'sumaja', 'Sumaja', 'navigationshilfe', 'T-Online Navigationshilfe', +'umfis', 'UMFIS-Online Das Umweltfirmen-Informationssystem der IHKs in Deutschland', # Minor hungarian search engines 'heureka','Heureka', 'origo','Origo-Vizsla', 'lapkereso','Startlapkereso', 'goliat','Goliat', 'indexhu','Index', 'wahoo','Wahoo', 'webmania','webmania.hu', 'internetto','Internetto Kereso', 'tango_hu','Tango', diff --git a/wwwroot/cgi-bin/lib/status_http.pm b/wwwroot/cgi-bin/lib/status_http.pm index e42cbff6..fa3925cb 100644 --- a/wwwroot/cgi-bin/lib/status_http.pm +++ b/wwwroot/cgi-bin/lib/status_http.pm @@ -3,7 +3,6 @@ # If you want to add a HTTP status code, you must add # an entry in httpcodelib. #------------------------------------------------------- -# $Revision$ - $Author$ - $Date$ #package AWSHTTPCODES; diff --git a/wwwroot/cgi-bin/lib/status_smtp.pm b/wwwroot/cgi-bin/lib/status_smtp.pm index c09579a8..5397a9c7 100644 --- a/wwwroot/cgi-bin/lib/status_smtp.pm +++ b/wwwroot/cgi-bin/lib/status_smtp.pm @@ -3,7 +3,6 @@ # If you want to add a SMTP status code, you must add # an entry in smtpcodelib. #------------------------------------------------------- -# $Revision$ - $Author$ - $Date$ #package AWSSMTPCODES; @@ -43,7 +42,7 @@ '504'=>'Command parameter not implemented', '521'=>' does not accept mail or closing transmission channel', # You must be pop-authenticated before you can use this SMTP server and you must use your mail address for the Sender/From field. '530'=>'Access denied', # a Sendmailism ? -'550'=>'Requested mail action not taken: relaying not allowed, unknown recipient user, ...', # Sending an email to recipients outside of your domain are not allowed or your mail server does not know that you have access to use it for relaying messages and authentication is required. Or to prevent the sending of SPAM some mail servers will not allow (relay) send mail to any e-mail using another company’s network and computer resources. +'550'=>'Requested mail action not taken: relaying not allowed, unknown recipient user, ...', # Sending an email to recipients outside of your domain are not allowed or your mail server does not know that you have access to use it for relaying messages and authentication is required. Or to prevent the sending of SPAM some mail servers will not allow (relay) send mail to any e-mail using another company�s network and computer resources. '551'=>'User not local: please try or Invalid Address: Relay request denied', '552'=>'Requested mail action aborted: exceeded storage allocation', # ISP mail server indicates, probable overloading from too many messages. '553'=>'Requested mail action not taken: mailbox name not allowed', # Some mail servers have the option to reduce the number of concurrent connection and also the number of messages sent per connection. If you have a lot of messages queued up (being sent) for a domain, it could go over the maximum number of messages per connection and/or some change to the message and/or destination must be made for successful delivery. diff --git a/wwwroot/cgi-bin/lib/worms.pm b/wwwroot/cgi-bin/lib/worms.pm index 9d2dba2d..a90c9950 100644 --- a/wwwroot/cgi-bin/lib/worms.pm +++ b/wwwroot/cgi-bin/lib/worms.pm @@ -3,7 +3,6 @@ # If you want to add worms to extend AWStats database detection capabilities, # you must add an entry in WormsSearchIDOrder, WormsHashID and WormsHashLib. #----------------------------------------------------------------------------- -# $Revision$ - $Author$ - $Date$ #package AWSWORMS;