rather large update, most important things done:

- implemented provided patch/diff file for bug #5350 (Highway of Life) with some tiny changes and alterations - more username/colour changes/fixes - added a note about PM rule-dependant message removals so the user is not wondering too much if he can't remember his rules. :) - some column changes to fix unicode issues - bugfixes git-svn-id: file:///svn/phpbb/trunk@6650 89ea8834-ac86-4346-8a33-228a782c2dd0
2025-07-31 14:00:31 +02:00 · 2006-11-24 14:59:26 +00:00
parent a0c3a326bd
commit d529f78adb
63 changed files with 378 additions and 162 deletions
--- a/phpBB/install/install_install.php
+++ b/phpBB/install/install_install.php
@@ -2065,12 +2065,92 @@ class install_install extends module

 	/**
 	* A list of the web-crawlers/bots we recognise by default
+	*
+	* Candidates but not included:
+	* 'Accoona [Bot]'				'Accoona-AI-Agent/'
+	* 'ASPseek [Crawler]'			'ASPseek/'
+	* 'Boitho [Crawler]'			'boitho.com-dc/'
+	* 'Bunnybot [Bot]'				'powered by www.buncat.de'
+	* 'Cosmix [Bot]'				'cfetch/'
+	* 'Crawler Search [Crawler]'	'.Crawler-Search.de'
+	* 'Findexa [Crawler]'			'Findexa Crawler ('
+	* 'GBSpider [Spider]'			'GBSpider v'
+	* 'genie [Bot]'					'genieBot ('
+	* 'Hogsearch [Bot]'				'oegp v. 1.3.0'
+	* 'Insuranco [Bot]'				'InsurancoBot'
+	* 'IRLbot [Bot]'				'http://irl.cs.tamu.edu/crawler'
+	* 'ISC Systems [Bot]'			'ISC Systems iRc Search'
+	* 'Jyxobot [Bot]'				'Jyxobot/'
+	* 'Kraehe [Metasuche]'			'-DIE-KRAEHE- META-SEARCH-ENGINE/'
+	* 'LinkWalker'					'LinkWalker'
+	* 'MMSBot [Bot]'				'http://www.mmsweb.at/bot.html'
+	* 'Naver [Bot]'					'nhnbot@naver.com)'
+	* 'NetResearchServer'			'NetResearchServer/'
+	* 'Nimble [Crawler]'			'NimbleCrawler'
+	* 'Ocelli [Bot]'				'Ocelli/'
+	* 'Onsearch [Bot]'				'onCHECK-Robot'
+	* 'Orange [Spider]'				'OrangeSpider'
+	* 'Sproose [Bot]'				'http://www.sproose.com/bot'
+	* 'Susie [Sync]'				'!Susie (http://www.sync2it.com/susie)'
+	* 'Tbot [Bot]'					'Tbot/'
+	* 'Thumbshots [Capture]'		'thumbshots-de-Bot'
+	* 'Vagabondo [Crawler]'			'http://webagent.wise-guys.nl/'
+	* 'Walhello [Bot]'				'appie 1.1 (www.walhello.com)'
+	* 'WissenOnline [Bot]'			'WissenOnline-Bot'
+	* 'WWWeasel [Bot]'				'WWWeasel Robot v'
+	* 'Xaldon [Spider]'				'Xaldon WebSpider'
 	*/
 	var $bot_list = array(
-		'Alexa'			=> array('ia_archiver', '66.28.250.,209.237.238.'),
-		'Fastcrawler'	=> array('FAST MetaWeb Crawler', '66.151.181.'),
-		'Googlebot'		=> array('Googlebot/', ''),
-		'Inktomi'		=> array('Slurp/', '216.35.116.,66.196.'),
+		'AdsBot [Google]'			=> array('AdsBot-Google', ''),
+		'Alexa [Bot]'				=> array('ia_archiver', ''),
+		'Alta Vista [Bot]'			=> array('Scooter/', ''),
+		'Ask Jeeves [Bot]'			=> array('Ask Jeeves', ''),
+		'Baidu [Spider]'			=> array('Baiduspider+(', ''),
+		'Exabot [Bot]'				=> array('Exabot/', ''),
+		'FAST Enterprise [Crawler]'	=> array('FAST Enterprise Crawler', ''),
+		'FAST WebCrawler [Crawler]'	=> array('FAST-WebCrawler/', ''),
+		'Francis [Bot]'				=> array('http://www.neomo.de/', ''),
+		'Gigabot [Bot]'				=> array('Gigabot/', ''),
+		'Google Adsense [Bot]'		=> array('Mediapartners-Google/', ''),
+		'Google Desktop'			=> array('Google Desktop', ''),
+		'Google Feedfetcher'		=> array('Feedfetcher-Google', ''),
+		'Google [Bot]'				=> array('Googlebot', ''),
+		'Heise IT-Markt [Crawler]'	=> array('heise-IT-Markt-Crawler', ''),
+		'Heritrix [Crawler]'		=> array('heritrix/1.', ''),
+		'IBM Research [Bot]'		=> array('ibm.com/cs/crawler', ''),
+		'ICCrawler - ICjobs'		=> array('ICCrawler - ICjobs', ''),
+		'ichiro [Crawler]'			=> array('ichiro/2', ''),
+		'Majestic-12 [Bot]'			=> array('MJ12bot/', ''),
+		'Metager [Bot]'				=> array('MetagerBot/', ''),
+		'MSN NewsBlogs'				=> array('msnbot-NewsBlogs/', ''),
+		'MSN [Bot]'					=> array('msnbot/', ''),
+		'MSNbot Media'				=> array('msnbot-media/', ''),
+		'NG-Search [Bot]'			=> array('NG-Search/', ''),
+		'Nutch [Bot]'				=> array('http://lucene.apache.org/nutch/', ''),
+		'Nutch/CVS [Bot]'			=> array('NutchCVS/', ''),
+		'OmniExplorer [Bot]'		=> array('OmniExplorer_Bot/', ''),
+		'Online link [Validator]'	=> array('online link validator', ''),
+		'psbot [Picsearch]'			=> array('psbot/0', ''),
+		'Seekport [Bot]'			=> array('Seekbot/', ''),
+		'Sensis [Crawler]'			=> array('Sensis Web Crawler', ''),
+		'SEO Crawler'				=> array('SEO search Crawler/', ''),
+		'Seoma [Crawler]'			=> array('Seoma [SEO Crawler]', ''),
+		'SEOSearch [Crawler]'		=> array('SEOsearch/', ''),
+		'Snappy [Bot]'				=> array('Snappy/1.1 ( http://www.urltrends.com/ )', ''),
+		'Steeler [Crawler]'			=> array('http://www.tkl.iis.u-tokyo.ac.jp/~crawler/', ''),
+		'Synoo [Bot]'				=> array('SynooBot/', ''),
+		'Telekom [Bot]'				=> array('crawleradmin.t-info@telekom.de', ''),
+		'TurnitinBot [Bot]'			=> array('TurnitinBot/', ''),
+		'Voyager [Bot]'				=> array('voyager/1.0', ''),
+		'W3 [Sitesearch]'			=> array('W3 SiteSearch Crawler', ''),
+		'W3C [Linkcheck]'			=> array('W3C-checklink/', ''),
+		'W3C [Validator]'			=> array('W3C_*Validator', ''),
+		'WiseNut [Bot]'				=> array('http://www.WISEnutbot.com', ''),
+		'Yacy [Bot]'				=> array('yacybot', ''),
+		'Yahoo MMCrawler [Bot]'		=> array('Yahoo-MMCrawler/', ''),
+		'Yahoo Slurp [Bot]'			=> array('Yahoo! DE Slurp', ''),
+		'Yahoo [Bot]'				=> array('Yahoo! Slurp', ''),
+		'YahooSeeker [Bot]'			=> array('YahooSeeker/', ''),
 	);

 	/**