From 1bbdbfed20d28daca4496371feb1fd0becb4171a Mon Sep 17 00:00:00 2001
From: Liviu-Mihail Concioiu <liviu.concioiu@gmail.com>
Date: Wed, 5 Feb 2025 17:44:41 +0100
Subject: [PATCH] Improve bot regexes (#7986)

---
 Tests/fixtures/bots.yml |   6 +-
 regexes/bots.yml        | 341 ++++++++++++++++++++--------------------
 2 files changed, 171 insertions(+), 176 deletions(-)

diff --git a/Tests/fixtures/bots.yml b/Tests/fixtures/bots.yml
index 8e821f2eef..844476f2f5 100644
--- a/Tests/fixtures/bots.yml
+++ b/Tests/fixtures/bots.yml
@@ -4497,7 +4497,7 @@
 -
   user_agent: Mozilla/5.0 (compatible; seolyt/1.1; +https://seolyt.com)
   bot:
-    name: seolyt
+    name: SeolytBot
     category: Crawler
     url: https://seolyt.com/
 -
@@ -5169,9 +5169,9 @@
 -
   user_agent: 'Mozilla/5.0 (compatible; SeolytBot/1.0.1;  https://seolyt.com)'
   bot:
-    name: Seolyt Bot
+    name: SeolytBot
     category: Crawler
-    url: https://seolyt.com
+    url: https://seolyt.com/
 -
   user_agent: LinkWalker/3.0 (http://www.brandprotect.com)
   bot:
diff --git a/regexes/bots.yml b/regexes/bots.yml
index c487d3ab7d..2ca61d3259 100644
--- a/regexes/bots.yml
+++ b/regexes/bots.yml
@@ -5,7 +5,7 @@
 # @license http://www.gnu.org/licenses/lgpl.html LGPL v3 or later
 ###############
 
-- regex: 'WireReaderBot(?:/([\d+.]+))?'
+- regex: 'WireReaderBot'
   name: 'WireReaderBot'
   category: 'Feed Fetcher'
   url: 'https://wirereader.app/'
@@ -66,7 +66,7 @@
     name: 'Ahrefs Pte Ltd'
     url: 'https://ahrefs.com/robot'
 
-- regex: 'AhrefsSiteAudit/[\d.]+'
+- regex: 'AhrefsSiteAudit'
   name: 'AhrefsSiteAudit'
   category: 'Site Monitor'
   url: 'https://ahrefs.com/robot/site-audit'
@@ -90,7 +90,7 @@
     name: 'Alexa Internet'
     url: 'https://www.alexa.com'
 
-- regex: 'Amazonbot/[\d.]+'
+- regex: 'Amazonbot'
   name: 'Amazon Bot'
   category: 'Crawler'
   url: 'https://developer.amazon.com/support/amazonbot'
@@ -98,7 +98,7 @@
     name: 'Amazon.com, Inc.'
     url: 'https://www.amazon.com/'
 
-- regex: 'AmazonAdBot/[\d.]+'
+- regex: 'AmazonAdBot'
   name: 'Amazon AdBot'
   category: 'Crawler'
   url: 'https://adbot.amazon.com/'
@@ -615,7 +615,7 @@
     name: 'Meta Platforms, Inc.'
     url: 'https://www.meta.com/'
 
-- regex: 'FacebookBot/[\d.]+'
+- regex: 'FacebookBot'
   name: 'FacebookBot'
   category: 'Crawler'
   url: 'https://developers.facebook.com/docs/sharing/bot'
@@ -663,7 +663,7 @@
     name: ''
     url: ''
 
-- regex: 'Fever/[0-9]'
+- regex: 'Fever/'
   name: 'Fever'
   url: 'http://feedafever.com/'
   category: 'Feed Fetcher'
@@ -937,7 +937,7 @@
   category: 'Search bot'
   url: 'https://vuhuv.com/bot.html'
 
-- regex: 'HTTPMon/[\d.]+'
+- regex: 'HTTPMon'
   name: 'HTTPMon'
   category: 'Site Monitor'
   url: 'http://www.httpmon.com'
@@ -981,7 +981,7 @@
     name: ''
     url: 'https://ip-guide.com'
 
-- regex: 'k6/[0-9.]+'
+- regex: 'k6/'
   name: 'K6'
   url: 'https://k6.io/'
 
@@ -1065,7 +1065,7 @@
     name: ''
     url: ''
 
-- regex: 'masscan-ng/[\d.]+'
+- regex: 'masscan-ng'
   name: 'masscan-ng'
   url: 'https://github.com/bi-zone/masscan-ng'
   category: 'Crawler'
@@ -1236,7 +1236,7 @@
     name: 'NodePing'
     url: 'https://nodeping.com'
 
-- regex: 'Octopus [0-9]'
+- regex: 'Octopus [\d.]+'
   name: 'Octopus'
 
 - regex: 'OnlineOrNot\.com_bot'
@@ -1308,7 +1308,7 @@
     name: 'PHP Server Monitor'
     url: 'http://www.phpservermonitor.org/'
 
-- regex: 'Pocket(?:ImageCache|Parser)/[\d.]+'
+- regex: 'Pocket(?:ImageCache|Parser)'
   name: 'Pocket'
   category: 'Read-it-later Service'
   url: 'https://getpocket.com/pocketparser_ua'
@@ -1470,7 +1470,7 @@
     name: 'Semrush Inc.'
     url: 'https://www.semrush.com/'
 
-- regex: 'SerpReputationManagementAgent/[\d.]+'
+- regex: 'SerpReputationManagementAgent'
   name: 'Semrush Reputation Management'
   category: 'Service Agent'
   url: 'https://www.semrush.com/bot/'
@@ -1486,7 +1486,7 @@
     name: 'Semrush Inc.'
     url: 'https://www.semrush.com/'
 
-- regex: 'SiteAuditBot/[\d.]+'
+- regex: 'SiteAuditBot'
   name: 'SiteAuditBot'
   category: 'Crawler'
   url: 'https://www.semrush.com/bot/'
@@ -1648,7 +1648,7 @@
     name: 'Superfeedr'
     url: 'https://superfeedr.com/'
 
-- regex: 'Sparkler/[0-9]'
+- regex: 'Sparkler'
   name: 'Sparkler'
   category: 'Crawler'
   url: 'https://github.com/USCDataScience/sparkler'
@@ -1793,7 +1793,7 @@
     name: 'UkrNet Ltd'
     url: 'https://www.ukr.net/'
 
-- regex: 'Uptime(?:bot)?/[\d.]+'
+- regex: 'Uptime(?:bot)?/'
   name: 'Uptimebot'
   category: 'Site Monitor'
   url: 'https://uptime.com/uptime-bot'
@@ -1949,7 +1949,7 @@
     name: 'WPBeginner, LLC'
     url: 'https://www.wpbeginner.com/'
 
-- regex: 'Automattic Analytics Crawler/[\d.]+'
+- regex: 'Automattic Analytics Crawler'
   name: 'Automattic Analytics'
   category: 'Crawler'
   url: 'https://wordpress.com/crawler/'
@@ -2093,7 +2093,7 @@
     name: 'NetEase, Inc.'
     url: 'http://corp.163.com'
 
-- regex: 'YOURLS v[0-9]'
+- regex: 'YOURLS'
   name: 'Yourls'
   category: 'Crawler'
   url: 'http://yourls.org'
@@ -2159,7 +2159,7 @@
     name: 'HubPages, Inc.'
     url: 'https://discover.hubpages.com/'
 
-- regex: 'Pinterest(?:bot)?/[\d.]+.*www\.pinterest\.com'
+- regex: 'Pinterest(?:bot)?/.*www\.pinterest\.com'
   name: 'Pinterest'
   url: 'https://help.pinterest.com/en/business/article/pinterest-crawler'
   category: 'Crawler'
@@ -2175,7 +2175,7 @@
     name: 'Site24x7'
     url: 'https://www.site24x7.com'
 
-- regex: '.* HLB/[\d.]+'
+- regex: '.* HLB'
   name: 'Site24x7 Defacement Monitor'
   category: 'Site Monitor'
   url: 'https://support.site24x7.com/portal/en/kb/articles/default-user-agent-used-in-website-defacement-monitor'
@@ -2199,7 +2199,7 @@
     name: 'Snapchat Inc.'
     url: 'https://www.snapchat.com/'
 
-- regex: 'SnapchatAds/[\d.]+'
+- regex: 'SnapchatAds'
   name: 'Snapchat Ads'
   category: 'Crawler'
   url: 'https://businesshelp.snapchat.com/s/article/adsbot-crawler?language=en_US'
@@ -2596,7 +2596,7 @@
     name: 'PPC Labs LLC'
     url: 'https://www.adbeat.com/'
 
-- regex: '(?:BuiltWith|BW)/[\d.]+'
+- regex: '(?:BuiltWith|BW/)'
   name: 'BuiltWith'
   category: 'Crawler'
   url: 'https://builtwith.com/biup'
@@ -2651,7 +2651,7 @@
   category: 'Site Monitor'
   url: 'http://cloudsystemnetworks.com'
 
-- regex: 'HeartRails_Capture/[\d.]+'
+- regex: 'HeartRails_Capture'
   name: 'Heart Rails Capture'
   category: 'Service Agent'
   url: 'http://capture.heartrails.com'
@@ -2664,7 +2664,7 @@
     name: 'RedHunt Labs Limited'
     url: 'https://redhuntlabs.com/'
 
-- regex: 'DataXu/[\d.]+'
+- regex: 'DataXu'
   name: 'DataXu'
   category: 'Service Agent'
   url: 'https://advertising.roku.com/dataxu'
@@ -2788,12 +2788,12 @@
     name: 'Hatena Co., Ltd.'
     url: 'https://www.hatena.ne.jp'
 
-- regex: 'RyowlEngine/[\d.]+'
+- regex: 'RyowlEngine'
   name: 'Ryowl'
   category: 'Crawler'
   url: 'https://ryowl.org'
 
-- regex: 'OdklBot/[\d.]+'
+- regex: 'OdklBot'
   name: 'Odnoklassniki Bot'
   category: 'Crawler'
   url: 'https://odnoklassniki.ru'
@@ -2808,7 +2808,7 @@
   category: 'Crawler'
   url: 'https://www.zoominfo.com'
 
-- regex: 'WeViKaBot/[\d.]+'
+- regex: 'WeViKaBot'
   name: 'WeViKaBot'
   category: 'Crawler'
   url: 'http://www.wevika.de'
@@ -2821,7 +2821,7 @@
     name: 'SEOkicks'
     url: 'https://www.seokicks.de/'
 
-- regex: 'Plukkie/[\d.]+'
+- regex: 'Plukkie'
   name: 'Plukkie'
   category: 'Crawler'
   url: 'http://www.botje.com/plukkie.htm'
@@ -2831,22 +2831,22 @@
   category: 'Crawler'
   url: 'https://www.comscore.com/Web-Crawler'
 
-- regex: 'SurdotlyBot/[\d.]+'
+- regex: 'SurdotlyBot'
   name: 'SurdotlyBot'
   category: 'Crawler'
   url: 'http://sur.ly/bot.html'
 
-- regex: 'Gowikibot/[\d.]+'
+- regex: 'Gowikibot'
   name: 'Gowikibot'
   category: 'Crawler'
   url: 'http:/www.gowikibot.com'
 
-- regex: 'SabsimBot/[\d.]+'
+- regex: 'SabsimBot'
   name: 'SabsimBot'
   category: 'Crawler'
   url: 'https://sabsim.com'
 
-- regex: 'LumtelBot/[\d.]+'
+- regex: 'LumtelBot'
   name: 'LumtelBot'
   category: 'Crawler'
   url: 'https://umtel.com'
@@ -2856,12 +2856,12 @@
   category: 'Crawler'
   url: 'http://www.pipl.com/bot'
 
-- regex: 'woobot/[\d.]+'
+- regex: 'woobot'
   name: 'WooRank'
   category: 'Crawler'
   url: 'https://www.woorank.com/bot'
 
-- regex: 'Cookiebot/[\d.]+'
+- regex: 'Cookiebot'
   name: 'Cookiebot'
   category: 'Crawler'
   url: 'https://support.cookiebot.com/hc/en-us/articles/360014264140-Scanner-User-Agent'
@@ -2877,7 +2877,7 @@
     name: 'NET SYSTEMS RESEARCH LLC'
     url: 'https://www.netsystemsresearch.com/'
 
-- regex: 'CensysInspect/[\d.]+'
+- regex: 'CensysInspect'
   name: 'CensysInspect'
   category: 'Security Checker'
   url: 'https://about.censys.io/'
@@ -2893,17 +2893,17 @@
     name: 'Global Digital Network Plus, LLC'
     url: 'https://gdnplus.com/'
 
-- regex: 'WellKnownBot/[\d.]+'
+- regex: 'WellKnownBot'
   name: 'WellKnownBot'
   category: 'Crawler'
   url: 'https://well-known.dev'
 
-- regex: 'Adsbot/[\d.]+'
+- regex: 'Adsbot'
   name: 'Adsbot'
   category: 'Crawler'
   url: 'https://seostar.co/robot/'
 
-- regex: 'MTRobot/[\d.]+'
+- regex: 'MTRobot'
   name: 'MTRobot'
   category: 'Crawler'
   url: 'https://metrics-tools.de/robot.html'
@@ -2911,7 +2911,7 @@
     name: 'Metrics Tools'
     url: 'https://metrics-tools.de/'
 
-- regex: 'serpstatbot/[\d.]+'
+- regex: 'serpstatbot'
   name: 'serpstatbot'
   category: 'Crawler'
   url: 'http://serpstatbot.com/'
@@ -2924,17 +2924,17 @@
   category: 'Crawler'
   url: 'https://github.com/gocolly/colly/'
 
-- regex: 'l9tcpid/v[\d.]+'
+- regex: 'l9tcpid'
   name: 'l9tcpid'
   category: 'Security Checker'
   url: 'https://github.com/LeakIX/l9tcpid'
 
-- regex: 'l9explore/[\d.]+'
+- regex: 'l9explore'
   name: 'l9explore'
   category: 'Security Checker'
   url: 'https://github.com/LeakIX/l9explore'
 
-- regex: 'l9scan/|^Lkx-.*/[\d.]+'
+- regex: 'l9scan/|^Lkx-.*/'
   name: 'LeakIX'
   category: 'Security Checker'
   url: 'https://leakix.net/'
@@ -2942,7 +2942,7 @@
     name: 'BaDaaS SRL'
     url: 'https://leakix.net/'
 
-- regex: 'MegaIndex\.ru/[\d.]+'
+- regex: 'MegaIndex\.ru'
   name: 'MegaIndex'
   category: 'Crawler'
   url: 'https://megaindex.com/crawler'
@@ -2955,12 +2955,12 @@
     name: 'SISTRIX GmbH'
     url: 'https://www.sistrix.de/'
 
-- regex: 'seolyt/[\d.]+'
-  name: 'seolyt'
+- regex: 'Seolyt(?:Bot)?'
+  name: 'SeolytBot'
   category: 'Crawler'
   url: 'https://seolyt.com/'
 
-- regex: 'YaK/[\d.]+'
+- regex: 'YaK/'
   name: 'YaK'
   category: 'Crawler'
   url: 'https://www.linkfluence.com/'
@@ -2968,7 +2968,7 @@
     name: 'Linkfluence SAS'
     url: 'https://www.linkfluence.com/'
 
-- regex: 'KomodiaBot/[\d.]+'
+- regex: 'KomodiaBot'
   name: 'KomodiaBot'
   category: 'Crawler'
   url: 'http://www.komodia.com/newwiki/index.php/URL_server_crawler'
@@ -2976,7 +2976,7 @@
     name: 'Komodia Inc.'
     url: 'https://www.komodia.com/'
 
-- regex: 'KStandBot/[\d.]+'
+- regex: 'KStandBot'
   name: 'KStandBot'
   category: 'Crawler'
   url: 'https://url-classification.io/wiki/index.php?title=URL_server_crawler'
@@ -2984,7 +2984,7 @@
     name: 'Komodia Inc.'
     url: 'https://www.komodia.com/'
 
-- regex: 'Neevabot/[\d.]+'
+- regex: 'Neevabot'
   name: 'Neevabot'
   category: 'Search bot'
   url: 'https://neeva.com/neevabot'
@@ -2992,17 +2992,25 @@
     name: 'Neeva Inc.'
     url: 'https://neeva.com/'
 
-- regex: 'LinkPreview/[\d.]+'
+- regex: 'Chatwork LinkPreview'
+  name: 'Chatwork LinkPreview'
+  category: 'Service Agent'
+  url: 'https://go.chatwork.com/en/'
+  producer:
+    name: 'kubell Co., Ltd.'
+    url: 'https://www.kubell.com/en/'
+
+- regex: 'LinkPreview'
   name: 'LinkPreview'
   category: 'Service Agent'
   url: 'https://www.linkpreview.net/'
 
-- regex: 'JungleKeyThumbnail/[\d.]+'
+- regex: 'JungleKeyThumbnail'
   name: 'JungleKeyThumbnail'
   category: 'Crawler'
   url: 'https://junglekey.com/'
 
-- regex: 'rocketmonitor(?: |bot/)[\d.]+'
+- regex: 'rocketmonitor(?:bot)?'
   name: 'RocketMonitorBot'
   category: 'Site Monitor'
   url: 'https://www.radiomast.io/docs/stream-monitoring/technical_details.html'
@@ -3010,7 +3018,7 @@
     name: 'Radio Mast, Inc.'
     url: 'https://www.radiomast.io/'
 
-- regex: 'SitemapParser-VIPnytt/[\d.]+'
+- regex: 'SitemapParser-VIPnytt'
   name: 'SitemapParser-VIPnytt'
   category: 'Crawler'
   url: 'https://github.com/VIPnytt/SitemapParser/'
@@ -3020,7 +3028,7 @@
   category: 'Crawler'
   url: 'https://turnitin.com/robot/crawlerinfo.html'
 
-- regex: 'DMBrowser/[\d.]+|DMBrowser-[UB]V'
+- regex: 'DMBrowser|DMBrowser-[UB]V'
   name: 'Dotcom Monitor'
   category: 'Site Monitor'
   url: 'https://www.dotcom-monitor.com'
@@ -3034,17 +3042,17 @@
   category: 'Crawler'
   url: 'https://dataforseo.com/dataforseo-bot'
 
-- regex: 'Discordbot/[\d.]+'
+- regex: 'Discordbot'
   name: 'Discord Bot'
   category: 'Service Agent'
   url: 'https://discordapp.com'
 
-- regex: 'Linespider/[\d.]+'
+- regex: 'Linespider'
   name: 'Linespider'
   category: 'Crawler'
   url: 'https://lin.ee/4dwXkTH'
 
-- regex: 'Cincraw/[\d.]+'
+- regex: 'Cincraw'
   name: 'Cincraw'
   category: 'Crawler'
   url: 'http://cincrawdata.net/bot/'
@@ -3078,17 +3086,17 @@
     name: 'Hochschule für angewandte Wissenschaften München'
     url: 'https://www.hm.edu/'
 
-- regex: 'TigerBot/[\d.]+'
+- regex: 'TigerBot'
   name: 'TigerBot'
   category: 'Crawler'
   url: 'https://tiger.ch/'
 
-- regex: 'TestCrawler/[\d.]+'
+- regex: 'TestCrawler'
   name: 'TestCrawler'
   category: 'Crawler'
   url: 'https://www.comcepta.com/'
 
-- regex: 'CrowdTanglebot/[\d.]+'
+- regex: 'CrowdTanglebot'
   name: 'CrowdTangle'
   category: 'Crawler'
   url: 'https://help.crowdtangle.com/en/articles/3009319-crowdtangle-bot'
@@ -3120,7 +3128,7 @@
     name: 'deepnoc, GmbH'
     url: 'https://deepnoc.com/'
 
-- regex: 'Newslitbot/[\d.]+'
+- regex: 'Newslitbot'
   name: 'Newslitbot'
   category: 'Crawler'
   url: 'https://www.newslit.co/'
@@ -3128,7 +3136,7 @@
     name: 'Newslit, LLC.'
     url: 'https://www.newslit.co/'
 
-- regex: 'um-(?:ANS|CC|FC|IC|LN)/[\d.]+'
+- regex: 'um-(?:ANS|CC|FC|IC|LN)'
   name: 'uMBot'
   category: 'Crawler'
   url: 'https://www.ubermetrics-technologies.com/'
@@ -3136,7 +3144,7 @@
     name: 'Ubermetrics Technologies GmbH'
     url: 'https://www.ubermetrics-technologies.com/'
 
-- regex: 'Abonti/[\d.]+'
+- regex: 'Abonti'
   name: 'Abonti'
   category: 'Crawler'
   url: 'http://abonti.com/'
@@ -3157,7 +3165,7 @@
     name: 'Beijing Tiantexin Tech. Co., Ltd.'
     url: 'https://en.ipip.net/'
 
-- regex: 'ev-crawler/[\d.]+'
+- regex: 'ev-crawler'
   name: 'Headline'
   category: 'Crawler'
   url: 'https://headline.com/legal/crawler'
@@ -3165,7 +3173,7 @@
     name: 'e.ventures Managementgesellschaft mbH'
     url: 'https://headline.com/'
 
-- regex: 'webprosbot/[\d.]+'
+- regex: 'webprosbot'
   name: 'WebPros'
   category: 'Crawler'
   url: 'https://webpros.com/'
@@ -3181,7 +3189,7 @@
     name: 'Amazon.com, Inc.'
     url: 'https://www.amazon.com/'
 
-- regex: 'Wheregoes\.com Redirect Checker/[\d.]+'
+- regex: 'Wheregoes\.com Redirect Checker'
   name: 'WhereGoes'
   category: 'Crawler'
   url: 'https://wheregoes.com/'
@@ -3191,12 +3199,12 @@
   category: 'Crawler'
   url: 'http://66.240.192.82/'
 
-- regex: 'InternetMeasurement/[\d.]+'
+- regex: 'InternetMeasurement'
   name: 'InternetMeasurement'
   category: 'Crawler'
   url: 'https://internet-measurement.com/'
 
-- regex: 'DomainAppender /[\d.]+'
+- regex: 'DomainAppender'
   name: 'DomainAppender'
   category: 'Crawler'
   url: 'https://www.profound.net/product/domain_append/'
@@ -3204,7 +3212,7 @@
     name: 'Profound Networks, LLC'
     url: 'https://www.profound.net/'
 
-- regex: 'FreeWebMonitoring SiteChecker/[\d.]+'
+- regex: 'FreeWebMonitoring SiteChecker'
   name: 'FreeWebMonitoring'
   category: 'Site Monitor'
   url: 'https://www.freewebmonitoring.com/bot.html'
@@ -3228,7 +3236,7 @@
     name: 'Jaohawi AB'
     url: 'https://adstxtlab.com/'
 
-- regex: 'Iframely/[\d.]+'
+- regex: 'Iframely'
   name: 'Iframely'
   category: 'Crawler'
   url: 'https://iframely.com/'
@@ -3236,7 +3244,7 @@
     name: 'Itteco Software, Corp.'
     url: 'https://iframely.com/'
 
-- regex: 'DomainStatsBot/[\d.]+'
+- regex: 'DomainStatsBot'
   name: 'DomainStatsBot'
   category: 'Crawler'
   url: 'https://domainstats.com/pages/our-bot'
@@ -3244,7 +3252,7 @@
     name: 'Domainstats Ltd'
     url: 'https://domainstats.com/'
 
-- regex: 'aiHitBot/[\d.]+'
+- regex: 'aiHitBot'
   name: 'aiHitBot'
   category: 'Crawler'
   url: 'https://www.aihitdata.com/about'
@@ -3262,7 +3270,7 @@
   name: 'GitCrawlerBot'
   category: 'Crawler'
 
-- regex: 'AdAuth/[\d.]+'
+- regex: 'AdAuth'
   name: 'AdAuth'
   category: 'Crawler'
   url: 'https://www.adauth.com'
@@ -3330,7 +3338,7 @@
     name: 'Swoppen Systems GmbH'
     url: 'https://www.swoppen.com/de'
 
-- regex: 'ScamadviserExternalHit/[\d.]+'
+- regex: 'ScamadviserExternalHit'
   name: 'Scamadviser External Hit'
   category: 'Crawler'
   url: 'https://www.scamadviser.com/'
@@ -3346,17 +3354,12 @@
     name: 'Zaldamo, LLC.'
     url: 'https://www.zaldamo.com/'
 
-- regex: 'AFB/[\d.]+'
+- regex: 'AFB'
   name: 'Allloadin Favicon Bot'
   category: 'Crawler'
   url: 'https://allloadin.com/'
 
-- regex: 'SeolytBot/[\d.]+'
-  name: 'Seolyt Bot'
-  category: 'Crawler'
-  url: 'https://seolyt.com'
-
-- regex: 'LinkWalker/[\d.]+'
+- regex: 'LinkWalker'
   name: 'LinkWalker'
   category: 'Crawler'
   url: 'https://www.phishlabs.com/'
@@ -3364,7 +3367,7 @@
     name: 'PhishLabs, Inc.'
     url: 'https://www.phishlabs.com/'
 
-- regex: 'RenovateBot/[\d.]+'
+- regex: 'RenovateBot'
   name: 'RenovateBot'
   category: 'Security Checker'
   url: 'https://github.com/renovatebot/renovate'
@@ -3372,7 +3375,7 @@
     name: 'White Source Ltd.'
     url: 'https://www.mend.io/free-developer-tools/renovate/'
 
-- regex: 'INETDEX-BOT/[\d.]+'
+- regex: 'INETDEX-BOT'
   name: 'Inetdex Bot'
   category: 'Crawler'
   url: 'https://www.inetdex.com/'
@@ -3401,7 +3404,7 @@
     name: 'PDR Labs'
     url: 'https://web.archive.org/web/20220420054123/http://www.pdrlabs.net/'
 
-- regex: 'Nicecrawler/[\d.]+'
+- regex: 'Nicecrawler'
   name: 'NiceCrawler'
   category: 'Crawler'
   url: 'https://www.nicecrawler.com/'
@@ -3409,7 +3412,7 @@
     name: 'Intelium Corp.'
     url: 'https://www.intelium.com/'
 
-- regex: 't3versionsBot/[\d.]+'
+- regex: 't3versionsBot'
   name: 't3versions'
   category: 'Crawler'
   url: 'https://www.t3versions.com/bot'
@@ -3417,7 +3420,7 @@
     name: 'Torben Hansen'
     url: 'https://www.t3versions.com/'
 
-- regex: 'Crawlson/[\d.]+'
+- regex: 'Crawlson'
   name: 'Crawlson'
   category: 'Crawler'
   url: 'https://www.crawlson.com/about'
@@ -3425,7 +3428,7 @@
     name: 'Crawlson'
     url: 'https://www.crawlson.com/'
 
-- regex: 'tchelebi/[\d.]+'
+- regex: 'tchelebi'
   name: 'tchelebi'
   category: 'Crawler'
   url: 'https://tchelebi.io/'
@@ -3441,7 +3444,7 @@
     name: 'New Work SE'
     url: 'https://www.xing.com/'
 
-- regex: 'RepoLookoutBot/v?[\d.]+'
+- regex: 'RepoLookoutBot'
   name: 'Repo Lookout'
   category: 'Security Checker'
   url: 'https://www.repo-lookout.org/'
@@ -3457,7 +3460,7 @@
     name: 'MAMI Project'
     url: 'https://mami-project.eu/'
 
-- regex: 'everyfeed-spider/[\d.]+'
+- regex: 'everyfeed-spider'
   name: 'Everyfeed'
   url: 'https://web.archive.org/web/20050930235914/http://www.everyfeed.com/'
   category: 'Feed Fetcher'
@@ -3481,7 +3484,7 @@
     name: ''
     url: ''
 
-- regex: 'Gregarius/[\d.]+'
+- regex: 'Gregarius'
   name: 'Gregarius'
   category: 'Feed Fetcher'
   url: 'https://web.archive.org/web/20100614011837/http://devlog.gregarius.net/docs/ua/'
@@ -3505,7 +3508,7 @@
     name: 'Sectigo Limited'
     url: 'https://sectigo.com/'
 
-- regex: 'KlarnaBot-(?:DownloadProductImage|EnrichProducts|PriceWatcher)/[\d.]+'
+- regex: 'KlarnaBot-(?:DownloadProductImage|EnrichProducts|PriceWatcher)'
   name: 'KlarnaBot'
   category: 'Crawler'
   url: 'https://docs.klarna.com/klarna-bot/'
@@ -3513,7 +3516,7 @@
     name: 'Klarna Bank AB'
     url: 'https://www.klarna.com/'
 
-- regex: 'Taboolabot/[\d.]+'
+- regex: 'Taboolabot'
   name: 'Taboolabot'
   category: 'Crawler'
   url: 'https://help.taboola.com/hc/en-us/articles/115002347594-The-Taboola-Crawler'
@@ -3521,7 +3524,7 @@
     name: 'Taboola, Inc.'
     url: 'https://www.taboola.com/'
 
-- regex: 'Asana/[\d.]+'
+- regex: 'Asana'
   name: 'Asana'
   category: 'Crawler'
   url: 'https://asana.com/'
@@ -3537,7 +3540,7 @@
     name: 'Google Inc.'
     url: 'https://www.google.com/'
 
-- regex: 'URLinspectorBot/[\d.]+'
+- regex: 'URLinspectorBot'
   name: 'URLinspector'
   category: 'Site Monitor'
   url: 'https://www.urlinspector.com/bot/'
@@ -3545,7 +3548,7 @@
     name: 'LinkResearchTools GmbH'
     url: 'https://www.linkresearchtools.com/'
 
-- regex: 'EntferBot/[\d.]+'
+- regex: 'EntferBot'
   name: 'Entfer'
   category: 'Crawler'
   url: 'https://entfer.com/'
@@ -3553,7 +3556,7 @@
     name: 'Entfer Ltd.'
     url: 'https://entfer.com/'
 
-- regex: 'TagInspector/[\d.]+'
+- regex: 'TagInspector'
   name: 'Tag Inspector'
   category: 'Crawler'
   url: 'https://taginspector.com/'
@@ -3577,7 +3580,7 @@
     name: 'Diffbot Technologies Corp.'
     url: 'https://www.diffbot.com/'
 
-- regex: 'DisqusAdstxtCrawler/[\d.]+'
+- regex: 'DisqusAdstxtCrawler'
   name: 'Disqus'
   category: 'Crawler'
   url: 'https://help.disqus.com/en/articles/1765357-ads-txt-implementation-guide'
@@ -3585,7 +3588,7 @@
     name: 'Disqus, Inc.'
     url: 'https://disqus.com/'
 
-- regex: 'startmebot/[\d.]+'
+- regex: 'startmebot'
   name: 'start.me'
   category: 'Crawler'
   url: 'https://about.start.me/'
@@ -3593,17 +3596,17 @@
     name: 'start.me BV'
     url: 'https://about.start.me/'
 
-- regex: '2ip bot/[\d.]+'
+- regex: '2ip bot'
   name: '2ip'
   category: 'Crawler'
   url: 'https://2ip.io/'
 
-- regex: 'ReqBin Curl Client/[\d.]+'
+- regex: 'ReqBin Curl Client'
   name: 'ReqBin'
   category: 'Crawler'
   url: 'https://reqbin.com/curl'
 
-- regex: 'XoviBot/[\d.]+'
+- regex: 'XoviBot'
   name: 'XoviBot'
   category: 'Crawler'
   url: 'https://www.xovibot.net'
@@ -3611,12 +3614,12 @@
     name: 'Xovi GmbH'
     url: 'http://www.xovi.de'
 
-- regex: 'Overcast/[\d.]+ Podcast Sync'
+- regex: 'Overcast/.+Podcast Sync'
   name: 'Overcast Podcast Sync'
   category: 'Service Agent'
   url: 'https://overcast.fm/podcasterinfo'
 
-- regex: '^Verity/[\d.]+'
+- regex: '^Verity'
   name: 'GumGum Verity'
   category: 'Service Agent'
   url: 'https://gumgum.com/verity'
@@ -3626,7 +3629,7 @@
   category: 'Feed Reader'
   url: 'https://github.com/snarfed/hackermention'
 
-- regex: 'BitSightBot/[\d.]+'
+- regex: 'BitSightBot'
   name: 'BitSight'
   category: 'Security Checker'
   url: 'https://www.bitsight.com/'
@@ -3634,7 +3637,7 @@
     name: 'BitSight Technologies, Inc.'
     url: 'https://www.bitsight.com/'
 
-- regex: 'Ezgif/[\d.]+'
+- regex: 'Ezgif'
   name: 'Ezgif'
   category: 'Service Agent'
   url: 'https://ezgif.com/about'
@@ -3647,7 +3650,7 @@
     name: 'Kleissner Investments s.r.o.'
     url: 'https://intelx.io/'
 
-- regex: 'FemtosearchBot/[\d.]+'
+- regex: 'FemtosearchBot'
   name: 'Femtosearch'
   category: 'Crawler'
   url: 'http://femtosearch.com/'
@@ -3655,7 +3658,7 @@
     name: 'Grier Forensics, LLC'
     url: 'https://www.grierforensics.com/'
 
-- regex: 'AdsTxtCrawler/[\d.]+'
+- regex: 'AdsTxtCrawler/'
   name: 'AdsTxtCrawler'
   category: 'Crawler'
   url: 'https://github.com/InteractiveAdvertisingBureau/adstxtcrawler'
@@ -3671,7 +3674,7 @@
     name: 'Morningscore'
     url: 'https://morningscore.io/'
 
-- regex: 'Uptime-Kuma/[\d.]+'
+- regex: 'Uptime-Kuma'
   name: 'Uptime-Kuma'
   category: 'Site Monitor'
   url: 'https://github.com/louislam/uptime-kuma'
@@ -3684,7 +3687,7 @@
     name: 'OpenAI OpCo, LLC'
     url: 'https://openai.com/'
 
-- regex: 'GPTBot/[\d.]+'
+- regex: 'GPTBot'
   name: 'GPTBot'
   category: 'Crawler'
   url: 'https://platform.openai.com/docs/bots'
@@ -3700,7 +3703,7 @@
     name: 'OpenAI OpCo, LLC'
     url: 'https://openai.com/'
 
-- regex: 'BrightEdge Crawler/[\d.]+'
+- regex: 'BrightEdge Crawler'
   name: 'BrightEdge'
   category: 'Crawler'
   url: 'https://www.brightedge.com/'
@@ -3708,7 +3711,7 @@
     name: 'BrightEdge Technologies, Inc'
     url: 'https://www.brightedge.com/'
 
-- regex: 'sfFeedReader/[\d.]+'
+- regex: 'sfFeedReader'
   name: 'sfFeedReader'
   url: 'https://github.com/diem-project/sfFeed2Plugin'
   category: 'Feed Fetcher'
@@ -3729,7 +3732,7 @@
     name: 'RWTH Aachen University'
     url: 'https://www.comsys.rwth-aachen.de/'
 
-- regex: 'newspaper/[\d.]+'
+- regex: 'newspaper'
   name: 'Scraping Robot'
   category: 'Crawler'
   url: 'https://scrapingrobot.com/'
@@ -3737,7 +3740,7 @@
     name: 'Sprious LLC'
     url: 'https://sprious.com/'
 
-- regex: 'Ant(?:\.com beta|Bot)(?:/([\d+.]+))?'
+- regex: 'Ant(?:\.com beta|Bot)'
   name: 'Ant'
   category: 'Crawler'
   url: 'https://www.ant.com/'
@@ -3745,7 +3748,7 @@
     name: 'Ant.com Ltd.'
     url: 'https://www.ant.com/'
 
-- regex: 'WebwikiBot/[\d.]+'
+- regex: 'WebwikiBot'
   name: 'Webwiki'
   category: 'Crawler'
   url: 'https://www.webwiki.com/'
@@ -3758,7 +3761,7 @@
   category: 'Service Agent'
   url: 'https://www.phpmyadmin.net/'
 
-- regex: 'Matomo/[\d.]+'
+- regex: 'Matomo'
   name: 'Matomo'
   category: 'Service Agent'
   url: 'https://github.com/matomo-org/matomo'
@@ -3766,7 +3769,7 @@
     name: 'InnoCraft Ltd'
     url: 'https://matomo.org/'
 
-- regex: 'Prometheus/[\d.]+'
+- regex: 'Prometheus'
   name: 'Prometheus'
   category: 'Service Agent'
   url: 'https://github.com/prometheus/prometheus'
@@ -3782,7 +3785,7 @@
     name: 'ArchiveTeam'
     url: 'https://wiki.archiveteam.org/'
 
-- regex: 'MADBbot/[\d.]+'
+- regex: 'MADBbot'
   name: 'MADBbot'
   category: 'Crawler'
   url: 'https://madb.zapto.org/bot.html'
@@ -3838,7 +3841,7 @@
   producer:
     name: 'Tactikast'
 
-- regex: 'Brightbot ([\d+.]+)'
+- regex: 'Brightbot'
   name: 'BrightBot'
   category: 'Crawler'
   url: 'https://www.brightbot.app/'
@@ -3846,7 +3849,7 @@
     name: 'Bright Interactive Ltd'
     url: 'https://www.builtbybright.com/'
 
-- regex: 'DaspeedBot/([\d+.]+)'
+- regex: 'DaspeedBot'
   name: 'DaspeedBot'
   category: 'Crawler'
   url: 'https://daspeed.io/'
@@ -3854,7 +3857,7 @@
     name: 'DAWAP SARL'
     url: 'https://dawap.fr/'
 
-- regex: 'StractBot(?:/([\d+.]+))?'
+- regex: 'StractBot'
   name: 'Stract'
   category: 'Crawler'
   url: 'https://stract.com/webmasters'
@@ -3862,7 +3865,7 @@
     name: 'Stract'
     url: 'https://github.com/StractOrg/stract/'
 
-- regex: 'GeedoBot(?:/([\d+.]+))?'
+- regex: 'GeedoBot'
   name: 'GeedoBot'
   category: 'Crawler'
   url: 'https://geedo.com/bot/'
@@ -3872,7 +3875,7 @@
   category: 'Crawler'
   url: 'https://geedo.com/product-search/'
 
-- regex: 'BackupLand(?:/([\d+.]+))?'
+- regex: 'BackupLand'
   name: 'BackupLand'
   category: 'Crawler'
   url: 'https://go.backupland.com/'
@@ -3880,7 +3883,7 @@
     name: 'ООО «КВАРТА»'
     url: 'https://go.backupland.com/'
 
-- regex: 'Konturbot(?:/([\d+.]+))?'
+- regex: 'Konturbot'
   name: 'Konturbot'
   category: 'Crawler'
   url: 'https://kontur.ru/'
@@ -3896,17 +3899,17 @@
     name: 'ООО «МОДЕСКО»'
     url: 'https://www.modesco.ru/'
 
-- regex: 'LetsearchBot(?:/([\d+.]+))?'
+- regex: 'LetsearchBot'
   name: 'LetSearch'
   category: 'Crawler'
   url: 'https://letsearch.ru/bots'
 
-- regex: 'Example3(?:/([\d+.]+))?'
+- regex: 'Example3'
   name: 'Example3'
   category: 'Crawler'
   url: 'https://www.example3.com/'
 
-- regex: 'StatOnlineRuBot(?:/([\d+.]+))?'
+- regex: 'StatOnlineRuBot'
   name: 'StatOnline.ru'
   category: 'Crawler'
   url: 'https://statonline.ru/'
@@ -3990,7 +3993,7 @@
     name: 'Anthropic, PBC'
     url: 'https://www.anthropic.com/'
 
-- regex: 'NetpeakCheckerBot/[\d.]+'
+- regex: 'NetpeakCheckerBot'
   name: 'Netpeak Checker'
   category: 'Crawler'
   url: 'https://netpeaksoftware.com/checker'
@@ -3998,7 +4001,7 @@
     name: 'Netpeak LTD'
     url: 'https://netpeaksoftware.com/'
 
-- regex: 'SandobaCrawler/[\d.]+'
+- regex: 'SandobaCrawler'
   name: 'Sandoba//Crawler'
   category: 'Crawler'
   url: 'https://www.sandoba.com/en/crawler/'
@@ -4014,7 +4017,7 @@
     name: 'Sirdata SAS'
     url: 'https://www.sirdata.com/'
 
-- regex: 'CheckMarkNetwork/[\d.]+'
+- regex: 'CheckMarkNetwork'
   name: 'CheckMark Network'
   category: 'Crawler'
   url: 'https://www.checkmarknetwork.com/spider.html/'
@@ -4030,7 +4033,7 @@
     name: 'Cohere, Inc.'
     url: 'https://cohere.com/'
 
-- regex: 'PerplexityBot/[\d.]+'
+- regex: 'PerplexityBot'
   name: 'PerplexityBot'
   category: 'Crawler'
   url: 'https://docs.perplexity.ai/docs/perplexitybot'
@@ -4054,12 +4057,12 @@
     name: 'Metadot, Corp.'
     url: 'https://www.metadot.com/'
 
-- regex: 'Ruby, Twurly v[\d.]+'
+- regex: 'Ruby, Twurly v'
   name: 'Twurly'
   category: 'Crawler'
   url: 'https://twurly.org/'
 
-- regex: 'Mixnode(?:(?:Cache)?/[\d.]+)?'
+- regex: 'Mixnode(?:Cache)?'
   name: 'Mixnode'
   category: 'Crawler'
   url: 'https://www.mixnode.com/'
@@ -4067,11 +4070,11 @@
     name: 'Mixnode Technologies, Inc.'
     url: 'https://www.mixnode.com/'
 
-- regex: 'CSSCheck/[\d.]+'
+- regex: 'CSSCheck'
   name: 'CSSCheck'
   category: 'Validator'
 
-- regex: 'MicrosoftPreview/[\d.]+'
+- regex: 'MicrosoftPreview'
   name: 'Microsoft Preview'
   category: 'Service Agent'
   url: 'https://www.bing.com/webmasters/help/which-crawlers-does-bing-use-8c184ec0'
@@ -4087,7 +4090,7 @@
     name: 'Chronicle Security Ireland Limited'
     url: 'https://chronicle.security/'
 
-- regex: 'TinEye/[\d.]+'
+- regex: 'TinEye'
   name: 'TinEye'
   category: 'Crawler'
   url: 'https://tineye.com/'
@@ -4119,7 +4122,7 @@
     name: 'AdScanner d.o.o'
     url: 'https://www.alleyesonscreens.com/'
 
-- regex: 'online-webceo-bot/[\d.]+'
+- regex: 'online-webceo-bot'
   name: 'WebCEO'
   category: 'Crawler'
   url: 'https://www.webceo.com/'
@@ -4140,7 +4143,7 @@
     name: 'Vistex LTD'
     url: 'https://www.htmlyse.com/'
 
-- regex: 'TrendsmapResolver/[\d.]+'
+- regex: 'TrendsmapResolver'
   name: 'Trendsmap'
   category: 'Crawler'
   url: 'https://www.trendsmap.com/'
@@ -4148,7 +4151,7 @@
     name: 'Trendsmap Pty Ltd'
     url: 'https://www.trendsmap.com/'
 
-- regex: 'Shareaholic(?:bot)?/[\d.]+'
+- regex: 'Shareaholic(?:bot)?'
   name: 'Steve Bot'
   category: 'Crawler'
   url: 'https://www.shareaholic.com/steve'
@@ -4182,7 +4185,7 @@
   category: 'Service Agent'
   url: 'https://www.whatsmyip.org/ua/'
 
-- regex: 'SenutoBot/[\d.]+'
+- regex: 'SenutoBot'
   name: 'Senuto'
   category: 'Crawler'
   url: 'https://www.senuto.com/'
@@ -4198,7 +4201,7 @@
     name: 'Doly Horjun HJ'
     url: 'https://gozle.com.tm/'
 
-- regex: 'Quantcastbot/[\d.]+'
+- regex: 'Quantcastbot'
   name: 'Quantcast'
   category: 'Crawler'
   url: 'https://www.quantcast.com/bot/'
@@ -4238,7 +4241,7 @@
     name: 'Barracuda Networks, Inc.'
     url: 'https://www.barracudanetworks.com/'
 
-- regex: 'RuxitSynthetic/[\d.]+'
+- regex: 'RuxitSynthetic'
   name: 'RuxitSynthetic'
   category: 'Site Monitor'
   url: 'https://community.dynatrace.com/t5/Troubleshooting/Basic-Commands-for-Synthetic/ta-p/198164'
@@ -4246,7 +4249,7 @@
     name: 'Dynatrace LLC'
     url: 'https://www.dynatrace.com/'
 
-- regex: 'DynatraceSynthetic/[\d.]+'
+- regex: 'DynatraceSynthetic'
   name: 'DynatraceSynthetic'
   category: 'Site Monitor'
   url: 'https://community.dynatrace.com/t5/Troubleshooting/Basic-Commands-for-Synthetic/ta-p/198164'
@@ -4262,7 +4265,7 @@
     name: 'Sitebulb Limited'
     url: 'https://sitebulb.com/'
 
-- regex: 'Monsidobot/[\d.]+'
+- regex: 'Monsidobot'
   name: 'Monsidobot'
   category: 'Crawler'
   url: 'https://monsido.com/bot-html'
@@ -4291,7 +4294,7 @@
   category: 'Service Agent'
   url: 'https://www.google.com/script/start/'
 
-- regex: 'SiteOne-Crawler/[\d.]+'
+- regex: 'SiteOne-Crawler'
   name: 'SiteOne Crawler'
   category: 'Crawler'
   url: 'https://crawler.siteone.io/bot/'
@@ -4315,7 +4318,7 @@
     name: 'Axeman Technology Solutions LLP'
     url: 'https://axemantech.com/'
 
-- regex: 'Paqlebot/[\d.]+'
+- regex: 'Paqlebot'
   name: 'Paqlebot'
   category: 'Crawler'
   url: 'https://www.paqle.dk/about/paqlebot'
@@ -4333,7 +4336,7 @@
   category: 'Crawler'
   url: 'https://github.com/matrix-org/synapse'
 
-- regex: 'OSZKbot/[\d.]+'
+- regex: 'OSZKbot'
   name: 'OSZKbot'
   category: 'Crawler'
   url: 'http://mekosztaly.oszk.hu/mia/'
@@ -4349,7 +4352,7 @@
     name: 'SEO Cube S.r.l.'
     url: 'https://www.seocube.it/'
 
-- regex: 'RavenCrawler/[\d.]+'
+- regex: 'RavenCrawler'
   name: 'RavenCrawler'
   category: 'Crawler'
   url: 'https://raventools.com/site-auditor/'
@@ -4365,7 +4368,7 @@
     name: 'Kadolijst'
     url: 'https://www.kadolijst.nl/'
 
-- regex: 'Dubbotbot/[\d.]+'
+- regex: 'Dubbotbot'
   name: 'Dubbotbot'
   category: 'Crawler'
   url: 'https://help.dubbot.com/en/articles/6746594-example-custom-user-agent'
@@ -4373,7 +4376,7 @@
     name: 'DubBot'
     url: 'https://dubbot.com/'
 
-- regex: 'Swiftbot/[\d.]+'
+- regex: 'Swiftbot'
   name: 'Swiftbot'
   category: 'Crawler'
   url: 'https://swiftype.com/swiftbot'
@@ -4397,15 +4400,15 @@
     name: 'Cisco Systems, Inc.'
     url: 'https://www.cisco.com/'
 
-- regex: 'OmtrBot/[\d.]+'
+- regex: 'OmtrBot'
   name: 'OmtrBot'
   category: 'Site Monitor'
 
-- regex: 'WebMon/[\d.]+'
+- regex: 'WebMon'
   name: 'WebMon'
   category: 'Site Monitor'
 
-- regex: 'AdsTxtCrawlerTP/[\d.]+'
+- regex: 'AdsTxtCrawlerTP'
   name: 'AdsTxtCrawlerTP'
   category: 'Crawler'
 
@@ -4425,7 +4428,7 @@
     name: 'Clickagy, LLC'
     url: 'https://www.clickagy.com/'
 
-- regex: 'kiwitcms-gitops/[\d.]+'
+- regex: 'kiwitcms-gitops'
   name: 'Kiwi TCMS GitOps'
   category: 'Service Agent'
   url: 'https://kiwitcms.org'
@@ -4483,7 +4486,7 @@
     name: 'Probely - Soluções de Cibersegurança, S.A.'
     url: 'https://probely.com/'
 
-- regex: 'Uptimia(?:/[\d.]+)?'
+- regex: 'Uptimia'
   name: 'Uptimia'
   category: 'Site Monitor'
   url: 'https://www.uptimia.com/'
@@ -4491,7 +4494,7 @@
     name: 'JJ Online GmbH'
     url: 'https://www.uptimia.com/'
 
-- regex: '2GDPR/[\d.]+'
+- regex: '2GDPR'
   name: '2GDPR'
   category: 'Service Agent'
   url: 'https://2gdpr.com/tos'
@@ -4515,7 +4518,7 @@
     name: 'CheckHost'
     url: 'https://check-host.net/'
 
-- regex: 'LAC_IAHarvester/[\d.]+'
+- regex: 'LAC_IAHarvester'
   name: 'LAC IA Harvester'
   category: 'Crawler'
   url: 'https://library-archives.canada.ca/eng/services/government-canada/web-social-media-preservation-program/Pages/web-archive.aspx'
@@ -4523,7 +4526,7 @@
     name: 'Library and Archives Canada'
     url: 'https://library-archives.canada.ca/'
 
-- regex: 'InsytfulBot/[\d.]+'
+- regex: 'InsytfulBot'
   name: 'InsytfulBot'
   category: 'Crawler'
   url: 'https://www.insytful.com/'
@@ -4539,7 +4542,7 @@
     name: 'Statista, Inc.'
     url: 'https://www.statista.com/'
 
-- regex: 'SubstackContentFetch/[\d.]+'
+- regex: 'SubstackContentFetch'
   name: 'Substack Content Fetch'
   category: 'Crawler'
   url: 'https://substack.com/'
@@ -4571,7 +4574,7 @@
     name: 'Tenable, Inc.'
     url: 'https://www.tenable.com/'
 
-- regex: 'Castopod/[\d.]+'
+- regex: 'Castopod'
   name: 'Castopod'
   category: 'Crawler'
   url: 'https://www.castopod.org/'
@@ -4584,7 +4587,7 @@
     name: 'Elasticsearch B.V.'
     url: 'https://www.elastic.co/'
 
-- regex: 'WDG_Validator/[\d.]+'
+- regex: 'WDG_Validator'
   name: 'WDG HTML Validator'
   category: 'Validator'
   url: 'http://www.htmlhelp.com/tools/validator/'
@@ -4594,7 +4597,7 @@
   category: 'Crawler'
   url: 'https://web.archive.org/web/20180910002802/http://www.aegis.network/'
 
-- regex: 'CrawlyProjectCrawler/[\d.]+'
+- regex: 'CrawlyProjectCrawler'
   name: 'Crawly Project'
   category: 'Crawler'
   url: 'https://web.archive.org/web/20240326141952/https://crawlyproject.digitaldragon.dev/'
@@ -4609,7 +4612,7 @@
   category: 'Security Checker'
   url: 'https://github.com/openeasm/punkmap'
 
-- regex: 'GenomeCrawlerd/[\d.]+'
+- regex: 'GenomeCrawlerd'
   name: 'Deepfield Genome'
   category: 'Crawler'
   url: 'https://www.nokia.com/networks/ip-networks/deepfield/genome/'
@@ -4617,12 +4620,12 @@
     name: 'Nokia Corporation'
     url: 'https://www.nokia.com/'
 
-- regex: 'Gaisbot/[\d.]+'
+- regex: 'Gaisbot'
   name: 'Gaisbot'
   category: 'Crawler'
   url: 'https://web.archive.org/web/20090604121511/https://gais.cs.ccu.edu.tw/robot.php'
 
-- regex: 'FAST-WebCrawler/[\d.]+'
+- regex: 'FAST-WebCrawler'
   name: 'AlltheWeb'
   category: 'Crawler'
   url: 'https://web.archive.org/web/20041020050801/http://www.alltheweb.com/help/webmaster/crawler'
@@ -4632,7 +4635,7 @@
   category: 'Security Checker'
   url: 'https://ducks.party/'
 
-- regex: 'DepSpid/[\d.]+'
+- regex: 'DepSpid'
   name: 'DepSpid'
   category: 'Crawler'
   url: 'https://web.archive.org/web/20080321224033/http://about.depspid.net/'
@@ -4743,7 +4746,7 @@
     name: 'Marginalia'
     url: 'https://www.marginalia.nu/'
 
-- regex: 'vu-server-health-scanner/[\d.]+'
+- regex: 'vu-server-health-scanner'
   name: 'VU Server Health Scanner'
   category: 'Security Checker'
   url: 'https://130.37.198.75/index.html'
@@ -4944,14 +4947,6 @@
     name: 'University of Passau'
     url: 'https://www.uni-passau.de/en/'
 
-- regex: 'Chatwork LinkPreview'
-  name: 'Chatwork LinkPreview'
-  category: 'Service Agent'
-  url: 'https://go.chatwork.com/en/'
-  producer:
-    name: 'kubell Co., Ltd.'
-    url: 'https://www.kubell.com/en/'
-
 - regex: 'WPMU DEV'
   name: 'WPMU DEV'
   category: 'Crawler'