device_detector 1.1.0 → 1.1.2

data/lib/device_detector/os.rb

@@ -94,6 +94,7 @@ class DeviceDetector
       'INF' => 'Inferno',
       'JME' => 'Java ME',
       'KOS' => 'KaiOS',
+      'KAL' => 'Kali',
       'KAN' => 'Kanotix',
       'KNO' => 'Knoppix',
       'KTV' => 'KreaTV',
@@ -104,6 +105,7 @@ class DeviceDetector
       'LEN' => 'Lineage OS',
       'LBT' => 'Lubuntu',
       'LOS' => 'Lumin OS',
+      'LUN' => 'LuneOS',
       'VLN' => 'VectorLinux',
       'MAC' => 'Mac',
       'MAE' => 'Maemo',
@@ -126,14 +128,17 @@ class DeviceDetector
       'OBS' => 'OpenBSD',
       'OWR' => 'OpenWrt',
       'OTV' => 'Opera TV',
+      'ORA' => 'Oracle Linux',
       'ORD' => 'Ordissimo',
       'PAR' => 'Pardus',
       'PCL' => 'PCLinuxOS',
+      'PIC' => 'PICO OS',
       'PLA' => 'Plasma Mobile',
       'PSP' => 'PlayStation Portable',
       'PS3' => 'PlayStation',
       'PUR' => 'PureOS',
       'RHT' => 'Red Hat',
+      'RED' => 'RedOS',
       'REV' => 'Revenge OS',
       'ROS' => 'RISC OS',
       'ROK' => 'Roku OS',
@@ -159,9 +164,12 @@ class DeviceDetector
       'TEN' => 'TencentOS',
       'TDX' => 'ThreadX',
       'TIZ' => 'Tizen',
+      'TIV' => 'TiVo OS',
       'TOS' => 'TmaxOS',
       'UBT' => 'Ubuntu',
+      'VID' => 'VIDAA',
       'WAS' => 'watchOS',
+      'WER' => 'Wear OS',
       'WTV' => 'WebTV',
       'WHS' => 'Whale OS',
       'WIN' => 'Windows',
@@ -186,7 +194,7 @@ class DeviceDetector
 
     OS_FAMILIES = {
       'Android' => %w[ AND CYN FIR REM RZD MLD MCD YNS GRI HAR
-                       ADR CLR BOS REV LEN SIR RRS],
+                       ADR CLR BOS REV LEN SIR RRS WER PIC],
       'AmigaOS' => %w[AMG MOR],
       'BlackBerry' => %w[BLB QNX],
       'Brew' => ['BMP'],
@@ -204,7 +212,7 @@ class DeviceDetector
         ORD TOS RSO DEE FRE MAG FEN CAI PCL HAS
         LOS DVK ROK OWR OTV KTV PUR PLA FUC PAR
         FOR MON KAN ZEN LND LNS CHN AMZ TEN CST
-        NOV ROU ZOR
+        NOV ROU ZOR VID
       ],
       'Mac' => ['MAC'],
       'Mobile Gaming Console' => %w[PSP NDS XBX],

data/lib/device_detector/parser.rb

@@ -58,7 +58,29 @@ class DeviceDetector
     end
 
     def load_regexes(file_paths)
-      file_paths.map { |path, full_path| [path, symbolize_keys!(YAML.load_file(full_path))] }
+      file_paths.map do |path, full_path|
+        object = YAML.load_file(full_path)
+        object = rewrite_device_object!(object) if is_device_yml_file?(full_path)
+        object = rewrite_vendor_object!(object) if is_vendor_yml_file?(full_path)
+
+        [path, symbolize_keys!(object)]
+      end
+    end
+
+    def is_device_yml_file?(file_path)
+      file_path.include?('/regexes/device/')
+    end
+
+    def is_vendor_yml_file?(file_path)
+      file_path.include?('/regexes/vendorfragments')
+    end
+
+    def rewrite_vendor_object!(object)
+      object.map { |key, values| values.map { |v| { 'regex_name' => key, 'regex' => v } } }.flatten
+    end
+
+    def rewrite_device_object!(object)
+      object.map { |key, value| [key, { 'regex_name' => key }.merge!(value)] }.to_h
     end
 
     def symbolize_keys!(object)
@@ -88,8 +110,8 @@ class DeviceDetector
       Regexp.new('(?:^|[^A-Z0-9\-_]|[^A-Z0-9\-]_|sprd-|MZ-)(?:' + src + ')', Regexp::IGNORECASE)
     end
 
-    def from_cache(key)
-      DeviceDetector.cache.get_or_set(key) { yield }
+    def from_cache(key, &block)
+      DeviceDetector.cache.get_or_set(key, &block)
     end
   end
 end

data/lib/device_detector/vendor_fragment.rb

@@ -0,0 +1,25 @@
+# frozen_string_literal: true
+
+require 'set'
+
+class DeviceDetector
+  class VendorFragment < Parser
+    def name
+      vendor_fragment_info
+    end
+
+    private
+
+    def vendor_fragment_info
+      from_cache(['vendor_fragment', self.class.name, user_agent]) do
+        return if regex_meta.nil? || regex_meta.empty?
+
+        regex_meta[:regex_name]
+      end
+    end
+
+    def filenames
+      ['vendorfragments.yml']
+    end
+  end
+end

data/lib/device_detector/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 class DeviceDetector
-  VERSION = '1.1.0'
+  VERSION = '1.1.2'
 end

data/lib/device_detector.rb

@@ -15,13 +15,34 @@ require 'device_detector/device'
 require 'device_detector/os'
 require 'device_detector/browser'
 require 'device_detector/client_hint'
+require 'device_detector/vendor_fragment'
 
 class DeviceDetector
   attr_reader :client_hint, :user_agent
 
   def initialize(user_agent, headers = nil)
     @client_hint = ClientHint.new(headers)
-    @user_agent = user_agent
+    utf8_user_agent = encode_user_agent_if_needed(user_agent)
+    @user_agent = set_user_agent(utf8_user_agent)
+  end
+
+  # https://github.com/matomo-org/device-detector/blob/c235832dba13961ab0f71b681616baf1aa48de23/Parser/Device/AbstractDeviceParser.php#L1873
+  def set_user_agent(user_agent)
+    return user_agent if client_hint.model.nil?
+
+    regex = build_regex('Android 10[.\d]*; K(?: Build/|[;)])')
+    return user_agent unless user_agent =~ regex
+
+    version = client_hint.os_version || '10'
+
+    user_agent.gsub(regex, "Android #{version}, #{client_hint.model}")
+  end
+
+  def encode_user_agent_if_needed(user_agent)
+    return if user_agent.nil?
+    return user_agent if user_agent.encoding.name == 'UTF-8'
+
+    user_agent.encode('utf-8', 'binary', undef: :replace)
   end
 
   def name
@@ -53,13 +74,18 @@ class DeviceDetector
   end
 
   def device_name
+    return if fake_ua?
+
     device.name || client_hint.model || fix_for_x_music
   end
 
   def device_brand
+    return if fake_ua?
+
     # Assume all devices running iOS / Mac OS are from Apple
     brand = device.brand
-    brand = 'Apple' if brand.nil? && ['Apple TV', 'iOS', 'Mac'].include?(os_name)
+    brand = 'Apple' if brand.nil? && %w[iPadOS tvOS watchOS iOS Mac].include?(os_name)
+
     brand
   end
 
@@ -136,7 +162,8 @@ class DeviceDetector
     t = 'tv' if t.nil? && tizen_samsung_tv?
 
     # Devices running Kylo or Espital TV Browsers are assumed to be a TV
-    t = 'tv' if t.nil? && ['Kylo', 'Espial TV Browser'].include?(name)
+    t = 'tv' if ['Kylo', 'Espial TV Browser', 'LUJO TV Browser', 'LogicUI TV Browser',
+                 'Open TV Browser'].include?(name)
 
     # All devices containing TV fragment are assumed to be a tv
     t = 'tv' if t.nil? && user_agent =~ build_regex('\(TV;')
@@ -206,6 +233,11 @@ class DeviceDetector
     @os ||= OS.new(user_agent)
   end
 
+  # https://github.com/matomo-org/device-detector/blob/827a3fab7e38c3274c18d2f5f5bc2a78b7ef4a3a/DeviceDetector.php#L921C5-L921C5
+  def fake_ua?
+    os_name == 'Android' && device.brand == 'Apple'
+  end
+
   # https://github.com/matomo-org/device-detector/blob/be1c9ef486c247dc4886668da5ed0b1c49d90ba8/Parser/Client/Browser.php#L772
   # Fix mobile browser names e.g. Chrome => Chrome Mobile
   def mobile_fix?
@@ -218,7 +250,7 @@ class DeviceDetector
 
   # Related to issue mentionned in device.rb#1562
   def fix_for_x_music
-    user_agent.include?('X-music Ⅲ') ? 'X-Music III' : nil
+    user_agent&.include?('X-music Ⅲ') ? 'X-Music III' : nil
   end
 
   def skip_os_version?
@@ -242,7 +274,7 @@ class DeviceDetector
   end
 
   def opera_tv_store?
-    user_agent =~ build_regex('Opera TV Store')
+    user_agent =~ build_regex('Opera TV Store|OMI/')
   end
 
   def opera_tablet?

data/regexes/bots.yml

@@ -13,6 +13,14 @@
     name: 'Plesk International GmbH'
     url: 'https://www.plesk.com'
 
+- regex: 'Cloudflare-Healthchecks'
+  name: 'Cloudflare Health Checks'
+  category: 'Service Agent'
+  url: 'https://developers.cloudflare.com/health-checks/'
+  producer:
+    name: 'CloudFlare'
+    url: 'https://www.cloudflare.com/'
+
 - regex: '360Spider'
   name: '360Spider'
   category: 'Search bot'
@@ -323,21 +331,53 @@
     name: 'CloudFlare'
     url: 'http://www.cloudflare.com'
 
-- regex: 'CloudflareDiagnostics'
+- regex: 'Cloudflare-?Diagnostics'
   name: 'Cloudflare Diagnostics'
   category: 'Site Monitor'
   url: 'https://www.cloudflare.com/'
   producer:
     name: 'Cloudflare'
-    url: 'https://www.cloudflare.com'
+    url: 'https://www.cloudflare.com/'
 
 - regex: 'CloudFlare-AlwaysOnline'
   name: 'CloudFlare Always Online'
   category: 'Site Monitor'
-  url: 'http://www.cloudflare.com/always-online'
+  url: 'https://www.cloudflare.com/always-online'
   producer:
     name: 'CloudFlare'
-    url: 'http://www.cloudflare.com'
+    url: 'https://www.cloudflare.com/'
+
+- regex: 'Cloudflare-SSLDetector'
+  name: 'Cloudflare SSL Detector'
+  category: 'Site Monitor'
+  url: 'https://developers.cloudflare.com/fundamentals/reference/cloudflare-site-crawling/'
+  producer:
+    name: 'CloudFlare'
+    url: 'https://www.cloudflare.com/'
+
+- regex: 'Cloudflare Custom Hostname Verification'
+  name: 'Cloudflare Custom Hostname Verification'
+  category: 'Service Agent'
+  url: 'https://developers.cloudflare.com/fundamentals/reference/cloudflare-site-crawling/'
+  producer:
+    name: 'CloudFlare'
+    url: 'https://www.cloudflare.com/'
+
+- regex: 'Cloudflare-Traffic-Manager'
+  name: 'Cloudflare Traffic Manager'
+  category: 'Site Monitor'
+  url: 'https://developers.cloudflare.com/fundamentals/reference/cloudflare-site-crawling/'
+  producer:
+    name: 'CloudFlare'
+    url: 'https://www.cloudflare.com/'
+
+- regex: 'https://developers.cloudflare.com/security-center/'
+  name: 'Cloudflare Security Insights'
+  category: 'Site Monitor'
+  url: 'https://developers.cloudflare.com/fundamentals/reference/cloudflare-site-crawling/'
+  producer:
+    name: 'CloudFlare'
+    url: 'https://www.cloudflare.com/'
 
 - regex: 'coccoc.com'
   name: 'Cốc Cốc Bot'
@@ -704,7 +744,15 @@
     name: 'Visual Meta'
     url: 'https://www.shopalike.cz/'
 
-- regex: 'AdsBot-Google|Adwords-(DisplayAds|Express|Instant)|Google Web Preview|Google[ -]Publisher[ -]Plugin|Google-(Ads-Conversions|Ads-Qualify|Adwords|AMPHTML|Assess|HotelAdsVerifier|Read-Aloud|Shopping-Quality|Site-Verification|speakr|Stale-Content-Probe|Test|Youtube-Links)|(APIs|DuplexWeb|Feedfetcher|Mediapartners)-Google|Googlebot|Google(?:AdSenseInfeed|AssociationService|Producer)|Google.*/\+/web/snippet'
+- regex: 'AdsBot-Google|Adwords-(DisplayAds|Express|Instant)|Google Web Preview|Google[ -]Publisher[ -]Plugin|Google-(Ads-Conversions|Ads-Qualify|Adwords|AMPHTML|Assess|HotelAdsVerifier|InspectionTool|Read-Aloud|Shopping-Quality|Site-Verification|speakr|Stale-Content-Probe|Test|Youtube-Links)|(APIs|DuplexWeb|Feedfetcher|Mediapartners)-Google|Googlebot|Google(?:AdSenseInfeed|AssociationService|Other|Prober|Producer)|Google.*/\+/web/snippet'
+  name: 'Googlebot'
+  category: 'Search bot'
+  url: 'http://www.google.com/bot.html'
+  producer:
+    name: 'Google Inc.'
+    url: 'http://www.google.com'
+
+- regex: '^Google$'
   name: 'Googlebot'
   category: 'Search bot'
   url: 'http://www.google.com/bot.html'
@@ -727,6 +775,11 @@
     name: 'HubSpot Inc.'
     url: 'https://www.hubspot.com'
 
+- regex: 'vuhuvBot'
+  name: 'Vuhuv Bot'
+  category: 'Crawler'
+  url: 'http://vuhuv.com/bot.html'
+
 - regex: 'HTTPMon'
   name: 'HTTPMon'
   category: 'Site Monitor'
@@ -1020,6 +1073,14 @@
 - regex: 'Octopus [0-9]'
   name: 'Octopus'
 
+- regex: 'OnlineOrNot.com_bot'
+  name: 'OnlineOrNot Bot'
+  category: 'Site Monitor'
+  url: 'https://onlineornot.com/website-monitoring'
+  producer:
+    name: 'OnlineOrNot'
+    url: 'https://onlineornot.com'
+
 - regex: 'omgili'
   name: 'Omgili bot'
   category: 'Search bot'
@@ -1741,7 +1802,15 @@
 - regex: 'Y!J-BRW'
   name: 'Yahoo! Japan BRW'
   category: 'Crawler'
-  url: 'https://www.yahoo-help.jp/app/answers/detail/p/595/a_id/42716/~/ウェブページにアクセスするシステムのユーザーエージェントについて'
+  url: 'https://support.yahoo-net.jp/PccSearch/s/article/H000007955'
+  producer:
+    name: 'Yahoo! Japan Corp.'
+    url: 'https://www.yahoo.co.jp/'
+
+- regex: 'Y!J-WSC'
+  name: 'Yahoo! Japan WSC'
+  category: 'Crawler'
+  url: 'https://support.yahoo-net.jp/PccSearch/s/article/H000007955'
   producer:
     name: 'Yahoo! Japan Corp.'
     url: 'https://www.yahoo.co.jp/'
@@ -1966,7 +2035,7 @@
 - regex: 'RSSRadio \(Push Notification Scanner;support@dorada\.co\.uk\)'
   name: 'RSSRadio Bot'
 
-- regex: '(A6-Indexer|nuhk|TsolCrawler|Yammybot|Openbot|Gulper Web Bot|grub-client|Download Demon|SearchExpress|Microsoft URL Control|borg|altavista|dataminr.com|tweetedtimes.com|TrendsmapResolver|teoma|blitzbot|oegp|furlbot|http%20client|polybot|htdig|mogimogi|larbin|scrubby|searchsight|seekbot|semanticdiscovery|snappy|vortex(?!(?: Build|Plus))|zeal(?!ot)|fast-webcrawler|converacrawler|dataparksearch|findlinks|BrowserMob|HttpMonitor|ThumbShotsBot|URL2PNG|ZooShot|GomezA|Google SketchUp|Read%20Later|RackspaceBot|robots|SeopultContentAnalyzer|7Siters|centuryb.o.t9|InterNaetBoten|EasyBib AutoCite|Bidtellect|tomnomnom/meg|My User Agent|cortex|CF-UC User Agent|Re-re Studio|adreview|AHC/|NameOfAgent|Request-Promise|ALittle Client|Hello,? world|wp_is_mobile|0xAbyssalDoesntExist|Anarchy99|daumoa,damoa,daum,daumos,duamoa,duam,duamos|^revolt|nvd0rz|xfa1|Hakai|gbrmss|fuck-your-hp|IDBTE4M CODE87|Antoine|Insomania|Hells-Net|b3astmode|Linux Gnu \(cow\)|custom_user_agent|Test Certificate Info|iplabel)'
+- regex: '(A6-Indexer|nuhk|TsolCrawler|Yammybot|Openbot|Gulper Web Bot|grub-client|Download Demon|SearchExpress|Microsoft URL Control|borg|altavista|dataminr.com|tweetedtimes.com|TrendsmapResolver|teoma|blitzbot|oegp|furlbot|http%20client|polybot|htdig|mogimogi|larbin|scrubby|searchsight|seekbot|semanticdiscovery|snappy|vortex(?!(?: Build|Plus))|zeal(?!ot)|fast-webcrawler|converacrawler|dataparksearch|findlinks|BrowserMob|HttpMonitor|ThumbShotsBot|URL2PNG|ZooShot|GomezA|Google SketchUp|Read%20Later|RackspaceBot|robots|SeopultContentAnalyzer|7Siters|centuryb.o.t9|InterNaetBoten|EasyBib AutoCite|Bidtellect|tomnomnom/meg|My User Agent|cortex|CF-UC User Agent|Re-re Studio|adreview|AHC/|NameOfAgent|Request-Promise|ALittle Client|Hello,? world|wp_is_mobile|0xAbyssalDoesntExist|Anarchy99|daumoa,damoa,daum,daumos,duamoa,duam,duamos|^revolt|nvd0rz|xfa1|Hakai|gbrmss|fuck-your-hp|IDBTE4M CODE87|Antoine|Insomania|Hells-Net|b3astmode|Linux Gnu \(cow\)|custom_user_agent|Test Certificate Info|iplabel|Magellan|CustomUserAgent)'
   name: 'Generic Bot'
 
 - regex: '^sentry'
@@ -2025,7 +2094,15 @@
     name: 'WooRank sprl'
     url: 'https://www.woorank.com/'
 
-- regex: '(Match|LinkCheck) by Siteimprove.com'
+- regex: 'by Siteimprove\.com'
+  name: 'Siteimprove'
+  category: 'Search bot'
+  url: 'https://siteimprove.com/'
+  producer:
+    name: 'Siteimprove GmbH'
+    url: 'https://siteimprove.com/'
+
+- regex: 'Image size by Siteimprove\.com'
   name: 'Siteimprove'
   category: 'Search bot'
   url: 'https://siteimprove.com/'
@@ -2153,6 +2230,14 @@
     name: 'Startpagina B.V.'
     url: 'https://www.startpagina.nl/'
 
+- regex: 'MoodleBot-Linkchecker'
+  name: 'MoodleBot Linkchecker'
+  category: 'Search bot'
+  url: 'hhttps://docs.moodle.org/en/Usage'
+  producer:
+    name: 'Moodle Pty Ltd'
+    url: 'https://moodle.org/'
+
 - regex: 'GTmetrix'
   name: 'GTmetrix'
   category: 'Crawler'
@@ -2412,6 +2497,13 @@
   producer:
     name: 'Hatena Co., Ltd.'
     url: 'https://www.hatena.ne.jp'
+- regex: 'Hatena-?Bookmark'
+  name: 'Hatena Bookmark'
+  category: 'Crawler'
+  url: 'https://www.hatena.ne.jp/faq/'
+  producer:
+    name: 'Hatena Co., Ltd.'
+    url: 'https://www.hatena.ne.jp'
 
 - regex: 'RyowlEngine/(\d+)'
   name: 'Ryowl'
@@ -2556,6 +2648,14 @@
   category: 'Security Checker'
   url: 'https://github.com/LeakIX/l9explore'
 
+- regex: 'l9scan/|^Lkx-(.*)/([\d+.]+)'
+  name: 'LeakIX'
+  category: 'Security Checker'
+  url: 'https://leakix.net/'
+  producer:
+    name: 'BaDaaS SRL'
+    url: 'https://leakix.net/'
+
 - regex: 'MegaIndex.ru/([\d+\.])'
   name: 'MegaIndex'
   category: 'Crawler'
@@ -3047,14 +3147,6 @@
     name: 'New Work SE'
     url: 'https://www.xing.com/'
 
-- regex: '^Lkx-(.*)/([\d+.]+)'
-  name: 'LeakIX'
-  category: 'Security Checker'
-  url: 'https://leakix.net/'
-  producer:
-    name: 'BaDaaS SRL'
-    url: 'https://leakix.net/'
-
 - regex: 'RepoLookoutBot/([\d+.]+)'
   name: 'Repo Lookout'
   category: 'Security Checker'
@@ -3217,6 +3309,205 @@
   category: 'Crawler'
   url: 'https://reqbin.com/curl'
 
+- regex: 'XoviBot/([\d+.]+)'
+  name: 'XoviBot'
+  category: 'Crawler'
+  url: 'https://www.xovibot.net'
+  producer:
+    name: 'Xovi GmbH'
+    url: 'http://www.xovi.de'
+
+- regex: 'Overcast/([\d+.]+) Podcast Sync'
+  name: 'Overcast Podcast Sync'
+  category: 'Service Agent'
+  url: 'https://overcast.fm/podcasterinfo'
+
+- regex: '^Verity/([\d+.]+)'
+  name: 'GumGum Verity'
+  category: 'Service Agent'
+  url: 'https://gumgum.com/verity'
+
+- regex: 'hackermention'
+  name: 'hackermention'
+  category: 'Feed Reader'
+  url: 'https://github.com/snarfed/hackermention'
+
+- regex: 'BitSightBot/([\d+.]+)'
+  name: 'BitSight'
+  category: 'Security Checker'
+  url: 'https://www.bitsight.com/'
+  producer:
+    name: 'BitSight Technologies, Inc.'
+    url: 'https://www.bitsight.com/'
+
+- regex: 'Ezgif/([\d+.]+)'
+  name: 'Ezgif'
+  category: 'Service Agent'
+  url: 'https://ezgif.com/about'
+
+- regex: 'intelx.io_bot'
+  name: 'Intelligence X'
+  category: 'Crawler'
+  url: 'https://intelx.io/'
+  producer:
+    name: 'Kleissner Investments s.r.o.'
+    url: 'https://intelx.io/'
+
+- regex: 'FemtosearchBot/([\d+.]+)'
+  name: 'Femtosearch'
+  category: 'Crawler'
+  url: 'http://femtosearch.com/'
+  producer:
+    name: 'Grier Forensics, LLC'
+    url: 'https://www.grierforensics.com/'
+
+- regex: 'AdsTxtCrawler/([\d+.]+)'
+  name: 'AdsTxtCrawler'
+  category: 'Crawler'
+  url: 'https://github.com/InteractiveAdvertisingBureau/adstxtcrawler'
+  producer:
+    name: 'IAB Technology Laboratory, Inc.'
+    url: 'https://iabtechlab.com/'
+
+- regex: 'Morningscore'
+  name: 'Morningscore Bot'
+  category: 'Crawler'
+  url: 'https://morningscore.io/'
+  producer:
+    name: 'Morningscore'
+    url: 'https://morningscore.io/'
+
+- regex: 'Uptime-Kuma/([\d+.]+)'
+  name: 'Uptime-Kuma'
+  category: 'Site Monitor'
+  url: 'https://github.com/louislam/uptime-kuma'
+
+- regex: 'ChatGPT-User'
+  name: 'ChatGPT'
+  category: 'Crawler'
+  url: 'https://platform.openai.com/docs/plugins/bot'
+  producer:
+    name: 'OpenAI OpCo, LLC'
+    url: 'https://openai.com/'
+
+- regex: 'BrightEdge Crawler/([\d+.]+)'
+  name: 'BrightEdge'
+  category: 'Crawler'
+  url: 'https://www.brightedge.com/'
+  producer:
+    name: 'BrightEdge Technologies, Inc'
+    url: 'https://www.brightedge.com/'
+
+- regex: 'sfFeedReader/([\d+.]+)'
+  name: 'sfFeedReader'
+  url: 'https://github.com/diem-project/sfFeed2Plugin'
+  category: 'Feed Fetcher'
+
+- regex: 'cyberscan.io'
+  name: 'Cyberscan'
+  category: 'Security Checker'
+  url: 'https://www.cyberscan.io/'
+  producer:
+    name: 'DGC Verwaltungs GmbH'
+    url: 'https://dgc.org/'
+
+- regex: 'deepcrawl\.com'
+  name: 'Lumar'
+  category: 'Crawler'
+  url: 'https://deepcrawl.com/bot'
+  producer:
+    name: 'Lumar'
+    url: 'https://www.lumar.io/'
+
+- regex: 'RepoLookoutBot'
+  name: 'Repo Lookout'
+  category: 'Crawler'
+  url: 'https://www.repo-lookout.org/'
+  producer:
+    name: 'Crissy Field GmbH'
+    url: 'https://www.crissyfield.de/'
+
+- regex: 'researchscan.comsys.rwth-aachen.de'
+  name: 'Research Scan'
+  category: 'Crawler'
+  url: 'http://researchscan.comsys.rwth-aachen.de/'
+  producer:
+    name: 'RWTH Aachen University'
+    url: 'https://www.comsys.rwth-aachen.de/'
+
+- regex: 'newspaper/([\d+.]+)'
+  name: 'Scraping Robot'
+  category: 'Crawler'
+  url: 'https://scrapingrobot.com/'
+  producer:
+    name: 'Sprious LLC'
+    url: 'https://sprious.com/'
+
+- regex: 'GPTBot/([\d+.]+)'
+  name: 'GPTBot'
+  category: 'Crawler'
+  url: 'https://platform.openai.com/docs/gptbot'
+  producer:
+    name: 'OpenAI OpCo, LLC'
+    url: 'https://openai.com/'
+
+- regex: 'Ant.com beta/([\d+.]+)'
+  name: 'Ant'
+  category: 'Crawler'
+  url: 'https://www.ant.com/'
+  producer:
+    name: 'Ant.com Ltd.'
+    url: 'https://www.ant.com/'
+
+- regex: 'WebwikiBot/([\d+.]+)'
+  name: 'Webwiki'
+  category: 'Crawler'
+  url: 'https://www.webwiki.com/'
+  producer:
+    name: 'webwiki GmbH'
+    url: 'https://www.webwiki.com/'
+
+- regex: 'phpMyAdmin'
+  name: 'phpMyAdmin'
+  category: 'Service Agent'
+  url: 'https://www.phpmyadmin.net/'
+
+- regex: 'Matomo/([\d+.]+)'
+  name: 'Matomo'
+  category: 'Service Agent'
+  url: 'https://github.com/matomo-org/matomo'
+  producer:
+    name: 'InnoCraft Ltd'
+    url: 'https://matomo.org/'
+
+- regex: 'Prometheus/([\d+.]+)'
+  name: 'Prometheus'
+  category: 'Service Agent'
+  url: 'https://github.com/prometheus/prometheus'
+  producer:
+    name: 'The Linux Foundation'
+    url: 'https://www.cncf.io/'
+
+- regex: 'ArchiveTeam ArchiveBot'
+  name: 'ArchiveBot'
+  category: 'Crawler'
+  url: 'https://wiki.archiveteam.org/index.php?title=ArchiveBot'
+  producer:
+    name: 'ArchiveTeam'
+    url: 'https://wiki.archiveteam.org/'
+
+- regex: 'MADBbot/([\d+.]+)'
+  name: 'MADBbot'
+  category: 'Crawler'
+  url: 'https://madb.zapto.org/bot.html'
+
+- regex: 'MeltwaterNews'
+  name: 'MeltwaterNews'
+  category: 'Crawler'
+  producer:
+    name: 'Meltwater Deutschland GmbH'
+    url: 'https://www.meltwater.com/'
+
 # Generic detections
-- regex: '[a-z0-9\-_]*((?<!cu|power[ _]|m[ _])bot(?![ _]TAB|[ _]?5[0-9]|[ _]Senior|[ _]Junior)|crawler|crawl|checker|archiver|transcoder|spider)([^a-z]|$)'
+- regex: '[a-z0-9\-_]*((?<!cu|power[ _]|m[ _])bot(?![ _]TAB|[ _]?5[0-9]|[ _]Senior|[ _]Junior)|crawler|crawl|checker|archiver|transcoder|spider|^firefox$|^chrome$)([^a-z]|$)'
   name: 'Generic Bot'