Adds detection for various bots

Tests/Parser/Client/fixtures/library.yml

@@ -731,3 +731,15 @@
     type: library
     name: Azure Blob Storage
     version: 12.23.0
+-
+  user_agent: trafilatura/1.5.0 (+https://github.com/adbar/trafilatura)
+  client:
+    type: library
+    name: trafilatura
+    version: 1.5.0
+-
+  user_agent: 'sqlmap/1.8.10.1#dev (https://sqlmap.org)'
+  client:
+    type: library
+    name: sqlmap
+    version: 1.8.10.1

Tests/fixtures/bots.yml

@@ -4000,15 +4000,6 @@
     producer:
       name: 'IBM Germany Research & Development GmbH'
       url: https://exchange.xforce.ibmcloud.com/
--
-  user_agent: 'sqlmap/1.1.8.2#dev (http://sqlmap.org)'
-  bot:
-    name: sqlmap
-    category: Security Checker
-    url: http://sqlmap.org/
-    producer:
-      name: sqlmap
-      url: http://sqlmap.org/
 -
   user_agent: Mozilla/5.0 (compatible; theoldreader.com; 1 subscribers; feed-id=aaa)
   bot:
@@ -8433,3 +8424,27 @@
     name: SuggestBot
     category: Crawler
     url: https://github.com/nettrom/suggestbot
+-
+  user_agent: Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/99.0.4844.51 Safari/537.36 (https://securitee.org/cms-experiment-fall2024/)
+  bot:
+    name: CMS Experiment
+    category: Security Checker
+    url: https://securitee.org/cms-experiment-fall2024/
+-
+  user_agent: SiteCheckerBotCrawler/1.0 (+http://sitechecker.pro)
+  bot:
+    name: SiteCheckerBotCrawler
+    category: Crawler
+    url: https://sitechecker.pro/
+    producer:
+      name: Cyber Circus Limited
+      url: https://sitechecker.pro/
+-
+  user_agent: SBIder/0.8-dev (SBIder; http://www.sitesell.com/sbider.html; http://support.sitesell.com/contact-support.html)
+  bot:
+    name: SBIder
+    category: Crawler
+    url: https://www.sitesell.com/sbider.html
+    producer:
+      name: SiteSell Inc.
+      url: https://www.sitesell.com/

regexes/bots.yml

@@ -1624,14 +1624,6 @@
     name: 'Sprinklr, Inc.'
     url: 'https://www.sprinklr.com/'
 
-- regex: 'sqlmap/'
-  name: 'sqlmap'
-  category: 'Security Checker'
-  url: 'http://sqlmap.org/'
-  producer:
-    name: 'sqlmap'
-    url: 'http://sqlmap.org/'
-
 - regex: 'SSL Labs'
   name: 'SSL Labs'
   category: 'Validator'
@@ -4912,6 +4904,27 @@
   category: 'Crawler'
   url: 'https://github.com/nettrom/suggestbot'
 
+- regex: 'cms-experiment'
+  name: 'CMS Experiment'
+  category: 'Security Checker'
+  url: 'https://securitee.org/cms-experiment-fall2024/'
+
+- regex: 'SiteCheckerBotCrawler'
+  name: 'SiteCheckerBotCrawler'
+  category: 'Crawler'
+  url: 'https://sitechecker.pro/'
+  producer:
+    name: 'Cyber Circus Limited'
+    url: 'https://sitechecker.pro/'
+
+- regex: 'SBIder'
+  name: 'SBIder'
+  category: 'Crawler'
+  url: 'https://www.sitesell.com/sbider.html'
+  producer:
+    name: 'SiteSell Inc.'
+    url: 'https://www.sitesell.com/'
+
 # Generic bots
 - regex: 'nuhk|grub-client|Download Demon|SearchExpress|Microsoft URL Control|borg|altavista|dataminr\.com|teoma|oegp|http%20client|htdig|mogimogi|larbin|scrubby|searchsight|semanticdiscovery|snappy|vortex(?!(?: Build|Plus| CM62| HD65))|zeal(?!ot)|dataparksearch|findlinks|BrowserMob|URL2PNG|ZooShot|GomezA|Google SketchUp|Read%20Later|7Siters|centuryb\.o\.t9|InterNaetBoten|EasyBib AutoCite|Bidtellect|tomnomnom/meg|cortex|Re-re Studio|adreview|AHC/|NameOfAgent|Request-Promise|ALittle Client|Hello,? world|wp_is_mobile|0xAbyssalDoesntExist|Anarchy99|^revolt|nvd0rz|xfa1|Hakai|gbrmss|fuck-your-hp|IDBTE4M CODE87|Antoine|Insomania|Hells-Net|b3astmode|Linux Gnu \(cow\)|Test Certificate Info|iplabel|Magellan|TheSafex?Internetx?Search|Searcherx?web|kirkland-signature|LinkChain|survey-security-dot-txt|infrawatch|Time/|r00ts3c-owned-you|nvdorz|Root Slut|NiggaBalls|BotPoke|GlobalWebSearch|xx032_bo9vs83_2a|sslshed|geckotrail|Wordup|Keydrop|^xenu|^(?:chrome|firefox|Abcd|Dark|KvshClient|Node.js|Report Runner|url|Zeus|ZmEu)$'
   name: 'Generic Bot'

regexes/client/libraries.yml

@@ -649,3 +649,13 @@
   name: 'Azure Blob Storage'
   version: '$1'
   url: 'https://learn.microsoft.com/en-us/azure/storage/blobs/storage-quickstart-blobs-python'
+
+- regex: 'trafilatura(?:/(\d+[.\d]+))?'
+  name: 'trafilatura'
+  version: '$1'
+  url: 'https://github.com/adbar/trafilatura'
+
+- regex: 'sqlmap(?:/(\d+[.\d]+))?'
+  name: 'sqlmap'
+  version: '$1'
+  url: 'https://sqlmap.org/'