Improves detection for various bots (matomo-org#7857)

* Improves detection for generic bots * Adds detection for Inspici * Adds detection for Meta-ExternalAgent * Adds detection for Meta-ExternalFetcher * Fix url for Facebook crawlers
sanchezzzhak · Oct 7, 2024 · f21f39c · f21f39c
1 parent c6cb44b
commit f21f39c
Show file tree

Hide file tree

Showing 2 changed files with 80 additions and 7 deletions.
diff --git a/Tests/fixtures/bots.yml b/Tests/fixtures/bots.yml
@@ -950,7 +950,7 @@
   bot:
     name: Facebook Crawler
     category: Social Media Agent
-    url: https://developers.facebook.com/docs/sharing/webmasters/crawler/
+    url: https://developers.facebook.com/docs/sharing/webmasters/web-crawlers
     producer:
       name: Meta Platforms, Inc.
       url: https://www.meta.com/
@@ -959,7 +959,7 @@
   bot:
     name: Facebook Crawler
     category: Social Media Agent
-    url: https://developers.facebook.com/docs/sharing/webmasters/crawler/
+    url: https://developers.facebook.com/docs/sharing/webmasters/web-crawlers
     producer:
       name: Meta Platforms, Inc.
       url: https://www.meta.com/
@@ -968,7 +968,7 @@
   bot:
     name: Facebook Crawler
     category: Social Media Agent
-    url: https://developers.facebook.com/docs/sharing/webmasters/crawler/
+    url: https://developers.facebook.com/docs/sharing/webmasters/web-crawlers
     producer:
       name: Meta Platforms, Inc.
       url: https://www.meta.com/
@@ -4642,7 +4642,7 @@
   bot:
     name: Facebook Crawler
     category: Social Media Agent
-    url: https://developers.facebook.com/docs/sharing/webmasters/crawler/
+    url: https://developers.facebook.com/docs/sharing/webmasters/web-crawlers
     producer:
       name: Meta Platforms, Inc.
       url: https://www.meta.com/
@@ -7762,7 +7762,7 @@
   bot:
     name: Facebook Crawler
     category: Social Media Agent
-    url: https://developers.facebook.com/docs/sharing/webmasters/crawler/
+    url: https://developers.facebook.com/docs/sharing/webmasters/web-crawlers
     producer:
       name: Meta Platforms, Inc.
       url: https://www.meta.com/
@@ -8309,3 +8309,52 @@
     producer:
       name: Immutable, SNC
       url: https://ohdear.app/
+-
+  user_agent: Mozilla/5.0 Keydrop
+  bot:
+    name: Generic Bot
+-
+  user_agent: Mozilla/6.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/127.0.0.0 Safari/537.36 Inspici (www.inspici.com)
+  bot:
+    name: Inspici
+    category: Crawler
+    url: https://www.inspici.com/
+    producer:
+      name: Inspici, LLC
+      url: https://www.inspici.com/
+-
+  user_agent: meta-externalagent/1.1 (+https://developers.facebook.com/docs/sharing/webmasters/crawler)
+  bot:
+    name: Meta-ExternalAgent
+    category: Crawler
+    url: https://developers.facebook.com/docs/sharing/webmasters/web-crawlers
+    producer:
+      name: Meta Platforms, Inc.
+      url: https://www.meta.com/
+-
+  user_agent: meta-externalagent/1.1
+  bot:
+    name: Meta-ExternalAgent
+    category: Crawler
+    url: https://developers.facebook.com/docs/sharing/webmasters/web-crawlers
+    producer:
+      name: Meta Platforms, Inc.
+      url: https://www.meta.com/
+-
+  user_agent: meta-externalfetcher/1.1 (+https://developers.facebook.com/docs/sharing/webmasters/crawler)
+  bot:
+    name: Meta-ExternalFetcher
+    category: Social Media Agent
+    url: https://developers.facebook.com/docs/sharing/webmasters/web-crawlers
+    producer:
+      name: Meta Platforms, Inc.
+      url: https://www.meta.com/
+-
+  user_agent: meta-externalfetcher/1.1
+  bot:
+    name: Meta-ExternalFetcher
+    category: Social Media Agent
+    url: https://developers.facebook.com/docs/sharing/webmasters/web-crawlers
+    producer:
+      name: Meta Platforms, Inc.
+      url: https://www.meta.com/
diff --git a/regexes/bots.yml b/regexes/bots.yml
@@ -594,7 +594,23 @@
 - regex: 'facebook(?:catalog|externalhit|externalua|platform|scraper)'
   name: 'Facebook Crawler'
   category: 'Social Media Agent'
-  url: 'https://developers.facebook.com/docs/sharing/webmasters/crawler/'
+  url: 'https://developers.facebook.com/docs/sharing/webmasters/web-crawlers'
+  producer:
+    name: 'Meta Platforms, Inc.'
+    url: 'https://www.meta.com/'
+
+- regex: 'meta-externalagent'
+  name: 'Meta-ExternalAgent'
+  category: 'Crawler'
+  url: 'https://developers.facebook.com/docs/sharing/webmasters/web-crawlers'
+  producer:
+    name: 'Meta Platforms, Inc.'
+    url: 'https://www.meta.com/'
+
+- regex: 'meta-externalfetcher'
+  name: 'Meta-ExternalFetcher'
+  category: 'Social Media Agent'
+  url: 'https://developers.facebook.com/docs/sharing/webmasters/web-crawlers'
   producer:
     name: 'Meta Platforms, Inc.'
     url: 'https://www.meta.com/'
@@ -4822,8 +4838,16 @@
     name: 'Immutable, SNC'
     url: 'https://ohdear.app/'
 
+- regex: 'Inspici'
+  name: 'Inspici'
+  category: 'Crawler'
+  url: 'https://www.inspici.com/'
+  producer:
+    name: 'Inspici, LLC'
+    url: 'https://www.inspici.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|^xenu|^(?:chrome|firefox|Abcd|Dark|KvshClient|Node.js|Report Runner|url|Zeus|ZmEu)$'
+- 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'
 
 # Generic detections