Adds detection for OWLer and BBC bots, improves version detection for…

… iOS and macOS (matomo-org#7546)

* Improves version detection for iOS and macOS
* Adds detection for OWLer
* Adds detection for BBC bots

Tests/Parser/fixtures/oss.yml

@@ -4102,3 +4102,19 @@
     version: 9.0.0
     platform:
     family: Android
+-
+  user_agent: Aloha/1 CFNetwork/1492.0.1 Darwin/23.3.0
+  os:
+    name: iOS
+    short_name: IOS
+    version: "17.3"
+    platform:
+    family: iOS
+-
+  user_agent: Safari/19617.1.17.11.9 CFNetwork/1490.0.4 Darwin/23.2.0
+  os:
+    name: Mac
+    short_name: MAC
+    version: "14.2"
+    platform:
+    family: Mac

Tests/fixtures/bots.yml

@@ -5881,3 +5881,39 @@
     producer:
       name: Meltwater Deutschland GmbH
       url: https://www.meltwater.com/
+-
+  user_agent: [email protected]/1
+  bot:
+    name: OWLer
+    category: Crawler
+    url: https://openwebsearch.eu/owler/
+    producer:
+      name: Open Search Foundation e.V.
+      url: https://openwebsearch.eu/
+-
+  user_agent: OWLer/0.1 (built with StormCrawler; https://ows.eu/owler; [email protected]
+  bot:
+    name: OWLer
+    category: Crawler
+    url: https://openwebsearch.eu/owler/
+    producer:
+      name: Open Search Foundation e.V.
+      url: https://openwebsearch.eu/
+-
+  user_agent: Page Monitor (https://confluence.dev.bbc.co.uk/display/men/Page+Monitor)
+  bot:
+    name: BBC Page Monitor
+    category: Site Monitor
+    url: https://confluence.dev.bbc.co.uk/display/men/Page+Monitor
+    producer:
+      name: BBC
+      url: https://www.bbc.com/
+-
+  user_agent: BBC-Forge-URL-Monitor-Twisted
+  bot:
+    name: BBC Forge URL Monitor
+    category: Site Monitor
+    url: https://www.bbc.com/
+    producer:
+      name: BBC
+      url: https://www.bbc.com/

regexes/bots.yml

@@ -3508,6 +3508,30 @@
     name: 'Meltwater Deutschland GmbH'
     url: 'https://www.meltwater.com/'
 
+- regex: '(?:[email protected]|OWLer)/([\d+.]+)'
+  name: 'OWLer'
+  category: 'Crawler'
+  url: 'https://openwebsearch.eu/owler/'
+  producer:
+    name: 'Open Search Foundation e.V.'
+    url: 'https://openwebsearch.eu/'
+
+- regex: 'bbc.co.uk/display/men/Page\+Monitor'
+  name: 'BBC Page Monitor'
+  category: 'Site Monitor'
+  url: 'https://confluence.dev.bbc.co.uk/display/men/Page+Monitor'
+  producer:
+    name: 'BBC'
+    url: 'https://www.bbc.com/'
+
+- regex: 'BBC-Forge-URL-Monitor-Twisted'
+  name: 'BBC Forge URL Monitor'
+  category: 'Site Monitor'
+  url: 'https://www.bbc.com/'
+  producer:
+    name: 'BBC'
+    url: 'https://www.bbc.com/'
+
 # Generic detections
 - 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'

regexes/oss.yml

@@ -871,6 +871,8 @@
 - regex: '^(?!com.apple.Safari.SearchHelper|Safari).*CFNetwork/.+ Darwin/(\d+[\.\d]+)(?!.*(?:x86_64|i386|PowerMac|Power%20Macintosh))'
   name: 'iOS'
   versions:
+    - regex: 'Darwin/23.3.0'
+      version: '17.3'
     - regex: 'Darwin/23.2.0'
       version: '17.2'
     - regex: 'Darwin/23.1.0'
@@ -1098,6 +1100,8 @@
 - regex: '(?:CFNetwork|StudioDisplay)/.+Darwin(?:/|; )(?:[\d\.]+).+(?:x86_64|i386|Power%20Macintosh)|(?:x86_64-apple-)?darwin(?:[\d\.]+)|PowerMac|com.apple.Safari.SearchHelper|^Safari'
   name: 'Mac'
   versions:
+    - regex: '(?:x86_64-apple-)?Darwin(?:/|; )?23.3.0'
+      version: '14.3'
     - regex: '(?:x86_64-apple-)?Darwin(?:/|; )?23.2.0'
       version: '14.2'
     - regex: '(?:x86_64-apple-)?Darwin(?:/|; )?23.1.0'