Properly detect Google-InspectionTool as a Spider

Author: jleider

regexes.yaml

@@ -148,7 +148,7 @@ user_agent_parsers:
     family_replacement: 'Pinterestbot'
 
   # Bots
-  - regex: '(CSimpleSpider|Cityreview Robot|CrawlDaddy|CrawlFire|Finderbots|Index crawler|Job Roboter|KiwiStatus Spider|Lijit Crawler|QuerySeekerSpider|ScollSpider|Trends Crawler|USyd-NLP-Spider|SiteCat Webbot|BotName\/\$BotVersion|123metaspider-Bot|1470\.net crawler|50\.nu|8bo Crawler Bot|Aboundex|Accoona-[A-z]{1,30}-Agent|AdsBot-Google(?:-[a-z]{1,30}|)|altavista|AppEngine-Google|archive.{0,30}\.org_bot|archiver|Ask Jeeves|[Bb]ai[Dd]u[Ss]pider(?:-[A-Za-z]{1,30})(?:-[A-Za-z]{1,30}|)|bingbot|BingPreview|blitzbot|BlogBridge|Bloglovin|BoardReader Blog Indexer|BoardReader Favicon Fetcher|boitho.com-dc|BotSeer|BUbiNG|\b\w{0,30}favicon\w{0,30}\b|\bYeti(?:-[a-z]{1,30}|)|Catchpoint(?: bot|)|[Cc]harlotte|Checklinks|clumboot|Comodo HTTP\(S\) Crawler|Comodo-Webinspector-Crawler|ConveraCrawler|CRAWL-E|CrawlConvera|Daumoa(?:-feedfetcher|)|Feed Seeker Bot|Feedbin|findlinks|Flamingo_SearchEngine|FollowSite Bot|furlbot|Genieo|gigabot|GomezAgent|gonzo1|(?:[a-zA-Z]{1,30}-|)Googlebot(?:-[a-zA-Z]{1,30}|)|GoogleOther|Google SketchUp|grub-client|gsa-crawler|heritrix|HiddenMarket|holmes|HooWWWer|htdig|ia_archiver|ICC-Crawler|Icarus6j|ichiro(?:/mobile|)|IconSurf|IlTrovatore(?:-Setaccio|)|InfuzApp|Innovazion Crawler|InternetArchive|IP2[a-z]{1,30}Bot|jbot\b|KaloogaBot|Kraken|Kurzor|larbin|LEIA|LesnikBot|Linguee Bot|LinkAider|LinkedInBot|Lite Bot|Llaut|lycos|Mail\.RU_Bot|masscan|masidani_bot|Mediapartners-Google|Microsoft .{0,30} Bot|mogimogi|mozDex|MJ12bot|msnbot(?:-media {0,2}|)|msrbot|Mtps Feed Aggregation System|netresearch|Netvibes|NewsGator[^/]{0,30}|^NING|Nutch[^/]{0,30}|Nymesis|ObjectsSearch|OgScrper|Orbiter|OOZBOT|PagePeeker|PagesInventory|PaxleFramework|Peeplo Screenshot Bot|PHPCrawl|PlantyNet_WebRobot|Pompos|Qwantify|Read%20Later|Reaper|RedCarpet|Retreiver|Riddler|Rival IQ|scooter|Scrapy|Scrubby|searchsight|seekbot|semanticdiscovery|SemrushBot|Simpy|SimplePie|SEOstats|SimpleRSS|SiteCon|Slackbot-LinkExpanding|Slack-ImgProxy|Slurp|snappy|Speedy Spider|Squrl Java|Stringer|TheUsefulbot|ThumbShotsBot|Thumbshots\.ru|Tiny Tiny RSS|Twitterbot|WhatsApp|URL2PNG|Vagabondo|VoilaBot|^vortex|Votay bot|^voyager|WASALive.Bot|Web-sniffer|WebThumb|WeSEE:[A-z]{1,30}|WhatWeb|WIRE|WordPress|Wotbox|www\.almaden\.ibm\.com|Xenu(?:.s|) Link Sleuth|Xerka [A-z]{1,30}Bot|yacy(?:bot|)|YahooSeeker|Yahoo! Slurp|Yandex\w{1,30}|YodaoBot(?:-[A-z]{1,30}|)|YottaaMonitor|Yowedo|^Zao|^Zao-Crawler|ZeBot_www\.ze\.bz|ZooShot|ZyBorg|ArcGIS Hub Indexer|GPTBot)(?:[ /]v?(\d+)(?:\.(\d+)(?:\.(\d+)|)|)|)'
+  - regex: '(CSimpleSpider|Cityreview Robot|CrawlDaddy|CrawlFire|Finderbots|Index crawler|Job Roboter|KiwiStatus Spider|Lijit Crawler|QuerySeekerSpider|ScollSpider|Trends Crawler|USyd-NLP-Spider|SiteCat Webbot|BotName\/\$BotVersion|123metaspider-Bot|1470\.net crawler|50\.nu|8bo Crawler Bot|Aboundex|Accoona-[A-z]{1,30}-Agent|AdsBot-Google(?:-[a-z]{1,30}|)|altavista|AppEngine-Google|archive.{0,30}\.org_bot|archiver|Ask Jeeves|[Bb]ai[Dd]u[Ss]pider(?:-[A-Za-z]{1,30})(?:-[A-Za-z]{1,30}|)|bingbot|BingPreview|blitzbot|BlogBridge|Bloglovin|BoardReader Blog Indexer|BoardReader Favicon Fetcher|boitho.com-dc|BotSeer|BUbiNG|\b\w{0,30}favicon\w{0,30}\b|\bYeti(?:-[a-z]{1,30}|)|Catchpoint(?: bot|)|[Cc]harlotte|Checklinks|clumboot|Comodo HTTP\(S\) Crawler|Comodo-Webinspector-Crawler|ConveraCrawler|CRAWL-E|CrawlConvera|Daumoa(?:-feedfetcher|)|Feed Seeker Bot|Feedbin|findlinks|Flamingo_SearchEngine|FollowSite Bot|furlbot|Genieo|gigabot|GomezAgent|gonzo1|(?:[a-zA-Z]{1,30}-|)Googlebot(?:-[a-zA-Z]{1,30}|)|GoogleOther|Google SketchUp|grub-client|gsa-crawler|heritrix|HiddenMarket|holmes|HooWWWer|htdig|ia_archiver|ICC-Crawler|Icarus6j|ichiro(?:/mobile|)|IconSurf|IlTrovatore(?:-Setaccio|)|InfuzApp|Innovazion Crawler|InternetArchive|IP2[a-z]{1,30}Bot|jbot\b|KaloogaBot|Kraken|Kurzor|larbin|LEIA|LesnikBot|Linguee Bot|LinkAider|LinkedInBot|Lite Bot|Llaut|lycos|Mail\.RU_Bot|masscan|masidani_bot|Mediapartners-Google|Microsoft .{0,30} Bot|mogimogi|mozDex|MJ12bot|msnbot(?:-media {0,2}|)|msrbot|Mtps Feed Aggregation System|netresearch|Netvibes|NewsGator[^/]{0,30}|^NING|Nutch[^/]{0,30}|Nymesis|ObjectsSearch|OgScrper|Orbiter|OOZBOT|PagePeeker|PagesInventory|PaxleFramework|Peeplo Screenshot Bot|PHPCrawl|PlantyNet_WebRobot|Pompos|Qwantify|Read%20Later|Reaper|RedCarpet|Retreiver|Riddler|Rival IQ|scooter|Scrapy|Scrubby|searchsight|seekbot|semanticdiscovery|SemrushBot|Simpy|SimplePie|SEOstats|SimpleRSS|SiteCon|Slackbot-LinkExpanding|Slack-ImgProxy|Slurp|snappy|Speedy Spider|Squrl Java|Stringer|TheUsefulbot|ThumbShotsBot|Thumbshots\.ru|Tiny Tiny RSS|Twitterbot|WhatsApp|URL2PNG|Vagabondo|VoilaBot|^vortex|Votay bot|^voyager|WASALive.Bot|Web-sniffer|WebThumb|WeSEE:[A-z]{1,30}|WhatWeb|WIRE|WordPress|Wotbox|www\.almaden\.ibm\.com|Xenu(?:.s|) Link Sleuth|Xerka [A-z]{1,30}Bot|yacy(?:bot|)|YahooSeeker|Yahoo! Slurp|Yandex\w{1,30}|YodaoBot(?:-[A-z]{1,30}|)|YottaaMonitor|Yowedo|^Zao|^Zao-Crawler|ZeBot_www\.ze\.bz|ZooShot|ZyBorg|ArcGIS Hub Indexer|GPTBot|Google-InspectionTool)(?:[ /]v?(\d+)(?:\.(\d+)(?:\.(\d+)|)|)|)'
 
   # AWS S3 Clients
   # must come before "Bots General matcher" to catch "boto"/"boto3" before "bot"
@@ -1931,7 +1931,7 @@ device_parsers:
   # Mobile Spiders
   # Catch the mobile crawler before checking for iPhones / Androids.
   #########
-  - regex: '^.{0,100}?(?:(?:iPhone|Windows CE|Windows Phone|Android).{0,300}(?:(?:Bot|Yeti)-Mobile|YRSpider|BingPreview|bots?/\d|(?:bot|spider)\.html)|AdsBot-Google-Mobile.{0,200}iPhone)'
+  - regex: '^.{0,100}?(?:(?:iPhone|Windows CE|Windows Phone|Android).{0,300}(?:(?:Bot|Yeti)-Mobile|YRSpider|BingPreview|bots?/\d|(?:bot|spider)\.html|Google-InspectionTool)|AdsBot-Google-Mobile.{0,200}iPhone)'
     regex_flag: 'i'
     device_replacement: 'Spider'
     brand_replacement: 'Spider'
@@ -5941,7 +5941,7 @@ device_parsers:
   ##########
   # Spiders (this is a hack...)
   ##########
-  - regex: '^.{0,100}(bot|BUbiNG|zao|borg|DBot|oegp|silk|Xenu|zeal|^NING|CCBot|crawl|htdig|lycos|slurp|teoma|voila|yahoo|Sogou|CiBra|Nutch|^Java/|^JNLP/|Daumoa|Daum|Genieo|ichiro|larbin|pompos|Scrapy|snappy|speedy|spider|msnbot|msrbot|vortex|^vortex|crawler|favicon|indexer|Riddler|scooter|scraper|scrubby|WhatWeb|WinHTTP|bingbot|BingPreview|openbot|gigabot|furlbot|polybot|seekbot|^voyager|archiver|Icarus6j|mogimogi|Netvibes|blitzbot|altavista|charlotte|findlinks|Retreiver|TLSProber|WordPress|SeznamBot|ProoXiBot|wsr\-agent|Squrl Java|EtaoSpider|PaperLiBot|SputnikBot|A6\-Indexer|netresearch|searchsight|baiduspider|YisouSpider|ICC\-Crawler|http%20client|Python-urllib|dataparksearch|converacrawler|Screaming Frog|AppEngine-Google|YahooCacheSystem|fast\-webcrawler|Sogou Pic Spider|semanticdiscovery|Innovazion Crawler|facebookexternalhit|Google.{0,200}/\+/web/snippet|Google-HTTP-Java-Client|BlogBridge|IlTrovatore-Setaccio|InternetArchive|GomezAgent|WebThumbnail|heritrix|NewsGator|PagePeeker|Reaper|ZooShot|holmes|NL-Crawler|Pingdom|StatusCake|WhatsApp|masscan|Google Web Preview|Qwantify|Yeti|OgScrper|RecipeRadar|GPTBot)'
+  - regex: '^.{0,100}(bot|BUbiNG|zao|borg|DBot|oegp|silk|Xenu|zeal|^NING|CCBot|crawl|htdig|lycos|slurp|teoma|voila|yahoo|Sogou|CiBra|Nutch|^Java/|^JNLP/|Daumoa|Daum|Genieo|ichiro|larbin|pompos|Scrapy|snappy|speedy|spider|msnbot|msrbot|vortex|^vortex|crawler|favicon|indexer|Riddler|scooter|scraper|scrubby|WhatWeb|WinHTTP|bingbot|BingPreview|openbot|gigabot|furlbot|polybot|seekbot|^voyager|archiver|Icarus6j|mogimogi|Netvibes|blitzbot|altavista|charlotte|findlinks|Retreiver|TLSProber|WordPress|SeznamBot|ProoXiBot|wsr\-agent|Squrl Java|EtaoSpider|PaperLiBot|SputnikBot|A6\-Indexer|netresearch|searchsight|baiduspider|YisouSpider|ICC\-Crawler|http%20client|Python-urllib|dataparksearch|converacrawler|Screaming Frog|AppEngine-Google|YahooCacheSystem|fast\-webcrawler|Sogou Pic Spider|semanticdiscovery|Innovazion Crawler|facebookexternalhit|Google.{0,200}/\+/web/snippet|Google-HTTP-Java-Client|BlogBridge|IlTrovatore-Setaccio|InternetArchive|GomezAgent|WebThumbnail|heritrix|NewsGator|PagePeeker|Reaper|ZooShot|holmes|NL-Crawler|Pingdom|StatusCake|WhatsApp|masscan|Google Web Preview|Qwantify|Yeti|OgScrper|RecipeRadar|GPTBot|Google-InspectionTool)'
     regex_flag: 'i'
     device_replacement: 'Spider'
     brand_replacement: 'Spider'

tests/test_device.yaml

@@ -80350,6 +80350,16 @@ test_cases:
     brand: 'Spider'
     model: 'Desktop'
 
+  - user_agent_string: 'Mozilla/5.0 (compatible; Google-InspectionTool/1.0;)'
+    family: 'Spider'
+    brand: 'Spider'
+    model: 'Desktop'
+
+  - user_agent_string: 'Mozilla/5.0 (Linux; Android 6.0.1; Nexus 5X Build/MMB29P) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/124.0.6367.201 Mobile Safari/537.36 (compatible; Google-InspectionTool/1.0;)'
+    family: 'Spider'
+    brand: 'Spider'
+    model: 'Smartphone'
+
   - user_agent_string: 'Mozilla/5.0 (compatible; Qwantify/2.4w; +https://www.qwant.com/)/2.4w'
     family: 'Spider'
     brand: 'Spider'

tests/test_os.yaml

@@ -525,6 +525,20 @@ test_cases:
     patch:
     patch_minor:
 
+  - user_agent_string: 'Mozilla/5.0 (compatible; Google-InspectionTool/1.0;)'
+    family: 'Other'
+    major:
+    minor:
+    patch:
+    patch_minor:
+
+  - user_agent_string: 'Mozilla/5.0 (Linux; Android 6.0.1; Nexus 5X Build/MMB29P) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/124.0.6367.201 Mobile Safari/537.36 (compatible; Google-InspectionTool/1.0;)'
+    family: 'Android'
+    major: '6'
+    minor: '0'
+    patch: '1'
+    patch_minor:
+
   - user_agent_string: 'Bunjalloo/0.7.6(Nintendo DS;U;en)'
     family: 'Other'
     major:

tests/test_ua.yaml

@@ -2658,6 +2658,18 @@ test_cases:
     minor:
     patch:
 
+  - user_agent_string: 'Mozilla/5.0 (compatible; Google-InspectionTool/1.0;)'
+    family: 'Google-InspectionTool'
+    major: '1'
+    minor: '0'
+    patch:
+
+  - user_agent_string: 'Mozilla/5.0 (Linux; Android 6.0.1; Nexus 5X Build/MMB29P) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/124.0.6367.201 Mobile Safari/537.36 (compatible; Google-InspectionTool/1.0;)'
+    family: 'Google-InspectionTool'
+    major: '1'
+    minor: '0'
+    patch:
+
   - user_agent_string: 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/60.0.3112.78 Safari/537.36'
     family: 'Chrome'
     major: '60'