aheh/bit
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge pull request #8 from sjdonado/automated/update-parsers

Browse Source 
chore: Update UA regexes and GeoLite2 database
This commit is contained in:
Juan Rodriguez Donado
2025-11-02 11:32:03 +01:00
committed by GitHub
parent 9fcd478f86 7c6d67c0c7
commit b8c1269d6e
3 changed files with 22 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files
cli
Executable
BIN
View File
Binary file not shown.
data/GeoLite2-Country.mmdb
BIN
View File
Binary file not shown.
data/uap_core_regexes.yaml
+22 -13
View File
@@ -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"
@@ -443,12 +443,6 @@ user_agent_parsers:
- regex: '(coc_coc_browser)/(\d+)\.(\d+)(?:\.(\d+)|)'
family_replacement: 'Coc Coc'
# Baidu Browsers (desktop spoofs chrome & IE, explorer is mobile)
- regex: '(baidubrowser)[/\s](\d+)(?:\.(\d+)|)(?:\.(\d+)|)'
family_replacement: 'Baidu Browser'
- regex: '(FlyFlow)/(\d+)\.(\d+)'
family_replacement: 'Baidu Explorer'
# MxBrowser is Maxthon. Must go before Mobile Chrome for Android
- regex: '(MxBrowser)/(\d+)\.(\d+)(?:\.(\d+)|)'
family_replacement: 'Maxthon'
@@ -477,6 +471,12 @@ user_agent_parsers:
- regex: 'Mozilla.{1,200}Android.{1,200}(GSA)/(\d+)\.(\d+)\.(\d+)'
family_replacement: 'Google'
# Baidu Browsers (desktop spoofs chrome & IE, explorer is mobile)
- regex: '(baidubrowser)[/\s](\d+)(?:\.(\d+)|)(?:\.(\d+)|)'
family_replacement: 'Baidu Browser'
- regex: '(FlyFlow|flyflow|baiduboxapp)/(\d+)\.(\d+)(?:\.(\d+)|)(?:\.(\d+)|)'
family_replacement: 'Baidu Explorer'
# QQ Browsers
- regex: '(MQQBrowser/Mini)(?:(\d+)(?:\.(\d+)|)(?:\.(\d+)|)|)'
family_replacement: 'QQ Browser Mini'
@@ -506,11 +506,18 @@ user_agent_parsers:
family_replacement: 'Ecosia Android'
# VivoBrowser
- regex: '(VivoBrowser)\/(\d+)\.(\d+)\.(\d+)\.(\d+)'
- regex: '(VivoBrowser)\/(\d+)\.(\d+)\.(\d+)(?:\.(\d+)|)'
# HiBrowser
- regex: '(HiBrowser)\/v(\d+)\.(\d+)\.(\d+)\.(\d+)'
# Weibo
# Must before Chrome Mobile WebView
- regex: '(weibo)__(\d+)\.(\d+)\.(\d+)'
family_replacement: 'Weibo'
- regex: '(WeiboliteiOS|WeiboIntliOS)'
family_replacement: 'Weibo'
# Chrome Mobile
- regex: 'Version/.{1,300}(Chrome)/(\d+)\.(\d+)\.(\d+)\.(\d+)'
family_replacement: 'Chrome Mobile WebView'
@@ -592,7 +599,7 @@ user_agent_parsers:
- regex: '(115Browser)/(\d+)\.(\d+)\.(\d+)\.(\d+)'
family_replacement: '115 Browser'
# Avira
# Avira
- regex: '(Avira)/(\d+)\.(\d+)\.(\d+)\.(\d+)'
family_replacement: 'Avira'
@@ -667,6 +674,10 @@ user_agent_parsers:
- regex: '(JiSu)/(\d+)\.(\d+)\.(\d+)'
family_replacement: 'JiSu Browser'
# Wolvic Browser
- regex: '(Wolvic)/(\d+)\.(\d+)\.(\d+)'
family_replacement: 'Wolvic Browser'
#### END SPECIAL CASES TOP ####
#### MAIN CASES - this catches > 50% of all browsers ####
@@ -2013,7 +2024,7 @@ 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'
@@ -5619,7 +5630,6 @@ device_parsers:
brand_replacement: 'Asus'
model_replacement: '$1'
##########
# Bird
##########
@@ -5819,7 +5829,6 @@ device_parsers:
brand_replacement: 'Motorola'
model_replacement: '$2'
##########
# nintendo
##########
@@ -6023,7 +6032,7 @@ 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'