From 1076c5c8fd3b7966cdb1d126be701534c95f12f8 Mon Sep 17 00:00:00 2001 From: Liviu-Mihail Concioiu Date: Mon, 16 Sep 2024 02:36:56 +0200 Subject: [PATCH] Adds detection for 1001FirmsBot --- Tests/fixtures/bots.yml | 6 ++++++ regexes/bots.yml | 5 +++++ 2 files changed, 11 insertions(+) diff --git a/Tests/fixtures/bots.yml b/Tests/fixtures/bots.yml index fcdfdf4c9d..e63710b15d 100644 --- a/Tests/fixtures/bots.yml +++ b/Tests/fixtures/bots.yml @@ -8243,3 +8243,9 @@ producer: name: Brave Software, Inc. url: https://brave.com/ +- + user_agent: Mozilla/5.0 (compatible; 1001FirmsBot/1.0; +https://www.1001firms.com/1001firmsbot.php) + bot: + name: 1001FirmsBot + category: Crawler + url: https://www.1001firms.com/1001firmsbot.php diff --git a/regexes/bots.yml b/regexes/bots.yml index 5acf14611b..58248f3908 100644 --- a/regexes/bots.yml +++ b/regexes/bots.yml @@ -4769,6 +4769,11 @@ name: 'Brave Software, Inc.' url: 'https://brave.com/' +- regex: '1001FirmsBot' + name: '1001FirmsBot' + category: 'Crawler' + url: 'https://www.1001firms.com/1001firmsbot.php' + # 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)$' name: 'Generic Bot'