From 15643689fdc7a9e2bf8d9f482736a3581409041f Mon Sep 17 00:00:00 2001 From: Cloudscape Germany <418352+cloudscape-germany@users.noreply.github.com> Date: Sat, 24 Jan 2026 12:40:44 +0100 Subject: [PATCH 1/8] Add exhaustive list of bot identifiers to badBotUA array - Minimizes false positives by using specific patterns like 'bot/', '-bot' - Catches most bot variants without being overly broad - Maintains case-sensitivity for precision - Includes both common patterns and specific known bots --- js/legacy.js | 67 ++++++++++++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 65 insertions(+), 2 deletions(-) diff --git a/js/legacy.js b/js/legacy.js index 38f3cb2d..e0d96c92 100644 --- a/js/legacy.js +++ b/js/legacy.js @@ -59,8 +59,71 @@ * @readonly */ var badBotUA = [ - 'Bot', - 'bot' + // Generic bot identifiers + 'bot/', + 'Bot/', + '-bot', + '-Bot', + 'crawler', + 'Crawler', + 'spider', + 'Spider', + 'scraper', + 'Scraper', + + // Search Engines + 'Googlebot', + 'Mediapartners-Google', + 'AdsBot-Google', + 'bingbot', + 'msnbot', + 'BingPreview', + 'Yahoo! Slurp', + 'Baiduspider', + 'YandexBot', + 'DuckDuckBot', + + // SEO & Analytics + 'AhrefsBot', + 'SemrushBot', + 'MJ12bot', + 'rogerbot', + 'Screaming Frog', + + // Social Media + 'facebookexternalhit', + 'Facebot', + 'Twitterbot', + 'LinkedInBot', + 'Pinterestbot', + 'Slackbot', + + // AI & LLM + 'GPTBot', + 'ChatGPT-User', + 'OAI-SearchBot', + 'ClaudeBot', + 'anthropic-ai', + 'PerplexityBot', + + // Monitoring & Uptime + 'Pingdom', + 'UptimeRobot', + 'BetterStackBot', + 'cron-job.org', + + // Security Scanners + 'CensysInspect', + 'Shodan', + 'BitSightBot', + + // Other Common Crawlers + '80legs', + 'ia_archiver', + 'Teoma', + 'Linguee Bot', + 'AddThis.com robot', + 'Speedy Spider' ]; /** From 968ec9cadab2a1015202f585bc87ec631112db0a Mon Sep 17 00:00:00 2001 From: Cloudscape Germany <418352+cloudscape-germany@users.noreply.github.com> Date: Sat, 24 Jan 2026 12:55:59 +0100 Subject: [PATCH 2/8] Fix JSDoc type for badBotUA variable Update JSDoc type annotation for badBotUA variable --- js/legacy.js | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/js/legacy.js b/js/legacy.js index e0d96c92..a648df9d 100644 --- a/js/legacy.js +++ b/js/legacy.js @@ -55,7 +55,7 @@ * blacklist of UserAgents (parts) known to belong to a bot * * @private - * @enum {Array} + * @type {string[]} * @readonly */ var badBotUA = [ From 0f4ac5e98e7be3a51e828a463957f7bf65d2ff23 Mon Sep 17 00:00:00 2001 From: Cloudscape Germany <418352+cloudscape-germany@users.noreply.github.com> Date: Sun, 25 Jan 2026 20:58:24 +0100 Subject: [PATCH 3/8] Update js/legacy.js Co-authored-by: El RIDO --- js/legacy.js | 2 -- 1 file changed, 2 deletions(-) diff --git a/js/legacy.js b/js/legacy.js index a648df9d..3c8ad473 100644 --- a/js/legacy.js +++ b/js/legacy.js @@ -108,8 +108,6 @@ // Monitoring & Uptime 'Pingdom', - 'UptimeRobot', - 'BetterStackBot', 'cron-job.org', // Security Scanners From 885ad4ff70a11e13efa5388924ae92dd7acab5a4 Mon Sep 17 00:00:00 2001 From: Cloudscape Germany <418352+cloudscape-germany@users.noreply.github.com> Date: Sun, 25 Jan 2026 21:03:51 +0100 Subject: [PATCH 4/8] Update js/legacy.js Co-authored-by: El RIDO --- js/legacy.js | 7 ------- 1 file changed, 7 deletions(-) diff --git a/js/legacy.js b/js/legacy.js index 3c8ad473..54537ef2 100644 --- a/js/legacy.js +++ b/js/legacy.js @@ -72,16 +72,9 @@ 'Scraper', // Search Engines - 'Googlebot', 'Mediapartners-Google', - 'AdsBot-Google', - 'bingbot', - 'msnbot', 'BingPreview', 'Yahoo! Slurp', - 'Baiduspider', - 'YandexBot', - 'DuckDuckBot', // SEO & Analytics 'AhrefsBot', From 3b543d327171fb3563ddb4963d3928cc6546917c Mon Sep 17 00:00:00 2001 From: Cloudscape Germany <418352+cloudscape-germany@users.noreply.github.com> Date: Sun, 25 Jan 2026 21:04:38 +0100 Subject: [PATCH 5/8] Update js/legacy.js Co-authored-by: El RIDO --- js/legacy.js | 13 ------------- 1 file changed, 13 deletions(-) diff --git a/js/legacy.js b/js/legacy.js index 54537ef2..5a6195ae 100644 --- a/js/legacy.js +++ b/js/legacy.js @@ -77,27 +77,14 @@ 'Yahoo! Slurp', // SEO & Analytics - 'AhrefsBot', - 'SemrushBot', - 'MJ12bot', - 'rogerbot', 'Screaming Frog', // Social Media 'facebookexternalhit', - 'Facebot', - 'Twitterbot', - 'LinkedInBot', - 'Pinterestbot', - 'Slackbot', // AI & LLM - 'GPTBot', 'ChatGPT-User', - 'OAI-SearchBot', - 'ClaudeBot', 'anthropic-ai', - 'PerplexityBot', // Monitoring & Uptime 'Pingdom', From 9c40afbdf344c786a4ad32f652f9c6725943af6c Mon Sep 17 00:00:00 2001 From: Cloudscape Germany <418352+cloudscape-germany@users.noreply.github.com> Date: Sun, 25 Jan 2026 21:06:23 +0100 Subject: [PATCH 6/8] Update js/legacy.js Co-authored-by: El RIDO --- js/legacy.js | 4 ---- 1 file changed, 4 deletions(-) diff --git a/js/legacy.js b/js/legacy.js index 5a6195ae..8fef3472 100644 --- a/js/legacy.js +++ b/js/legacy.js @@ -93,15 +93,11 @@ // Security Scanners 'CensysInspect', 'Shodan', - 'BitSightBot', // Other Common Crawlers '80legs', 'ia_archiver', 'Teoma', - 'Linguee Bot', - 'AddThis.com robot', - 'Speedy Spider' ]; /** From 4711d9135a3422509bd858cc3c17e4f47d28c036 Mon Sep 17 00:00:00 2001 From: Cloudscape Germany <418352+cloudscape-germany@users.noreply.github.com> Date: Sun, 25 Jan 2026 21:10:36 +0100 Subject: [PATCH 7/8] Remove monitoring services from legacy.js Removed monitoring and uptime services from the list. --- js/legacy.js | 4 ---- 1 file changed, 4 deletions(-) diff --git a/js/legacy.js b/js/legacy.js index 8fef3472..fa33d081 100644 --- a/js/legacy.js +++ b/js/legacy.js @@ -86,10 +86,6 @@ 'ChatGPT-User', 'anthropic-ai', - // Monitoring & Uptime - 'Pingdom', - 'cron-job.org', - // Security Scanners 'CensysInspect', 'Shodan', From 0d24bac155ce35ded560cee126cc533b8995930e Mon Sep 17 00:00:00 2001 From: Cloudscape Germany <418352+cloudscape-germany@users.noreply.github.com> Date: Tue, 27 Jan 2026 14:50:23 +0100 Subject: [PATCH 8/8] Update js/legacy.js Co-authored-by: El RIDO --- js/legacy.js | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/js/legacy.js b/js/legacy.js index fa33d081..638425aa 100644 --- a/js/legacy.js +++ b/js/legacy.js @@ -60,10 +60,8 @@ */ var badBotUA = [ // Generic bot identifiers - 'bot/', - 'Bot/', - '-bot', - '-Bot', + 'bot', + 'Bot', 'crawler', 'Crawler', 'spider',