[extensions][helpers] Add some new AI bots: Bravebot, Cotoyogi, FirecrawlAgent, HuggingFace-Bot, Kangaroo Bot, PanguBot, Replicate-Bot, RunPod-Bot, Together-Bot, xAI-Bot

This commit is contained in:
Faisal Salman 2025-08-14 20:42:17 +07:00
parent 647b6232bd
commit 975c4860f4
3 changed files with 131 additions and 3 deletions

View File

@ -43,6 +43,7 @@ const Crawlers = Object.freeze({
// AhrefsBot - https://ahrefs.com/robot
// Amazonbot - https://developer.amazon.com/amazonbot
// Bingbot / AdIdxBot - https://www.bing.com/webmasters/help/which-crawlers-does-bing-use-8c184ec0
// Bravebot - https://search.brave.com/help/brave-search-crawler
// CCBot - https://commoncrawl.org/faq
// Coveobot - https://connect.coveo.com/s/article/19648
// CriteoBot - https://www.criteo.com/criteo-crawler/
@ -51,6 +52,7 @@ const Crawlers = Object.freeze({
// FacebookBot - https://developers.facebook.com/docs/sharing/bot/
// GPTBot - https://platform.openai.com/docs/gptbot
// iAskBot - https://iask.ai
// Kangaroo Bot - https://kangaroollm.com.au/kangaroo-bot/
// LinkedInBot - http://www.linkedin.com
// MJ12bot - https://mj12bot.com/
// MojeekBot - https://www.mojeek.com/bot.html
@ -58,7 +60,7 @@ const Crawlers = Object.freeze({
// OpenAI's SearchGPT - https://platform.openai.com/docs/bots
// PerplexityBot - https://perplexity.ai/perplexitybot
// SeznamBot - http://napoveda.seznam.cz/seznambot-intro
/((?:adidx|ahrefs|amazon|bing|cc|coveo|criteo|dot|duckduck(?:go-favicons-)?|exa|facebook|gpt|iask|linkedin|mj12|mojeek|oai-search|onespot-scraper|perplexity|semrush|seznam)bot)\/([\w\.-]+)/i,
/((?:adidx|ahrefs|amazon|bing|brave|cc|coveo|criteo|dot|duckduck(?:go-favicons-)?|exa|facebook|gpt|iask|kangaroo |linkedin|mj12|mojeek|oai-search|onespot-scraper|perplexity|semrush|seznam)bot)\/([\w\.-]+)/i,
// Applebot - http://apple.com/go/applebot
/(applebot(?:-extended)?)\/?([\w\.]*)/i,
@ -103,8 +105,9 @@ const Crawlers = Object.freeze({
// Yeti (Naver)
/(yeti)\/([\w\.]+)/i,
// aiHitBot / Diffbot / Linespider / Magpie-Crawler / Omgilibot / OpenAI Image Downloader / Webzio-Extended / Screaming Frog SEO Spider / Startpage / Timpibot / VelenPublicWebCrawler / YisouSpider / YouBot
/((?:aihit|diff|timpi|you)bot|omgili(?:bot)?|openai image downloader|(?:magpie-|velenpublicweb)crawler|startpageprivateimageproxy|webzio-extended|(?:chatglm-|line|screaming frog seo |yisou)spider)\/?([\w\.]*)/i
// aiHitBot / Diffbot / FirecrawlAgent / HuggingFace-Bot / Linespider / Magpie-Crawler / Omgilibot / OpenAI Image Downloader / PanguBot / Replicate-Bot / RunPod-Bot / Webzio-Extended / Screaming Frog SEO Spider / Startpage / Timpibot / Together-Bot / VelenPublicWebCrawler / xAI-Bot / YisouSpider / YouBot
// Cotoyogi - https://ds.rois.ac.jp/en_center8/en_crawler/
/((?:aihit|diff|huggingface-|pangu|replicate-|runpod-|timpi|together-|xai-|you)bot|omgili(?:bot)?|cotoyogi|firecrawlagent|openai image downloader|(?:magpie-|velenpublicweb)crawler|startpageprivateimageproxy|webzio-extended|(?:chatglm-|line|screaming frog seo |yisou)spider)\/?([\w\.]*)/i
],
[NAME, VERSION, [TYPE, CRAWLER]],

View File

@ -59,6 +59,9 @@ const isAIBot = (resultOrUA) => [
'applebot',
'applebot-extended',
// Brave
'bravebot',
// ByteDance
'bytespider',
'tiktokspider',
@ -92,6 +95,16 @@ const isAIBot = (resultOrUA) => [
// Huawei
'petalbot',
'pangubot',
// Hugging Face
'huggingface-bot',
// Kangaroo
'kangaroo bot',
// Mendable.ai
'firecrawlagent',
// Meta
'facebookbot',
@ -104,12 +117,21 @@ const isAIBot = (resultOrUA) => [
// Perplexity
'perplexitybot',
// Replicate
'replicate-bot',
// Runpod
'runpod-bot',
// Semrush
'semrushbot-ocob',
// Timpi
'timpibot',
// Together AI
'together-bot',
// Velen.io
'velenpublicwebcrawler',
@ -121,6 +143,9 @@ const isAIBot = (resultOrUA) => [
'omgilibot',
'webzio-extended',
// X
'xai-bot',
// You.com
'youbot',

View File

@ -229,6 +229,16 @@
"type" : "crawler"
}
},
{
"desc" : "Bravebot",
"ua" : "Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko; compatible; Bravebot/1.0; +https://search.brave.com/help/brave-search-crawler) Chrome/W.X.Y.Z Safari/537.36",
"expect" :
{
"name" : "Bravebot",
"version" : "1.0",
"type" : "crawler"
}
},
{
"desc" : "Bytespider",
"ua" : "Mozilla/5.0 (Linux; Android 8.0; Pixel 2 Build/OPD3.170816.012) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/56.0.1511.1269 Mobile Safari/537.36; Bytespider",
@ -309,6 +319,16 @@
"type" : "crawler"
}
},
{
"desc" : "Cotoyogi",
"ua" : "Mozilla/5.0 (compatible; Cotoyogi/4.0; +https://ds.rois.ac.jp/center8/crawler/)",
"expect" :
{
"name" : "Cotoyogi",
"version" : "4.0",
"type" : "crawler"
}
},
{
"desc" : "Coveobot",
"ua" : "Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko) (compatible; Coveobot/2.0;+http://www.coveo.com/bot.html)",
@ -469,6 +489,16 @@
"type" : "crawler"
}
},
{
"desc" : "FirecrawlAgent",
"ua" : "Mozilla/5.0 (compatible; FirecrawlAgent/1.0)",
"expect" :
{
"name" : "FirecrawlAgent",
"version" : "1.0",
"type" : "crawler"
}
},
{
"desc" : "Googlebot-Video",
"ua" : "Googlebot-Video/1.0",
@ -589,6 +619,16 @@
"type" : "crawler"
}
},
{
"desc" : "HuggingFace-Bot",
"ua" : "Mozilla/5.0 (compatible; HuggingFace-Bot/1.0; +https://huggingface.co/)",
"expect" :
{
"name" : "HuggingFace-Bot",
"version" : "1.0",
"type" : "crawler"
}
},
{
"desc" : "iAskBot",
"ua" : "Mozilla/5.0 AppleWebKit/605.1.15 (KHTML, like Gecko; compatible; iAskBot/1.0; +https://iask.ai/) Chrome/120.0.6099.119 Safari/605.1.15",
@ -609,6 +649,16 @@
"type" : "crawler"
}
},
{
"desc" : "Kangaroo Bot",
"ua" : "Mozilla/5.0 (compatible; Kangaroo Bot/1.0)",
"expect" :
{
"name" : "Kangaroo Bot",
"version" : "1.0",
"type" : "crawler"
}
},
{
"desc" : "Linespider",
"ua" : "Mozilla/5.0 (compatible; Linespider/1.1; +https://lin.ee/4dwXkTH)",
@ -710,6 +760,16 @@
"type" : "crawler"
}
},
{
"desc" : "PanguBot",
"ua" : "Mozilla/5.0 (compatible; PanguBot/1.0)",
"expect" :
{
"name" : "PanguBot",
"version" : "1.0",
"type" : "crawler"
}
},
{
"desc" : "PerplexityBot",
"ua" : "Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko; compatible; PerplexityBot/1.0; +https://perplexity.ai/perplexitybot)",
@ -770,6 +830,26 @@
"type" : "crawler"
}
},
{
"desc" : "Replicate-Bot",
"ua" : "Mozilla/5.0 (compatible; Replicate-Bot/1.0; +https://replicate.com/)",
"expect" :
{
"name" : "Replicate-Bot",
"version" : "1.0",
"type" : "crawler"
}
},
{
"desc" : "RunPod-Bot",
"ua" : "Mozilla/5.0 (compatible; RunPod-Bot/1.0; +https://runpod.io/)",
"expect" :
{
"name" : "RunPod-Bot",
"version" : "1.0",
"type" : "crawler"
}
},
{
"desc" : "SemrushBot",
"ua" : "Mozilla/5.0 (compatible; SemrushBot/7~bl; +http://www.semrush.com/bot.html)",
@ -860,6 +940,16 @@
"type" : "crawler"
}
},
{
"desc" : "Together-Bot",
"ua" : "Mozilla/5.0 (compatible; Together-Bot/1.0; +https://together.ai/)",
"expect" :
{
"name" : "Together-Bot",
"version" : "1.0",
"type" : "crawler"
}
},
{
"desc" : "TurnitinBot",
"ua" : "TurnitinBot (https://turnitin.com/robot/crawlerinfo.html)",
@ -870,6 +960,16 @@
"type" : "crawler"
}
},
{
"desc" : "xAI-Bot",
"ua" : "Mozilla/5.0 (compatible; xAI-Bot/1.0; +https://x.ai/)",
"expect" :
{
"name" : "xAI-Bot",
"version" : "1.0",
"type" : "crawler"
}
},
{
"desc" : "VelenPublicWebCrawler",
"ua" : "Mozilla/5.0 (compatible; VelenPublicWebCrawler/1.0; +https://velen.io)",