[extensions] Add new crawlers: Algolia, Baidu, BLEXBot, Botify, Freespoke, Marginalia, MSNBot, OnCrawl, SeekportBot, Siteimprove, TwinAgent, YepBot, ZumBot

This commit is contained in:
Faisal Salman 2025-08-21 21:40:50 +07:00
parent 9003fe5724
commit c9badeb345
2 changed files with 155 additions and 8 deletions

View File

@ -62,7 +62,11 @@ 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|brave|cc|contx|coveo|criteo|dot|duckduck(?:go-favicons-)?|exa|facebook|gpt|iask|kagi|kangaroo |linkedin|mj12|mojeek|oai-search|onespot-scraper|perplexity|semrush|seznam)bot)\/([\w\.-]+)/i,
// YepBot - https://yep.com/yepbot/
/((?:adidx|ahrefs|amazon|bing|brave|cc|contx|coveo|criteo|dot|duckduck(?:go-favicons-)?|exa|facebook|gpt|iask|kagi|kangaroo |linkedin|mj12|mojeek|oai-search|onespot-scraper|perplexity|semrush|seznam|yep)bot)\/([\w\.-]+)/i,
// Algolia Crawler
/(algolia crawler(?: renderscript)?)\/?([\w\.]*)/i,
// Applebot - http://apple.com/go/applebot
/(applebot(?:-extended)?)\/?([\w\.]*)/i,
@ -89,6 +93,9 @@ const Crawlers = Object.freeze({
// Internet Archive (archive.org)
/(ia_archiver|archive\.org_bot)\/?([\w\.]*)/i,
// OnCrawl
/(oncrawl) mobile\/([\w\.]+)/i,
// Qwantbot - https://help.qwant.com/bot
/(qwantbot)[-\w]*\/?([\w\.]*)/i,
@ -107,9 +114,10 @@ const Crawlers = Object.freeze({
// Yeti (Naver)
/(yeti)\/([\w\.]+)/i,
// aiHitBot / Algolia Crawler / 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
// aiHitBot / Algolia Crawler / BLEXBot / Diffbot / FirecrawlAgent / HuggingFace-Bot / Linespider / MSNBot / 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 / ZumBot
// 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|(?:algolia |magpie-|velenpublicweb)crawler|startpageprivateimageproxy|webzio-extended|(?:chatglm-|line|screaming frog seo |yisou)spider)\/?([\w\.]*)/i
// Freespoke - https://docs.freespoke.com/search/bot/
/((?:aihit|blex|diff|huggingface-|msn|pangu|replicate-|runpod-|timpi|together-|xai-|you|zum)bot|(?:magpie-|velenpublicweb)crawler|(?:chatglm-|line|screaming frog seo |yisou)spider|cotoyogi|firecrawlagent|freespoke|omgili(?:bot)?|openai image downloader|startpageprivateimageproxy|twinagent|webzio-extended)\/?([\w\.]*)/i
],
[NAME, VERSION, [TYPE, CRAWLER]],
@ -119,16 +127,15 @@ const Crawlers = Object.freeze({
/((?:adsbot|apis|mediapartners)-google(?:-mobile)?|google-?(?:other|cloudvertexbot|extended|safety))/i,
// AI2Bot - https://allenai.org/crawler
// Bytespider
// DataForSeoBot - https://dataforseo.com/dataforseo-bot
// DeepSeekBot
// Huawei AspiegelBot / PetalBot https://aspiegel.com/petalbot
// ImagesiftBot - https://imagesift.com/about
// Qihoo 360Spider
// Siteimprove - https://help.siteimprove.com/support/solutions/articles/80000448553
// TurnitinBot - https://www.turnitin.com/robot/crawlerinfo.html
// v0bot - https://vercel.com/docs/bot-management
// Yahoo! Slurp - http://help.yahoo.com/help/us/ysearch/slurp
/\b(360spider-?(?:image|video)?|bytespider|cohere-training-data-crawler|elastic(?=\/s)|(?:ai2|aspiegel|dataforseo|deepseek|imagesift|petal|turnitin|v0)bot|teoma|yahoo! slurp)/i
// Botify / Bytespider / DeepSeekBot / Qihoo 360Spider / SeekportBot
/\b((?:ai2|aspiegel|dataforseo|deepseek|imagesift|petal|seekport|turnitin|v0)bot|360spider-?(?:image|video)?|baidu-ads|botify|bytespider|cohere-training-data-crawler|elastic(?=\/s)|marginalia|siteimprove(?=bot|\.com)|teoma|yahoo! slurp)/i
],
[NAME, [TYPE, CRAWLER]]
]

View File

@ -89,6 +89,16 @@
"type" : "crawler"
}
},
{
"desc" : "Algolia Crawler Renderscript",
"ua" : "Algolia Crawler Renderscript",
"expect" :
{
"name" : "Algolia Crawler Renderscript",
"version" : "undefined",
"type" : "crawler"
}
},
{
"desc" : "Applebot",
"ua" : "Mozilla/5.0 (iPhone; CPU iPhone OS 8_1 like Mac OS X) AppleWebKit/600.1.4 (KHTML, like Gecko) Version/8.0 Mobile/12B410 Safari/600.1.4 (Applebot/0.1;+http://www.apple.com/go/applebot)",
@ -149,6 +159,16 @@
"type" : "crawler"
}
},
{
"desc" : "Baidu ADS",
"ua" : "Baidu-ADS",
"expect" :
{
"name" : "Baidu-ADS",
"version" : "undefined",
"type" : "crawler"
}
},
{
"desc" : "Baiduspider",
"ua" : "Mozilla/5.0 (compatible; Baiduspider/2.0; +http://www.baidu.com/search/spider.html)",
@ -239,6 +259,26 @@
"type" : "crawler"
}
},
{
"desc" : "BLEXBot",
"ua" : "Mozilla/5.0 (compatible; BLEXBot/1.0; +http://webmeup-crawler.com/)",
"expect" :
{
"name" : "BLEXBot",
"version" : "1.0",
"type" : "crawler"
}
},
{
"desc" : "botify",
"ua" : "Desktop: Mozilla/5.0 (compatible; botify; http://botify.com)",
"expect" :
{
"name" : "botify",
"version" : "undefined",
"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",
@ -519,6 +559,16 @@
"type" : "crawler"
}
},
{
"desc" : "Freespoke",
"ua" : "Mozilla/5.0 (compatible; Freespoke/2.0; +https://docs.freespoke.com/search/bot)",
"expect" :
{
"name" : "Freespoke",
"version" : "2.0",
"type" : "crawler"
}
},
{
"desc" : "Googlebot-Video",
"ua" : "Googlebot-Video/1.0",
@ -719,6 +769,16 @@
"type" : "crawler"
}
},
{
"desc" : "Marginalia Search",
"ua" : "search.marginalia.nu",
"expect" :
{
"name" : "marginalia",
"version" : "undefined",
"type" : "crawler"
}
},
{
"desc" : "Meta-ExternalAgent",
"ua" : "meta-externalagent/1.1 (+https://developers.facebook.com/docs/sharing/webmasters/crawler)",
@ -750,6 +810,16 @@
"type" : "crawler"
}
},
{
"desc" : "msnbot",
"ua" : "msnbot/2.0b (+http://search.msn.com/msnbot.htm)",
"expect" :
{
"name" : "msnbot",
"version" : "2.0b",
"type" : "crawler"
}
},
{
"desc" : "Omgili",
"ua" : "omgili/0.5 +https://omgili.com",
@ -770,6 +840,16 @@
"type" : "crawler"
}
},
{
"desc" : "OnCrawl",
"ua" : "Mozilla/5.0 (iPhone; CPU iPhone OS 8_3 like Mac OS X) AppleWebKit/600.1.4 (KHTML, like Gecko) Version/8.0 Mobile/12F70 Safari/600.1.4 (compatible; OnCrawl Mobile/1.0; +http://www.oncrawl.com/)",
"expect" :
{
"name" : "OnCrawl",
"version" : "1.0",
"type" : "crawler"
}
},
{
"desc" : "Onespot",
"ua" : "Mozilla/5.0 (compatible; Onespot-ScraperBot/1.0; +https://www.onespot.com/identifying-traffic.html)",
@ -880,6 +960,16 @@
"type" : "crawler"
}
},
{
"desc" : "SeekportBot",
"ua" : "Mozilla/5.0 (compatible; SeekportBot; +https://bot.seekport.com)",
"expect" :
{
"name" : "SeekportBot",
"version" : "undefined",
"type" : "crawler"
}
},
{
"desc" : "SemrushBot",
"ua" : "Mozilla/5.0 (compatible; SemrushBot/7~bl; +http://www.semrush.com/bot.html)",
@ -931,7 +1021,27 @@
}
},
{
"desc" : "Sogou",
"desc" : "Siteimprove",
"ua" : "Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko; compatible; SiteCheck-sitecrawl by Siteimprove.com; +https://siteimprove.com/bots) Chrome/[VERSION] Safari/537.36",
"expect" :
{
"name" : "Siteimprove",
"version" : "undefined",
"type" : "crawler"
}
},
{
"desc" : "Sogou Pic Spider",
"ua" : "Sogou Pic Spider/3.0( http://www.sogou.com/docs/help/webmasters.htm#07)",
"expect" :
{
"name" : "Sogou Pic Spider",
"version" : "3.0",
"type" : "crawler"
}
},
{
"desc" : "Sogou web spider",
"ua" : "Sogou web spider/4.0(+http://www.sogou.com/docs/help/webmasters.htm#07)",
"expect" :
{
@ -990,6 +1100,16 @@
"type" : "crawler"
}
},
{
"desc" : "TwinAgent",
"ua" : "TwinAgent/1.0",
"expect" :
{
"name" : "TwinAgent",
"version" : "1.0",
"type" : "crawler"
}
},
{
"desc" : "xAI-Bot",
"ua" : "Mozilla/5.0 (compatible; xAI-Bot/1.0; +https://x.ai/)",
@ -1050,6 +1170,16 @@
"type" : "crawler"
}
},
{
"desc" : "YepBot",
"ua" : "Mozilla/5.0 (compatible; YepBot/1.0; +http://yep.com/yepbot/)",
"expect" :
{
"name" : "YepBot",
"version" : "1.0",
"type" : "crawler"
}
},
{
"desc" : "Yeti",
"ua" : "Mozilla/5.0 (compatible; Yeti/1.1; +http://naver.me/spd)",
@ -1089,5 +1219,15 @@
"version" : "undefined",
"type" : "crawler"
}
},
{
"desc" : "ZumBot",
"ua" : "Mozilla/5.0 (compatible; ZumBot/1.0; http://help.zum.com/inquiry)",
"expect" :
{
"name" : "ZumBot",
"version" : "1.0",
"type" : "crawler"
}
}
]