[submodule:extensions] Add some new bots: 360Spider, Archive.org Bots, CCBot, DataForSeoBot, DuckAssistBot, Exabot, Google Bots, Meta Bots, MojeekBot, PerplexityBot, PetalBot, TurnitinBot, Yeti, YisouSpider

This commit is contained in:
Faisal Salman
2024-11-10 13:01:46 +07:00
parent 3b3361fe53
commit a0e11b701e
3 changed files with 415 additions and 12 deletions

View File

@@ -1,4 +1,44 @@
[
{
"desc" : "360Spider",
"ua" : "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Trident/5.0); 360Spider",
"expect" :
{
"name" : "360Spider",
"version" : "undefined",
"type" : "crawler"
}
},
{
"desc" : "AdsBot Mobile Web",
"ua" : "AdsBot-Google (+http://www.google.com/adsbot.html)",
"expect" :
{
"name" : "AdsBot-Google",
"version" : "undefined",
"type" : "crawler"
}
},
{
"desc" : "AdsBot Mobile Web",
"ua" : "Mozilla/5.0 (Linux; Android 6.0.1; Nexus 5X Build/MMB29P) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/41.0.2272.96 Mobile Safari/537.36 (compatible; AdsBot-Google-Mobile; +http://www.google.com/mobile/adsbot.html)",
"expect" :
{
"name" : "AdsBot-Google-Mobile",
"version" : "undefined",
"type" : "crawler"
}
},
{
"desc" : "AdSense",
"ua" : "Mediapartners-Google",
"expect" :
{
"name" : "Mediapartners-Google",
"version" : "undefined",
"type" : "crawler"
}
},
{
"desc" : "AhrefsBot",
"ua" : "Mozilla/5.0 (compatible; AhrefsBot/7.0; +http://ahrefs.com/robot/)",
@@ -49,6 +89,16 @@
"type" : "crawler"
}
},
{
"desc" : "CCBot",
"ua" : "CCBot/1.0 (+https://commoncrawl.org/bot.html)",
"expect" :
{
"name" : "CCBot",
"version" : "1.0",
"type" : "crawler"
}
},
{
"desc" : "Coc Coc Bot (web)",
"ua" : "Mozilla/5.0 (compatible; coccocbot-web/1.0; +http://help.coccoc.com/searchengine)",
@@ -79,6 +129,16 @@
"type" : "crawler"
}
},
{
"desc" : "DataForSEO",
"ua" : "Mozilla/5.0 (compatible; DataForSeoBot; +https://dataforseo.com/dataforseo-bot) ",
"expect" :
{
"name" : "DataForSeoBot",
"version" : "undefined",
"type" : "crawler"
}
},
{
"desc" : "Dotbot",
"ua" : "Mozilla/5.0 (compatible; DotBot/1.2; +https://opensiteexplorer.org/dotbot; help@moz.com)",
@@ -89,6 +149,16 @@
"type" : "crawler"
}
},
{
"desc" : "Exabot",
"ua" : "Mozilla/5.0 (compatible; Exabot/3.0; +http://www.exabot.com/go/robot)",
"expect" :
{
"name" : "Exabot",
"version" : "3.0",
"type" : "crawler"
}
},
{
"desc" : "FacebookBot",
"ua" : "Mozilla/5.0 (compatible; FacebookBot/1.0; +https://developers.facebook.com/docs/sharing/webmasters/facebookbot/",
@@ -99,6 +169,26 @@
"type" : "crawler"
}
},
{
"desc" : "FacebookExternalHit",
"ua" : "facebookexternalhit/1.1 (+http://www.facebook.com/externalhit_uatext.php)",
"expect" :
{
"name" : "facebookexternalhit",
"version" : "1.1",
"type" : "crawler"
}
},
{
"desc" : "FacebookExternalHit",
"ua" : "facebookcatalog/1.0",
"expect" :
{
"name" : "facebookcatalog",
"version" : "1.0",
"type" : "crawler"
}
},
{
"desc" : "Googlebot-Video",
"ua" : "Googlebot-Video/1.0",
@@ -109,6 +199,106 @@
"type" : "crawler"
}
},
{
"desc" : "Googlebot",
"ua" : "Mozilla/5.0 (compatible; Googlebot/2.1; +http://www.google.com/bot.html)",
"expect" :
{
"name" : "Googlebot",
"version" : "2.1",
"type" : "crawler"
}
},
{
"desc" : "Googlebot Image",
"ua" : "Googlebot-Image/1.0",
"expect" :
{
"name" : "Googlebot-Image",
"version" : "1.0",
"type" : "crawler"
}
},
{
"desc" : "Googlebot Video",
"ua" : "Googlebot-Video/1.0",
"expect" :
{
"name" : "Googlebot-Video",
"version" : "1.0",
"type" : "crawler"
}
},
{
"desc" : "Googlebot News",
"ua" : "Googlebot-News/1.0",
"expect" :
{
"name" : "Googlebot-News",
"version" : "1.0",
"type" : "crawler"
}
},
{
"desc" : "Google Storebot",
"ua" : "Storebot-Google/1.0",
"expect" :
{
"name" : "Storebot-Google",
"version" : "1.0",
"type" : "crawler"
}
},
{
"desc" : "Google InspectionTool",
"ua" : "Mozilla/5.0 (compatible; Google-InspectionTool/1.0;)",
"expect" :
{
"name" : "Google-InspectionTool",
"version" : "1.0",
"type" : "crawler"
}
},
{
"desc" : "GoogleOther",
"ua" : "Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko; compatible; GoogleOther) Chrome/41.0.2272.96 Safari/537.36",
"expect" :
{
"name" : "GoogleOther",
"version" : "undefined",
"type" : "crawler"
}
},
{
"desc" : "GoogleOther-Image",
"ua" : "GoogleOther-Image/1.0",
"expect" :
{
"name" : "GoogleOther-Image",
"version" : "1.0",
"type" : "crawler"
}
},
{
"desc" : "GoogleOther-Video",
"ua" : "GoogleOther-Video/1.0",
"expect" :
{
"name" : "GoogleOther-Video",
"version" : "1.0",
"type" : "crawler"
}
},
{
"desc" : "Google-Safety",
"ua" : "Google-Safety",
"expect" :
{
"name" : "Google-Safety",
"version" : "undefined",
"type" : "crawler"
}
},
{
"desc" : "GPTBot",
"ua" : "Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko; compatible; GPTBot/1.0; +https://openai.com/gptbot)",
@@ -119,6 +309,36 @@
"type" : "crawler"
}
},
{
"desc" : "Archive.org Bot",
"ua" : "ia_archiver/8.1 (Windows 2000 1.9; en-US;)",
"expect" :
{
"name" : "ia_archiver",
"version" : "8.1",
"type" : "crawler"
}
},
{
"desc" : "Archive.org Bot",
"ua" : "Mozilla/5.0 (compatible; archive.org_bot/3.3.0 +https://archive.org/details/archive.org_bot)",
"expect" :
{
"name" : "archive.org_bot",
"version" : "3.3.0",
"type" : "crawler"
}
},
{
"desc" : "Meta-ExternalAgent",
"ua" : "meta-externalagent/1.1 (+https://developers.facebook.com/docs/sharing/webmasters/crawler)",
"expect" :
{
"name" : "meta-externalagent",
"version" : "1.1",
"type" : "crawler"
}
},
{
"desc" : "MJ12bot",
"ua" : "Mozilla/5.0 (compatible; MJ12bot/v1.4.8; http://mj12bot.com/)",
@@ -126,6 +346,17 @@
{
"name" : "MJ12bot",
"version" : "v1.4.8",
"major" : "1",
"type" : "crawler"
}
},
{
"desc" : "MojeekBot",
"ua" : "Mozilla/5.0 (compatible; MojeekBot/0.11; +https://www.mojeek.com/bot.html)",
"expect" :
{
"name" : "MojeekBot",
"version" : "0.11",
"type" : "crawler"
}
},
@@ -139,6 +370,36 @@
"type" : "crawler"
}
},
{
"desc" : "PerplexityBot",
"ua" : "Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko; compatible; PerplexityBot/1.0; +https://perplexity.ai/perplexitybot)",
"expect" :
{
"name" : "PerplexityBot",
"version" : "1.0",
"type" : "crawler"
}
},
{
"desc" : "PetalBot",
"ua" : "Mozilla/5.0 (compatible;PetalBot; +https://webmaster.petalsearch.com/site/petalbot) ",
"expect" :
{
"name" : "PetalBot",
"version" : "undefined",
"type" : "crawler"
}
},
{
"desc" : "PetalBot",
"ua" : "Mozilla/5.0 (Linux; Android 7.0;) AppleWebKit/537.36 (KHTML, like Gecko) Mobile Safari/537.36 (compatible; PetalBot;+https://webmaster.petalsearch.com/site/petalbot) ",
"expect" :
{
"name" : "PetalBot",
"version" : "undefined",
"type" : "crawler"
}
},
{
"desc" : "SemrushBot",
"ua" : "Mozilla/5.0 (compatible; SemrushBot/7~bl; +http://www.semrush.com/bot.html)",
@@ -149,6 +410,16 @@
"type" : "crawler"
}
},
{
"desc" : "TurnitinBot",
"ua" : "TurnitinBot (https://turnitin.com/robot/crawlerinfo.html)",
"expect" :
{
"name" : "TurnitinBot",
"version" : "undefined",
"type" : "crawler"
}
},
{
"desc" : "Yahoo! Japan",
"ua" : "Y!J-BRW/1.0 (https://www.yahoo-help.jp/app/answers/detail/p/595/a_id/42716)",
@@ -168,5 +439,35 @@
"version" : "3.0",
"type" : "crawler"
}
},
{
"desc" : "Yeti",
"ua" : "Mozilla/5.0 (compatible; Yeti/1.1; +http://naver.me/spd)",
"expect" :
{
"name" : "Yeti",
"version" : "1.1",
"type" : "crawler"
}
},
{
"desc" : "YisouSpider",
"ua" : "Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.81 YisouSpider/5.0 Safari/537.36",
"expect" :
{
"name" : "YisouSpider",
"version" : "5.0",
"type" : "crawler"
}
},
{
"desc" : "YisouSpider",
"ua" : "YisouSpider",
"expect" :
{
"name" : "YisouSpider",
"version" : "undefined",
"type" : "crawler"
}
}
]

View File

@@ -29,6 +29,76 @@
"type" : "fetcher"
}
},
{
"desc" : "DuckAssistBot",
"ua" : "DuckAssistBot/1.2; (+http://duckduckgo.com/duckassistbot.html)",
"expect" :
{
"name" : "DuckAssistBot",
"version" : "1.2",
"type" : "fetcher"
}
},
{
"desc" : "Google FeedFetcher",
"ua" : "FeedFetcher-Google; (+http://www.google.com/feedfetcher.html)",
"expect" :
{
"name" : "FeedFetcher-Google",
"version" : "undefined",
"type" : "fetcher"
}
},
{
"desc" : "Google Read Aloud - Mobile agent",
"ua" : "Mozilla/5.0 (Linux; Android 7.0; SM-G930V Build/NRD90M) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/59.0.3071.125 Mobile Safari/537.36 (compatible; Google-Read-Aloud; +https://support.google.com/webmasters/answer/1061943)",
"expect" :
{
"name" : "Google-Read-Aloud",
"version" : "undefined",
"type" : "fetcher"
}
},
{
"desc" : "Google Read Aloud - Desktop agent",
"ua" : "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/41.0.2272.118 Safari/537.36 (compatible; Google-Read-Aloud; +https://support.google.com/webmasters/answer/1061943)",
"expect" :
{
"name" : "Google-Read-Aloud",
"version" : "undefined",
"type" : "fetcher"
}
},
{
"desc" : "Google Publisher Center",
"ua" : "GoogleProducer; (+https://developers.google.com/search/docs/crawling-indexing/google-producer)",
"expect" :
{
"name" : "GoogleProducer",
"version" : "undefined",
"type" : "fetcher"
}
},
{
"desc" : "Google Site Verifier",
"ua" : "Mozilla/5.0 (compatible; Google-Site-Verification/1.0)",
"expect" :
{
"name" : "Google-Site-Verification",
"version" : "1.0",
"type" : "fetcher"
}
},
{
"desc" : "Meta-ExternalFetcher",
"ua" : "meta-externalfetcher/1.1 (+https://developers.facebook.com/docs/sharing/webmasters/crawler)",
"expect" :
{
"name" : "meta-externalfetcher",
"version" : "1.1",
"type" : "fetcher"
}
},
{
"desc" : "Rogerbot",
"ua" : "Mozilla/5.0 (compatible; rogerBot/1.0; UrlCrawler; http://www.seomoz.org/dp/rogerbot)",