1
0
mirror of https://github.com/lancedikson/bowser synced 2026-03-02 03:40:27 +00:00

Add support for AI crawl bots

This commit is contained in:
naorpeled
2025-11-22 16:56:19 +02:00
parent 771dfb2dfe
commit fdd5a5e8e6
3 changed files with 344 additions and 0 deletions

View File

@@ -1,6 +1,7 @@
// NOTE: this list must be up-to-date with browsers listed in
// test/acceptance/useragentstrings.yml
export const BROWSER_ALIASES_MAP = {
'Applebot-Extended': 'applebot_extended',
AmazonBot: 'amazonbot',
'Amazon Silk': 'amazon_silk',
'Android Browser': 'android',
@@ -9,15 +10,21 @@ export const BROWSER_ALIASES_MAP = {
BingCrawler: 'bingcrawler',
BlackBerry: 'blackberry',
Chrome: 'chrome',
'ChatGPT-User': 'chatgpt_user',
ClaudeBot: 'claudebot',
Chromium: 'chromium',
Diffbot: 'diffbot',
DuckDuckBot: 'duckduckbot',
Electron: 'electron',
Epiphany: 'epiphany',
FacebookBot: 'facebookbot',
Firefox: 'firefox',
Focus: 'focus',
Generic: 'generic',
'Google Search': 'google_search',
'Google-Extended': 'google_extended',
Googlebot: 'googlebot',
GPTBot: 'gptbot',
'Internet Explorer': 'ie',
InternetArchiveCrawler: 'internetarchivecrawler',
'K-Meleon': 'k_meleon',
@@ -26,11 +33,14 @@ export const BROWSER_ALIASES_MAP = {
'Microsoft Edge': 'edge',
'MZ Browser': 'mz',
'NAVER Whale Browser': 'naver',
'OAI-SearchBot': 'oai_searchbot',
Omgilibot: 'omgilibot',
Opera: 'opera',
'Opera Coast': 'opera_coast',
'Pale Moon': 'pale_moon',
PhantomJS: 'phantomjs',
PingdomBot: 'pingdombot',
PerplexityBot: 'perplexitybot',
Puffin: 'puffin',
QQ: 'qq',
QQLite: 'qqlite',
@@ -50,9 +60,11 @@ export const BROWSER_ALIASES_MAP = {
YahooSlurp: 'yahooslurp',
'Yandex Browser': 'yandex',
YandexBot: 'yandexbot',
YouBot: 'youbot',
};
export const BROWSER_MAP = {
applebot_extended: 'Applebot-Extended',
amazonbot: 'AmazonBot',
amazon_silk: 'Amazon Silk',
android: 'Android Browser',
@@ -61,16 +73,22 @@ export const BROWSER_MAP = {
bingcrawler: 'BingCrawler',
blackberry: 'BlackBerry',
chrome: 'Chrome',
chatgpt_user: 'ChatGPT-User',
claudebot: 'ClaudeBot',
chromium: 'Chromium',
diffbot: 'Diffbot',
duckduckbot: 'DuckDuckBot',
edge: 'Microsoft Edge',
electron: 'Electron',
epiphany: 'Epiphany',
facebookbot: 'FacebookBot',
firefox: 'Firefox',
focus: 'Focus',
generic: 'Generic',
google_extended: 'Google-Extended',
google_search: 'Google Search',
googlebot: 'Googlebot',
gptbot: 'GPTBot',
ie: 'Internet Explorer',
internetarchivecrawler: 'InternetArchiveCrawler',
k_meleon: 'K-Meleon',
@@ -83,6 +101,9 @@ export const BROWSER_MAP = {
pale_moon: 'Pale Moon',
phantomjs: 'PhantomJS',
pingdombot: 'PingdomBot',
perplexitybot: 'PerplexityBot',
oai_searchbot: 'OAI-SearchBot',
omgilibot: 'Omgilibot',
puffin: 'Puffin',
qq: 'QQ Browser',
qqlite: 'QQ Browser Lite',
@@ -102,6 +123,7 @@ export const BROWSER_MAP = {
yahooslurp: 'YahooSlurp',
yandex: 'Yandex Browser',
yandexbot: 'YandexBot',
youbot: 'YouBot',
};
export const PLATFORMS_MAP = {

View File

@@ -28,6 +28,193 @@ import Utils from './utils.js';
const commonVersionIdentifier = /version\/(\d+(\.?_?\d+)+)/i;
const browsersList = [
/* GPTBot */
{
test: [/gptbot/i],
describe(ua) {
const browser = {
name: 'GPTBot',
};
const version = Utils.getFirstMatch(/gptbot\/(\d+(\.\d+)+)/i, ua) || Utils.getFirstMatch(commonVersionIdentifier, ua);
if (version) {
browser.version = version;
}
return browser;
},
},
/* ChatGPT-User */
{
test: [/chatgpt-user/i],
describe(ua) {
const browser = {
name: 'ChatGPT-User',
};
const version = Utils.getFirstMatch(/chatgpt-user\/(\d+(\.\d+)+)/i, ua) || Utils.getFirstMatch(commonVersionIdentifier, ua);
if (version) {
browser.version = version;
}
return browser;
},
},
/* OAI-SearchBot */
{
test: [/oai-searchbot/i],
describe(ua) {
const browser = {
name: 'OAI-SearchBot',
};
const version = Utils.getFirstMatch(/oai-searchbot\/(\d+(\.\d+)+)/i, ua) || Utils.getFirstMatch(commonVersionIdentifier, ua);
if (version) {
browser.version = version;
}
return browser;
},
},
/* Google-Extended */
{
test: [/google-extended/i],
describe(ua) {
const browser = {
name: 'Google-Extended',
};
const version = Utils.getFirstMatch(/google-extended\/(\d+(\.\d+)+)/i, ua) || Utils.getFirstMatch(commonVersionIdentifier, ua);
if (version) {
browser.version = version;
}
return browser;
},
},
/* Applebot-Extended */
{
test: [/applebot-extended/i],
describe(ua) {
const browser = {
name: 'Applebot-Extended',
};
const version = Utils.getFirstMatch(/applebot-extended\/(\d+(\.\d+)+)/i, ua) || Utils.getFirstMatch(commonVersionIdentifier, ua);
if (version) {
browser.version = version;
}
return browser;
},
},
/* ClaudeBot */
{
test: [/claudebot/i, /claude-web/i],
describe(ua) {
const browser = {
name: 'ClaudeBot',
};
const version = Utils.getFirstMatch(/(?:claudebot|claude-web)\/(\d+(\.\d+)+)/i, ua) || Utils.getFirstMatch(commonVersionIdentifier, ua);
if (version) {
browser.version = version;
}
return browser;
},
},
/* Omgilibot */
{
test: [/omgilibot/i],
describe(ua) {
const browser = {
name: 'Omgilibot',
};
const version = Utils.getFirstMatch(/omgilibot\/(\d+(\.\d+)+)/i, ua) || Utils.getFirstMatch(commonVersionIdentifier, ua);
if (version) {
browser.version = version;
}
return browser;
},
},
/* FacebookBot */
{
test: [/facebookbot/i],
describe(ua) {
const browser = {
name: 'FacebookBot',
};
const version = Utils.getFirstMatch(/facebookbot\/(\d+(\.\d+)+)/i, ua) || Utils.getFirstMatch(commonVersionIdentifier, ua);
if (version) {
browser.version = version;
}
return browser;
},
},
/* Diffbot */
{
test: [/diffbot/i],
describe(ua) {
const browser = {
name: 'Diffbot',
};
const version = Utils.getFirstMatch(/diffbot\/(\d+(\.\d+)+)/i, ua) || Utils.getFirstMatch(commonVersionIdentifier, ua);
if (version) {
browser.version = version;
}
return browser;
},
},
/* PerplexityBot */
{
test: [/perplexitybot/i],
describe(ua) {
const browser = {
name: 'PerplexityBot',
};
const version = Utils.getFirstMatch(/perplexitybot\/(\d+(\.\d+)+)/i, ua) || Utils.getFirstMatch(commonVersionIdentifier, ua);
if (version) {
browser.version = version;
}
return browser;
},
},
/* YouBot */
{
test: [/youbot/i],
describe(ua) {
const browser = {
name: 'YouBot',
};
const version = Utils.getFirstMatch(/youbot\/(\d+(\.\d+)+)/i, ua) || Utils.getFirstMatch(commonVersionIdentifier, ua);
if (version) {
browser.version = version;
}
return browser;
},
},
/* Googlebot */
{
test: [/googlebot/i],