Crawler Detect

November 16, 2024 ยท View on GitHub



crawlerdetect.io

DeepScan grade Static Badge npm version NPM Downloads contributions welcome

About

This Library is an ES6 version of the original PHP class @CrawlerDetect, it helps you detect bots/crawlers and spiders only by scanning the user-agent string or from the global request.headers.

Installation

npm install es6-crawler-detect

Usage

ECMAScript 6 (ES6)

'use strict';

const express = require('express')
const { Crawler, middleware } = require('es6-crawler-detect')

const app = express()

app.get('your/route', function async (request, response) {
  // create a new Crawler instance
  var CrawlerDetector = new Crawler(request)
  
  // check the current visitor's useragent
  if ( CrawlerDetector.isCrawler() )
  {
    // true if crawler user agent detected
  }
  
  // or check a user agent string
  if ( CrawlerDetector.isCrawler('Mozilla/5.0 (compatible; Sosospider/2.0; +http://help.soso.com/webspider.htm)') )
  {
    // true if crawler user agent detected
  }
  
  // Output the name of the bot that matched (if any)
  response.send(CrawlerDetector.getMatches())
})

/**
 * Or by using the middleware
*/
app.use(middleware((request, reponse) => {
  // do something here
  // e.g. console.log(request.body)
  // e.g. return response.status(403).send('Forbidden')
}))

app.get('/crawler', function async (request, response) {
  // or check a user agent string
  request.Crawler.isCrawler('Mozilla/5.0 (compatible; Sosospider/2.0; +http://help.soso.com/webspider.htm)')
  
  // Output the name of the bot that matched (if any)
  response.send(request.Crawler.getMatches())
})

TypeScript

import { Crawler, middleware } from 'es6-crawler-detect'

const CrawlerDetector = new Crawler()

// check the current visitor's useragent
if ( CrawlerDetector.isCrawler() )
{
  // true if crawler user agent detected
}

// or check a user agent string
if ( CrawlerDetector.isCrawler('Mozilla/5.0 (compatible; Sosospider/2.0; +http://help.soso.com/webspider.htm)') )
{
  // true if crawler user agent detected
}

// Output the name of the bot that matched (if any)
console.log(CrawlerDetector.getMatches())

/**
 * Or by using the middleware
*/
middleware((request, reponse) => {
  // do something here
  // e.g. console.log(request.body)
  // e.g. return response.status(403).send('Forbidden')
})

Contributing

If you find a bot/spider/crawler user agent that CrawlerDetect fails to detect, please submit a pull request with the regex pattern added to the data array in ./crawler/crawlers.ts.