Created
November 22, 2018 09:21
-
-
Save dvas0004/7d6b673c985e40754858385fd50ef010 to your computer and use it in GitHub Desktop.
Employee Harvesting from Linked In (companion code to blog post)
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
const linkedinEmail = '*******'; | |
const linkedinPassword = '*******'; | |
const companyName = 'CHANGE ME'; | |
const extraFilter = 'change me (or set to null)'; | |
const maxPages = 2; | |
//////// | |
const puppeteer = require('puppeteer'); | |
(async () => { | |
const browser = await puppeteer.launch({headless: false}); | |
const page = await browser.newPage(); | |
const encodedCompanyName = encodeURIComponent(companyName) | |
// Login | |
await page.goto('https://www.linkedin.com'); | |
await page.waitForSelector('#login-email'); | |
await page.type('#login-email', linkedinEmail); | |
await page.type('#login-password', linkedinPassword); | |
await page.click('#login-submit'); | |
await page.waitFor(5000); | |
let users = []; | |
for (let pageNumber=1; pageNumber <= maxPages; pageNumber++){ | |
await page.goto(`https://www.linkedin.com/search/results/all/?keywords=${encodedCompanyName}&page=${pageNumber}`); | |
await page.waitForSelector('#nav-settings__dropdown-trigger > img'); | |
await page.evaluate(()=>{ | |
window.scrollTo(0,document.body.scrollHeight); | |
}); | |
await page.waitFor(5000); | |
let results = await page.evaluate( (extraFilter)=>{ | |
let pageUsers = []; | |
let pagePositions = []; | |
let pageResults = []; | |
Array.from(document.getElementsByClassName('actor-name')).forEach( el => pageUsers.push(el.textContent)); | |
Array.from(document.querySelectorAll('span[dir="ltr"]')).forEach( el => pagePositions.push(el.innerHTML)); | |
let innerCounter = 0; | |
for (let counter = 0; counter < pageUsers.length; counter++){ | |
const fullPosition = `${pagePositions[innerCounter]}, ${pagePositions[innerCounter+1]}`; | |
if (extraFilter && fullPosition.toLowerCase().indexOf(extraFilter.toLowerCase()) >= 0){ | |
pageResults.push(`${pageUsers[counter]} : ${fullPosition}`); | |
} else if (extraFilter===null){ | |
pageResults.push(`${pageUsers[counter]} : ${fullPosition}`); | |
} | |
innerCounter = innerCounter +2; | |
} | |
return pageResults; | |
}, extraFilter); | |
users = users.concat(results); | |
} | |
console.log(users); | |
await browser.close(); | |
})(); |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment