Created
December 28, 2022 06:01
-
-
Save r-shafi/0dcd097a19ddea17ff7c4ba0eb0d816d to your computer and use it in GitHub Desktop.
A working modal data scraper. This uses Puppeteer to scrape user data from a forum. Error handling included.
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 puppeteer = require('puppeteer'); | |
async function scrape() { | |
const browser = await puppeteer.launch({ headless: false }); | |
const page = await browser.newPage(); | |
await page.goto('https://forum.freecodecamp.org/'); | |
const avatars = await page.$$('.topic-poster img.avatar'); | |
const names = []; | |
for (const avatar of avatars) { | |
try { | |
await page.evaluate((element) => element.click(), avatar); | |
await page.waitForSelector('.user-card.show', { timeout: 5000 }); | |
let userNameElement = null; | |
let fullNameElement = null; | |
try { | |
userNameElement = await page.waitForSelector( | |
'.user-card.show .name-username-wrapper', | |
{ | |
timeout: 2000, | |
} | |
); | |
} catch (error) { | |
console.log(error.message); | |
} | |
try { | |
fullNameElement = await page.waitForSelector( | |
'.user-card.show .full-name', | |
{ | |
timeout: 2000, | |
} | |
); | |
} catch (error) { | |
console.log(error.message); | |
} | |
let userName = null; | |
let fullName = null; | |
if (userNameElement) { | |
userName = await page.evaluate( | |
(element) => element.textContent.trim(), | |
userNameElement | |
); | |
} | |
if (fullNameElement) { | |
fullName = await page.evaluate( | |
(element) => element.textContent.trim(), | |
fullNameElement | |
); | |
} | |
names.push({ | |
userName, | |
fullName, | |
}); | |
await new Promise((resolve) => setTimeout(resolve, 500)); | |
} catch (error) { | |
console.error(error.message); | |
continue; | |
} | |
} | |
await browser.close(); | |
console.log(names); | |
} | |
scrape(); |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment