Created
October 24, 2017 17:27
-
-
Save bmorelli25/6f78f8d9c6bd2c1de733078091bfb4cf to your computer and use it in GitHub Desktop.
Scrape all books on the hompage
This file contains hidden or 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'); | |
let scrape = async () => { | |
const browser = await puppeteer.launch({headless: false}); | |
const page = await browser.newPage(); | |
await page.goto('http://books.toscrape.com/'); | |
const result = await page.evaluate(() => { | |
let data = []; // Create an empty array that will store our data | |
let elements = document.querySelectorAll('.product_pod'); // Select all Products | |
for (var element of elements){ // Loop through each proudct | |
let title = element.childNodes[5].innerText; // Select the title | |
let price = element.childNodes[7].children[0].innerText; // Select the price | |
data.push({title, price}); // Push an object with the data onto our array | |
} | |
return data; // Return our data array | |
}); | |
browser.close(); | |
return result; // Return the data | |
}; | |
scrape().then((value) => { | |
console.log(value); // Success! | |
}); |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment