Created
October 27, 2019 00:30
-
-
Save sojohnnysaid/a88f935f4670359d2ab657177c013313 to your computer and use it in GitHub Desktop.
scrapping
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'); | |
const fs = require('fs'); | |
const HTMLParser = require('node-html-parser'); | |
const urls = ['https://www.tripadvisor.com/Airline_Review-d8729099-Reviews-JetBlue', | |
'https://www.tripadvisor.com/Airline_Review-d8729099-Reviews-or5-JetBlue#REVIEWS', | |
'https://www.tripadvisor.com/Airline_Review-d8729099-Reviews-or10-JetBlue#REVIEWS', | |
'https://www.tripadvisor.com/Airline_Review-d8729099-Reviews-or15-JetBlue#REVIEWS', | |
'https://www.tripadvisor.com/Airline_Review-d8729099-Reviews-or20-JetBlue#REVIEWS', | |
'https://www.tripadvisor.com/Airline_Review-d8729099-Reviews-or25-JetBlue#REVIEWS', | |
'https://www.tripadvisor.com/Airline_Review-d8729099-Reviews-or30-JetBlue#REVIEWS', | |
'https://www.tripadvisor.com/Airline_Review-d8729099-Reviews-or35-JetBlue#REVIEWS', | |
'https://www.tripadvisor.com/Airline_Review-d8729099-Reviews-or40-JetBlue#REVIEWS', | |
'https://www.tripadvisor.com/Airline_Review-d8729099-Reviews-or45-JetBlue#REVIEWS', | |
'https://www.tripadvisor.com/Airline_Review-d8729099-Reviews-or45-JetBlue#REVIEWS']; | |
(async() => { | |
for (let i = 0; i < urls.length; i++) { | |
const url = urls[i]; | |
const browser = await puppeteer.launch(); | |
const page = await browser.newPage(); | |
await page.goto(url, {waitUntil: 'networkidle0'}); | |
const html = await page.content(); | |
//save our html in a file | |
fs.writeFile('page' + i + '.html', html, _ => console.log('HTML saved')); | |
}; | |
await browser.close(); | |
})(); |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment