Created
November 28, 2017 06:46
-
-
Save pshapiro/2258dd1128d7ad37b38731bc4af6512d to your computer and use it in GitHub Desktop.
Puppeteer Crawler Example
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
var Walker = require('puppeteer-walker') | |
var fs = require('fs') | |
var walker = Walker() | |
fs.writeFile('output.csv', 'URL, Title, H2\r\n', 'utf8', function (err) { | |
console.log(`Header written`) | |
}) | |
walker.on('end', () => console.log('finished walking')) | |
walker.on('error', (err) => console.log('error', err)) | |
walker.on('page', async (page) => { | |
var url = await page.url() | |
var title = await page.title() | |
try { | |
var h2 = await page.evaluate(() => document.querySelector('h2').innerText); | |
fs.appendFile('output.csv', `${url}, ${title}, ${h2}\r\n`, 'utf8', function (err) { | |
console.log( | |
`url: ${url}, title: ${title}, h2: ${h2}`) | |
}) | |
} catch(e) { | |
fs.appendFile('output.csv', `${url}, ${title}, ERROR\r\n`, 'utf8', function (err) { | |
console.log( | |
`url: ${url}, title: ${title}, h2: ERROR`) | |
}) | |
} | |
}) | |
walker.walk('http://jsseo.expert/') |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment