Created
February 18, 2020 10:23
-
-
Save himulawang/33f8740eddfd44a626ec379175427b36 to your computer and use it in GitHub Desktop.
Headless Chrome Download Images
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"); | |
let crawlPage = async (url, pageID) => { | |
const browser = await puppeteer.launch({headless:true, }); | |
const page = await browser.newPage(); | |
// prevent | |
// TimeoutError: Navigation timeout of 30000 ms exceeded | |
await page.setDefaultNavigationTimeout(0); | |
await page.goto(url); | |
await page.waitFor(1000); | |
const nodes = await page.evaluate(() => { | |
const images = document.querySelectorAll(`.chimg_photo`); | |
return [].map.call(images, img => img.src); | |
}); | |
for (let i = 0; i < nodes.length; i++) { | |
let imgURL = nodes[i]; | |
let imgPath = imgURL.split('/'); | |
let imgName = imgPath[imgPath.length - 1]; | |
let viewSource = await page.goto(imgURL); | |
fs.writeFile("./img/" + imgName, await viewSource.buffer(), function (err) { | |
if (err) { | |
return console.log(err); | |
} | |
console.log('PageID: '+ pageID + ', ' + imgName + ' downloaded.'); | |
}); | |
} | |
await browser.close(); | |
}; | |
(async() => { | |
for (let i = 60; i > 50; i--) { | |
await crawlPage('http://program.tving.com/tvn/cloy/5/Board/View?page=1&b_seq=' + i, i); | |
} | |
})(); | |
(async() => { | |
for (let i = 50; i > 40; i--) { | |
await crawlPage('http://program.tving.com/tvn/cloy/5/Board/View?page=1&b_seq=' + i, i); | |
} | |
})(); | |
(async() => { | |
for (let i = 30; i > 20; i--) { | |
await crawlPage('http://program.tving.com/tvn/cloy/5/Board/View?page=1&b_seq=' + i, i); | |
} | |
})(); |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment