PHPnews.io

Building a Website Screenshot API with Puppeteer and Google Cloud Functions

Written by Bram.us / Original link on Dec. 2, 2019

website-screenshot-api.png

Here’s the source of a Google Cloud function that, using Puppeteer, takes a screenshot of a given website and store the resulting screenshot in a bucket on Google Cloud Storage:

const puppeteer = require('puppeteer');
const { Storage } = require('@google-cloud/storage');

const GOOGLE_CLOUD_PROJECT_ID = "screenshotapi";
const BUCKET_NAME = "screenshot-api-net";

exports.run = async (req, res) => {
  res.setHeader("content-type", "application/json");
  
  try {
    const buffer = await takeScreenshot(req.body);
    
    let screenshotUrl = await uploadToGoogleCloud(buffer, "screenshot.png");
    
    res.status(200).send(JSON.stringify({
      'screenshotUrl': screenshotUrl
    }));
    
  } catch(error) {
    res.status(422).send(JSON.stringify({
      error: error.message,
    }));
  }
};

async function uploadToGoogleCloud(buffer, filename) {
    const storage = new Storage({
        projectId: GOOGLE_CLOUD_PROJECT_ID,
    });

    const bucket = storage.bucket(BUCKET_NAME);

    const file = bucket.file(filename);
    await uploadBuffer(file, buffer, filename);
  
    await file.makePublic();

  	return `https://${BUCKET_NAME}.storage.googleapis.com/${filename}`;
}

async function takeScreenshot(params) {
	const browser = await puppeteer.launch({
		args: ['--no-sandbox']
	});
	const page = await browser.newPage();
	await page.goto(params.url, {waitUntil: 'networkidle2'});

	const buffer = await page.screenshot();

	await page.close();
	await browser.close();
  
  	return buffer;
}

async function uploadBuffer(file, buffer, filename) {
    return new Promise((resolve) => {
        file.save(buffer, { destination: filename }, () => {
            resolve();
        });
    })
}

Usage:

curl -X POST -d '{"url": "https://github.com"}' https://google-cloud-endpoint/my-function

Building a Website Screenshot API →

💡 If I were to run this in production I’d extend the code to first check the presence of an existing screenshot in the bucket or not, and – if the screenshot is not too old – redirect to it.

bram elsewhere link puppeteer screenshot bram

« Manage React State with zustand - Automatically upgrade your PHP code from 5.3 to PHP 7.4 with Rector »