Serverless HTML to PDF with AWS Lambda + Chrome

README.md

AWS Lambda Image/PDF Capture

Puppeteer

To deploy Puppeteer in AWS Lambda we need to use a slim version of chromium, and layers.

Get the supported versions from this list.

npm install puppeteer-core@$PUPPETEER_VERSION
npm install @sparticuz/chromium@$CHROMIUM_VERSION

To configure puppeteer:

const browser = await puppeteer.launch({
  args: chromium.args,
  defaultViewport: chromium.defaultViewport,
  executablePath: await chromium.executablePath(),
  headless: chromium.headless,
  ignoreHTTPSErrors: true,
});

Alternative option to render content:

await page.setContent(html);

const content = await page.$("body");
const imageBuffer = await content.screenshot({ omitBackground: true });

Send image to S3:

const s3File = await s3.putObject({
  bucket: "<Your Bucket Name Here>",
  key: `${screenshot}.png`,
  body: imageBuffer,
  contentType: "image/png",
});

Links

How to setup an S3 bucket and access from the lambda function here. Create a layer.

payload.json

{
  "html": "<p>Hello, world!</p>",
  "format": "image|pdf"
}

web2pdf.js

const chromium = require('chrome-aws-lambda');
const fs = require('fs');

exports.handler = async (event, context, callback) => {
  let result = null;
  let browser = null;

  try {
    browser = await chromium.puppeteer.launch({
      args: chromium.args,
      defaultViewport: chromium.defaultViewport,
      executablePath: await chromium.executablePath(
        process.env.AWS_EXECUTION_ENV
          ? '/opt/nodejs/node_modules/@sparticuz/chromium/bin'
          : undefined,
      ),
      headless: chromium.headless,
      ignoreHTTPSErrors: true,
    });
    
    // this guarantees that the file won't conflict with other files
    // that could possibly be generated at the same time
    //
    // this is assuming of course that the file system in lambda
    // is shared and that we don't want name conflicts to occur
    // if the function is invoked at the same time
    let fileName = Date.now(); 
    
    fs.writeFileSync(`/tmp/${fileName}.html`, event.html);

    const page = await browser.newPage();

    await page.goto(`file:///tmp/${fileName}.html`);
    
    if (event.format === 'pdf') {
      result = await makePDF(page);
    } else {
      result = await makeImage(page);
    }
    result = result.toString('base64');
  } catch (error) {
    return callback(error);
  } finally {
    if (browser !== null) {
      await page.close();
      await browser.close();
    }
  }

  return callback(null, result);
};

function makeImage(page, filename='screenshot.png') {
  return page.screenshot({path: filename});
}

function makePDF(page) {
  return page.pdf({
      displayHeaderFooter: false,
      printBackground: true,
      margin: {
        'top': '0.4in',
        'bottom': '0.4in',
        'left': '0.4in',
        'right': '0.4in'
      }
    });
}

Golang browser drivers and more:

• rod: A Chrome DevTools Protocol driver for web automation and scraping.
• chromedp: A faster, simpler way to drive browsers supporting the Chrome DevTools Protocol.
• playwright-go: Playwright for Go a browser automation library to control Chromium, Firefox and WebKit with a single API.