How to Convert PDF Pages into Images and Combine Them Using Node.js

When working with PDFs, you may encounter scenarios where you need to convert each page of a PDF into an image and then combine those images into a single file. This task can be accomplished efficiently using Node.js and a few powerful libraries. In this article, I'll walk you through the process using three main packages: pdf-lib, jimp, and pdf2pic.

Prerequisites

node >= 14.x
graphicsmagick
ghostscript

To install GraphicsMagick, follow these steps

On macOS: Use Homebrew to install GraphicsMagick.

brew install graphicsmagick

On Linux: Use your package manager to install it. For example, on Ubuntu:

sudo apt-get install graphicsmagic

On Windows: Download and install GraphicsMagick from here.

Setting Up the Node.js Project

Create a new Node.js project and install the required libraries:

1. mkdir pdf-to-images

2. cd pdf-to-images

3. npm init -y

4. npm install pdf-lib jimp pdf2pic

Step 1: Reading and Counting Pages in the PDF

The first step is to read the PDF file and count the number of pages using pdf-lib.

const { PDFDocument } = require('pdf-lib');
const fs = require('fs');

async function getPdfPageCount(pdfPath) {
  const pdfData = fs.readFileSync(pdfPath);
  const pdfDoc = await PDFDocument.load(pdfData);
  return pdfDoc.getPageCount();
}

(async () => {
  const pageCount = await getPdfPageCount('sample.pdf');
  console.log(`The PDF has ${pageCount} pages.`);
})();

Step 2: Converting PDF Pages to Images

Now that we know how many pages are in the PDF, we can convert each page into an image using pdf2pic.

const { fromPath } = require('pdf2pic');

async function convertPdfToImages(pdfPath) {
  const pdf2pic = fromPath(pdfPath, {
    density: 300, // DPI
    saveFilename: 'page',
    savePath: '.',
    format: 'png',
    width: 800,
    height: 1000
  });

  const pageCount = await getPdfPageCount(pdfPath);

  for (let i = 1; i <= pageCount; i++) {
    await pdf2pic(i); // Convert each page to an image
    console.log(`Converted page ${i} to image.`);
  }
}

(async () => {
  await convertPdfToImages('sample.pdf');
})();

Step 3: Combining the Images

After converting the PDF pages into images, the final step is to combine these images into a single image using jimp.

const Jimp = require('jimp');

async function combineImages(imagePaths, outputPath) {
  const images = await Promise.all(imagePaths.map(path => Jimp.read(path)));
  
  const totalHeight = images.reduce((sum, img) => sum + img.bitmap.height, 0);
  const maxWidth = Math.max(...images.map(img => img.bitmap.width));

  const combinedImage = new Jimp(maxWidth, totalHeight);

  let yOffset = 0;
  for (const img of images) {
    combinedImage.composite(img, 0, yOffset);
    yOffset += img.bitmap.height;
  }

  await combinedImage.writeAsync(outputPath);
  console.log('Combined image saved to', outputPath);
}

(async () => {
  const imagePaths = ['./images/page1.png', './images/page2.png']; // Add paths to all your images
  await combineImages(imagePaths, 'combined-image.png');
})();

Combining all the code:-

const { PDFDocument } = require('pdf-lib');
const fs = require('fs');
const { fromPath } = require('pdf2pic');
const Jimp = require('jimp');

// Step 1: Reading and Counting Pages in the PDF
async function getPdfPageCount(pdfPath) {
  const pdfData = fs.readFileSync(pdfPath);
  const pdfDoc = await PDFDocument.load(pdfData);
  return pdfDoc.getPageCount();
}

// Step 2: Converting PDF Pages to Images
async function convertPdfToImages(pdfPath) {
  const pdf2pic = fromPath(pdfPath, {
    density: 300, // DPI
    saveFilename: 'page',
    savePath: '.',
    format: 'png',
    width: 800,
    height: 1000
  });

  const pageCount = await getPdfPageCount(pdfPath);
  const imagePaths = [];

  for (let i = 1; i <= pageCount; i++) {
    const outputFile = await pdf2pic(i); // Convert each page to an image
    imagePaths.push(outputFile.path); // Store the path to the generated image
    console.log(`Converted page ${i} to image.`);
  }

  return imagePaths;
}

// Step 3: Combining the Images
async function combineImages(imagePaths, outputPath) {
  const images = await Promise.all(imagePaths.map(path => Jimp.read(path)));
  
  const totalHeight = images.reduce((sum, img) => sum + img.bitmap.height, 0);
  const maxWidth = Math.max(...images.map(img => img.bitmap.width));

  const combinedImage = new Jimp(maxWidth, totalHeight);

  let yOffset = 0;
  for (const img of images) {
    combinedImage.composite(img, 0, yOffset);
    yOffset += img.bitmap.height;
  }

  await combinedImage.writeAsync(outputPath);
  console.log('Combined image saved to', outputPath);
}

// Main function to execute the steps
(async () => {
  const pdfPath = 'file.pdf';
  const outputImagePath = 'combined-image.png';

  // Convert PDF pages to images
  const imagePaths = await convertPdfToImages(pdfPath);

  // Combine images into a single image
  await combineImages(imagePaths, outputImagePath);
})();

Conclusion

By following the steps outlined above, you can successfully convert a PDF's pages into images and then combine those images into a single file using Node.js. The pdf-lib library allows us to read and count PDF pages, pdf2pic handles the conversion of pages to images, and jimp enables the combination of these images into one.

Header Ads Widget

How to Convert PDF Pages into Images and Combine Them Using Node.js