Node.js で PDF ページを画像に変換する方法

const fs = require('fs');
const path = require('path');
const pdfjs = require('pdfjs-dist/legacy/build/pdf.js');
const Canvas = require('canvas');

/**
 * Converts a PDF to images by rendering each page and saving them to a local directory.
 * 
 * @param {Buffer} pdfBuffer - The PDF file as a buffer.
 * @param {string} outputDir - The directory where images will be saved.
 * @returns {Promise<void>} Resolves when all images are saved.
 */
async function convertPdfToImages(pdfBuffer, outputDir) {
  try {
    // Ensure the output directory exists
    if (!fs.existsSync(outputDir)) {
      fs.mkdirSync(outputDir, { recursive: true });
    }

    // Load the original PDF using pdf.js
    const loadingTask = pdfjs.getDocument({ data: pdfBuffer });
    const pdfDocument = await loadingTask.promise;

    // Loop through each page of the PDF
    for (let i = 1; i <= pdfDocument.numPages; i++) {
      const page = await pdfDocument.getPage(i);

      // Render the page as an image and save it
      const imageBuffer = await renderPageToImage(page);

      // Save the image to the output directory
      const imagePath = path.join(outputDir, `page_${i}.jpg`);
      fs.writeFileSync(imagePath, imageBuffer);
      console.log(`Saved: ${imagePath}`);
    }
  } catch (error) {
    console.error('Error converting PDF to images:', error);
  }
}

/**
 * Renders a single PDF page to an image buffer.
 * 
 * @param {PDFPageProxy} page - The PDF.js page object.
 * @returns {Promise<Buffer>} The image as a buffer (JPEG format).
 */
async function renderPageToImage(page) {
  // Scale the page to 2x for a higher quality image output
  const viewport = page.getViewport({ scale: 2.0 });
  const canvas = Canvas.createCanvas(viewport.width, viewport.height);
  const context = canvas.getContext('2d');

  const renderContext = {
    canvasContext: context,
    viewport: viewport,
  };

  // Render the PDF page to the canvas
  await page.render(renderContext).promise;

  // Convert the canvas content to a JPEG image buffer and return it
  return canvas.toBuffer('image/jpeg');
}

// Example usage:
// const pdfBuffer = fs.readFileSync('sample.pdf');
// convertPdfToImages(pdfBuffer, './output_images');

const loadingTask = pdfjs.getDocument({ data: pdfBuffer });
const pdfDocument = await loadingTask.promise;

const page = await pdfDocument.getPage(pageNumber);
const renderContext = {
  canvasContext: context,
  viewport: viewport,
};
await page.render(renderContext).promise;

fs.writeFileSync(imagePath, imageBuffer);