如何在Node.js中跨操作系统转换文档、图片、文本为PDF？

Got it, let's solve this cross-platform PDF conversion challenge in Node.js. The node-msoffice-pdf tool’s limitation makes total sense—it relies on Microsoft Office, which is only fully supported on Windows (and has quirks on macOS). So we need platform-agnostic tools that work everywhere. Here’s how to handle each file type:

The best cross-platform solution here is LibreOffice/OpenOffice, which has a headless command-line interface we can call from Node.js. It supports most Office formats (docx, xlsx, pptx, etc.) and runs on Windows, macOS, and Linux.

Step 1: Install LibreOffice on all systems #

• Windows: Download from the official site, ensure soffice.exe is added to your system PATH
• macOS: Run brew install libreoffice via Homebrew
• Linux (Debian/Ubuntu): Run sudo apt install libreoffice

Step 2: Node.js Code #

const { exec } = require('child_process');
const path = require('path');

function convertOfficeToPdf(inputPath, outputDir) {
  return new Promise((resolve, reject) => {
    const resolvedInput = path.resolve(inputPath);
    const resolvedOutput = path.resolve(outputDir);
    
    // Cross-platform LibreOffice command
    const cmd = `soffice --headless --convert-to pdf --outdir "${resolvedOutput}" "${resolvedInput}"`;
    
    exec(cmd, (error, stdout, stderr) => {
      if (error) {
        reject(new Error(`Conversion failed: ${stderr || error.message}`));
        return;
      }
      // LibreOffice uses the input filename with a .pdf extension by default
      const pdfPath = path.join(resolvedOutput, path.basename(resolvedInput, path.extname(resolvedInput)) + '.pdf');
      resolve(pdfPath);
    });
  });
}

// Example usage
convertOfficeToPdf('./annual-report.docx', './output')
  .then(pdfPath => console.log(`PDF saved to: ${pdfPath}`))
  .catch(err => console.error(err));

Use sharp—a fast, cross-platform image processing library built on libvips. It handles single-image-to-PDF conversion seamlessly.

Step 1: Install Sharp #

npm install sharp

Step 2: Node.js Code #

const sharp = require('sharp');
const path = require('path');

function convertImageToPdf(inputPath, outputPath) {
  return sharp(inputPath)
    .pdf()
    .toFile(outputPath)
    .then(() => outputPath)
    .catch(err => Promise.reject(new Error(`Image conversion failed: ${err.message}`)));
}

// Example usage
convertImageToPdf('./product-photo.png', './product-photo.pdf')
  .then(pdfPath => console.log(`PDF saved to: ${pdfPath}`))
  .catch(err => console.error(err));

Note: For multiple images, convert each to a PDF page then merge them using a library like pdf-lib.

Pure Text (TXT) #

Use pdf-lib to create a PDF from scratch and render text directly.

Step 1: Install pdf-lib

npm install pdf-lib

Step 2: Node.js Code

const { PDFDocument, StandardFonts, rgb } = require('pdf-lib');
const fs = require('fs').promises;

async function convertTextToPdf(inputPath, outputPath) {
  const textContent = await fs.readFile(inputPath, 'utf8');
  const pdfDoc = await PDFDocument.create();
  const page = pdfDoc.addPage([600, 800]); // A4-like dimensions in points

  // Load a standard font
  const helveticaFont = await pdfDoc.embedFont(StandardFonts.Helvetica);
  page.setFont(helveticaFont);
  page.setFontSize(12);
  page.setTextColor(rgb(0, 0, 0));

  // Render text with line breaks
  const lines = textContent.split('\n');
  let yPosition = 750; // Start near the top of the page
  const lineHeight = 15;

  for (const line of lines) {
    if (yPosition < 50) { // Add new page if we hit the bottom
      const newPage = pdfDoc.addPage([600, 800]);
      newPage.setFont(helveticaFont);
      newPage.setFontSize(12);
      newPage.setTextColor(rgb(0, 0, 0));
      yPosition = 750;
    }
    page.drawText(line, { x: 50, y: yPosition });
    yPosition -= lineHeight;
  }

  const pdfBytes = await pdfDoc.save();
  await fs.writeFile(outputPath, pdfBytes);
  return outputPath;
}

// Example usage
convertTextToPdf('./notes.txt', './notes.pdf')
  .then(pdfPath => console.log(`PDF saved to: ${pdfPath}`))
  .catch(err => console.error(err));

Markdown (MD) #

First convert Markdown to HTML with marked, then render the HTML to PDF using Puppeteer (headless Chrome), which ensures consistent styling across platforms.

Step 1: Install Dependencies

npm install marked puppeteer

Step 2: Node.js Code

const marked = require('marked');
const puppeteer = require('puppeteer');
const fs = require('fs').promises;

async function convertMarkdownToPdf(inputPath, outputPath) {
  const mdContent = await fs.readFile(inputPath, 'utf8');
  const htmlContent = marked.parse(mdContent);

  // Wrap HTML in a styled template for better PDF output
  const fullHtml = `
    <!DOCTYPE html>
    <html>
      <head>
        <style>
          body { font-family: Arial, sans-serif; margin: 2rem; line-height: 1.6; }
          h1, h2, h3 { color: #2d3748; }
          code { background: #f7fafc; padding: 0.2rem; border-radius: 0.2rem; }
          pre { background: #f7fafc; padding: 1rem; border-radius: 0.5rem; overflow-x: auto; }
        </style>
      </head>
      <body>${htmlContent}</body>
    </html>
  `;

  const browser = await puppeteer.launch({ headless: 'new' });
  const page = await browser.newPage();
  await page.setContent(fullHtml);

  await page.pdf({
    path: outputPath,
    format: 'A4',
    margin: { top: '1cm', right: '1cm', bottom: '1cm', left: '1cm' }
  });

  await browser.close();
  return outputPath;
}

// Example usage
convertMarkdownToPdf('./readme.md', './readme.pdf')
  .then(pdfPath => console.log(`PDF saved to: ${pdfPath}`))
  .catch(err => console.error(err));

You can wrap all these functions into a single helper to auto-detect file types:

const path = require('path');

async function convertFileToPdf(inputPath, outputPath) {
  const ext = path.extname(inputPath).toLowerCase();

  switch (ext) {
    case '.docx': case '.doc': case '.xlsx': case '.xls': case '.pptx': case '.ppt':
      return convertOfficeToPdf(inputPath, path.dirname(outputPath));
    case '.jpg': case '.jpeg': case '.png': case '.gif': case '.bmp':
      return convertImageToPdf(inputPath, outputPath);
    case '.txt':
      return convertTextToPdf(inputPath, outputPath);
    case '.md':
      return convertMarkdownToPdf(inputPath, outputPath);
    default:
      throw new Error(`Unsupported file type: ${ext}`);
  }
}

内容的提问来源于stack exchange，提问作者Hiten