Node.js NodeJS：使用读取的缓冲区将两个PDF文件合并为一个

我正在使用填充pdf npm模块填充模板pdf，它创建了新文件，该文件从磁盘读取并作为缓冲返回回调。我有两个文件，对它们执行相同的操作。我想将两个缓冲区组合在一起，形成一个pdf文件，然后发送回客户端。我尝试了不同的缓冲区连接方法。可以使用buffer.concat连接缓冲区，如

var newBuffer = Buffer.concat([result_pdf.output, result_pdf_new.output]);

新缓冲区的大小也是输入缓冲区大小的总和。但是当

newBuffer

作为响应发送到客户机时，它仍然只显示数组中最后提到的文件

res.type("application/pdf");
return res.send(buffer);

有什么想法吗？

支持使用其方法组合PDF

使用流处理缓冲区的示例：

const hummus = require('hummus');
const memoryStreams = require('memory-streams');

/**
 * Concatenate two PDFs in Buffers
 * @param {Buffer} firstBuffer 
 * @param {Buffer} secondBuffer 
 * @returns {Buffer} - a Buffer containing the concactenated PDFs
 */
const combinePDFBuffers = (firstBuffer, secondBuffer) => {
    var outStream = new memoryStreams.WritableStream();

    try {
        var firstPDFStream = new hummus.PDFRStreamForBuffer(firstBuffer);
        var secondPDFStream = new hummus.PDFRStreamForBuffer(secondBuffer);

        var pdfWriter = hummus.createWriterToModify(firstPDFStream, new hummus.PDFStreamForResponse(outStream));
        pdfWriter.appendPDFPagesFromPDF(secondPDFStream);
        pdfWriter.end();
        var newBuffer = outStream.toBuffer();
        outStream.end();

        return newBuffer;
    }
    catch(e){
        outStream.end();
        throw new Error('Error during PDF combination: ' + e.message);
    }
};

combinePDFBuffers(PDFBuffer1, PDFBuffer2);

---

下面是我们在Express服务器中用于合并PDF blob列表的内容

const { PDFRStreamForBuffer, createWriterToModify, PDFStreamForResponse } = require('hummus');
const { WritableStream } = require('memory-streams');

// Merge the pages of the pdfBlobs (Javascript buffers) into a single PDF blob                                                                                                                                                                  
const mergePdfs = pdfBlobs => {
  if (pdfBlobs.length === 0) throw new Error('mergePdfs called with empty list of PDF blobs');
  // This optimization is not necessary, but it avoids the churn down below                                                                                                                                                
  if (pdfBlobs.length === 1) return pdfBlobs[0];

  // Adapted from: https://stackoverflow.com/questions/36766234/nodejs-merge-two-pdf-files-into-one-using-the-buffer-obtained-by-reading-them?answertab=active#tab-top                                                     
  // Hummus is useful, but with poor interfaces -- E.g. createWriterToModify shouldn't require any PDF stream                                                                                                              
  // And Hummus has many Issues: https://github.com/galkahana/HummusJS/issues                                                                                                                                              
  const [firstPdfRStream, ...restPdfRStreams] = pdfBlobs.map(pdfBlob => new PDFRStreamForBuffer(pdfBlob));
  const outStream = new WritableStream();
  const pdfWriter = createWriterToModify(firstPdfRStream, new PDFStreamForResponse(outStream));
  restPdfRStreams.forEach(pdfRStream => pdfWriter.appendPDFPagesFromPDF(pdfRStream));
  pdfWriter.end();
  outStream.end();
  return outStream.toBuffer();
};

module.exports = exports = {
  mergePdfs,
};

---

正如@MechaCode所提到的，创建者已经停止了对HummusJS的支持

所以我想给你们两个解决方案

使用npm模块

const PDFDocument = require('pdf-lib').PDFDocument

var pdfBuffer1 = fs.readFileSync("./pdf1.pdf"); 
var pdfBuffer2 = fs.readFileSync("./pdf2.pdf");

var pdfsToMerge = [pdfBuffer1, pdfBuffer2]

const mergedPdf = await PDFDocument.create(); 
for (const pdfBytes of pdfsToMerge) { 
    const pdf = await PDFDocument.load(pdfBytes); 
    const copiedPages = await mergedPdf.copyPages(pdf, pdf.getPageIndices());
    copiedPages.forEach((page) => {
         mergedPdf.addPage(page); 
    }); 
} 

const buf = await mergedPdf.save();        // Uint8Array

let path = 'merged.pdf'; 
fs.open(path, 'w', function (err, fd) {
    fs.write(fd, buf, 0, buf.length, null, function (err) {
        fs.close(fd, function () {
            console.log('wrote the file successfully');
        }); 
    }); 
}); 

以下示例代码使用

节点pdftk

npm模块进行组合 两个pdf缓冲区无缝连接

const pdftk = require('node-pdftk');

var pdfBuffer1 = fs.readFileSync("./pdf1.pdf");
var pdfBuffer2 = fs.readFileSync("./pdf2.pdf");

pdftk
    .input([pdfBuffer1, pdfBuffer2])
    .output()
    .then(buf => {
        let path = 'merged.pdf';
        fs.open(path, 'w', function (err, fd) {
            fs.write(fd, buf, 0, buf.length, null, function (err) {
                fs.close(fd, function () {
                    console.log('wrote the file successfully');
                });
            });
        });
    });

节点pdftk npm模块的要求是您需要安装 PDFtk图书馆。你们中的一些人可能会觉得这项开销/乏味。所以我有另一个使用pdf库的解决方案

使用npm模块

const PDFDocument = require('pdf-lib').PDFDocument

var pdfBuffer1 = fs.readFileSync("./pdf1.pdf"); 
var pdfBuffer2 = fs.readFileSync("./pdf2.pdf");

var pdfsToMerge = [pdfBuffer1, pdfBuffer2]

const mergedPdf = await PDFDocument.create(); 
for (const pdfBytes of pdfsToMerge) { 
    const pdf = await PDFDocument.load(pdfBytes); 
    const copiedPages = await mergedPdf.copyPages(pdf, pdf.getPageIndices());
    copiedPages.forEach((page) => {
         mergedPdf.addPage(page); 
    }); 
} 

const buf = await mergedPdf.save();        // Uint8Array

let path = 'merged.pdf'; 
fs.open(path, 'w', function (err, fd) {
    fs.write(fd, buf, 0, buf.length, null, function (err) {
        fs.close(fd, function () {
            console.log('wrote the file successfully');
        }); 
    }); 
}); 

---

就我个人而言，我更喜欢使用pdf lib npm模块。

可能重复使用请说明PDFBuffer1的类型，PDFBuffer2@M.Abulsoud它们都是由二进制PDF数据填充的。在我的例子中，我使用的方法创建了缓冲区，下面是作者合并PDF的一个示例：我试图在React组件中使用它，但这似乎是不可能的。我遗漏了什么？@ZachEsposito puppeter's page.pdf（）返回缓冲区HummusJS现在不受creater支持。谢谢！pdf-lib非常好，这是使用pdf-lib的一个更好的例子