Java中如何將兩個PDF文件合並為一個？

Question

我想使用PDFBox將許多 PDF 文件合並為一個文件，這就是我所做的：

PDDocument document = new PDDocument();
for (String pdfFile: pdfFiles) {
    PDDocument part = PDDocument.load(pdfFile);
    List<PDPage> list = part.getDocumentCatalog().getAllPages();
    for (PDPage page: list) {
        document.addPage(page);
    }
    part.close();
}
document.save("merged.pdf");
document.close();

其中pdfFiles是一個ArrayList<String>包含所有 PDF 文件。

當我運行上述內容時，我總是得到：

org.apache.pdfbox.exceptions.COSVisitorException: Bad file descriptor

難道我做錯了什么？ 還有其他方法嗎？

Answer 1

為什么不使用 pdfbox 的PDFMergerUtility ？

PDFMergerUtility ut = new PDFMergerUtility();
ut.addSource(...);
ut.addSource(...);
ut.addSource(...);
ut.setDestinationFileName(...);
ut.mergeDocuments();

Answer 2

一個快速的谷歌搜索返回了這個錯誤： “保存帶有導入 PDF 的文檔時文件描述符錯誤” 。

看起來您需要將要合並的 PDF 保持打開狀態，直到您保存並關閉合並的 PDF。

Answer 3

這是一個即用型代碼，將四個 pdf 文件與來自http://central.maven.org/maven2/com/itextpdf/itextpdf/5.5.0/itextpdf-5.5.0.jar的 itext.jar 合並，更多關於http //tutorialspointexamples.com/

import com.itextpdf.text.Document;
import com.itextpdf.text.pdf.PdfContentByte;
import com.itextpdf.text.pdf.PdfImportedPage;
import com.itextpdf.text.pdf.PdfReader;
import com.itextpdf.text.pdf.PdfWriter;

/**
 * This class is used to merge two or more 
 * existing pdf file using iText jar.
 */
public class PDFMerger {

static void mergePdfFiles(List<InputStream> inputPdfList,
        OutputStream outputStream) throws Exception{
    //Create document and pdfReader objects.
    Document document = new Document();
    List<PdfReader> readers = 
            new ArrayList<PdfReader>();
    int totalPages = 0;

    //Create pdf Iterator object using inputPdfList.
    Iterator<InputStream> pdfIterator = 
            inputPdfList.iterator();

    // Create reader list for the input pdf files.
    while (pdfIterator.hasNext()) {
            InputStream pdf = pdfIterator.next();
            PdfReader pdfReader = new PdfReader(pdf);
            readers.add(pdfReader);
            totalPages = totalPages + pdfReader.getNumberOfPages();
    }

    // Create writer for the outputStream
    PdfWriter writer = PdfWriter.getInstance(document, outputStream);

    //Open document.
    document.open();

    //Contain the pdf data.
    PdfContentByte pageContentByte = writer.getDirectContent();

    PdfImportedPage pdfImportedPage;
    int currentPdfReaderPage = 1;
    Iterator<PdfReader> iteratorPDFReader = readers.iterator();

    // Iterate and process the reader list.
    while (iteratorPDFReader.hasNext()) {
            PdfReader pdfReader = iteratorPDFReader.next();
            //Create page and add content.
            while (currentPdfReaderPage <= pdfReader.getNumberOfPages()) {
                  document.newPage();
                  pdfImportedPage = writer.getImportedPage(
                          pdfReader,currentPdfReaderPage);
                  pageContentByte.addTemplate(pdfImportedPage, 0, 0);
                  currentPdfReaderPage++;
            }
            currentPdfReaderPage = 1;
    }

    //Close document and outputStream.
    outputStream.flush();
    document.close();
    outputStream.close();

    System.out.println("Pdf files merged successfully.");
}

public static void main(String args[]){
    try {
        //Prepare input pdf file list as list of input stream.
        List<InputStream> inputPdfList = new ArrayList<InputStream>();
        inputPdfList.add(new FileInputStream("..\\pdf\\pdf_1.pdf"));
        inputPdfList.add(new FileInputStream("..\\pdf\\pdf_2.pdf"));
        inputPdfList.add(new FileInputStream("..\\pdf\\pdf_3.pdf"));
        inputPdfList.add(new FileInputStream("..\\pdf\\pdf_4.pdf"));


        //Prepare output stream for merged pdf file.
        OutputStream outputStream = 
                new FileOutputStream("..\\pdf\\MergeFile_1234.pdf");

        //call method to merge pdf files.
        mergePdfFiles(inputPdfList, outputStream);     
    } catch (Exception e) {
        e.printStackTrace();
    }
    }
}

Answer 4

使用org.apache.pdfbox的多個 pdf 合並方法：

public void mergePDFFiles(List<File> files,
                          String mergedFileName) {
    try {
        PDFMergerUtility pdfmerger = new PDFMergerUtility();
        for (File file : files) {
            PDDocument document = PDDocument.load(file);
            pdfmerger.setDestinationFileName(mergedFileName);
            pdfmerger.addSource(file);
            pdfmerger.mergeDocuments(MemoryUsageSetting.setupTempFileOnly());
            document.close();
        }
    } catch (IOException e) {
        logger.error("Error to merge files. Error: " + e.getMessage());
    }
}

在主程序中，使用文件列表和目標文件名調用mergePDFFiles方法。

        String mergedFileName = "Merged.pdf";
        mergePDFFiles(files, mergedFileName);

調用mergePDFFiles后，加載合並文件

        File mergedFile = new File(mergedFileName);

Answer 5

package article14;

import java.io.File;
import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.pdmodel.PDPage;
import org.apache.pdfbox.util.PDFMergerUtility;

public class Pdf
{
    public static void main(String args[])
    {
        new Pdf().createNew();
        new Pdf().combine();
        }

    public void combine()
    {
        try
        {
        PDFMergerUtility mergePdf = new PDFMergerUtility();
        String folder ="pdf";
        File _folder = new File(folder);
        File[] filesInFolder;
        filesInFolder = _folder.listFiles();
        for (File string : filesInFolder)
        {
            mergePdf.addSource(string);    
        }
    mergePdf.setDestinationFileName("Combined.pdf");
    mergePdf.mergeDocuments();
        }
        catch(Exception e)
        {

        }  
    }

public void createNew()
{
    PDDocument document = null;
    try
    {
        String filename="test.pdf";
        document=new PDDocument();
        PDPage blankPage = new PDPage();
        document.addPage( blankPage );
        document.save( filename );
    }
    catch(Exception e)
    {

    }
}

}

Answer 6

如果您想合並兩個文件，其中一個文件覆蓋另一個文件（例如：文檔 A 是一個模板，而文檔 B 有您要放在模板上的文本），這可以工作：

創建“doc”后，您想在其上編寫模板（templateFile） -

   PDDocument watermarkDoc = PDDocument.load(getServletContext()
                .getRealPath(templateFile));
   Overlay overlay = new Overlay();

   overlay.overlay(watermarkDoc, doc);

Answer 7

使用 iText（以字節為單位的現有 PDF）

    public static byte[] mergePDF(List<byte[]> pdfFilesAsByteArray) throws DocumentException, IOException {

    ByteArrayOutputStream outStream = new ByteArrayOutputStream();
    Document document = null;
    PdfCopy writer = null;

    for (byte[] pdfByteArray : pdfFilesAsByteArray) {

        try {
            PdfReader reader = new PdfReader(pdfByteArray);
            int numberOfPages = reader.getNumberOfPages();

            if (document == null) {
                document = new Document(reader.getPageSizeWithRotation(1));
                writer = new PdfCopy(document, outStream); // new
                document.open();
            }
            PdfImportedPage page;
            for (int i = 0; i < numberOfPages;) {
                ++i;
                page = writer.getImportedPage(reader, i);
                writer.addPage(page);
            }
        }

        catch (Exception e) {
            e.printStackTrace();
        }

    }

    document.close();
    outStream.close();
    return outStream.toByteArray();

}

Answer 8

//假設我們要將一個 pdf 與另一個主 pdf 合並

          InputStream is1 = null;



          if (file1 != null) {

                 FileInputStream fis1 = new FileInputStream(file1);

                 byte[] file1Data = new byte[(int) file1.length()];

                 fis1.read(file1Data);

                 is1 = new java.io.ByteArrayInputStream(file1Data);

          }



          //

          InputStream mainContent = <ur main content>



          org.apache.pdfbox.pdmodel.PDDocument mergedPDF = new org.apache.pdfbox.pdmodel.PDDocument();

          org.apache.pdfbox.pdmodel.PDDocument mainDoc = org.apache.pdfbox.pdmodel.PDDocument.load(mainContent);

          org.apache.pdfbox.multipdf.PDFMergerUtility merger = new org.apache.pdfbox.multipdf.PDFMergerUtility();



          merger.appendDocument(mergedPDF, mainDoc);



          PDDocument doc1 = null;



          if (is1 != null) {

                 doc1 = PDDocument.load(is1);

                 merger.appendDocument(mergedPDF, doc1);

                //1st file appended to main pdf");

          }

         



          ByteArrayOutputStream baos = new ByteArrayOutputStream();

          mergedPDF.save(baos);

//現在要么你把它保存在這里，要么如果你想轉換成 InputStream

          ByteArrayInputStream mergedInputStream = new ByteArrayInputStream(baos.toByteArray());