使用 PDFBox (Java) 列出 pdf 附件

Question

我想获取所有PDF文档的附件/嵌入文件的文件名。我已经搜索了很长时间，但我的代码仍然无法正常工作。

我尝试了什么：

File input = new File(inputfile); // Input File Path, Given as param from args[]
pd = PDDocument.load(input);
PDDocumentNameDictionary names = new PDDocumentNameDictionary(pd.getDocumentCatalog());
PDEmbeddedFilesNameTreeNode efTree = names.getEmbeddedFiles();
Map<String, COSObjectable> existedNames = efTree.getNames();

System.out.println(existedNames);//Print Embedded-Filenames to console
pd.close();

我不知道是否可以将 MAP 的内容打印到控制台。我在 eclipse 中编码，这不会给我任何错误。但是当我运行 jar 文件时，我总是得到：NullPointerException at org.apache.pdfbox.pdmodel.PDDocument.getDocumentCatalog(PDDocument.java:778)

有什么想法或帮助吗？非常感谢...

Answer 1

这是源代码下载中的ExtractEmbeddedFiles example：

public final class ExtractEmbeddedFiles
{
    private ExtractEmbeddedFiles()
    {
    }

    /**
     * This is the main method.
     *
     * @param args The command line arguments.
     *
     * @throws IOException If there is an error parsing the document.
     */
    public static void main( String[] args ) throws IOException
    {
        if( args.length != 1 )
        {
            usage();
            System.exit(1);
        }
        else
        {
            PDDocument document = null;
            try
            {
                File pdfFile = new File(args[0]);
                String filePath = pdfFile.getParent() + System.getProperty("file.separator");
                document = PDDocument.load(pdfFile );
                PDDocumentNameDictionary namesDictionary = 
                        new PDDocumentNameDictionary( document.getDocumentCatalog() );
                PDEmbeddedFilesNameTreeNode efTree = namesDictionary.getEmbeddedFiles();
                if (efTree != null)
                {
                    Map<String, PDComplexFileSpecification> names = efTree.getNames();
                    if (names != null)
                    {
                        extractFiles(names, filePath);
                    }
                    else
                    {
                        List<PDNameTreeNode<PDComplexFileSpecification>> kids = efTree.getKids();
                        for (PDNameTreeNode<PDComplexFileSpecification> node : kids)
                        {
                            names = node.getNames();
                            extractFiles(names, filePath);
                        }
                    }
                }

                // extract files from annotations
                for (PDPage page : document.getPages())
                {
                    for (PDAnnotation annotation : page.getAnnotations())
                    {
                        if (annotation instanceof PDAnnotationFileAttachment)
                        {
                            PDAnnotationFileAttachment annotationFileAttachment = (PDAnnotationFileAttachment) annotation;
                            PDComplexFileSpecification fileSpec = (PDComplexFileSpecification) annotationFileAttachment.getFile();
                            PDEmbeddedFile embeddedFile = getEmbeddedFile(fileSpec);
                            extractFile(filePath, fileSpec.getFilename(), embeddedFile);
                        }
                    }
                }

            }
            finally
            {
                if( document != null )
                {
                    document.close();
                }
            }
        }
    }

    private static void extractFiles(Map<String, PDComplexFileSpecification> names, String filePath) 
            throws IOException
    {
        for (Entry<String, PDComplexFileSpecification> entry : names.entrySet())
        {
            String filename = entry.getKey();
            PDComplexFileSpecification fileSpec = entry.getValue();
            PDEmbeddedFile embeddedFile = getEmbeddedFile(fileSpec);
            extractFile(filePath, filename, embeddedFile);
        }
    }

    private static void extractFile(String filePath, String filename, PDEmbeddedFile embeddedFile)
            throws IOException
    {
        String embeddedFilename = filePath + filename;
        File file = new File(filePath + filename);
        System.out.println("Writing " + embeddedFilename);
        FileOutputStream fos = null;
        try
        {
            fos = new FileOutputStream(file);
            fos.write(embeddedFile.toByteArray());
        }
        finally
        {
            IOUtils.closeQuietly(fos);
        }
    }

    private static PDEmbeddedFile getEmbeddedFile(PDComplexFileSpecification fileSpec )
    {
        // search for the first available alternative of the embedded file
        PDEmbeddedFile embeddedFile = null;
        if (fileSpec != null)
        {
            embeddedFile = fileSpec.getEmbeddedFileUnicode(); 
            if (embeddedFile == null)
            {
                embeddedFile = fileSpec.getEmbeddedFileDos();
            }
            if (embeddedFile == null)
            {
                embeddedFile = fileSpec.getEmbeddedFileMac();
            }
            if (embeddedFile == null)
            {
                embeddedFile = fileSpec.getEmbeddedFileUnix();
            }
            if (embeddedFile == null)
            {
                embeddedFile = fileSpec.getEmbeddedFile();
            }
        }
        return embeddedFile;
    }

    /**
     * This will print the usage for this program.
     */
    private static void usage()
    {
        System.err.println( "Usage: java " + ExtractEmbeddedFiles.class.getName() + " <input-pdf>" );
    }
}

Answer 2

终于找到了解决办法。对于有同样问题的任何人，以下代码对我有用：

PDDocument pd;

File input = new File(inputfile); // Input File

pd = PDDocument.load(input);

//Writes all embedded Filenames (from pdf document) into Logfile
try{
    PDDocumentCatalog catalog = pd.getDocumentCatalog();
    PDDocumentNameDictionary names = catalog.getNames();
    PDEmbeddedFilesNameTreeNode embeddedFiles = names.getEmbeddedFiles();
    Map<String, COSObjectable> embeddedFileNames = embeddedFiles.getNames();

    //For-Each Loop is used to list all embedded files (if there is more than one)          
    for (Map.Entry<String, COSObjectable> entry : embeddedFileNames.entrySet())
    {   
        //You might need to configure the logger first
        logger.info("Inputfile: " + inputfile +"Found embedded File: " + entry.getKey() + ":");
    }

}
catch (Exception e){
    System.out.println("Document has no attachments. ");
}