java - 如何搜索 from PDMetadata(xmpmeta) using java

Question

From the below code I got pdf metadata in xmp as shown below. From this output how to get the values of each property (eg: "pdf:Keywords")

InputStream in=new FileInputStream(pdfFile);
    PDFParser parser=new PDFParser(in);
    parser.parse();
    PDMetadata metadata = parser.getPDDocument().getDocumentCatalog().getMetadata();
    if(metadata!=null)
    {
    System.out.println(metadata.getInputStreamAsString());
    }

输出类似

    metadata<?xpacket begin="" id="W5M0MpCehiHzreSzNTczkc9d"?>
<x:xmpmeta xmlns:x="adobe:ns:meta/" x:xmptk="Adobe XMP Core 5.2-c001 63.139439, 2010/09/27-13:37:26        ">
   <rdf:RDF xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#">
      <rdf:Description rdf:about=""
            xmlns:pdf="http://ns.adobe.com/pdf/1.3/">
         <pdf:Producer>Acrobat Distiller 7.0 (Windows)</pdf:Producer>
         <pdf:Keywords>F3392|4|Name 2016|02|2016|04|Sub111 |Three Hours|30|(5X1=5),(5X2=10), (3X5=15)&#xD;&#xA;</pdf:Keywords>
      </rdf:Description>
      <rdf:Description rdf:about=""
            xmlns:pdfx="http://ns.adobe.com/pdfx/1.3/"
         <pdfx:semester>02</pdfx:semester>
   </rdf:RDF>
</x:xmpmeta>          
<?xpacket end="w"?>

Answer 1

您需要 Apache PDFBox 及其已弃用的 JempBox 库(实现 Adob​​e 的 XMP(TM) 规范 - 他们现在使用 Xmpbox，但它更加严格，无法处理大多数 pdf 格式)

PDDocument document = PDDocument.load(inputStream);
PDDocumentCatalog cat = document.getDocumentCatalog();
PDMetadata metadata = cat.getMetadata();

if( metadata != null )
{
    try
    {
        XMPMetadata meta = XMPMetadata.load(metadata.exportXMPMetadata());

        XMPSchema xs = meta.getDublinCoreSchema();
        if (xs != null)
        {
            System.out.println("About: " + xs.getAbout());
            List<String> bagList = xs.getBagList("author");
            if(bagList != null)
            {
                System.out.println("BagList: ");
                ShowString(bagList);
            }
            List<String> creators = xs.getBagList("creator");
            if(creators != null)
            {
                System.out.println("Creators: ");
                ShowString(creators);
            }
        }

        XMPSchemaDublinCore dc = meta.getDublinCoreSchema();
        if (dc != null)
        {
            System.out.println("Title: " + dc.getTitle());
            System.out.println("Description:" + dc.getDescription());
            System.out.println("Source:" + dc.getSource());
            System.out.println("Identifier:" + dc.getIdentifier());
            System.out.println("Coverage:" + dc.getCoverage());
            System.out.println("About:" + dc.getAbout());
            List<String> relationships = dc.getRelationships();
            if(relationships != null)
            {
                System.out.println("Relationships: ");
                ShowString(relationships);
            }
            List<String> contributors = dc.getContributors();
            if(contributors != null)
            {
                System.out.println("Contributors: ");
                ShowString(contributors);
            }
            List<String> creators = dc.getCreators();
            if(creators != null)
            {
                System.out.println("Creators: ");
                ShowString(creators);
            }
            List<Calendar> dates = dc.getDates();
            if(dates != null)
            {
                System.out.println("Dates: ");
                ShowCalendar(dates);
            }
            List<String> subjects = dc.getSubjects();
            if(subjects != null)
            {
                System.out.println("Subjects: ");
                ShowString(subjects);
            }
            List<String> publishers = dc.getPublishers();
            if(publishers != null)
            {
                System.out.println("Publishers: ");
                ShowString(publishers);
            }
            List<String> languages = dc.getLanguages();
            if(languages != null)
            {
                System.out.println("Languages: ");
                ShowString(languages);
            }
        }

        XMPSchemaPDF pdf = meta.getPDFSchema();
        if (pdf != null)
        {
            System.out.println("Keywords:" + pdf.getKeywords());
            System.out.println("PDF Version:" + pdf.getPDFVersion());
            System.out.println("PDF Producer:" + pdf.getProducer());
        }

        XMPSchemaBasic basic = meta.getBasicSchema();
        if (basic != null)
        {
            System.out.println("Create Date:" + basic.getCreateDate().getTime());
            System.out.println("Modify Date:" + basic.getModifyDate().getTime());
            System.out.println("Creator Tool:" + basic.getCreatorTool());
            System.out.println("Label:" + basic.getLabel());
            System.out.println("About:" + basic.getAbout());
            System.out.println("Nickname:" + basic.getNickname());
            System.out.println("Title:" + basic.getTitle());
        }
    }
    catch (Exception e)
    {
        System.err.println("An error occurred while parsing the meta data: "
                + e.getMessage());
    }                   
}
else
{
    PDDocumentInformation info = document.getDocumentInformation();
    System.out.println( "Title:" + info.getTitle() );
    System.out.println( "Author:" + info.getAuthor() );
    System.out.println( "Subject:" + info.getSubject() );
    System.out.println( "Keywords:" + info.getKeywords() );
    System.out.println( "Creator:" + info.getCreator() );
    System.out.println( "Producer:" + info.getProducer() );
    System.out.println( "Creation Date:" + info.getCreationDate().getTime() );
    System.out.println( "Modification Date:" + info.getModificationDate().getTime() );
    System.out.println( "Trapped:" + info.getTrapped() );
}

document.close();

Direct download of PDFBox jar

PDFBox Maven link

Direct download of JempBox jar

JempBox Maven link