玩飛盤工程師的部落格

PDFBox 1.8.x

import org.apache.pdfbox.pdfparser.PDFStreamParser;
import org.apache.pdfbox.pdfwriter.ContentStreamWriter;

import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.pdmodel.PDPage;
import org.apache.pdfbox.pdmodel.common.PDStream;
import org.apache.pdfbox.util.PDFOperator;

import java.util.ArrayList;
import java.util.List;

/**
 * This is an example on how to remove all text from PDF document.
 *
 * Usage: java org.apache.pdfbox.examples.util.RemoveAllText <input-pdf> <output-pdf>
 *
 * @author Ben Litchfield
 * @version $Revision: 1.2 $
 */
public class RemoveAllText
{
    /**
     * Default constructor.
     */
    private RemoveAllText()
    {
        //example class should not be instantiated
    }

    /**
     * This will remove all text from a PDF document.
     *
     * @param args The command line arguments.
     *
     * @throws Exception If there is an error parsing the document.
     */
    public static void main( String[] args ) throws Exception
    {
        if( args.length != 2 )
        {
            usage();
        }
        else
        {
            PDDocument document = null;
            try
            {
                document = PDDocument.load( args[0] );
                if( document.isEncrypted() )
                {
                    System.err.println( "Error: Encrypted documents are not supported for this example." );
                    System.exit( 1 );
                }
                List allPages = document.getDocumentCatalog().getAllPages();
                for( int i=0; i " );
    }

}