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< allPages.size(); i++ )
{
PDPage page = (PDPage)allPages.get( i );
PDFStreamParser parser = new PDFStreamParser(page.getContents());
parser.parse();
List tokens = parser.getTokens();
List newTokens = new ArrayList();
for( int j=0; j< tokens.size(); j++)
{
Object token = tokens.get( j );
if( token instanceof PDFOperator )
{
PDFOperator op = (PDFOperator)token;
if( op.getOperation().equals( "TJ") || op.getOperation().equals( "Tj" ))
{
//remove the one argument to this operator
newTokens.remove( newTokens.size() -1 );
continue;
}
}
newTokens.add( token );
}
PDStream newContents = new PDStream( document );
ContentStreamWriter writer = new ContentStreamWriter( newContents.createOutputStream() );
writer.writeTokens( newTokens );
newContents.addCompression();
page.setContents( newContents );
}
document.save( args[1] );
}
finally
{
if( document != null )
{
document.close();
}
}
}
}
This will remove all text from a PDF document. |