public static void main(String[] args) throws Exception {
if( args.length != 1 )
{
usage();
}
else
{
PDDocument document = null;
try
{
document = PDDocument.load( args[0] );
if( document.isEncrypted() )
{
try
{
document.decrypt( "" );
}
catch( InvalidPasswordException e )
{
System.err.println( "Error: Document is encrypted with a password." );
System.exit( 1 );
}
}
PDFTextStripperByArea stripper = new PDFTextStripperByArea();
stripper.setSortByPosition( true );
Rectangle rect = new Rectangle( 10, 280, 275, 60 );
stripper.addRegion( "class1", rect );
List allPages = document.getDocumentCatalog().getAllPages();
PDPage firstPage = (PDPage)allPages.get( 0 );
stripper.extractRegions( firstPage );
System.out.println( "Text in the area:" + rect );
System.out.println( stripper.getTextForRegion( "class1" ) );
}
finally
{
if( document != null )
{
document.close();
}
}
}
}
This will print the documents text in a certain area. |