I'm trying to extract text except watermark text from PDF files with Apache PDFBox library,so I want to remove the watermark first and the rest is what I want.but unfortunately,Both PDmetadata and PDXObject can't recognize the watermark,any help will be appreciated.I found some code below.
// Open PDF document
PDDocument document = null;
try {
document = PDDocument.load(PATH_TO_YOUR_DOCUMENT);
} catch (IOException e) {
e.printStackTrace();
}
// Get all pages and loop through them
List pages = document.getDocumentCatalog().getAllPages();
Iterator iter = pages.iterator();
while( iter.hasNext() ) {
PDPage page = (PDPage)iter.next();
PDResources resources = page.getResources();
Map images = null;
// Get all Images on page
try {
images = resources.getImages();//How to specify watermark instead of images??
} catch (IOException e) {
e.printStackTrace();
}
if( images != null ) {
// Check all images for metadata
Iterator imageIter = images.keySet().iterator();
while( imageIter.hasNext() ) {
String key = (String)imageIter.next();
PDXObjectImage image = (PDXObjectImage)images.get( key );
PDMetadata metadata = image.getMetadata();
System.out.println("Found a image: Analyzing for Metadata");
if (metadata == null) {
System.out.println("No Metadata found for this image.");
} else {
InputStream xmlInputStream = null;
try {
xmlInputStream = metadata.createInputStream();
} catch (IOException e) {
e.printStackTrace();
}
try {
System.out.println("--------------------------------------------------------------------------------");
String mystring = convertStreamToString(xmlInputStream);
System.out.println(mystring);
} catch (IOException e) {
e.printStackTrace();
}
}
// Export the images
String name = getUniqueFileName( key, image.getSuffix() );
System.out.println( "Writing image:" + name );
try {
image.write2file( name );
} catch (IOException e) {
// TODO Auto-generated catch block
//e.printStackTrace();
}
System.out.println("--------------------------------------------------------------------------------");
}
}
}
