How to extract reference from PDF file using Java? Cheers
Use itext api.
import java.io.*;
import java.util.*;
import com.lowagie.text.*;
import com.lowagie.text.pdf.*;
public class ReadPDF {
public static void main(String[] args) throws IOException {
try {
Document document = new Document();
document.open();
PdfReader reader = new PdfReader("file.pdf");
PdfDictionary dictionary = reader.getPageN(1);
PRIndirectReference reference = (PRIndirectReference) dictionary.get(PdfName.CONTENTS);
PRStream stream = (PRStream) PdfReader.getPdfObject(reference);
byte[] bytes = PdfReader.getStreamBytes(stream);
PRTokeniser tokenizer = new PRTokeniser(bytes);
StringBuffer buffer = new StringBuffer();
while (tokenizer.nextToken()) {
if (tokenizer.getTokenType() == PRTokeniser.TK_STRING) {
buffer.append(tokenizer.getStringValue());
}
}
String test = buffer.toString();
System.out.println(test);
} catch (Exception e) {
}
}
}