import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.util.PDFTextStripper;
import javax.swing.text.*;
import java.util.*;
import java.io.*;
import org.apache.pdfbox.exceptions.InvalidPasswordExcept ion;
import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.pdmodel.PDPage;
import org.apache.pdfbox.util.PDFTextStripperByArea;
[/code
PDDocument document=null;
PDFTextStripper stripper=null;
String result=null;
int numpages=0;
try {
stripper = new PDFTextStripper();
} catch (IOException e1) {
// TODO Auto-generated catch block
result="An error occurs while extracting text for: , Technical error: "+e1.getMessage()+"\n";
}
try {
document = PDDocument.load("E://backup18july24/uni/lecs/os/OS120102011.pdf");
numpages=document.getPageCount();
} catch (IOException e0) {
result="An error occurs while extracting text for:, Technical error: "+e0.getMessage()+"\n";
}
try {
stripper.setStartPage( 2);
stripper.setEndPage( numpages );
result=stripper.getText(document);
} catch (IOException e0) {
result="An error occurs while extracting text for: Technical error: "+e0.getMessage()+"\n";
}
/code]
Hello...you can use pdfbox api to manipulate pdf files...my code just extracts the text from a pdf file.
good luck