Hello,
I want to parse pdf websites.
Can anyone say how to extract all the words (word by word) from a pdf file using java.
The code below extract content from a pdf file and write it in another pdf file. I want that the program write it in a text file.
import java.io.FileOutputStream;
import java.io.IOException;
import com.itextpdf.text.*;
import com.itextpdf.text.pdf.*;
public class pdf {
private static String INPUTFILE = "http://www.britishcouncil.org/learning-infosheets-medicine.pdf" ;
private static String OUTPUTFILE = "c:/new3.pdf";
public static void main(String[] args) throws DocumentException,
IOException {
Document document = new Document();
PdfWriter writer = PdfWriter.getInstance(document,
new FileOutputStream(OUTPUTFILE));
document.open();
PdfReader reader = new PdfReader(INPUTFILE);
int n = reader.getNumberOfPages();
PdfImportedPage page;
for (int i = 1; i <= n; i++) {
page = writer.getImportedPage(reader, i);
Image instance = Image.getInstance(page);
document.add(instance);
}
document.close();
}
}
Thanks in advance