Table of Contents
Convert Pdf to Word in Java
Required Jars
- itextpdf-5.4.4
- xmlbeans-xpath-2.3.0
- xmlbeans-2.6.0
- poi-3.9
- dom4j-1.6.1
- poi-ooxml-schemas-3.7
- poi-ooxml-3.7
Java Program to Convert PDF to Word
package com.ngdeveloper;
import java.io.FileOutputStream;
import java.io.IOException;
import org.apache.poi.xwpf.usermodel.BreakType;
import org.apache.poi.xwpf.usermodel.XWPFDocument;
import org.apache.poi.xwpf.usermodel.XWPFParagraph;
import org.apache.poi.xwpf.usermodel.XWPFRun;
import com.itextpdf.text.pdf.PdfReader;
import com.itextpdf.text.pdf.parser.PdfReaderContentParser;
import com.itextpdf.text.pdf.parser.SimpleTextExtractionStrategy;
import com.itextpdf.text.pdf.parser.TextExtractionStrategy;
public class ConvertPdf2Word {
public static void main(String[] args) throws IOException {
System.out.println("Document converted started");
XWPFDocument doc = new XWPFDocument();
String pdf = "D:\\javadomain.pdf";
PdfReader reader = new PdfReader(pdf);
PdfReaderContentParser parser = new PdfReaderContentParser(reader);
for (int i = 1; i <= reader.getNumberOfPages(); i++) {
TextExtractionStrategy strategy = parser.processContent(i,
new SimpleTextExtractionStrategy());
String text = strategy.getResultantText();
XWPFParagraph p = doc.createParagraph();
XWPFRun run = p.createRun();
run.setText(text);
run.addBreak(BreakType.PAGE);
}
FileOutputStream out = new FileOutputStream("D:\\javadomain.docx");
doc.write(out);
out.close();
reader.close();
System.out.println("Document converted successfully");
}
}