package com.springcloud.learn.test;
import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.text.PDFTextStripper;
import java.io.*;
public class pdfToWord {
public static void main(String[] args){
try{
String pdfFile = "D:\\ElasticSearch.pdf";
PDDocument doc = PDDocument.load(new File(pdfFile));
int pagenumber = doc.getNumberOfPages();
pdfFile = pdfFile.substring(0, pdfFile.lastIndexOf("."));
String fileName = pdfFile + ".doc";
File file = new File(fileName);
if (!file.exists()){
file.createNewFile();
}
FileOutputStream fos = new FileOutputStream(fileName);
Writer writer = new OutputStreamWriter(fos, "UTF-8");
PDFTextStripper stripper = new PDFTextStripper();
stripper.setSortByPosition(true);
stripper.setStartPage(1);
stripper.setEndPage(pagenumber);
stripper.writeText(doc, writer);
writer.close();
doc.close();
System.out.println("pdf转换word成功!");
}
catch (IOException e){
e.printStackTrace();
}
}
}