poi读取docx中的文字和图片(自己应用)

poi读取docx中的文字和图片(自己应用)

 1 package com.fry.poiDemo.dao;
 2 
 3 import java.io.File;
 4 import java.io.FileInputStream;
 5 import java.io.FileOutputStream;
 6 import java.io.IOException;
 7 import java.io.PrintStream;
 8 import java.util.List;
 9 
10 import org.apache.poi.xwpf.extractor.XWPFWordExtractor;
11 import org.apache.poi.xwpf.usermodel.XWPFDocument;
12 import org.apache.poi.xwpf.usermodel.XWPFPictureData;
13 
14 public class Word {
15     // maven太好用了
16     // 读取srcFile源word文件docx文字
17     // 读取srcFile源word文件docx中的image图片并且存放在文件夹imageFile中
18     public String readDocxImage(String srcFile, String imageFile) {
19         String path = srcFile;
20         File file = new File(path);
21         try {
22             // 用XWPFWordExtractor来获取文字
23             FileInputStream fis = new FileInputStream(file);
24             XWPFDocument document = new XWPFDocument(fis);
25             XWPFWordExtractor xwpfWordExtractor = new XWPFWordExtractor(document);
26             String text = xwpfWordExtractor.getText();
27 //            System.out.println(text);
28             //将获取到的文字存放到对应文件名中的txt文件中
29             String temp[]=srcFile.split("\/");
30             String temp1=temp[temp.length-1];
31             String temp3[]=temp1.split("\.");
32             String txtFileName="myRes//txt//"+temp3[0]+".txt";
33             PrintStream ps = new PrintStream(txtFileName);
34             ps.println(text);
35             
36 
37             // 用XWPFDocument的getAllPictures来获取所有的图片
38             List<XWPFPictureData> picList = document.getAllPictures();
39             for (XWPFPictureData pic : picList) {
40 //                System.out.println(pic.getPictureType() + file.separator + pic.suggestFileExtension() + file.separator
41 //                        + pic.getFileName());
42                 byte[] bytev = pic.getData();
43 //                System.out.println(bytev.length);
44                 // 大于1000bites的图片我们才弄下来,消除word中莫名的小图片的影响
45                 if (bytev.length > 300) {
46                     FileOutputStream fos = new FileOutputStream(imageFile + pic.getFileName());
47                     fos.write(bytev);
48                 }
49             }
50             fis.close();
51             return text;
52         } catch (IOException e) {
53             e.printStackTrace();
54         }
55         return null;
56     }
57 }
原文地址:https://www.cnblogs.com/Renyi-Fan/p/8167288.html