利用POI抽取word中的图片并保存在文件中

利用POI抽取word中的图片并保存在文件中

poi.apache.org/hwpf/quick-guide.html 
1.抽取word doc中的图片

package parse;

import java.io.*;
import java.util.*;


import org.apache.poi.hwpf.HWPFDocument;
import org.apache.poi.hwpf.model.PicturesTable;
import org.apache.poi.hwpf.usermodel.CharacterRun;
import org.apache.poi.hwpf.usermodel.Picture;
import org.apache.poi.hwpf.usermodel.Range;

public class ReadImgDoc { 

public static void main(String[] args) throws Exception {   
  new ReadImgDoc().readPicture("E:\\上海项目测试\\文档\\模板.doc");
}

  private void readPicture(String path)throws Exception{
     FileInputStream in=new FileInputStream(new File(path)); 
     HWPFDocument doc=new HWPFDocument(in); 
     int length=doc.characterLength();
     PicturesTable pTable=doc.getPicturesTable();
    // int TitleLength=doc.getSummaryInformation().getTitle().length();

     //  System.out.println(TitleLength);
      // System.out.println(length);
       for (int i=0;i<length;i++){
         Range range=new Range(i, i+1,doc);

         CharacterRun cr=range.getCharacterRun(0);
         if(pTable.hasPicture(cr)){
            Picture pic=pTable.extractPicture(cr, false);
          String afileName=pic.suggestFullFileName();
          OutputStream out=new FileOutputStream(new File("E:\\上海项目测试\\docImage\\"+UUID.randomUUID()+afileName));
          pic.writeImageContent(out);

        }
       }

  }

}

 

2.抽取 word docx文件中的图片

package parse;

import java.io.File;
import java.io.FileInputStream;
import java.io.FileOutputStream;
import java.io.IOException;
import java.util.List;

import org.apache.poi.xwpf.extractor.XWPFWordExtractor;
import org.apache.poi.xwpf.usermodel.XWPFDocument;
import org.apache.poi.xwpf.usermodel.XWPFPictureData;

public class GetPicsDocx {
  public static void main(String[] args) {
    String path ="E:\\上海项目测试\\文档\\35.docx";
    File file = new File(path);
    try {
      FileInputStream fis = new FileInputStream(file);
      XWPFDocument document = new XWPFDocument(fis);
      XWPFWordExtractor xwpfWordExtractor = new XWPFWordExtractor(document);
      String text = xwpfWordExtractor.getText();
      System.out.println(text);
      List<XWPFPictureData> picList = document.getAllPictures();
      for (XWPFPictureData pic : picList) {
        System.out.println(pic.getPictureType() + file.separator + pic.suggestFileExtension()
            +file.separator+pic.getFileName());
        byte[] bytev = pic.getData();
        FileOutputStream fos = new FileOutputStream("E:\\上海项目测试\\docxImage\\"+pic.getFileName()); 
        fos.write(bytev);
      }
      fis.close();
    } catch (IOException e) {
      e.printStackTrace();
    }
  }
}