利用poi解析word文件

最新推荐文章于 2021-11-13 14:45:49 发布

baihuanbaiv55389

最新推荐文章于 2021-11-13 14:45:49 发布

阅读量112

点赞数

文章标签： java

原文链接：http://www.cnblogs.com/lcqBlogs/archive/2011/08/22/2392395.html

版权

package com.dreamers.read;

import java.io.File;
import java.io.FileInputStream;

import org.apache.poi.hwpf.extractor.WordExtractor;

public class WordReader {

public String readDoc(String doc) {
  // 创建输入流读取DOC文件
//ArrayList<String> list = new ArrayList<String>();
try{ FileInputStream in = new FileInputStream(new File(doc));
  WordExtractor extractor = null;
  String text = null;
  // 创建WordExtractor
  extractor = new WordExtractor(in);
  // 对DOC文件进行提取
  text = extractor.getText();

  return text;
}catch(Exception e){
  System.out.println("未找到文件");
}
return null;
}

/*
public static void main(String[] args) {
  // TODO Auto-generated method stub
  WordReader re = new WordReader();
  try {
   ArrayList<String> list = new ArrayList<String>();
    list = re.readDoc("d://《喂出来〉〉自学指导.doc");
   System.out.println(list.get(0));
  } catch (Exception e) {
   e.printStackTrace();
  }
}*/

}

自己测试一下吧

转载于:https://www.cnblogs.com/lcqBlogs/archive/2011/08/22/2392395.html