清晨

新的开始

导航

通过POI读取word文件

Posted on 2014-07-12 21:33  gdds  阅读(291)  评论(0)    收藏  举报

POI读取word只能读取内容不能读取格式

tm-extractors-0.4.jar

import java.io.FileInputStream;

 

import org.textmining.text.extraction.WordExtractor;

 

public class Test {

    public static void main(String[] args) {

       try {

           FileInputStream in = new FileInputStream("d:\\a.doc");

           WordExtractor extractor = new WordExtractor();

           System.out.println(in.available());

           String str = extractor.extractText(in);

           System.out.println(str);

       } catch (Exception e) {

           e.printStackTrace();

       }

    }

}