doc文件解析 java_poi解析doc文件内容

class="java" name="code">package com.app.doc;

import java.io.File;

import java.io.FileInputStream;

import java.io.InputStream;

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

/**

*poi-3.9-20121203.jar

*poi-examples-3.9-20121203.jar

*poi-excelant-3.9-20121203.jar

*poi-ooxml-3.9-20121203.jar

*poi-ooxml-schemas-3.9-20121203.jar

*poi-scratchpad-3.9-20121203.jar

*/

public class DocWord {

/**

* @param args

*/

public static void main(String[] args) throws Exception{

String path="D:/ecmall数据字典.doc";

String text =readWordDoc(path);

System.out.println(text);

}

/**

* 读word文件的内容

* @param path

* @return

* @throws Exception

*/

public static String readWordDoc(String path) throws Exception {

InputStream input=new FileInputStream(new File(path));

WordExtractor extractor = null;

// 创建WordExtractor

extractor = new WordExtractor(input);

// 对doc文件进行提取

return extractor.getText();

}

}

?