一、第三方jar包下载:

在java中将html文件导出到word需要应用到第三方的jar包:采用poi-bin-3.0-FINAL-20070503.zip。可以到http://poi.apache.org/官方网站下载最新版本。

二、开发思路:

采用Java IO将html文件读入到一个临时的String对象中,然后采用poi提供的API生成word文档。

三、开发源代码:

package com.solid.util;

import java.io.BufferedReader;

import java.io.ByteArrayInputStream;

import java.io.File;

import java.io.FileOutputStream;

import java.io.FileReader;

import java.io.IOException;

import org.apache.poi.poifs.filesystem.DirectoryEntry;

import org.apache.poi.poifs.filesystem.DocumentEntry;

import org.apache.poi.poifs.filesystem.POIFSFileSystem;

/**

* 将html文档转为doc

* @author soildwang

*

*/

public class HtmlToDoc {

       /**

        * 读取html文件到word

        * @param filepath html文件的路径

        * @return

        * @throws Exception

        */

public boolean writeWordFile(String filepath) throws Exception {

              boolean flag = false;

              ByteArrayInputStream bais = null;

              FileOutputStream fos = null;

              String path = "C:/";  //根据实际情况写路径

              try {

                     if (!"".equals(path)) {

                            File fileDir = new File(path);

                            if (fileDir.exists()) {

                                   String content = readFile(filepath);

                                   byte b[] = content.getBytes();

                                   bais = new ByteArrayInputStream(b);

                                   POIFSFileSystem poifs = new POIFSFileSystem();

                                   DirectoryEntry directory = poifs.getRoot();

                                   DocumentEntry documentEntry = directory.createDocument("WordDocument", bais);

                                   fos = new FileOutputStream(path + "temp.doc");

                                   poifs.writeFilesystem(fos);

                                   bais.close();

                                   fos.close();

                            }

                     }

              } catch (IOException e) {

                     e.printStackTrace();

              } finally {

                     if(fos != null) fos.close();

                     if(bais != null) bais.close();

              }

              return flag;

       }

       /**

        * 读取html文件到字符串

        * @param filename

        * @return

        * @throws Exception

        */

       public String readFile(String filename) throws Exception {

              StringBuffer buffer = new StringBuffer("");

              BufferedReader br = null;

              try {

                     br = new BufferedReader(new FileReader(filename));

                     buffer = new StringBuffer();

                     while (br.ready())

                            buffer.append((char) br.read());

              } catch (Exception e) {

                     e.printStackTrace();

              } finally {

                     if(br!=null) br.close();

              }

              return buffer.toString();

       }

      

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

              new HtmlToDoc().writeWordFile("C:/preview4510.html");

       }

}


本文转载:CSDN博客