word2007文档转html,WORD2007转HTML

代码网上找的，但是网上只提供了代码，没有JAR包，而这个功能需要的JAR包很多，收集

起来不是太方便，我这里收集好了，点此下载。

代码如下，亲测可用(图片在本地不显示，放在服务器上即可)：

package com.wei.liu.word;

import java.io.BufferedReader;

import java.io.File;

import java.io.FileInputStream;

import java.io.FileOutputStream;

import java.io.FileReader;

import java.io.InputStream;

import java.io.OutputStream;

import org.apache.poi.xwpf.converter.core.FileImageExtractor;

import org.apache.poi.xwpf.converter.core.FileURIResolver;

import org.apache.poi.xwpf.converter.xhtml.XHTMLConverter;

import org.apache.poi.xwpf.converter.xhtml.XHTMLOptions;

import org.apache.poi.xwpf.usermodel.XWPFDocument;

public class Word2007 {

public static void main(String[] args) {

try {

File f = new File("e:\\test\\33.docx");

if (!f.exists()) {

System.out.println("Sorry File does not Exists!");

} else {

if (f.getName().endsWith(".docx")

|| f.getName().endsWith(".DOCX")) {

// 1) Load DOCX into XWPFDocument

InputStream in = new FileInputStream(f);

XWPFDocument document = new XWPFDocument(in);

// 2) Prepare XHTML options (here we set the IURIResolver to

// load images from a "word/media" folder)

File imageFolderFile = new File("e://test");

XHTMLOptions options = XHTMLOptions.create().URIResolver(

new FileURIResolver(imageFolderFile));

options.setExtractor(new FileImageExtractor(imageFolderFile));

options.setIgnoreStylesIfUnused(false);

options.setFragment(true);

// 3) Convert XWPFDocument to XHTML

File file = new File("e:\\test\\33.html");

OutputStream out = new FileOutputStream(file);

XHTMLConverter.getInstance()

.convert(document, out, options);

BufferedReader in1 = new BufferedReader(new FileReader(

"e:\\test\\33.html"));

String str;

while ((str = in1.readLine()) != null) {

System.out.println(str);

}

in1.close();

// file.delete();

} else {

System.out.println("Enter only MS Office 2007+ files");

}

}

} catch (Exception e) {

e.printStackTrace();

}

}

}