Word转换成Html

本文详细介绍了如何使用Apache POI库将Word文档转换为HTML格式,包括代码实现及注意事项。
package com.baiyang.lc.util;

import java.io.ByteArrayOutputStream;
import java.io.FileInputStream;
import java.io.FileNotFoundException;
import java.io.IOException;

import javax.xml.parsers.DocumentBuilderFactory;
import javax.xml.parsers.ParserConfigurationException;
import javax.xml.transform.OutputKeys;
import javax.xml.transform.Transformer;
import javax.xml.transform.TransformerException;
import javax.xml.transform.TransformerFactory;
import javax.xml.transform.dom.DOMSource;
import javax.xml.transform.stream.StreamResult;

import org.apache.poi.hwpf.HWPFDocumentCore;
import org.apache.poi.hwpf.converter.WordToHtmlConverter;
import org.apache.poi.hwpf.converter.WordToHtmlUtils;
import org.w3c.dom.Document;

public class Word {
	/**
	 * word2003转Html
	 * 
	 * @param fileName
	 * @return
	 * @throws FileNotFoundException
	 * @throws IOException
	 * @throws ParserConfigurationException
	 * @throws TransformerException
	 * @author baiyang
	 */
	public static String Word2003ToHtml(String fileName) throws FileNotFoundException, IOException, ParserConfigurationException, TransformerException {
		WordToHtmlConverter wordToHtmlConverter = new WordToHtmlConverter(DocumentBuilderFactory.newInstance().newDocumentBuilder().newDocument());
		HWPFDocumentCore wordDocument = WordToHtmlUtils.loadDoc(new FileInputStream(fileName));
		wordToHtmlConverter.processDocument(wordDocument);
		Document htmlDocument = wordToHtmlConverter.getDocument();

		ByteArrayOutputStream out = new ByteArrayOutputStream();
		DOMSource domSource = new DOMSource(htmlDocument);
		StreamResult streamResult = new StreamResult(out);

		TransformerFactory tf = TransformerFactory.newInstance();
		Transformer serializer = tf.newTransformer();
		serializer.setOutputProperty(OutputKeys.ENCODING, "UTF-8");
		serializer.setOutputProperty(OutputKeys.INDENT, "yes");
		serializer.setOutputProperty(OutputKeys.METHOD, "html");
		serializer.transform(domSource, streamResult);

		out.flush();
		out.close();

		String result = new String(out.toByteArray());
		return result;
	}
}
所需jar包
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值