package com.Utils;

import java.io.BufferedWriter;
import java.io.File;
import java.io.FileInputStream;
import java.io.FileNotFoundException;
import java.io.FileOutputStream;
import java.io.IOException;
import java.io.OutputStream;
import java.io.OutputStreamWriter;
import java.util.List;

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.commons.io.output.ByteArrayOutputStream;
import org.apache.poi.hwpf.HWPFDocument;
import org.apache.poi.hwpf.converter.PicturesManager;
import org.apache.poi.hwpf.converter.WordToHtmlConverter;
import org.apache.poi.hwpf.model.PicturesTable;
import org.apache.poi.hwpf.usermodel.CharacterRun;
import org.apache.poi.hwpf.usermodel.Paragraph;
import org.apache.poi.hwpf.usermodel.Picture;
import org.apache.poi.hwpf.usermodel.PictureType;
import org.apache.poi.hwpf.usermodel.Range;
import org.apache.poi.hwpf.usermodel.Table;
import org.apache.poi.hwpf.usermodel.TableCell;
import org.apache.poi.hwpf.usermodel.TableIterator;
import org.apache.poi.hwpf.usermodel.TableRow;
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;
import org.w3c.dom.Document;

/**
 *
 * @author Jackray
 *
 */
public class Word2HtmlUtils {

	private final static String  tempPath = "D:\\W2H";

	public static void main(String argv[]) {
		try {
			docx2Html("D:\\W2H\\big.docx", "D:\\W2H\\big.html");
		} catch (Exception e) {
			e.printStackTrace();
		}
	}

	/**
	 * docx格式word轉換為html
	 *
	 * @param fileName
	 *            docx檔案路徑
	 * @param outPutFile
	 *            html輸出檔案路徑
	 * @throws TransformerException
	 * @throws IOException
	 * @throws ParserConfigurationException
	 */
	public static void docx2Html(String fileName, String outPutFile) throws TransformerException, IOException, ParserConfigurationException {
		//輸出檔名
		String fileOutName = outPutFile;
		//start時間
		long startTime = System.currentTimeMillis();
		//獲取word的docment
		XWPFDocument document = new XWPFDocument(new FileInputStream(fileName));
		XHTMLOptions options = XHTMLOptions.create().indent(4);
		// 匯出圖片
		File imageFolder = new File(tempPath);
		options.setExtractor(new FileImageExtractor(imageFolder));
		// URI resolver  解析
		options.URIResolver(new FileURIResolver(imageFolder));
		File outFile = new File(fileOutName);
		outFile.getParentFile().mkdirs();
		OutputStream out = new FileOutputStream(outFile);
		XHTMLConverter.getInstance().convert(document, out, options);
		//計算時間
		System.out.println("Generate " + fileOutName + " with " + (System.currentTimeMillis() - startTime) + " ms.");

	}

}

 

depenency jar包

	<dependency>
			<groupId>commons-io</groupId>
			<artifactId>commons-io</artifactId>
			<version>2.4</version>
		</dependency>

		<dependency>
			<groupId>org.apache.poi</groupId>
			<artifactId>poi</artifactId>
			<version>3.8</version>
		</dependency>

		<dependency>
			<groupId>org.apache.poi</groupId>
			<artifactId>poi-ooxml</artifactId>
			<version>3.8</version>
		</dependency>
		<dependency>
			<groupId>org.apache.poi</groupId>
			<artifactId>poi-scratchpad</artifactId>
			<version>3.8</version>
		</dependency>

		<dependency>
			<groupId>fr.opensagres.xdocreport</groupId>
			<artifactId>xdocreport</artifactId>
			<version>1.0.4</version>
		</dependency>
		
		<dependency>
			<groupId>org.apache.poi</groupId>
			<artifactId>ooxml-schemas</artifactId>
			<version>1.1</version>
		</dependency>