Java代碼
import java.io.ByteArrayOutputStream;
import java.io.File;
import java.io.FileInputStream;
import java.io.FileNotFoundException;
import java.io.FileOutputStream;
import java.io.IOException;
import java.io.InputStream;
import java.io.OutputStream;
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.HWPFDocument;
import org.apache.poi.hwpf.converter.PicturesManager;
import org.apache.poi.hwpf.converter.WordToHtmlConverter;
import org.apache.poi.hwpf.usermodel.PictureType;
import org.apache.poi.xwpf.converter.core.BasicURIResolver;
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;
/**
* word 轉(zhuǎn)換成html 2017-2-27
*/
public class Word2Html {
/**
* 將word2003轉(zhuǎn)換為html文件 2017-2-27
*
* @param wordPath
* word文件路徑
* @param wordName
* word文件名稱無后綴
* @param suffix
* word文件后綴
* @throws IOException
* @throws TransformerException
* @throws ParserConfigurationException
*/
public static String Word2003ToHtml(String wordPath, String wordName,
String suffix) throws IOException, TransformerException,
ParserConfigurationException {
String htmlPath = wordPath + File.separator + "html"
+ File.separator;
String htmlName = wordName + ".html";
final String imagePath = htmlPath + "image" + File.separator;
// 判斷html文件是否存在恩够，每次重新生成
File htmlFile = new File(htmlPath + htmlName);
// if (htmlFile.exists()) {
// return htmlFile.getAbsolutePath();
// }
// 原word文檔
final String file = wordPath + File.separator + wordName + suffix;
InputStream input = new FileInputStream(new File(file));
HWPFDocument wordDocument = new HWPFDocument(input);
WordToHtmlConverter wordToHtmlConverter = new WordToHtmlConverter(
DocumentBuilderFactory.newInstance().newDocumentBuilder()
.newDocument());
// 設(shè)置圖片存放的位置
wordToHtmlConverter.setPicturesManager(new PicturesManager() {
public String savePicture(byte[] content, PictureType pictureType,
String suggestedName, float widthInches, float heightInches) {
File imgPath = new File(imagePath);
if (!imgPath.exists()) {// 圖片目錄不存在則創(chuàng)建
imgPath.mkdirs();
}
File file = new File(imagePath + suggestedName);
try {
OutputStream os = new FileOutputStream(file);
os.write(content);
os.close();
} catch (FileNotFoundException e) {
e.printStackTrace();
} catch (IOException e) {
e.printStackTrace();
}
// 圖片在html文件上的路徑 相對路徑
return "image/" + suggestedName;
}
});
// 解析word文檔
wordToHtmlConverter.processDocument(wordDocument);
Document htmlDocument = wordToHtmlConverter.getDocument();
// 生成html文件上級文件夾
File folder = new File(htmlPath);
if (!folder.exists()) {
folder.mkdirs();
}
// 生成html文件地址
OutputStream outStream = new FileOutputStream(htmlFile);
DOMSource domSource = new DOMSource(htmlDocument);
StreamResult streamResult = new StreamResult(outStream);
TransformerFactory factory = TransformerFactory.newInstance();
Transformer serializer = factory.newTransformer();
serializer.setOutputProperty(OutputKeys.ENCODING, "utf-8");
serializer.setOutputProperty(OutputKeys.INDENT, "yes");
serializer.setOutputProperty(OutputKeys.METHOD, "html");
serializer.transform(domSource, streamResult);
outStream.close();
return htmlFile.getAbsolutePath();
}
/**
* 2007版本word轉(zhuǎn)換成html 2017-2-27
*
* @param wordPath
* word文件路徑
* @param wordName
* word文件名稱無后綴
* @param suffix
* word文件后綴
* @return
* @throws IOException
*/
public static String Word2007ToHtml(String wordPath, String wordName, String suffix)
throws IOException {
String htmlPath = wordPath + File.separator + "html"
+ File.separator;
String htmlName = wordName + ".html";
String imagePath = htmlPath + "image" + File.separator;
// 判斷html文件是否存在
File htmlFile = new File(htmlPath + htmlName);
// if (htmlFile.exists()) {
// return htmlFile.getAbsolutePath();
// }
// word文件
File wordFile = new File(wordPath + File.separator + wordName + suffix);
// 1) 加載word文檔生成 XWPFDocument對象
InputStream in = new FileInputStream(wordFile);
XWPFDocument document = new XWPFDocument(in);
// 2) 解析 XHTML配置 (這里設(shè)置IURIResolver來設(shè)置圖片存放的目錄)
File imgFolder = new File(imagePath);
XHTMLOptions options = XHTMLOptions.create();
options.setExtractor(new FileImageExtractor(imgFolder));
// html中圖片的路徑 相對路徑
options.URIResolver(new BasicURIResolver("image"));
options.setIgnoreStylesIfUnused(false);
options.setFragment(true);
// 3) 將 XWPFDocument轉(zhuǎn)換成XHTML
// 生成html文件上級文件夾
File folder = new File(htmlPath);
if (!folder.exists()) {
folder.mkdirs();
}
OutputStream out = new FileOutputStream(htmlFile);
XHTMLConverter.getInstance().convert(document, out, options);
return htmlFile.getAbsolutePath();
}
public static void main(String[] args) throws Exception,
TransformerException, ParserConfigurationException {
System.out.println(Word2003ToHtml("C:/", "1", ".doc"));
// System.out.println(Word2007ToHtml("C:/", "docx", ".docx"));
}
}
需要的jar包
下載地址 https://pan.baidu.com/s/1jHJQSxK
找相關(guān)jar包找了好久，測試了03和07版本的word文檔伍宦，插入了簡單圖片咐鹤，均可轉(zhuǎn)換為HTML文件，復雜word文檔未做測試签舞。
參考來源 http://www.jb51.net/article/109307.htm
