java poi doc 转html_用poi实现doc转html

废话，不多说直接上代码。

一、doc转html，并且带文件夹

/ * word转html

* html转图片

* @param tagPath 转换html文件之后，所带的图片附件文件夹

* @param sourceFileName 源文件

* @param outPath 输出文件xx.html

* @return

* @throws Exception

*/

public static String docToHtml(String tagPath,

String sourceFileName, String outPath) throws Exception {

File file = new File(tagPath);

if(!file.exists()) {

file.mkdirs();

}

HWPFDocument wordDocument = new HWPFDocument(new FileInputStream(sourceFileName));

org.w3c.dom.Document document = DocumentBuilderFactory.newInstance().newDocumentBuilder().newDocument();

WordToHtmlConverter wordToHtmlConverter = new WordToHtmlConverter(document);

//保存图片，并返回图片的相对路径

wordToHtmlConverter.setPicturesManager((content, pictureType, name, width, height) -> {

try (FileOutputStream out = new FileOutputStream(tagPath + name)) {

out.write(content);

} catch (Exception e) {

e.printStackTrace();

}

return "image/" + name;

});

wordToHtmlConverter.processDocument(wordDocument);

org.w3c.dom.Document htmlDocument = wordToHtmlConverter.getDocument();

DOMSource domSource = new DOMSource(htmlDocument);

StreamResult streamResult = new StreamResult(new File(outPath));

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);

return outPath;

}

调用：

/**doc

* 转html

*/

String tagPath = "D:\\red_ant_file\\20180915\\image\\";

String sourcePath = "D:\\red_ant_file\\20180915\\RedAnt的实验作业.doc";

String outPath = "D:\\red_ant_file\\20180915\\123.html";

try {

AllServiceIsHere.docToHtml(tagPath, sourcePath, outPath);

} catch (Exception e) {

// TODO Auto-generated catch block

e.printStackTrace();

}

演示：

走你：