JAVA利用POI scratchpad 5.2.1 将Word文档doc格式转换成HTML 格式 含文档里面图片
一、POM文件
org.apache.poi
poi-scratchpad
5.2.1
二、转换具体代码
package org.zhao.component;
import org.apache.commons.collections4.CollectionUtils;
import org.apache.poi.hwpf.HWPFDocument;
import org.apache.poi.hwpf.converter.WordToHtmlConverter;
import org.apache.poi.hwpf.usermodel.Picture;
import org.w3c.dom.Document;
import javax.xml.parsers.DocumentBuilderFactory;
import javax.xml.transform.OutputKeys;
import javax.xml.transform.Transformer;
import javax.xml.transform.TransformerFactory;
import javax.xml.transform.dom.DOMSource;
import javax.xml.transform.stream.StreamResult;
import java.io.File;
import java.io.FileInputStream;
import java.io.FileOutputStream;
import java.io.IOException;
import java.util.List;
/**
* word文档转换HTML 含文档里面的图片
*
* @author Administrator
* @date 2022年03月18日
*/
public class WordComponent {
private static String getFileExtname(String filename) {
return filename.substring(filename.lastIndexOf(".")).toLowerCase();
}
private static void createFileDir(String dirPath) {
File file = new File(dirPath);
if (!file.exists() && !file.isDirectory()) {
boolean r = file.mkdirs();
System.out.println(dirPath + "不存在，创建文件夹->" + r);
}
}
public static void docToHtml(String docFilePath) throws Exception {
File file = new File(docFilePath);
if (!file.exists()) {
System.err.println(docFilePath + "->文件不存在");
return;
}
String name = file.getName();
String dirName = name.replace(getFileExtname(name), "");
if (dirName.length() > 100) {
dirName = String.valueOf(System.currentTimeMillis());
}
//html文件目录
String htmlDirPath = file.getParent() + dirName;
//创建目录
createFileDir(htmlDirPath);
//存储图片目录
String imagePath = htmlDirPath + "/image/";
HWPFDocument wordDocument = new HWPFDocument(new FileInputStream(docFilePath));
WordToHtmlConverter wordToHtmlConverter = new WordToHtmlConverter(DocumentBuilderFactory.newInstance().newDocumentBuilder().newDocument());
wordToHtmlConverter.setPicturesManager((content, pictureType, suggestedName, widthInches, heightInches) -> imagePath + suggestedName);
wordToHtmlConverter.processDocument(wordDocument);
List allPictures = wordDocument.getPicturesTable().getAllPictures();
if (CollectionUtils.isNotEmpty(allPictures)) {
createFileDir(imagePath);
allPictures.forEach(picture -> {
try {
picture.writeImageContent(new FileOutputStream(imagePath + picture.suggestFullFileName()));
} catch (IOException e) {
e.printStackTrace();
}
});
}
Document htmlDocument = wordToHtmlConverter.getDocument();
String htmlPath = htmlDirPath + "/" + dirName + ".html";
File out = new File(htmlPath);
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);
System.out.println("转换成功");
}
public static void main(String[] args) throws Exception {
docToHtml("D:/我是一篇简历.doc");
}
} 三、Word内容
四、转换后内容
代码块
个人简历表格
个人简历表格
姓 名
出生年月
民族
籍 贯
毕业时间
学历
性 别
专 业
求
职
意
向
兴
趣
爱
好
社会
实践
经验
在校期间担任过何种职务
计
算
机
水
平
自
我
评
价