1.依賴
<dependency>
<groupId>org.apache.poi</groupId>
<artifactId>poi-ooxml</artifactId>
<version>3.15</version>
</dependency>
<dependency>
<groupId>org.apache.poi</groupId>
<artifactId>poi-scratchpad</artifactId>
<version>3.15</version>
</dependency>
<dependency>
<groupId>fr.opensagres.xdocreport</groupId>
<artifactId>fr.opensagres.xdocreport.document</artifactId>
<version>1.0.5</version>
</dependency>
<dependency>
<groupId>fr.opensagres.xdocreport</groupId>
<artifactId>org.apache.poi.xwpf.converter.xhtml</artifactId>
<version>1.0.5</version>
</dependency>
2.java代碼
package com.dxl.core;
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.xhtml.XHTMLConverter;
import org.apache.poi.xwpf.converter.xhtml.XHTMLOptions;
import org.apache.poi.xwpf.usermodel.XWPFDocument;
import org.w3c.dom.Document;
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 java.io.*;
/**
* <b> Word轉html(會丟失Word的格式)
* </b><br><br><i>Description</i> :
* <br><br>Date: 2019/11/12 ${time} <br>Author : dxl
*/
public class WordToHtmlUtil {
/**
* 2007版本word轉換成html 2018-4-9
*
* @param wordPath
* word文件路徑
* @param wordName
* word文件名稱無後綴
* @param suffix
* word文件後綴
* @return
* @throws IOException
*/
public static String Word2007ToHtml(String wordPath, String wordName,
String suffix) throws IOException {
wordPath = "E:\\myGiteeProject\\mygenerator\\src\\main\\resources\\testdocx\\";
wordName = "demo3";
suffix =".docx";
String htmlPath = wordPath + File.separator + wordName + "_show"
+ 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 (這裏設置IURIResolver來設置圖片存放的目錄)
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);
// 也可以使用字符數組流獲取解析的內容
// ByteArrayOutputStream baos = new ByteArrayOutputStream();
// XHTMLConverter.getInstance().convert(document, baos, options);
// String content = baos.toString();
// System.out.println("2007-docx"+content);
// baos.close();
return htmlFile.getAbsolutePath();
}
/**
* 將word2003轉換爲html文件 2018-4-9
*
* @param wordPath
* word文件路徑
* @param wordName
* word文件名稱無後綴
* @param suffix
* word文件後綴
* @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 + wordName + "_show"
+ File.separator;
String htmlName = wordName + ".html";
final 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();
}
// 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
// 也可以使用字符數組流獲取解析的內容
// ByteArrayOutputStream baos = new ByteArrayOutputStream();
// OutputStream outStream = new BufferedOutputStream(baos);
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);
// 也可以使用字符數組流獲取解析的內容
// String content = baos.toString();
// System.out.println(content);
// baos.close();
// System.out.println("2003-doc"+content);
return htmlFile.getAbsolutePath();
}
}
注:只測試了20072即docx格式的
3.效果
生成目錄(我是生成在項目裏了,測試方便)
html: