1、简介
最近，因项目需要，需要对word文档进行解析拆分，感觉直接解析word有点麻烦，于是想到，先将word转为html文档，然后用jsoup解析html文件更方便，jsoup的使用可以参考相关API,操作简单，类似javascript。
word转html文档方法如下：
一般word文件后缀有doc、docx两种。docx是office word 2007以及以后版本文档的扩展名；doc是office word 2003文档保存的扩展名。对于这两种格式的word转换成html需要使用不同的方法。
2、添加依赖
<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>
对于docx格式的文档使用poi进行转换。依赖如下：
<dependency>
<groupId>org.apache.poi</groupId>
<artifactId>poi</artifactId>
<version>3.12</version>
</dependency>
<dependency>
<groupId>org.apache.poi</groupId>
<artifactId>poi-scratchpad</artifactId>
<version>3.12</version>
</dependency>
3、代码示例
package com.test.word;
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.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.junit.Test;
import org.w3c.dom.Document;
/**
* word 转换成html
*/
public class WordToHtml {
/**
* 2007版本word转换成html
* @throws IOException
*/
@Test
public void Word2007ToHtml() throws IOException {
String filepath = "C:/test/";
String fileName = "滕王阁序2007.docx";
String htmlName = "滕王阁序2007.html";
final String file = filepath + fileName;
File f = new File(file);
if (!f.exists()) {
System.out.println("Sorry File does not Exists!");
} else {
if (f.getName().endsWith(".docx") || f.getName().endsWith(".DOCX")) {
// 1) 加载word文档生成 XWPFDocument对象
InputStream in = new FileInputStream(f);
XWPFDocument document = new XWPFDocument(in);
// 2) 解析 XHTML配置 (这里设置IURIResolver来设置图片存放的目录)
File imageFolderFile = new File(filepath);
XHTMLOptions options = XHTMLOptions.create().URIResolver(new FileURIResolver(imageFolderFile));
options.setExtractor(new FileImageExtractor(imageFolderFile));
options.setIgnoreStylesIfUnused(false);
options.setFragment(true);
// 3) 将 XWPFDocument转换成XHTML
OutputStream out = new FileOutputStream(new File(filepath + htmlName));
XHTMLConverter.getInstance().convert(document, out, options);
//也可以使用字符数组流获取解析的内容
// ByteArrayOutputStream baos = new ByteArrayOutputStream();
// XHTMLConverter.getInstance().convert(document, baos, options);
// String content = baos.toString();
// System.out.println(content);
// baos.close();
} else {
System.out.println("Enter only MS Office 2007+ files");
}
}
}
/**
* /**
* 2003版本word转换成html
* @throws IOException
* @throws TransformerException
* @throws ParserConfigurationException
*/
@Test
public void Word2003ToHtml() throws IOException, TransformerException, ParserConfigurationException {
String filepath = "C:/test/";
final String imagepath = "C:/test/image/";
String fileName = "滕王阁序2003.doc";
String htmlName = "滕王阁序2003.html";
final String file = filepath + fileName;
InputStream input = new FileInputStream(new File(file));
HWPFDocument wordDocument = new HWPFDocument(input);
WordToHtmlConverter wordToHtmlConverter = new WordToHtmlConverter(DocumentBuilderFactory.newInstance().newDocumentBuilder().newDocument());
//设置图片存放的位置
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()){
//图片目录不存在则创建
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();
}
return imagepath + suggestedName;
}
});
//解析word文档
wordToHtmlConverter.processDocument(wordDocument);
Document htmlDocument = wordToHtmlConverter.getDocument();
File htmlFile = new File(filepath + htmlName);
OutputStream outStream = new FileOutputStream(htmlFile);
//也可以使用字符数组流获取解析的内容
// ByteArrayOutputStream baos = new ByteArrayOutputStream();
// OutputStream outStream = new BufferedOutputStream(baos);
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);
//也可以使用字符数组流获取解析的内容
// String content = baos.toString();
// System.out.println(content);
// baos.close();
outStream.close();
}
}
运行结果：
原文参考：https://www.cnblogs.com/always-online/p/4800131.html