POI操作word和html相互转化

下面是里两个类:第一个类是html转为word,第二个是word转html(最下面附上jar包下载链接)

package com.wz.poi.wordHtml;

/**
* 2018/4/24
* @author Administrator
*
*/

import java.io.BufferedReader;
import java.io.ByteArrayInputStream;
import java.io.FileInputStream;
import java.io.FileOutputStream;
import java.io.IOException;
import java.io.InputStream;
import java.io.InputStreamReader;
import java.io.OutputStream;

import org.apache.poi.poifs.filesystem.POIFSFileSystem;

public class HtmlToWord {

/**
* 外部接口
* @param htmlPath html文件的路径
* @param cssPath css文件的路径
* @param wordPath word文件的路径(保存本地的路径)
* @param code 编码方式(一般都为utf-8)
* @throws Exception
*/
public void htmlToWord2(String htmlPath, String cssPath, String wordPath, String code) throws Exception {
/*InputStream bodyIs = new FileInputStream("H:\\MyTest\\Java\\test_show\\test.html");
InputStream cssIs = new FileInputStream("H:\\MyTest\\Java\\test_show\\test.css");*/
InputStream bodyIs = new FileInputStream(htmlPath);
InputStream cssIs = new FileInputStream(cssPath);
String body = this.getContent(bodyIs);
String css = this.getContent(cssIs);
// 拼一个标准的HTML格式文档
String content = "<html><head><style>" + css + "</style></head><body>" + body + "</body></html>";
InputStream is = new ByteArrayInputStream(content.getBytes(code));
OutputStream os = new FileOutputStream(wordPath);
this.inputStreamToWord(is, os);
}

/**
* 把is写入到对应的word输出流os中不考虑异常的捕获，直接抛出
*
* @param is
* @param os
* @throws IOException
*/
private void inputStreamToWord(InputStream is, OutputStream os) throws IOException {
POIFSFileSystem fs = new POIFSFileSystem();
// 对应于org.apache.poi.hdf.extractor.WordDocument
fs.createDocument(is, "WordDocument");
fs.writeFilesystem(os);
os.close();
is.close();
fs.close();
}

/**
* 把输入流里面的内容以UTF-8编码当文本取出。不考虑异常，直接抛出
*
* @param ises
* @return
* @throws IOException
*/
private String getContent(InputStream... ises) throws IOException {
if (ises != null) {
StringBuilder result = new StringBuilder();
BufferedReader br;
String line;
for (InputStream is : ises) {
br = new BufferedReader(new InputStreamReader(is, "UTF-8"));
while ((line = br.readLine()) != null) {
result.append(line);
}
}
return result.toString();
}
return null;
}

}

package com.wz.poi.wordHtml;

/**
* 2018/4/24
* @author Administrator
*
*/

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.xhtml.XHTMLConverter;
import org.apache.poi.xwpf.converter.xhtml.XHTMLOptions;
import org.apache.poi.xwpf.usermodel.XWPFDocument;
import org.w3c.dom.Document;

public class WordToHtml {

/**
* 调用的模板
* @param args
*/
public static void main(String[] args) {
try {
Word2003ToHtml("H:\\MyTest\\Java\\","test",".doc");
} catch (IOException e) {
// TODO Auto-generated catch block
e.printStackTrace();
} catch (TransformerException e) {
// TODO Auto-generated catch block
e.printStackTrace();
} catch (ParserConfigurationException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
}

/**
* 将word2003转换为html文件 2017-2-27
* @param wordPath word文件路径
* @param wordName word文件名称无后缀
* @param suffix word文件后缀
* @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;

//判断html文件是否存在
File htmlFile = new File(htmlPath + htmlName);
if(htmlFile.exists()){
return htmlFile.getAbsolutePath();
}

//原word文档
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());
//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();
}
//图片在html文件上的路径相对路径
return "image/" + suggestedName;
}
});

//解析word文档
wordToHtmlConverter.processDocument(wordDocument);
Document htmlDocument = wordToHtmlConverter.getDocument();

//生成html文件上级文件夹
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转换成html 2017-2-27
* @param wordPath word文件路径
* @param wordName word文件名称无后缀
* @param suffix word文件后缀
* @return
* @throws IOException
*/
public String Word2007ToHtml(String wordPath,String wordName,String suffix) throws IOException {
String htmlPath = wordPath + File.separator + wordName + "_show" + File.separator;
String htmlName = wordName + ".html";
String imagePath = htmlPath + "image" + File.separator;

//判断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) 加载word文档生成 XWPFDocument对象
InputStream in = new FileInputStream(wordFile);
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 imgFolder = new File(imagePath);
XHTMLOptions options = XHTMLOptions.create();
options.setExtractor(new FileImageExtractor(imgFolder));
//html中图片的路径相对路径
options.URIResolver(new BasicURIResolver("image"));
options.setIgnoreStylesIfUnused(false);
options.setFragment(true);

// 3) 将 XWPFDocument转换成XHTML
//生成html文件上级文件夹
File folder = new File(htmlPath);
if(!folder.exists()){
folder.mkdirs();
}
OutputStream out = new FileOutputStream(htmlFile);
XHTMLConverter.getInstance().convert(document, out, options);

return htmlFile.getAbsolutePath();
}

}

附上百度网盘下载连接:

链接：https://pan.baidu.com/s/1t_jXUq3CuhZo9j_UI4URAQ 密码：r2qi

巴特西

POI操作word和html相互转化

最新文章

热门文章