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
POI操作word和html相互转化的更多相关文章
- Java操作word文档使用JACOB和POI操作word,Excel,PPT需要的jar包
可参考文档: http://wibiline.iteye.com/blog/1725492 下载jar包 http://download.csdn.net/download/javashixiaofe ...
- 利用poi操作word文档
关键字:POI JAVA 批注 总页数 总字符数 一:认识POI Apache POI是一个开源的利用Java读写Excel.WORD等微软OLE2组件文档的项目.最新的3.5版本有很多改进,加入了对 ...
- poi操作word文档文件操作
import org.apache.poi.POITextExtractor; import org.apache.poi.hwpf.extractor.WordExtractor; //得到.doc ...
- java使用poi操作word, 支持动态的行(一个占位符插入多条)和表格中动态行, 支持图片
依赖 <dependency> <groupId>org.apache.poi</groupId> <artifactId>poi</artifa ...
- poi操作word 2007 常用方法总结
import java.io.File; import java.io.FileInputStream; import java.io.FileOutputStream; import java.io ...
- 简单poi操作word@2020
个人采用POI(3.16版本)一.段落部分XWPFParagraph paragraph = docxDocument.createParagraph();1.段落对齐方式paragraph.setA ...
- Apache Poi 操作word,替换字符保留样式问题,runs段落混乱问题。
关于这个问题也是刚好遇到,一通搜索也没有找到类似的或者是有效的方法.下面介绍一下. 首先apache poi的引入 <dependency> <groupId>org.apac ...
- poi操作Word创建超链接
项目引入poi: <dependency> <groupId>org.apache.poi</groupId> <artifactId>poi</ ...
- poi操作word,简单写docx
参考博客: https://www.cnblogs.com/guilty/p/3977016.html 在HWPF中换行符是"\013",在XWPF中是run.addBreak() ...
随机推荐
- 帝国cms后台集成ueditor编辑器
我更换成百度编辑器的原因有以下几点:1.使用百度编辑器的图片粘贴上传功能,这个功能实在是太有必要了,有开发的过程中或上传的过程中,通常用qq直接截图,直接放到文章上面,避免了再放到本地保存的情况,真是 ...
- vue 自定义全局按键修饰符
在监听键盘事件时,我们经常需要检查常见的键值.Vue 允许为 v-on 在监听键盘事件时添加按键修饰符: JS部分: Vue.config.keyCodes = { f2:113, } var app ...
- 下一个时代的发展架构竟然是它!FaaaaaaaaS到底是个啥?
欢迎大家前往腾讯云+社区,获取更多腾讯海量技术实践干货哦~ 本文由腾讯云serverless团队发表于云+社区专栏 导读:2018年7月6 - 7日,一年一度的技术圈盛会ArchSummit全球架构师 ...
- 2019第十届蓝桥杯 E题 迷宫
/*输入 30 50 01010101001011001001010110010110100100001000101010 00001000100000101010010000100000001001 ...
- Vue的computed计算属性是如何实现的
一个开始 有如下代码,full是一个计算属性,开始,他的值是'hello world',1s后,msg变成了‘I like’, full的值同步变成了'I like world';其原理解析来看一下. ...
- LeetCode 303. Range Sum Query - Immutable (C++)
题目: Given an integer array nums, find the sum of the elements between indices iand j (i ≤ j), inclus ...
- spring boot开启热部署
步骤一:添加依赖 <dependency> <groupId>org.springframework.boot</groupId> <artifactId&g ...
- mysql 修改语句及耗时
1.含有某串字母的字段替换: update imagetable set imageID = replace(imageID, 'ZH0211001', 'ZH4111001') 只要imageID含 ...
- 一个简单的加减乘除自动生成小程序升级版(JAVA)
import java.util.Scanner; public class Suan { public static void main(String[] args) { int []b;//设置数 ...
- gdb调试器学习链接
首先要带 -g 选项用gcc编译 常用指令:http://linuxtools-rst.readthedocs.io/zh_CN/latest/tool/gdb.html#gdb 带main的命令行参 ...