Springboot实现富文本HTML转Word(近乎百分之百还

写在前面：日常开发中，经常会碰到富文本使用场景，有些需求是必须导出到word中，所以我们来实现吧！

一、引入POM
<properties>
<poi.version>4.1.2</poi.version>
<hutool.version>4.6.10</hutool.version>
<guava.version>20.0</guava.version>
<commons-lang3.version>3.9</commons-lang3.version>
</properties>
<dependencies>
<dependency>
<groupId>com.google.guava</groupId>
<artifactId>guava</artifactId>
<version>{commons-lang3.version}</version>
</dependency>
<dependency>
<groupId>cn.hutool</groupId>
<artifactId>hutool-all</artifactId>
<version>{poi.version}</version>
</dependency>
<dependency>
<groupId>org.apache.poi</groupId>
<artifactId>poi</artifactId>
<version>{poi.version}</version>
</dependency>

<dependency>
<groupId>com.deepoove</groupId>
<artifactId>poi-tl</artifactId>
<version>1.9.1</version>
<exclusions>
<exclusion>
<groupId>org.apache.poi</groupId>
<artifactId>poi-ooxml</artifactId>
</exclusion>
</exclusions>
</dependency>
<dependency>
<groupId>org.apache.poi</groupId>
<artifactId>ooxml-schemas</artifactId>
<version>1.4</version>
</dependency>

<dependency>
<groupId>io.github.draco1023</groupId>
<artifactId>poi-tl-ext</artifactId>
<version>0.3.3</version>
<exclusions>
<exclusion>
<groupId>com.deepoove</groupId>
<artifactId>poi-tl</artifactId>
</exclusion>
<exclusion>
<groupId>org.apache.poi</groupId>
<artifactId>ooxml-schemas</artifactId>
</exclusion>
</exclusions>
</dependency>

<dependency>
<groupId>org.w3c.css</groupId>
<artifactId>sac</artifactId>
<version>1.3</version>
</dependency>
<dependency>
<groupId>net.sourceforge.cssparser</groupId>
<artifactId>cssparser</artifactId>
<version>0.9.29</version>
</dependency>

<dependency>
<groupId>e-iceblue</groupId>
<artifactId>spire.doc.free</artifactId>
<version>3.9.0</version>
</dependency>
</dependencies>
二、Java测试类

import cn.hutool.core.io.FileUtil;
import com.deepoove.poi.XWPFTemplate;
import com.deepoove.poi.config.Configure;
import com.deepoove.poi.data.PictureRenderData;
import com.deepoove.poi.policy.PictureRenderPolicy;
import com.deepoove.poi.xwpf.NiceXWPFDocument;
import com.spire.doc.Document;
import com.spire.doc.DocumentObject;
import com.spire.doc.Section;
import com.spire.doc.FileFormat;
import org.apache.commons.io.IOUtils;
import org.apache.commons.lang3.StringUtils;
import org.ddr.poi.html.HtmlRenderPolicy;

import java.io.;
import java.util.;

/**

• java生成word

• @author wangdy

• @date 2021-06-15 11:16
  */
  public class Java2Word {

  public static void main(String[] args) throws IOException {
  // html渲染插件
  HtmlRenderPolicy htmlRenderPolicy = new HtmlRenderPolicy();
  // 第一个案例
  Configure configure = Configure.builder()
  // 注册html解析插件
  .bind("content", htmlRenderPolicy)
  // .bind("content2", htmlRenderPolicy)
  .build();
  // 映射数据Map
  Map<String, Object> data = new HashMap<>();
  data.put("title", "我是一个案例名称1");
  data.put("keywords", "我是一个案例keywords");
  data.put("cty", "我是一个案例cty");
  data.put("content", readFile("/demo1.html"));
  // 读取模板文件，并渲染数据
  XWPFTemplate template = XWPFTemplate.compile(getResourceInputStream("/html2wordtemplate.docx"), configure).render(data);
  // 写入文件
  template.writeToFile("demo1.docx");
  template.close();

   // 第二个案例
   Configure configure1 = Configure.builder()
           .bind("content", htmlRenderPolicy)
           .build();
   Map<String, Object> data1 = new HashMap<>();
   data1.put("title", "我是一个案例名称2");
   data1.put("keywords", "我是一个案例keywords2");
   data1.put("cty", "我是一个案例分类2");
   data1.put("content", readFile("/demo2.html"));
   XWPFTemplate template1 = XWPFTemplate.compile(getResourceInputStream("/html2wordtemplate.docx"), configure1).render(data1);
   template1.writeToFile("demo2.docx");
   template1.close();
  
   // 合并word
   //加载需要合并的两个文档
   Document doc1 = new Document("demo1.docx");
   Document doc2 = new Document("demo2.docx");
   //获取文档1的最后一节
   Section lastsec = doc1.getLastSection();
   //遍历文档2的所有段落内容，添加到文档1
   for (Section section : (Iterable<Section>) doc2.getSections()) {
       for (DocumentObject obj : (Iterable<DocumentObject>) section.getBody().getChildObjects()) {
           lastsec.getBody().getChildObjects().add(obj.deepClone());
       }
   }
   //保存合并后的文档
   doc1.saveToFile("ALL-Word.docx", FileFormat.Docx);
  

  }

/**
* 读取文件内容
*
* @param resourceFile 文件路径
* @return 文件内容
* @throws IOException IO异常
* import org.apache.commons.io.IOUtils;
*/
public static String readFile(String resourceFile) throws IOException {
try (InputStream inputStream = FileReader.class.getResourceAsStream(resourceFile)) {
return IOUtils.toString(inputStream, StandardCharsets.UTF_8);
}
}

}

三、运行结果

image.png

注意：poi-tl-ext 0.3.3的版本，在实际用的过程中，对于如下html解析有误，比如行距问题，切换到到0.3.18解决问题。