HTML网页转DOC文档

1、引入POM相关包

<properties>
    <poi.version>4.1.2</poi.version>
</properties>
<dependency>
    <groupId>org.jsoup</groupId>
    <artifactId>jsoup</artifactId>
    <version>1.13.1</version>
</dependency>
<dependency>
    <groupId>org.apache.poi</groupId>
    <artifactId>poi</artifactId>
    <version>${poi.version}</version>
</dependency>
<dependency>
    <groupId>org.apache.poi</groupId>
    <artifactId>poi-ooxml</artifactId>
    <version>${poi.version}</version>
</dependency>
<dependency>
    <groupId>org.apache.poi</groupId>
    <artifactId>poi-ooxml-schemas</artifactId>
    <version>${poi.version}</version>
</dependency>
<dependency>
    <groupId>org.apache.poi</groupId>
    <artifactId>poi-scratchpad</artifactId>
    <version>${poi.version}</version>
</dependency>

2、代码编写

import org.apache.commons.lang3.StringUtils;
import org.apache.poi.poifs.filesystem.DirectoryEntry;
import org.apache.poi.poifs.filesystem.POIFSFileSystem;
import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.springframework.web.multipart.MultipartFile;
import java.io.File;
import java.io.FileOutputStream;
import java.text.SimpleDateFormat;
import java.util.Date;
import java.io.*;
import java.util.*;


public class World {


    /**
     * Html转Word
     * @author zsj
     */
    public static MultipartFile htmlToWord(String html, String filePath)  throws Exception {
        // 1.生成文件名称
        SimpleDateFormat sdf = new SimpleDateFormat("yyyyMMddHHmmss");
        String fileName = filePath+"/"+"LangChain" + sdf.format(new Date())+".doc";
        // 返回MyltipartFile类
        MultipartFile multipartFile = null;
        if (StringUtils.isNotEmpty(html)) {
            if (StringUtils.isNotEmpty(html)) {
                // 生成临时文件（doc）
                try {
                    // 生成doc格式的word文档，需要手动改为docx
                    byte by[] = html.getBytes("UTF-8");
                    ByteArrayInputStream byteArrayInputStream = new ByteArrayInputStream(by);
                    POIFSFileSystem poifsFileSystem = new POIFSFileSystem();
                    DirectoryEntry directoryEntry = poifsFileSystem.getRoot();
                    directoryEntry.createDocument("WordDocument", byteArrayInputStream);
                    // 临时文件夹
// 临时文件夹
                    String sqlFilePath = "I:\\supply-link\\工作" + File.separator + "patrolReport" + File.separator + "temp_" + UUID.randomUUID();
                    File directory = new File(sqlFilePath);
                    if (!directory.exists()) {
                        directory.mkdirs();
                    }


                    // 文件路径
                    String fileUrl = filePath + File.separator + "招标公告详情.doc";
                    // 保存doc文档
                    FileOutputStream outputStream = new FileOutputStream(fileUrl);
                    poifsFileSystem.writeFilesystem(outputStream);
                    byteArrayInputStream.close();
                    outputStream.close();
                    File file = new File(fileUrl);

                } catch (Exception e) {
                    e.printStackTrace();
                }
            }


        }
        return multipartFile;
    }

    public static void main(String[] args) {
        String htmlUrl = "***"; // 替换为你要解析的HTML页面的URL
        try {
            // 解析HTML
            Document doc = Jsoup.connect(htmlUrl).get();
            String htmlSection = doc.select(".Content").html();
            //String html =World.html ;
            String filePath="I:\\supply-link\\工作";
            htmlToWord(htmlSection, filePath);

        } catch (Exception e) {
            e.printStackTrace();
        }
    }
}

3、页面效果

3、word成品效果