word解析

1、pom.xml

    com.aspose
    aspose-words
    15.8.0


    org.jsoup
    jsoup
    1.14.3

2、代码

package com.nancal.plant.controller;


import com.aspose.words.Document;
import com.aspose.words.SaveFormat;
import com.nancal.plant.dto.WordDTO;
import io.swagger.annotations.Api;
import io.swagger.annotations.ApiOperation;
import lombok.extern.slf4j.Slf4j;
import org.apache.commons.collections4.CollectionUtils;
import org.apache.commons.io.IOUtils;
import org.apache.commons.lang3.StringUtils;
import org.jsoup.Jsoup;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;
import org.springframework.web.bind.annotation.*;
import org.springframework.web.multipart.MultipartFile;
import java.io.File;
import java.io.FileInputStream;
import java.io.IOException;
import java.io.InputStream;
import java.util.*;

@RestController
@RequestMapping("/dme/api/v1")
@Api(tags = "文件的控制器")
@Slf4j
public class FileController {
    /**
     * word文档解析接口
     *
     * @param multipartFile
     * @return
     * @throws Exception
     */
    @ApiOperation(value = "word文档解析接口")
    @PostMapping(value = "/word/upload")
    public List commonDmeRequest(@RequestParam("file") MultipartFile multipartFile) throws Exception {
        InputStream inputStream = multipartFile.getInputStream();
        Document document = new Document(inputStream);
        String tmp = System.getProperty("java.io.tmpdir");
        String filename = multipartFile.getOriginalFilename();
        if (StringUtils.isNotBlank(filename)) {
            filename = filename.substring(0, filename.lastIndexOf("."));
        }
        String htmlFilePath = tmp + filename +".html";
        document.save(htmlFilePath, SaveFormat.HTML);
        String htmlStr = getHtmlStrFromFile(htmlFilePath);
        org.jsoup.nodes.Document htmlDoc = Jsoup.parse(htmlStr);
        // 解析word
        List wordDTOList = parseWord(htmlDoc);
        return wordDTOList;
    }


    /**
     * 解析word
     *
     * @param htmlDoc
     * @return
     * @throws Exception
     */
    private List parseWord(org.jsoup.nodes.Document htmlDoc) throws Exception {
        Elements elementList = htmlDoc.getElementsByTag("h1");
        if (CollectionUtils.isEmpty(elementList)) {
            throw new Exception("不存在一级标题");
        }
        List wordDTOList = new ArrayList<>();
        for (Element element : elementList) {
            WordDTO wordDTO = new WordDTO();
            parseElement(element, wordDTO);
            wordDTOList.add(wordDTO);
        }
        return wordDTOList;
    }

    /**
     * 递归解析单个h1整个结构
     *
     * @param element
     * @param wordDTO
     */
    private void parseElement(Element element, WordDTO wordDTO) {
        wordDTO.setTitle(element.toString());
        Element nextElement = element.nextElementSibling();
        String tagName = nextElement.tagName();
        if (!Objects.equals("p", tagName)) {
            WordDTO word = new WordDTO();
            wordDTO.setChild(word);
            parseElement(nextElement, word);
        } else {
            wordDTO.setContent(nextElement.toString());
        }
    }

    private static String getHtmlStrFromFile(String filePath) throws IOException {
        FileInputStream in = null;
        File file = new File(filePath);
        Long filelength = file.length();
        byte[] filecontent = new byte[filelength.intValue()];
        try {
            in = new FileInputStream(file);
            in.read(filecontent);
        } catch (IOException e) {
            e.printStackTrace();
        } finally {
            IOUtils.closeQuietly(in);
        }
        return new String(filecontent, "UTF-8");
    }

}

3、WordDTO

package com.nancal.plant.dto;


import lombok.AllArgsConstructor;
import lombok.Data;
import lombok.NoArgsConstructor;

/**
 * wordDTO
 *
 * @since 2023-07-19
 * @author zhouwb
 *
 */
@NoArgsConstructor
@AllArgsConstructor
@Data
public class WordDTO {
    // 标题
    private String title;

    // 子节点
    private WordDTO child;

    // 内容
    private String content;
}