基于springboot实现的最便捷的解析word文档

概述

导入excel或word是一些web应用常见的需求，本demo详细介绍怎么导入word,读取word里面的数据

详细

一、运行效果

二、实现过程

①、首先用maven快速搭建一个spring boot 项目

<properties>
        <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
        <project.reporting.outputEncoding>UTF-8</project.reporting.outputEncoding>
        <java.version>1.8</java.version>
    </properties>
  
    <dependencies>
        <dependency>
            <groupId>org.springframework.boot</groupId>
            <artifactId>spring-boot-starter-web</artifactId>
        </dependency>
    </dependencies>

②、添加启动主类

@SpringBootApplication
public class WordParseApplication {
        public static void main(String[] args) {
            SpringApplication.run(WordParseApplication.class, args);
        }
}

③、引入poi和swagger相关依赖

<!-- 引入poi -->
        <dependency>
            <groupId>org.apache.poi</groupId>
            <artifactId>poi</artifactId>
            <version>3.17</version>
        </dependency>
        <dependency>
            <groupId>org.apache.poi</groupId>
            <artifactId>poi-ooxml</artifactId>
            <version>3.17</version>
        </dependency>
        <dependency>
            <groupId>org.apache.poi</groupId>
            <artifactId>poi-scratchpad</artifactId>
            <version>3.17</version>
        </dependency>

④、为了方便测试我们引入swagger，直接图形化界面调用接口

 <!-- 引入swagger相关jar包 -->
        <dependency>
            <groupId>io.springfox</groupId>
            <artifactId>springfox-swagger2</artifactId>
            <version>2.8.0</version>
        </dependency>
        <dependency>
            <groupId>io.springfox</groupId>
            <artifactId>springfox-swagger-ui</artifactId>
            <version>2.8.0</version>
        </dependency>

⑤、创建swagger配置类

import org.springframework.context.annotation.Bean;
import org.springframework.context.annotation.Configuration;
import springfox.documentation.builders.ApiInfoBuilder;
import springfox.documentation.builders.PathSelectors;
import springfox.documentation.builders.RequestHandlerSelectors;
import springfox.documentation.service.ApiInfo;
import springfox.documentation.service.Contact;
import springfox.documentation.spi.DocumentationType;
import springfox.documentation.spring.web.plugins.Docket;
import springfox.documentation.swagger2.annotations.EnableSwagger2;
  
@Configuration //让Spring来加载该类配置
@EnableSwagger2 //启用Swagger2
public class SwaggerConfig {
    @Bean
    public Docket dataManagerApi() {
        return new Docket(DocumentationType.SWAGGER_2)
                .groupName("POI解析word文档")
                .apiInfo(apiInfo())
                .select()
                .apis(RequestHandlerSelectors.basePackage("com.hello.word.controller"))
                .paths(PathSelectors.any()).build();
    }
  
    private ApiInfo apiInfo() {
        return new ApiInfoBuilder()
                .title("POI解析word文档")
                .description("POI解析word文档，包括doc和docx格式")
                .termsOfServiceUrl("-----")
                .contact(new Contact("zhangwq","----", "lion_qiang@163.com"))
                .version("1.0").build();
    }
  
}

⑥、PoiWordController中添加如下方法，解析doc和docx需要使用不同的组件

/**
     * 按段落解析一个word文档
     * @param file
     * @return
     * @throws Exception
     */
    @ApiOperation(value="解析word文档", notes="按段落解析word文档")
    @RequestMapping(value = "upload", method = RequestMethod.POST)
    public Map uploadFile(@RequestParam(value = "file", required = true) MultipartFile file){
        String textFileName=file.getOriginalFilename();
        Map wordMap = new LinkedHashMap();//创建一个map对象存放word中的内容
        try {
            if(textFileName.endsWith(".doc")){ //判断文件格式
                InputStream fis = file.getInputStream();
                WordExtractor wordExtractor = new WordExtractor(fis);//使用HWPF组件中WordExtractor类从Word文档中提取文本或段落
                int i=1;
                for(String words : wordExtractor.getParagraphText()){//获取段落内容
                    System.out.println(words);
                    wordMap.put("DOC文档，第（"+i+"）段内容",words);
                    i++;
                }
                fis.close();
            }
            if(textFileName.endsWith(".docx")){
                File uFile = new File("tempFile.docx");//创建一个临时文件
                if(!uFile.exists()){
                    uFile.createNewFile();
                }
                FileCopyUtils.copy(file.getBytes(), uFile);//复制文件内容
                OPCPackage opcPackage = POIXMLDocument.openPackage("tempFile.docx");//包含所有POI OOXML文档类的通用功能，打开一个文件包。
                XWPFDocument document = new XWPFDocument(opcPackage);//使用XWPF组件XWPFDocument类获取文档内容
                List<XWPFParagraph> paras = document.getParagraphs();
                int i=1;
                for(XWPFParagraph paragraph : paras){
                    String words = paragraph.getText();
                    System.out.println(words);
                    wordMap.put("DOCX文档，第（"+i+"）段内容",words);
                    i++;
                }
                uFile.delete();
            }
        } catch (Exception e) {
            e.printStackTrace();
        }
        System.out.println(wordMap);
        return wordMap;
    }

三、项目结构图

四、补充

实际应用中，每个段落可能会有特殊的用途。我们可以添加特殊字符对他们进行归类，按照自己的逻辑进行处理。