java 读取word文档的内容

首先在pom中添加依赖

		<dependency>
            <groupId>org.apache.poi</groupId>
            <artifactId>poi</artifactId>
            <version>4.0.0</version>
        </dependency>
        <dependency>
            <groupId>org.apache.poi</groupId>
            <artifactId>poi-ooxml</artifactId>
            <version>4.0.0</version>
        </dependency>
        <dependency>
            <groupId>org.apache.poi</groupId>
            <artifactId>poi-scratchpad</artifactId>
            <version>4.0.0</version>
        </dependency>

第一种java后台接收的是文件路径

public String readWord(String path){
        String buffer = "";
        try {
            if (path.endsWith(".doc")){
                InputStream is = new FileInputStream(new File(path));
                WordExtractor ex = new WordExtractor(is);
                buffer = ex.getText();
            }else if (path.endsWith(".docx")){
             /* 如果poi版本在4.0.0及以上那么可以使用注释的方式
             	OPCPackage opcPackage = POIXMLDocument.openPackage(path);
                POIXMLTextExtractor extractor = new XWPFWordExtractor(opcPackage);
                buffer = extractor.getText();*/
                FileInputStream fs = new FileInputStream(new File(path));
                XWPFDocument xdoc = new XWPFDocument(fs);
                XWPFWordExtractor extractor = new XWPFWordExtractor(xdoc);
                buffer = extractor.getText();
            }
        }catch (Exception e){
            e.printStackTrace();
        }
        return buffer;
    }

第二种java后台接收的是文件流

//使用MultipartFile 接收文件流
public void importWord(MultipartFile file) throws IOException {
        InputStream inputStream = file.getInputStream();
        String fileName = file.getOriginalFilename();
        String suff = fileName.substring(fileName.lastIndexOf(".") + 1);
        String content = "";
        if (suff.equals("docx")) {
            XWPFDocument xdoc = new XWPFDocument(inputStream);
            XWPFWordExtractor extractor = new XWPFWordExtractor(xdoc);
            content = extractor.getText();
            System.out.println(content);
            extractor.close();
        } else if (suff.equals("doc")) {
            WordExtractor ex = new WordExtractor(inputStream);
            content = ex.getText();
            System.out.println(content);
            ex.close();
        } else {
            System.out.println("此文件不是word文件");
        }
    }