【Java】Java实现读取Word文档中的文字信息

导入依赖

		<!-- https://mvnrepository.com/artifact/org.apache.poi/poi-ooxml -->
        <dependency>
            <groupId>org.apache.poi</groupId>
            <artifactId>poi-ooxml</artifactId>
            <version>3.17</version>
        </dependency>

        <!-- https://mvnrepository.com/artifact/org.apache.poi/poi-scratchpad -->
        <dependency>
            <groupId>org.apache.poi</groupId>
            <artifactId>poi-scratchpad</artifactId>
            <version>3.17</version>
        </dependency>

案例

本地文件

public static String readDocx(String path) {
        String buffer = "";
        try {
            if (path.endsWith(".doc")) {
                InputStream is = new FileInputStream(new File(path));
                WordExtractor we = new WordExtractor(is);
                buffer = we.getText();
                we.close();
            } else if (path.endsWith(".docx")) {
                OPCPackage opcPackage = POIXMLDocument.openPackage(path);
                POIXMLTextExtractor extractor = new XWPFWordExtractor(opcPackage);
                buffer = extractor.getText();
                extractor.close();
            }else {
                System.err.println("该文件不是word文件!");
            }
        } catch (Exception e) {
            e.printStackTrace();
        }
        return buffer;
    }

public static void main(String[] args) {
        String path = "D:\\zyz worker\\doc-docx-Test\\张三请假审批.xml";
        String text = "";
        try {
            text = readDocx(path);
            System.err.println(text);
        } catch (Exception e) {
            e.printStackTrace();
        }
    }

使用接收文件流的方式

//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");
        }
    }