Java将word转换为文本

在Java中，你可以使用Apache POI库来读取Word文档并提取文本内容。你可以在 Maven 项目中添加以下依赖：

<!--Word-->
<dependency>
	<groupId>org.apache.poi</groupId>
	<artifactId>poi</artifactId>
	<version>4.1.2</version>
</dependency>
<dependency>
	<groupId>org.apache.poi</groupId>
	<artifactId>poi-ooxml</artifactId>
	<version>4.1.2</version>
</dependency>

以下是一个简单的示例代码，展示如何使用Apache POI将Word文档转换为文本：

import com.fasterxml.jackson.databind.exc.InvalidFormatException;
import org.apache.poi.xwpf.extractor.XWPFWordExtractor;
import org.apache.poi.xwpf.usermodel.XWPFDocument;
import java.io.FileInputStream;

public class WordToTextConverter {


    public static void main(String[] args) {
        String filePath = "C:\\xxx.docx";

        try (FileInputStream fis = new FileInputStream(filePath);
             XWPFDocument document = new XWPFDocument(fis)) {

            // 1. Check if the document is empty
            if (document.getParagraphs().isEmpty()) {
                System.err.println("Word文档为空");
                return;
            }

            // 2. Create XWPFWordExtractor
            XWPFWordExtractor extractor = new XWPFWordExtractor(document);

            // 3. Get text from the Word document
            String text = extractor.getText();

            // 4. Print the extracted text
            System.out.println("Text from Word document:\n" + text);

        } catch (InvalidFormatException e) {
            System.err.println("无效的Word文档格式");
            e.printStackTrace();
        } catch (Exception e) {
            System.err.println("无法读取Word文档");
            e.printStackTrace();
        }
    }
}