java 读取word内容

在Java中读取Word内容，可以使用Apache POI库。下面是两种不同的实现方法：

方法1：使用XWPF读取器

import org.apache.poi.xwpf.usermodel.XWPFDocument;
import org.apache.poi.xwpf.usermodel.XWPFParagraph;
import org.apache.poi.xwpf.usermodel.XWPFRun;
 
import java.io.FileInputStream;
import java.io.IOException;
import java.io.InputStream;
 
public class WordReader {
    public static void main(String[] args) {
        try {
            InputStream fis = new FileInputStream("path/to/your/word/document.docx");
            XWPFDocument document = new XWPFDocument(fis);
 
            for (XWPFParagraph paragraph : document.getParagraphs()) {
                String text = paragraph.getText();
                System.out.println(text);
            }
 
            document.close();
            fis.close();
        } catch (IOException e) {
            e.printStackTrace();
        }
    }
}

方法2：使用HWPF读取器

import org.apache.poi.hwpf.HWPFDocument;
import org.apache.poi.hwpf.extractor.WordExtractor;
 
import java.io.FileInputStream;
import java.io.IOException;
import java.io.InputStream;
 
public class WordReader {
    public static void main(String[] args) {
        try {
            InputStream fis = new FileInputStream("path/to/your/word/document.doc");
            HWPFDocument document = new HWPFDocument(fis);
            WordExtractor extractor = new WordExtractor(document);
            
            String[] paragraphs = extractor.getParagraphText();
 
            for (String paragraph : paragraphs) {
                System.out.println(paragraph);
            }
 
            extractor.close();
            fis.close();
        } catch (IOException e) {
            e.printStackTrace();
        }
    }
}

注意：方法1适用于读取.docx格式的Word文档，需要导入poi-ooxml依赖；方法2适用于读取.doc格式的Word文档，需要导入poi依赖。