Java 实现poi方式读取word文件内容

本文介绍了一个简单的Java程序，该程序能够从指定路径的 .doc/.docx 文件中读取文本内容。通过使用Apache POI库中的WordExtractor类，实现了对Microsoft Word文档的解析。

1、Maven Jar包

<!-- .docx -->
<dependency>
    <groupId>org.apache.poi</groupId>
    <artifactId>poi-ooxml</artifactId>
    <version>5.2.3</version>
</dependency>
<!-- .doc -->
<dependency>
    <groupId>org.apache.poi</groupId>
    <artifactId>poi-scratchpad</artifactId>
    <version>5.2.3</version>
</dependency>

2、Java代码

package org.example.utils;

import org.apache.poi.hwpf.HWPFDocument;
import org.apache.poi.hwpf.extractor.WordExtractor;
import org.apache.poi.xwpf.extractor.XWPFWordExtractor;
import org.apache.poi.xwpf.usermodel.XWPFDocument;

import java.io.FileInputStream;
import java.io.IOException;
import java.io.InputStream;

public class WordUtils {

    public String read(String path) {
        try  {
            if (path.toLowerCase().endsWith(".docx"))
                return readDocx(path);
            else if (path.toLowerCase().endsWith(".doc"))
                return readDoc(path);
            else
                throw new IllegalArgumentException("不支持的文件格式");
        } catch (Exception e){
            e.printStackTrace();
        }
        return null;
    }
    public String readDocx(String path) throws IOException {
        try (InputStream in = new FileInputStream(path);
             XWPFDocument doc = new XWPFDocument(in)) {
            return new XWPFWordExtractor(doc).getText();
        }
    }
    public String readDoc(String path) throws IOException {
        try (InputStream in = new FileInputStream(path);
             HWPFDocument doc = new HWPFDocument(in)) {
            return new WordExtractor(doc).getText();
        }
    }

    public static void main(String[] args) {
        WordUtils wordUtils = new WordUtils();
        try {
            String docx = wordUtils.read("/Users/work/Documents/数据分析报告.doc");
            System.out.println(docx);
        } catch (Exception e) {
            throw new RuntimeException(e);
        }
    }

}