java 读取word内容

接到一个任务，要读取doc文件的内容。解析里面的内容，进行一个处理和返回。

读取doc:

看了

很多文章，基本都是：

import org.apache.poi.hwpf.HWPFDocument;
import org.apache.poi.hwpf.extractor.WordExtractor;
import java.io.File;
import java.io.FileInputStream;
import java.io.IOException;

public class WordImportUtils {

    public static String readWordFile(String path) {
        File file = new File(path);
        FileInputStream fileInputStream = null;
        try {
            fileInputStream = new FileInputStream((file.getAbsolutePath()));
            HWPFDocument document = new HWPFDocument(fileInputStream);
            WordExtractor extractor = new WordExtractor(document);
            return extractor.getText();//此处还有很多别的方法可以使用
        } catch (IOException e) {
            e.printStackTrace();
        } finally {
            if(fileInputStream != null){
                try {
                    fileInputStream.close();
                }catch (Exception e){