java读取.doc文件

需要的jar包：

poi-3.17.jar

poi-scratchpad-3.17.jar

poi-ooxml-3.17.jar

poi-ooxml-schemas-3.17.jar

下载地址：poi jar包下载地址

package jichu.test_simple;
import java.io.*;

import java.io.File;
import java.io.FileInputStream;
import java.io.InputStream;

import org.apache.poi.hwpf.HWPFDocument;
import org.apache.poi.hwpf.extractor.WordExtractor;
import org.apache.poi.hwpf.usermodel.Range;
import org.apache.poi.ooxml.POIXMLDocument;
import org.apache.poi.ooxml.extractor.POIXMLTextExtractor;
import org.apache.poi.openxml4j.opc.OPCPackage;
import org.apache.poi.xwpf.extractor.XWPFWordExtractor;
/**
 * @Author：sks
 * @Description：
 * @Date：Created in 15:49 2018/1/24
 * @Modified by：
 **/
/*
* 
* */
public class poi_doc {
    public static void main(String[] args) {
        File file = new File("C:\\YQ\\123.doc");
        HWPFDocument doc = null;
        try {
            doc = new HWPFDocument(new FileInputStream(file));
        } catch (IOException e) {
            e.printStackTrace();
        }
        //通过 Doc对象直接获取Text
        StringBuilder sb = doc.getText();
        System.out.println(sb.toString());
        //通过Range对象获取Text
        Range range = doc.getRange();
        String text = range.text();
        //System.out.println(text);

    }
}

缺点：虽然两种方式都能读取，但只能读取doc文件，无法读取docx文件