读取Word 内容

import org.apache.poi.POIXMLDocument;
import org.apache.poi.POIXMLTextExtractor;
import org.apache.poi.hwpf.extractor.WordExtractor;
import org.apache.poi.openxml4j.opc.OPCPackage;
import org.apache.poi.xwpf.extractor.XWPFWordExtractor;

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

/**
 *  Word 读取Word 内容， 但是没有格式， 图片读取不了
 */
public class ImortWordUtil {

    public static void main(String[] args){
        StringBuffer str = readWord("C:/Users/Lenovo/Desktop/test/xxxxx.docx");
        System.out.println(str.toString());
    }

    public static StringBuffer readWord(String path) {
        String s = "";
        try {
            if(path.endsWith(".doc")) {
                InputStream is = new FileInputStream(new File(path));
                WordExtractor ex = new WordExtractor(is);
                s = ex.getText();
            }else if (path.endsWith("docx")) {
                OPCPackage opcPackage = POIXMLDocument.openPackage(path);
                POIXMLTextExtractor extractor = new XWPFWordExtractor(opcPackage);
                s = extractor.getText();
            }else {
                System.out.println("传入的word文件不正确:"+path);
            }

        } catch (Exception e) {
            e.printStackTrace();
        }
        StringBuffer bf = new StringBuffer(s);
        return bf;
    }

}