Java 读取Doc/Docx 文档

    Java后台系统中常常会遇到读取文档内容的需求，今天把 Java 读取两种格式的word文档写了一个简单的工具类附上：

1. 需要添加 Apache.poi 的依赖

 
        
            org.apache.poi
            poi-scratchpad
            3.8
        
        
            commons-io
            commons-io
            2.6
        

2. 工具类代码

package com.lq.file.word;

/**
 * 
Description:POIUtil 工具类
 * 
Copyright: Copyright (c)2019
 * 
Company: Tope
 * 
@version 1.0
 */
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;
import java.util.ArrayList;
import java.util.List;

public class POIUtil {

	/**
	* @Description: POI 读取  word
	* @create: 2019-07-27 9:48
	* @update logs
	* @throws Exception
	*/
	public static List readWord(String filePath) throws Exception{
		
		List linList = new ArrayList();
		String buffer = "";
		try {
			if (filePath.endsWith(".doc")) {
				InputStream is = new FileInputStream(new File(filePath));
				WordExtractor ex = new WordExtractor(is);
				buffer = ex.getText();
				ex.close();
				
				if(buffer.length() > 0){
					//使用回车换行符分割字符串
					String [] arry = buffer.split("\\r\\n");
					for (String string : arry) {
						linList.add(string.trim());
					}
				}
			} else if (filePath.endsWith(".docx")) {
				OPCPackage opcPackage = POIXMLDocument.openPackage(filePath);
				POIXMLTextExtractor extractor = new XWPFWordExtractor(opcPackage);
				buffer = extractor.getText();
				extractor.close();
				
				if(buffer.length() > 0){
					//使用换行符分割字符串
					String [] arry = buffer.split("\\n");
					for (String string : arry) {
						linList.add(string.trim());
					}
				}
			} else {
				return null;
			}
			
			return linList;
		} catch (Exception e) {
			System.out.print("error---->"+filePath);
			e.printStackTrace();
			return null;
		}
	}

}