Java 从word中提取文字信息(开发笔记)

男娘i 2022-05-15 02:42 573阅读 0赞

所需jar包：

![70][]

下载地址：

[https://download.csdn.net/download/qq\_34246546/10622595][https_download.csdn.net_download_qq_34246546_10622595]

代码如下：

package com.xc.test.utils;
    
    import java.io.File;
    
    
    import java.io.FileInputStream;
    import java.io.InputStream;
    
    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;
    
    public class Java2Word {
    	public static String readWord(String path) {
    		String buffer = "";
    		try {
    			if (path.endsWith(".doc")) {
    				InputStream is = new FileInputStream(new File(path));
    				WordExtractor ex = new WordExtractor(is);
    				buffer = ex.getText();
    				ex.close();
    			} else if (path.endsWith("docx")) {
    				OPCPackage opcPackage = POIXMLDocument.openPackage(path);
    				POIXMLTextExtractor extractor = new XWPFWordExtractor(opcPackage);
    				buffer = extractor.getText();
    				extractor.close();
    			} else {
    				System.out.println("此文件不是word文件！");
    			}
     
    		} catch (Exception e) {
    			e.printStackTrace();
    		}
     
    		return buffer;
    	}
     
    	public static void main(String[] args) {
    //		String content = tp.readWord("D:\\20180807.doc");
    		String content = Java2Word.readWord("F:\\wordToPdf\\bookOrders\\《“种子”与“灵光”王阳明心学喻象体系通论》#鲍永玲#上海书店出版社.docx");
    		System.out.println("content===="+content);
    	}
    
    }

[70]: /images/20220515/4746600ca2474941896037c471403bd8.png
[https_download.csdn.net_download_qq_34246546_10622595]: https://download.csdn.net/download/qq_34246546/10622595