Java读取docx和pdf文本内容

 

需要先引入对应jar包

        <!-- 获取pdf文件内容 -->
        <dependency>
            <groupId>org.apache.pdfbox</groupId>
            <artifactId>pdfbox</artifactId>
            <version>2.0.26</version>
        </dependency>

        <!-- excel工具 -->
        <dependency>
            <groupId>org.apache.poi</groupId>
            <artifactId>poi-ooxml</artifactId>
        </dependency>

        <dependency>
            <groupId>org.apache.poi</groupId>
            <artifactId>poi-scratchpad</artifactId>
        </dependency>
import org.apache.pdfbox.io.RandomAccessBufferedFileInputStream;
import org.apache.pdfbox.io.RandomAccessRead;
import org.apache.pdfbox.pdfparser.PDFParser;
import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.text.PDFTextStripper;
import org.apache.poi.xwpf.extractor.XWPFWordExtractor;
import org.apache.poi.xwpf.usermodel.XWPFDocument;

import java.io.*;

public class Test {


    public static void main(String[] args) {
        File docx = new File("F:/Java/docx.docx");
        File pdf = new File("F:/Java/pdf.pdf");
        String docxContent = readDocxContent(docx);
        String pdfContent = readPdfContent(pdf);
        System.out.println("docx="+docxContent);
        System.out.println("pdf="+pdfContent);
    }

    /**
     * 读取docx文件内容
     * @param file
     * @return
     */
    public static String readDocxContent(File file){
        FileInputStream inputStream = null;
        String content = "";
        try {
            inputStream =  new FileInputStream(file);

            XWPFDocument xdoc = new XWPFDocument(inputStream);
            XWPFWordExtractor extractor = new XWPFWordExtractor(xdoc);
            content = extractor.getText();
            extractor.close();
        } catch (FileNotFoundException e) {
            e.printStackTrace();
        } catch (Exception e) {
            e.printStackTrace();
        }
        return content;
    }

    /**
     * 读取pdf文件内容
     * @param file
     * @return
     */
    public static String readPdfContent(File file){
        FileInputStream inputStream = null;
        String content = "";
        try {
            inputStream =  new FileInputStream(file);
            RandomAccessRead randomAccessRead = new RandomAccessBufferedFileInputStream(inputStream);
            PDFParser parser = new PDFParser(randomAccessRead);
            parser.parse();
            PDDocument pdDocument = parser.getPDDocument();
            PDFTextStripper stripper = new PDFTextStripper();
            content = stripper.getText(pdDocument);
            randomAccessRead.close();
            pdDocument.close();
        } catch (FileNotFoundException e) {
            e.printStackTrace();
        } catch (Exception e) {
            e.printStackTrace();
        }
        return content;
    }

}

  • 0
    点赞
  • 1
    收藏
    觉得还不错? 一键收藏
  • 0
    评论

“相关推荐”对你有帮助么?

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值