使用Java读取PDF文件内容

1.引入jar包

		<dependency>
            <groupId>org.apache.pdfbox</groupId>
            <artifactId>pdfbox-tools</artifactId>
            <version>2.0.2</version>
        </dependency>

2.编写PFD工具类

package com.example.apitest.util;

import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.text.PDFTextStripper;

import java.io.File;
import java.io.IOException;

public class PDFUtil {

    String filePath = "";

    public PDFUtil(String filePath){
        this.filePath = filePath;
    }

    //读取PDF中的数据
    public String parsePDF(){
        String result = "";
        try {
            PDDocument load = PDDocument.load(new File(filePath));
            PDFTextStripper stripper = new PDFTextStripper();
            stripper.setSortByPosition(true);
            for (int i = 1; i < load.getNumberOfPages()+1; i++) {
                //读取pdf的开始到结束页
                stripper.setStartPage(i);
                stripper.setEndPage(i);
                String text = stripper.getText(load);
                //拼接不同页数的数据返回
                result += text;
            }
        } catch (IOException e) {
            e.printStackTrace();
        }
        return result;
    }
    //将一个PDF分割成多个
    public void splitPDF(){
        try {
            PDDocument load = PDDocument.load(new File(filePath));
            PDFTextStripper stripper = new PDFTextStripper();
            stripper.setStartPage(1);
            stripper.setEndPage(load.getNumberOfPages());
            load.save("D:\\testFile\\读取PDF文件COPY.pdf");
        } catch (IOException e) {
            e.printStackTrace();
        }
    }
}

3.调用工具类实现读取功能

private static void testPDF(){
        PDFUtil pdfUtil = new PDFUtil("D:\\testFile\\读取PDF文件.pdf");
        String s = pdfUtil.parsePDF();
        pdfUtil.splitPDF();
        //System.out.println(s);
        System.out.println("产品："+s.substring(s.indexOf("产品")+3).split("\\n")[0]);
//        System.out.println("价格："+s.substring(s.indexOf("价格")+3));
//        System.out.println("数量："+s.substring(s.indexOf("数量")+3));
//        System.out.println("质量："+s.substring(s.indexOf("质量")+3));
//        System.out.println("生产率："+s.substring(s.indexOf("生产率")+3));
    }