pdfBox 解析 pdf文件

Spting boot 项目

1.添加依赖

 <dependency>
       <groupId>org.apache.pdfbox</groupId>
       <artifactId>pdfbox</artifactId>
       <version>2.0.16</version>
 </dependency>

 

2.PDFTest.java

package com.nenu.pdf;

import org.apache.pdfbox.io.RandomAccessFile;
import org.apache.pdfbox.pdfparser.PDFParser;
import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.text.PDFTextStripper;


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

public class PDFTest {
    public static String getTextFromPDF(String pdfFilePath)
    {
        String result = null;
        PDDocument document = null;
        File file = new File(pdfFilePath);
        try {
            PDFParser parser = new PDFParser(new RandomAccessFile(file,"rw"));
            parser.parse();
            document = parser.getPDDocument();
            PDFTextStripper stripper = new PDFTextStripper();
            result = stripper.getText(document);
        } catch (FileNotFoundException e) {
            // TODO Auto-generated catch block
            e.printStackTrace();
        } catch (IOException e) {
            // TODO Auto-generated catch block
            e.printStackTrace();
        } finally {
            if (document != null) {
                try {
                    document.close();
                } catch (IOException e) {
                    // TODO Auto-generated catch block
                    e.printStackTrace();
                }
            }
        }
        return result;
    }
    public  static void main(String[] args)
    {
        String str=PDFTest.getTextFromPDF("D:\\pdf.pdf");
        System.out.println(str);

    }

}