PDFBox –如何讀取PDF的內容

pom.xml

<dependency>
        <groupId>org.apache.pdfbox</groupId>
        <artifactId>pdfbox</artifactId>
        <version>2.0.6</version>
</dependency>

2.讀取pdf的文件內容

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

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

public class ReadPdf {

    public static void main(String[] args) throws IOException {

        try (PDDocument document = PDDocument.load(new File("/path-to/abc.pdf"))) {

            document.getClass();

            if (!document.isEncrypted()) {

                PDFTextStripperByArea stripper = new PDFTextStripperByArea();
                stripper.setSortByPosition(true);

                PDFTextStripper tStripper = new PDFTextStripper();

                String pdfFileInText = tStripper.getText(document);
                //System.out.println("Text:" + st);

				// split by whitespace
                String lines[] = pdfFileInText.split("\\r?\\n");
                for (String line : lines) {
                    System.out.println(line);
                }

            }

        }

    }
}