New course! Every coder should learn Generative AI!
Try a free lesson+ 1
// At first get PDFBox http://pdfbox.apache.org/
import java.io.File;
import java.io.FileInputStream;
import java.io.IOException;
import org.apache.pdfbox.cos.COSDocument;
import org.apache.pdfbox.pdfparser.PDFParser;
import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.util.PDFTextStripper;
public class Main {
public static void main(String args[]) throws IOException {
File pdfFile = new File("/your/pdf/file.pdf");
PDFParser parser = new PDFParser(new FileInputStream(pdfFile));
parser.parse();
try (COSDocument cosDoc = parser.getDocument();
PDDocument pdDoc = new PDDocument(cosDoc)) {
PDFTextStripper pdfStripper = new PDFTextStripper();
System.out.println(pdfStripper.getText(pdDoc));
}
}
}