Text extraction in Java from PDF with pdfbox-2.0.8

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

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

public class PdfToTextMain1 {

	public static void main(String[] args) {

		// https://pdfbox.apache.org/download.cgi
		// pdfbox-2.0.8
		// fontbox-2.0.8.jar

		String filepath = "file/pdf_ja.pdf";

		try {

			PDDocument pdDoc = PDDocument.load(new File(filepath)); // throws
																	// IOException
			PDFTextStripper pdfStripper = new PDFTextStripper();// throws
																// IOException

			pdfStripper.setStartPage(1);
			pdfStripper.setEndPage(5);

			String parsedText = pdfStripper.getText(pdDoc); // throws
															// IOException

			System.out.println(parsedText);
		} catch (IOException e) {
			e.printStackTrace();
		}
	}

}

Recommended Posts