1. 程式人生 > >java 用pdfbox讀取pdf

java 用pdfbox讀取pdf

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 {
PDDocument document = PDDocument.load(new File("pdf檔案路徑"));
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);
}
}
}


}