Napisalem sobie program ktory czyta pdf'a i wyszukuje pewne rzeczy, :
package javaapplication10;
import org.apache.pdfbox.util.PDFTextStripper;
import java.io.File;
import org.apache.pdfbox.pdmodel.PDDocument;
import java.io.PrintWriter;
public class JavaApplication10 {
public static void main(String[] args) throws Exception {
String TargetFile = "C:\Java Folder\Pedersen et al 2013 HICSS-46 Proceedings.pdf";
String ExtractedText;
try (PDDocument pdf = PDDocument.load(new File(TargetFile))) {
PDFTextStripper stripper = new PDFTextStripper();
ExtractedText = stripper.getText(pdf);
}
try (PrintWriter SaveTxt = new PrintWriter("C:\\Java Folder\\wyn2.doc")) {
int refposition1 = ExtractedText.indexOf("References");
System.out.println("Position of References first: " + refposition1);
int refposition2 = ExtractedText.lastIndexOf("References");
System.out.println("Position of References last: " + refposition2);
String ReferencesText = ExtractedText.substring(refposition1);
System.out.println(ReferencesText);
SaveTxt.println(ReferencesText);
}
}
jak zrobic zeby czytal kila pdf'ów i zapisywal do jednego doc?