package org.jsoup.examples;

import java.io.*;

import org.jsoup.*;
import org.jsoup.nodes.*;
import org.jsoup.select.Elements;

import java.io.IOException;

/**
 * Example program to list links from a URL.
 */
public class parseEasy {



        static parseEasy parseIt = new parseEasy();

        String companyName = "Platzhalter";
        String jobTitle = "Platzhalter";
        String location = "Platzhalter";
        String timeAdded = "Platzhalter";

    public static void main(String[] args) throws IOException
    {
        Database connect = new Database();
        connect.OpenConnectionDB();

        parseIt.getData(connect);

        connect.closeConnectionDB();


    }

    //
    public void getData(Database c) throws IOException
    {


        Document document = Jsoup.parse(new File("C:/Talend/workspace/WEBCRAWLER/output/keywords_SOA.txt"), "utf-8");
        Elements elements = document.select(".joblisting");
        for (Element element : elements)
        {
            // Counter for Number of Elements returned


            // Parse Data into Elements
            Elements jobTitleElement = element.select(".job_title span");
            Elements companyNameElement = element.select(".company_name span[itemprop=name]");
            Elements locationElement = element.select(".locality span[itemprop=addressLocality]");
            Elements dateElement = element.select(".job_date_added [datetime]");

            // Strip Data from unnecessary tags
            String companyName = companyNameElement.text();
            String jobTitle = jobTitleElement.text();
            String location = locationElement.text();
            String timeAdded = dateElement.attr("datetime");



            c.insert(companyName, jobTitle, timeAdded, location);
            c.closeConnectionDB();



            // Test output
            //System.out.println("Firma:t"+ companyName + "t" + jobTitle + "t in:t" + location + " t Erstellt am t" + timeAdded + "t. Eintrag Nummer:t" + count);
        }
    }
  }