网络抓取工具未创建 CSV 文件

Question

I have created a web scraper which brings the market data of share rates from the website of stock exchange. www.psx.com.pk in that site there is a hyperlink of Market Summary. From that link I have to scrap the data. I have created a program which is as follows.

package com.market_summary;

import java.io.File;
import java.io.FileWriter;
import java.io.IOException;
import java.text.ParseException;
import java.text.SimpleDateFormat;
import java.util.ArrayList;
import java.util.Date;
import java.util.Iterator;
import java.util.Locale;
import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;

public class ComMarket_summary {

    boolean writeCSVToConsole = true;
    boolean writeCSVToFile = true;
    boolean sortTheList = true;
    boolean writeToConsole;
    boolean writeToFile;
    public static Document doc = null;
    public static Elements tbodyElements = null;
    public static Elements elements = null;
    public static Elements tdElements = null;
    public static Elements trElement2 = null;
    public static String Dcomma = ",";
    public static String line = "";
    public static ArrayList<Elements> sampleList = new ArrayList<Elements>();

    public static void createConnection() throws IOException {
        System.setProperty("http.proxyHost", "191.1.1.202");
        System.setProperty("http.proxyPort", "8080");
        String tempUrl = "http://www.psx.com.pk/index.php";
        doc = Jsoup.connect(tempUrl).get();
        System.out.println("Successfully Connected");
    }

    public static void parsingHTML() throws Exception {

        File fold = new File("C:\\market_smry.csv");
        fold.delete();
        File fnew = new File("C:\\market_smry.csv");
        for (Element table : doc.getElementsByTag("table")) {
            for (Element trElement : table.getElementsByTag("tr")) {
                trElement2 = trElement.getElementsByTag("td");
                tdElements = trElement.getElementsByTag("td");
                FileWriter sb = new FileWriter(fnew, true);

                if (trElement.hasClass("marketData")) {
                    for (Iterator<Element> it = tdElements.iterator(); it.hasNext();) {
                        if (it.hasNext()) {
                            sb.append("\r\n");

                        }

                        for (Iterator<Element> it2 = trElement2.iterator(); it.hasNext();) {
                            Element tdElement2 = it.next();
                            final String content = tdElement2.text();
                            if (it2.hasNext()) {

                                sb.append(formatData(content));
                                sb.append("   |   ");

                            }

                        }

                        System.out.println(sb.toString());
                        sb.flush();
                        sb.close();
                    }
                }
                System.out.println(sampleList.add(tdElements));

            }
        }
    }
    private static final SimpleDateFormat FORMATTER_MMM_d_yyyy = new SimpleDateFormat("MMM d, yyyy", Locale.US);
    private static final SimpleDateFormat FORMATTER_dd_MMM_yyyy = new SimpleDateFormat("dd-MMM-YYYY", Locale.US);

    public static String formatData(String text) {
        String tmp = null;

        try {
            Date d = FORMATTER_MMM_d_yyyy.parse(text);
            tmp = FORMATTER_dd_MMM_yyyy.format(d);
        } catch (ParseException pe) {
            tmp = text;
        }

        return tmp;
    }

    public static void main(String[] args) throws IOException, Exception {
        createConnection();
        parsingHTML();

    }
}

Now, the problem is when I execute this program it should create a .csv file but what actually happens is it's not creating any file. When I debug this code I found that program is not entering in the loop. I don't understand that why it is doing so. While when I run the same program on the other website which have slightly different page structure it is running fine.
What I understand that this data is present in the #document which is a virtual element and doesn't mean anything that's why program can't read it while there is no such thing in other website. Kindly, help me out to read the data inside the #document element.

Answer 1

Long Story Short

Change your temp url to http://www.psx.com.pk/phps/index1.php

Explanation

There is no table in the document of http://www.psx.com.pk/index.php .

Instead it is showing it's content in two frameset .

One is dummy with url http://www.psx.com.pk/phps/blank.php . Another one is the real page which is showing actual data and it's url is http://www.psx.com.pk/phps/index1.php