jeudi 18 août 2016

this web crawling code can fetch the required data but is only limited to 1 page need to fetch all pages in the Url index

i have been trying to fetch multiple pages in the urls given but the code i have came up with fetch only a limited data which is only on the first screen , need to fetch all pages in the index can anyone help

import java.util.ArrayList;

import com.webscrap4j.WebScrap;
import com.webscrap4j.WebScrapException;

import java.io.FileOutputStream;
import java.io.IOException;

import org.apache.poi.hssf.usermodel.HSSFRow;
import org.apache.poi.hssf.usermodel.HSSFSheet;
import org.apache.poi.hssf.usermodel.HSSFWorkbook;
import org.apache.poi.ss.usermodel.Row;


public class crawl 
{
    @SuppressWarnings("resource")
    public static void main(String[] args) throws IOException {



        ArrayList<String> al = new ArrayList<String>();
        ArrayList<String> bl = new ArrayList<String>();
        ArrayList<String> cl = new ArrayList<String>();
        WebScrap ws = new WebScrap();

        ws.setUrl("http://ift.tt/2bhDK0C");
        try


        {

            ws.startWebScrap();
            //al = ws.getImageTagData("img", "title");
            al = ws.getSingleHTMLScriptData("<div class='card-body-title hidden-txt'>", "</div>");
            bl = ws.getSingleHTMLScriptData("<span class='strike'>", "</span>");
            cl = ws.getSingleHTMLScriptData("<p class='card-body-price txt-red'>", "</p>");




            HSSFWorkbook workBook = new HSSFWorkbook();
             FileOutputStream fos = new FileOutputStream("/Users/parthpatil/Documents/TL .xls"); {

            // Create the Sheet
            HSSFSheet Sheet = workBook.createSheet("products");

            // Create the first row corresponding to the header
            Row header = Sheet.createRow(0);
            header.createCell(0).setCellValue("Product Name");
            header.createCell(1).setCellValue("Product Price");
            header.createCell(2).setCellValue("Product MRP");

            // Ensure that all the List have the same size otherwise throw an exception
            if (al.size() != bl.size() || al.size() != cl.size())
                throw new IllegalStateException("Some data is missing");

            // Iterate over all the list an create the rows of data
            for(int i = 0; i < al.size(); i++){
                // Create the current starting from 1 to al.size()
                HSSFRow row = Sheet.createRow((short) i + 1);
                // Cell of the Product Name
                row.createCell(0).setCellValue(al.get(i));
                // Cell of the Product Price
                row.createCell(1).setCellValue(cl.get(i));
                // Cell of the Product MRP
                row.createCell(2).setCellValue(bl.get(i));
            }
            // Write the result into the file
            workBook.write(fos);


            for (String adata : al)
            {

                System.out.println("the product are:- " + adata);

            }
            for (String bdata : bl)
            {

                System.out.println("the MRp are:- " + bdata);

            }
            for (String cdata : cl)
            {

                System.out.println("the selling price is:- " + cdata);

            }


        }
             }catch (WebScrapException e) {
            // TODO Auto-generated catch block
            e.printStackTrace();
        }
        }
    }




Aucun commentaire:

Enregistrer un commentaire