Question

所以我最初编译之前我做了一些更改以允许我指定搜索和位置。如果需要，我可以把它拿出来，但我宁愿不要。这就是我得到的：

import java.util.ArrayList;
import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;
import java.io.IOException;
import java.util.Scanner;

public class YelpScrapper
{
    public static void main(String[] args) throws IOException
    {
        String description;
        String location;
        int pages;

        Scanner keyboard = new Scanner(System.in);

        System.out.print("Enter a description: ");
        description = keyboard.nextLine();

        System.out.print("Enter a location: ");
        location = keyboard.nextLine();

        System.out.print("How many pages should we scan? ");
        pages = keyboard.nextInt();

        String descString = "find_desc=" + description.replace(' ', '+') + "&";
        String locString = "find_loc=" + location.replace(' ', '+') + "&";
        int number = (pages * 10) - 10;

        String url = "https://www.yelp.com/search?" + descString + locString + "start=" + number;
        ArrayList<String> names = new ArrayList<String>();
        ArrayList<String> address = new ArrayList<String>();
        ArrayList<String> phone = new ArrayList<String>();
        Document document = Jsoup.connect(url).get();

        Elements nameElements = document.select(".indexed-biz-name span");
        Elements addressElements = document.select(".secondary-attributes address");
        Elements phoneElements = document.select(".biz-phone");

        for (Element element : nameElements)
        {
            names.add(element.text());
        }

        for (Element element : addressElements)
        {
            address.add(element.text());
        }

        for (Element element : phoneElements)
        {
            phone.add(element.text());
        }

        for (int index = 0 ; index <= number ; index++)
        {
            System.out.println("\nLead " + index);
            System.out.println("Company Name: " + names.get(index));
            System.out.println("Address: " + address.get(index));
            System.out.println("Phone Number: " + phone.get(index));
        }

        //for (String name : names)
        //{
           // System.out.println(name);
        //}

        //System.out.println("\n");

        //for (String add : address)
        //{
            //System.out.println(add);
        //}

        //for (String pho : phone)
        //{
            //System.out.println(pho);
        //}
    }
}

我从BlueJ java.net.SocketTimeoutException收到的错误;读取超时（在java.net.SocketInputStream中）

我应该抛出另一个例外吗？非常感谢您提供的任何帮助！

Answer 1

也许设置超时可能会有所帮助？

Document document = Jsoup.connect(url).timeout(10000).get();

如何为Yelp提取器解决此错误？

1 个答案: