Reputation: 11
Here is the problem. I have a websites and few subpages
subpages: DAMSKIE, MĘSKIE, DZIECIĘCE, SPORT, AKCESORIA, PREMIUM, TOREBKI, WYPRZEDAŻ,
On each of it are few categorizing elemens like "Półbuty", "Klapki" etc.
I can get Subpages but i can't get the list of categorizing elements (Półbuty, Klapki etc). If list looks like: "Półbuty", "Klapki", "Obcasy" my code gets only "Półbuty", but he doesn't get "Klapki" or "Obcasy".
[Image of subpages+the list of elements im trying to get][1]
using HtmlAgilityPack;
using System;
using System.Collections.Generic;
using System.Linq;
using System.Net.Http;
using System.Text;
using System.Threading.Tasks;
namespace Crawler_Shoes
{
public class Crawl
{
private static string navBar = "megamenu__item";
private const string shoesTypes = "sidebar-section__wrapper sidebar-section__wrapper--categories";
private static string mainSite = "https://www.eobuwie.com.pl/";
public static List<string> categoriesNames = new List<string>();
public static List<string> linksNames = new List<string>();
public static List<string> categoriesOfCategoriesNames = new List<string>();
private readonly List<Shoes> shoes = new List<Shoes>();
public static async Task<IEnumerable<HtmlNode>> HttpClient(string site, string descendant, string equals)
{
var httpClient = new HttpClient();
var html = await httpClient.GetStringAsync(site);
var htmlDocument = new HtmlDocument();
htmlDocument.LoadHtml(html);
return htmlDocument.DocumentNode.Descendants(descendant)
.Where(node => node.GetAttributeValue("class", "").Equals(equals)).ToList();
}
public static async Task GetCategories()
{
var menu = await HttpClient(mainSite, "li", navBar);
foreach (var nav in menu)
{
//links.Add(nav.Descendants("a").FirstOrDefault().ChildAttributes("href").FirstOrDefault().Value);
categoriesNames.Add(nav.Descendants("a").FirstOrDefault().InnerText); //gets names of categories
linksNames.Add(nav.Descendants("a").FirstOrDefault().ChildAttributes("href").FirstOrDefault().Value); //gets links for categories
if(categoriesNames.Last() == "\n\t\t\tWyprzedaż\t\t")
{
categoriesNames.Remove(categoriesNames.Last());
linksNames.Remove(categoriesNames.Last());
}
}
Crawl.GetCategoriesofCategories();
}
public static async Task GetCategoriesofCategories()
{
for (var i = 0; i <= categoriesNames.Count-1; i++)
{
var categories = await HttpClient(linksNames.ElementAt(i), "ul", shoesTypes);
categoriesOfCategoriesNames.Add(categoriesNames.ElementAt(i));
foreach(var li in categories)
{
categoriesOfCategoriesNames.Add(li.Descendants("a").FirstOrDefault().ChildAttributes("href").FirstOrDefault().Value);
}
}
}
}
}
The part with the problem:
public static async Task GetCategoriesofCategories()
{
for (var i = 0; i <= categoriesNames.Count-1; i++)
{
var categories = await HttpClient(linksNames.ElementAt(i), "ul", shoes
Types);
categoriesOfCategoriesNames.Add(categoriesNames.ElementAt(i));
foreach(var li in categories)
{
categoriesOfCategoriesNames.Add(li.Descendants("a").FirstOrDefault().ChildAttributes("href").FirstOrDefault().Value);
}
}
}
Upvotes: 1
Views: 189
Reputation: 407
I had success with this:
string url = "https://www.eobuwie.com.pl/damskie.html";
HtmlWeb web = new HtmlWeb();
HtmlDocument doc = web.Load(url);
var sidebar = doc.DocumentNode.SelectSingleNode("//ul[@class='sidebar-section__wrapper sidebar-section__wrapper--categories']");
var categories = sidebar.SelectNodes("li");
foreach (var category in categories)
{
var anchor = category.SelectSingleNode("a");
string shoeCategory = anchor.InnerText.Trim();
Console.WriteLine(shoeCategory);
}
It's a bit different than how you're doing it, but I at least hope you'll be able to take some hints from this and apply it to your own code.
If you need the links as well, add this:
string shoeCategoryLink = anchor.GetAttributeValue("href", string.Empty);
Upvotes: 1