Polarnik Posts - Answer Overflow

Polarnik

•Created by Polarnik on 10/29/2023 in #help

✅ Unsuccessfully trying to parse web pages.

I want to parse last.fm for artists but my code works only first iteration, in all iterations where pages > 1 var nodeArtist = document.DocumentNode.QuerySelectorAll("td.chartlist-name"); returns empty list which is strange because pages are identical in structure

using System.Text;
using HtmlAgilityPack;

namespace Parser
{
    public class Program
    {
        public static async Task Main()
        {
            const int pageNum = 6;
            string url = "https://www.last.fm/user/Polarnichek/library/artists?page=0";
            var web = new HtmlWeb();
            var sb = new StringBuilder(url.Length + 1);
            sb.Append(url);
            var artists = new List<string>(500);

            for (int page = 4; page <= pageNum; page++)
            {
                sb.Clear();
                sb.Append(url);
                sb.Replace("page=0", $"page={page}");
                
                var document = await web.LoadFromWebAsync(sb.ToString());

                var nodeArtist = document.DocumentNode.QuerySelectorAll("td.chartlist-name");
                foreach (var artist in nodeArtist)
                {
                    var artistName = artist.QuerySelector("a").Attributes["title"].Value;
                    artists.Add(artistName);
                }
            }
            Console.WriteLine(artists.Count);
        }
    }
}

using System.Text;
using HtmlAgilityPack;

namespace Parser
{
    public class Program
    {
        public static async Task Main()
        {
            const int pageNum = 6;
            string url = "https://www.last.fm/user/Polarnichek/library/artists?page=0";
            var web = new HtmlWeb();
            var sb = new StringBuilder(url.Length + 1);
            sb.Append(url);
            var artists = new List<string>(500);

            for (int page = 4; page <= pageNum; page++)
            {
                sb.Clear();
                sb.Append(url);
                sb.Replace("page=0", $"page={page}");
                
                var document = await web.LoadFromWebAsync(sb.ToString());

                var nodeArtist = document.DocumentNode.QuerySelectorAll("td.chartlist-name");
                foreach (var artist in nodeArtist)
                {
                    var artistName = artist.QuerySelector("a").Attributes["title"].Value;
                    artists.Add(artistName);
                }
            }
            Console.WriteLine(artists.Count);
        }
    }
}

20 replies

Gaming

Programming