HtmlExtractor lolcats

ExtractLolCats.cs

using HtmlAgilityPack;
using Newtonsoft.Json.Linq;
using System.IO;
using System.Linq;

namespace HtmlExtractor
{
    class Program
    {
        static void Main(string[] args)
        {
            var document = new HtmlWeb().Load(args[0]);
            var nodes = document.DocumentNode.SelectNodes("//p[contains(@class,'mine_image')]");
            var lolcats = new JArray(nodes.Select(node => {
                string caption = null;
                var captionNode = node.SelectSingleNode("following-sibling::p");
                if (captionNode != null)
                {
                    caption = captionNode.InnerText;
                }
                return new JObject(
                    new JProperty("image", node.SelectSingleNode(".//img").GetAttributeValue("src", "")),
                    new JProperty("caption", caption));
            }));
            File.WriteAllText("lolcats.json", lolcats.ToString());
        }
    }
}