Get Links From HTML : HTML « Network « C# / C Sharp

1. C# / C Sharp
2. Network
3. HTML

Get Links From HTML

 

using System;
using System.Collections.Generic;
using System.Linq;
using System.Text;
using System.Collections.Specialized;
using System.Text.RegularExpressions;
using System.Net;

public static class LinkCheckerUtilities
{

    public static StringCollection GetLinksFromHTML(string HtmlContent)
    {


        StringCollection links = new StringCollection();

        MatchCollection AnchorTags = Regex.Matches(HtmlContent.ToLower(), @"(<a.*?>.*?</a>)", RegexOptions.Singleline);

        foreach (Match AnchorTag in AnchorTags)
        {
            string value = AnchorTag.Groups[1].Value;

            Match HrefAttribute = Regex.Match(value, @"href=\""(.*?)\""",
                RegexOptions.Singleline);
            if (HrefAttribute.Success)
            {
                string HrefValue = HrefAttribute.Groups[1].Value;
                if (!links.Contains(HrefValue))
                {
                    links.Add(HrefValue);
                }
            }
        }

        return links;
    }
}

   
  

Related examples in the same category