C#: Download All Image Links from Html Page

I know this is not perfect way. But I would like to give hints to anyone who would like to download all links in html page.


Example usage is something like this.

// only download "jpg" files
HttpUtils.SaveFirstLevelLinksToFile("", Encoding.UTF8, "c:/temp/", 
    link => link => ".jpg".Equals(Path.GetExtension(link.Link), StringComparison.OrdinalIgnoreCase)
);

Main code is below.

// main entry point method
public static void SaveFirstLevelLinksToFile(string baseUri, Encoding enc, string dir, Func<LinkAttr, bool> filter)
{
    ProcessAllExtractedLinksInHtmlText(GetPage(baseUri, enc),
        link =>
        {
            try
            {
                if (!filter(link)) return;
                
                Uri uri = ConvertToAbsoluteURL(baseUri, link.Link);
                var filePath = dir + uri.AbsoluteUri.GetFileName().Replace("?", "");
                uri.AbsoluteUri.GetAndSaveToFile(filePath);
            }
            catch (Exception e)
            {
                Console.WriteLine(e.StackTrace);
            }
        }
   );
}

private readonly static Regex LINK_REGEX = new Regex(
    @"<a\s+[^>]*href\s*=\s*(?:(?<3>'|"")(?<1>[^\3>]*?)\3|(?<1>[^\s>]+))[^>]*>(?<2>.*?)</a>",
    RegexOptions.IgnoreCase | RegexOptions.Compiled
);

public static void ProcessAllExtractedLinksInHtmlText(string text, Action<LinkAttr> process)
{
    LINK_REGEX.ApplyAllMatched(text, (m) =>
    {
         process(new LinkAttr(m.Groups[1].Value, m.Groups[2].Value));
    });
}

public static void ApplyAllMatched(this Regex regex, string text, Action<Match> apply)
{
    for (var m = regex.Match(text); m.Success; )
    {
        apply(m);
        m = m.NextMatch();
    }
}

public static string GetPage(string url, Encoding encoding)
{
     return ProcessGet<string>(url, stream => stream.ReadAsString(encoding));
}

public static T ProcessGet<T>(string url, Func<Stream, T> process)
{
     var request = WebRequest.Create(url);
     using (var response = request.GetResponse())
     using (var resStream = response.GetResponseStream())
     {
         return process(resStream);
     }
}

public static Uri ConvertToAbsoluteURL(string rootUri, string relativeUri)
{
    var relative = new Uri(relativeUri, UriKind.RelativeOrAbsolute);
    if (relative.IsAbsoluteUri)
    {
        return relative;
    }
    else
    {
        return new Uri(new Uri(rootUri), relative);
    }
}

Helper class which represents link.

public class LinkAttr
{
    public string Link { get; set; }
    public string Body { get; set; }
    public LinkAttr(string link, string body)
    {
        this.Link = link;
        this.Body = body;
    }
}