How do I retrieve response html from within a HttpModule?

Question

Here is what I'm specifically trying to do:

I have written a HttpModule to do some site specific tracking. Some old .aspx pages on our site are hard coded with no real controls, but they are .aspx files so my module still runs when they are requested.

My module's handler is attached to the PostRequestHandlerExecute, so I believe what will be sent back to the requester should have already been determined.

I need to be able to extract whatever string is in the title tag.

So if

<title>Chunky Bacon</title>

is sent to the requester in the final rendered HTML. Then I want "Chunky Bacon".

Ideas?

Answer 1

Fun little challenge.

Here's the code:

StreamWatcher.cs

    public class StreamWatcher : Stream
    {
        private Stream _base;
        private MemoryStream _memoryStream = new MemoryStream();

        public StreamWatcher(Stream stream)
        {
            _base = stream;
        }

        public override void Flush()
        {
            _base.Flush();
        }

        public override int Read(byte[] buffer, int offset, int count)
        {
            return _base.Read(buffer, offset, count);
        }

        public override void Write(byte[] buffer, int offset, int count)
        {
            _memoryStream.Write(buffer, offset, count);
            _base.Write(buffer, offset, count);
        }

        public override string ToString()
        {
            return Encoding.UTF8.GetString(_memoryStream.ToArray());
        }

        #region Rest of the overrides
        public override bool CanRead
        {
            get { throw new NotImplementedException(); }
        }

        public override bool CanSeek
        {
            get { throw new NotImplementedException(); }
        }

        public override bool CanWrite
        {
            get { throw new NotImplementedException(); }
        }

        public override long Seek(long offset, SeekOrigin origin)
        {
            throw new NotImplementedException();
        }

        public override void SetLength(long value)
        {
            throw new NotImplementedException();
        }

        public override long Length
        {
            get { throw new NotImplementedException(); }
        }

        public override long Position
        {
            get
            {
                throw new NotImplementedException();
            }
            set
            {
                throw new NotImplementedException();
            }
        }
        #endregion
    }

TitleModule.cs

public class TitleModule : IHttpModule
{
    public void Dispose()
    {
    }

    private static Regex regex = new Regex(@"(?<=<title>)[\w\s\r\n]*?(?=</title)", RegexOptions.Compiled | RegexOptions.IgnoreCase);
    private StreamWatcher _watcher;
    public void Init(HttpApplication context)
    {
        context.BeginRequest += (o, e) => 
        {
            _watcher = new StreamWatcher(context.Response.Filter);
            context.Response.Filter = _watcher;
        };


        context.EndRequest += (o, e) =>
        {
            string value = _watcher.ToString();
            Trace.WriteLine(regex.Match(value).Value.Trim());
        };
    }
}

Answer 2

There is an article on 4GuysFromRolla that talks about creating HttpResponse filters which are basically streams that process the response before passing it through to the final output stream (an interceptor).

http://aspnet.4guysfromrolla.com/articles/120308-1.aspx