I have a C # application that needs to clear many pages in a specific domain as quickly as possible. I have Parallel.Foreach that looks at all the URLs (multi-threaded) and resets them using the code below:
private string ScrapeWebpage(string url, DateTime? updateDate)
{
HttpWebRequest request = null;
HttpWebResponse response = null;
Stream responseStream = null;
StreamReader reader = null;
string html = null;
try
{
request = (HttpWebRequest)WebRequest.Create(url);
request.Pipelined = true;
request.KeepAlive = true;
request.Headers.Add(HttpRequestHeader.AcceptEncoding, "gzip,deflate");
if (updateDate != null)
request.IfModifiedSince = updateDate.Value;
response = (HttpWebResponse)request.GetResponse();
responseStream = response.GetResponseStream();
if (response.ContentEncoding.ToLower().Contains("gzip"))
responseStream = new GZipStream(responseStream, CompressionMode.Decompress);
else if (response.ContentEncoding.ToLower().Contains("deflate"))
responseStream = new DeflateStream(responseStream, CompressionMode.Decompress);
reader = new StreamReader(responseStream, Encoding.Default);
html = reader.ReadToEnd();
}
catch
{
throw;
}
finally
{
request = null;
if (response != null)
{
response.Close();
response = null;
}
if (responseStream != null)
{
responseStream.Close();
responseStream.Dispose();
}
if (reader != null)
{
reader.Close();
reader.Dispose();
}
}
return html;
}
, HTTP request.keepalive request.pipelined true. , , , - , , . , , , ? keepalive?