快速获取网页的title值

using System.Text.RegularExpressions;

static string GetTitle(string html)

        {

            //string regex = @"(<title>)([\s\S]*)(</title>)";

            string regex = @"(?<=<title.*>)([\s\S]*)(?=</title>)";

            //正向预搜索与反向预搜索：http://www.rczjp.cn/HTML/120709/20120409090416.html

            Regex reg = new Regex(regex, RegexOptions.IgnoreCase);

            return reg.Match(html).Value.Trim();

        }

 

        static void Main(string[] args)

        {

            string html = GetHtmlInfo("www.rczjp.cn", 5000, Encoding.UTF8);

            Console.WriteLine(html);

            Console.WriteLine(GetTitle(html));

 

            Console.Read();

 

        }

 

        ///<summary>

        ///获取页面的HTML信息，到标题（</title>）位置结束

        ///</summary>

        ///<param name="url">页面地址</param>

        ///<param name="timeout">超时时间，单位：ms</param>

        ///<param name="EnCodeType">编码</param>

        ///<returns></returns>

        static string GetHtmlInfo(string url, int timeout, Encoding EnCodeType)

        {

            if (!url.StartsWith("http://") && !url.StartsWith("https://")) { url = "http://" + url; }

            string result = "";

            System.IO.StreamReader reader = null;

            string temp = "";

            try

            {

                HttpWebRequest request = (HttpWebRequest)HttpWebRequest.Create(url);//初始化WebRequest

                request.Timeout = timeout;

                request.UserAgent = "User-Agent:Mozilla/5.0 (compatible; MSIE 6.0; Windows NT 5.2; SV1; .NET CLR 2.0.40607; .NET CLR 1.1.4322; .NET CLR 3.5.30729)";

                request.Accept = "*/*";

                request.KeepAlive = true;

                request.Headers.Add("Accept-Language", "zh-cn,en-us;q=0.5");

                HttpWebResponse response = (HttpWebResponse)request.GetResponse();//返回来自Internet的响应

                if (response.StatusCode == System.Net.HttpStatusCode.OK)

                {

                    StringBuilder builder = new StringBuilder();

                    Stream stream = response.GetResponseStream();

                    reader = new StreamReader(stream, EnCodeType);

                    string tmp = "";

                    while ((temp = reader.ReadLine()) != null)

                    {

                        builder.Append(temp);

                        tmp = builder.ToString();

                        if (tmp.IndexOf("</title>") > 0) { break; }//ReadLine是读取整行，所以有时在它后面的很多字符串也会读取

                        Console.WriteLine(tmp.IndexOf("</title>"));

                        builder.Append("\r\n");

                    }

                    result = builder.ToString();

                    return result;

                }

                return string.Empty;

            }

            catch (Exception ex)

            {

                return ex.Message;

            }

            finally { if (reader != null) { reader.Close(); } }

        }