请求网址并解析返回的html

- 中国WEB开发者网络 (http://www.webasp.net)
-- 技术教程 (http://www.webasp.net/article/)
--- 请求网址并解析返回的html (http://www.webasp.net/article/28/27924.htm)
-- 作者:未知
-- 发布日期: 2006-10-30
 

目的,把远程服务器传回的Html,解析到类里面,为GridView等提供数据源
1 、向远程服务器Post数据
public int PostData(string url, string data, out string info)
        {

            info = "";
            CookieContainer cc = new CookieContainer();
            HttpWebRequest request = WebRequest.Create(url) as HttpWebRequest;
            request.CookieContainer = cc;
            request.Method = "POST";
            request.ContentType = "application/x-www-form-urlencoded";
            Stream requestStream = request.GetRequestStream();
            byte[] byteArray = Encoding.UTF8.GetBytes(data);
            requestStream.Write(byteArray, 0, byteArray.Length);
            requestStream.Close();
            HttpWebResponse response = request.GetResponse() as HttpWebResponse;
            Uri responseUri = response.ResponseUri;
            Stream receiveStream = response.GetResponseStream();
            Encoding encode = System.Text.Encoding.GetEncoding("utf-8");
            StreamReader readStream = new StreamReader(receiveStream, encode);
            string result = readStream.ReadToEnd();
            info = result;
            return 0;

        }2、解析返回的html,有省略
 public ClassInfo[] GetClass(string html)
        {

            ArrayList ar = new ArrayList();
            ArrayList arr = new ArrayList();
            string table = "";
            Regex regtable = new Regex(@"(?<=<table.*>).*?(?=</table>)", RegexOptions.Singleline);
            Match ma = regtable.Match(html);
            while (ma.Success)
            {
                if (ma.Value.Trim() != "")
                {
                    arr.Add(HttpUtility.HtmlDecode(ma.Value));
                }
                ma = ma.NextMatch();
            }
            for (int i = 0; i < arr.Count; i++)
            {
                table = arr[i].ToString() + table;
            }


            Regex reg = new Regex(@"(?<=<.*?>).*?(?=<.*?>)", RegexOptions.Singleline);
            Match m = reg.Match(table);


            while (m.Success)
            {
                if (m.Value.Trim() != "")
                {

                    ar.Add(HttpUtility.HtmlDecode(m.Value));
                }
                m = m.NextMatch();
            }


           ClassInfo[] ci = new ClassInfo[classno];
            for (int i = 0; i < classno; i++)
            {
                ci[i] = new ClassInfo();
                ci[i].RegisterDate = (ar[i * 8 + 0]).ToString();

                ci[i].LoginDate = (ar[i * 8 + 1]).ToString();
                ci[i].LogoutDate = (ar[i * 8 + 2]).ToString();
                ci[i].UseMin = ar[i * 8 + 3].ToString();
                ci[i].ClassName = ar[i * 8 + 5].ToString();
                ci[i].ClassType = ar[i * 8 + 6].ToString();
                ci[i].Percent = ar[i * 8 + 7].ToString();

            }

 

            return ci;


        }
3、定义ClassInfo类(课程类),用CodeSmith生成
 public class ClassInfo
    {
        Member Variables#region Member Variables


        protected string _loginDate;
        protected string _logoutDate;
        protected string _registerDate;
        protected string _useMin;
        protected string _className;
        protected string _classType;
        protected string _percent;
        //protected string _nouse;
        #endregion

        Constructors#region Constructors

        public ClassInfo() { }

        public ClassInfo(string loginDate, string logoutDate, string registerDate, string useMin, string className, string classType, string percent)
        {
            this._loginDate = loginDate;
            this._logoutDate = logoutDate;
            this._registerDate = registerDate;
            this._useMin = useMin;
            this._className = className;
            this._classType = classType;
            this._percent = percent;
        }

        #endregion

        Public Properties#region Public Properties
        //        public string NoUse
        //        {
        //            get{return _nouse;}
        //            set{ _nouse= value;}
        //        }

 

        public string LoginDate
        {
            get { return _loginDate; }
            set { _loginDate = value; }
        }

        public string LogoutDate
        {
            get { return _logoutDate; }
            set { _logoutDate = value; }
        }

        public string RegisterDate
        {
            get { return _registerDate; }
            set { _registerDate = value; }
        }

        public string UseMin
        {
            get { return _useMin; }
            set { _useMin = value; }
        }

        public string ClassName
        {
            get { return _className; }
            set
            {
                if (value != null && value.Length > 50)
                    throw new ArgumentOutOfRangeException("Invalid value for ClassName", value, value.ToString());
                _className = value;
            }
        }

        public string ClassType
        {
            get { return _classType; }
            set
            {
                if (value != null && value.Length > 50)
                    throw new ArgumentOutOfRangeException("Invalid value for ClassType", value, value.ToString());
                _classType = value;
            }
        }

        public string Percent
        {
            get { return _percent; }
            set
            {
                if (value != null && value.Length > 50)
                    throw new ArgumentOutOfRangeException("Invalid value for Percent", value, value.ToString());
                _percent = value;
            }
        }

        #endregion
    }

http://bluewater.cnblogs.com/archive/2006/06/19/429720.html

转自:动态网站制作指南 | www.knowsky.com

webasp.net