网页小偷

 string PageUrl = "http://news.sina.com.cn/china/sz/";
        string url = "";
        WebClient wc = new WebClient();
        wc.Credentials = CredentialCache.DefaultCredentials;

        Byte[] pageData = wc.DownloadData(PageUrl);
        string content = Encoding.Default.GetString(pageData);
        MatchCollection mc = Regex.Matches(content, @"<A\shref=(?<url>.*(?<date>(?<year>\d{4})-(?<month>\d{2})-(?<day>\d{2})).*shtml)\s*TARGET=_blank>(?<subject>.*)</a>", RegexOptions.IgnoreCase);
        string OriginalURL;
        string Subject;
        string date;
        string month;
        string day;

        foreach (Match match in mc)
        {

            OriginalURL = match.Groups["url"].Value;//新闻内容链接，如"/c/2006-02-19/19568247131s.shtml "

            //WebClient wc2 = new WebClient();
            //wc2.Credentials = CredentialCache.DefaultCredentials;

            /////方法一：
            //Byte[] pageData1 = wc2.DownloadData("http://sports.sina.com.cn" + OriginalURL);
            //string content1 = Encoding.Default.GetString(pageData1);

            ///方法二：
            WebRequest request = WebRequest.Create("http://news.sina.com.cn" + OriginalURL);
            WebResponse response = request.GetResponse();
            Stream resStream = response.GetResponseStream();
            StreamReader sr = new StreamReader(resStream, System.Text.Encoding.Default);

            string HTML = "";
            string sLine = "";
            int i = 0;
            while (sLine != null)
            {
                i++;
                sLine = sr.ReadLine();
                if (sLine != null)
                    HTML += sLine;
            }
            HTML = HTML.Replace("&lt;", "<");
            HTML = HTML.Replace("&gt;", ">");

            //Regex.Split(HTML, @"<!--正文内容开始-->", RegexOptions.IgnoreCase);

            //int start, stop;
            //start = HTML.IndexOf("<!--正文内容开始-->", 0, HTML.Length);
            //stop = HTML.IndexOf("<!--正文内容结束-->", start);
           
            string[] strTemp = Regex.Split(HTML, @"<!--正文内容开始-->", RegexOptions.IgnoreCase);
            string[] strTemp1 = Regex.Split(strTemp[1].ToString(), @"<!--正文内容结束-->", RegexOptions.IgnoreCase);
            string temp = strTemp1[0].ToString();
            Subject = match.Groups["subject"].Value;//新闻标题，如"巴基斯坦总统穆沙拉夫抵京访华"
            date = match.Groups["year"].Value;//新闻发布时间，从新闻链接中提取，如“2006-02-19”
            month = match.Groups["month"].Value;
            day = match.Groups["day"].Value;
            int rowsAffected;
            SqlParameter[] parameters = {
     new SqlParameter("@NewsID", SqlDbType.Int,4),
     new SqlParameter("@NewsTitle", SqlDbType.NVarChar),
     new SqlParameter("@NewsContent", SqlDbType.Text),
     new SqlParameter("@AdminID", SqlDbType.Int,4),
     new SqlParameter("@Createtime", SqlDbType.DateTime),
     new SqlParameter("@categoryid", SqlDbType.Int,4)};
            parameters[0].Direction = ParameterDirection.Output;
            parameters[1].Value = Subject;
            parameters[2].Value = temp;
            parameters[3].Value = 1;
            parameters[4].Value = System.DateTime.Now;
            parameters[5].Value = 2;

            DbHelperSQL.RunProcedure("UP_News_ADD", parameters, out rowsAffected);
            url += "<tr><td><a href=" + OriginalURL + ">" + Subject + "</a>(" + date + "-" + month + "-" + day + ")</td></tr> ";
            flag++;
            if (flag >= 10)
                break;
        }
        lblhtml.Text = url;