利用HttpWebRequest自动抓取

kenter1643

1、利用httpwatch找到网站入口及参数：（详情略，请百度httpwatch的使用方法）
2、利用httpwebRequest将51拉查看密码Post到网站入口,登陆成功后再进入你想要进入的页面抓取页面 
<div class="cnblogs_code"><!--<br /><br />Code highlighting produced by Actipro CodeHighlighter (freeware)<br />http://www.CodeHighlighter.com/<br /><br />-->        /// <summary>
        /// 某日或者叫时间段，51la里组员ID里——搜索引擎内——的数据。
        /// </summary>
        /// <param name="strStaticId"></param>
        /// <param name="LookPass"></param>
        /// <param name="strBeginDate"></param>
        /// <param name="strEndDate"></param>
        /// <returns></returns>
        public string FiveLaSeo(string strStaticId, string LookPass,string strBeginDate,string strEndDate)
        {
            CookieContainer Cc = new CookieContainer();

            ASCIIEncoding encoding = new ASCIIEncoding();
            string postData = "id=" + strStaticId;
            postData += ("&lookpass=" + LookPass);
            postData += "&t=chalogin";

            //将提交的字符串数据转换成字节数组
            byte[] data = encoding.GetBytes(postData);

            // 设置提交的相关参数   
            HttpWebRequest myRequest = (HttpWebRequest)WebRequest.Create("http://www.51.la/report/0_help.asp");
            myRequest.Method = "POST";
            myRequest.ContentType = "application/x-www-form-urlencoded";
            myRequest.ContentLength = data.Length;
            //cookie的容器一定要加
            myRequest.CookieContainer = Cc;

            // 提交请求数据  
            Stream newStream = myRequest.GetRequestStream();            
            newStream.Write(data, 0, data.Length);
            newStream.Close();

            // 接收返回的页面  
            HttpWebResponse myResponse = (HttpWebResponse)myRequest.GetResponse();
            StreamReader reader = new StreamReader(myResponse.GetResponseStream(), Encoding.Default);
            string content = reader.ReadToEnd();

            //进去后打开特定页面的参数设置
            myRequest = (HttpWebRequest)WebRequest.Create("http://www.51.la/report/3_SE.asp?id=" + strStaticId + "&d1=" + strBeginDate + "&d2=" + strEndDate);
            myRequest.Method = "GET";
            myRequest.KeepAlive = false;
            myRequest.CookieContainer = Cc;

            //接收返回的特定页面
            myResponse = (HttpWebResponse)myRequest.GetResponse();
            newStream = myResponse.GetResponseStream();
            reader = new StreamReader(myResponse.GetResponseStream(),Encoding.Default);
            content = reader.ReadToEnd();
            return content;
        }