(转)asp.net c#如何采集需要登录的页面？

原文地址：http://www.cnblogs.com/subendong/archive/2013/01/31/2886568.html

首先说明：代码片段是从网络获取，然后自己修改。我想好的东西应该拿来分享。

先说下原理：当我们采集页面的时候，如果被采集的网站需要登录才能采集。不管是基于Cookie还是基于Session，我们都会首先发送一个Http请求头，这个Http请求头里面就包含了网站需要的Cookie信息。当网站接收到发送过来的Http请求头时，会从Http请求头获取相关的Cookie或者Session信息，然后由程序来处理，决定你是否有权限访问当前页面。

好了，原理搞清楚了，就好办了。我们所要做的仅仅是在采集的时候（或者说HttpWebRequest提交数据的时候），将Cookie信息放入Http请求头里面就可以了。

在这里我提供2种方法。

第一种，直接将Cookie信息放入HttpWebRequest的CookieContainer里。看代码：

protected void Page_Load(object sender, EventArgs e)
        {
            //设置Cookie，存入Hashtable
            Hashtable ht = new Hashtable();
            ht.Add("username", "youraccount");
            ht.Add("id", "yourid");
            this.Collect(ht);
        }
        public void Collect(Hashtable ht)
        {
            string content = string.Empty;
            string url = "http://www.ibest100.com/需要登录后才能采集的页面";
            string host = "http://www.ibest100.com";
            try
            {
                //获取提交的字节
                byte[] bs = Encoding.UTF8.GetBytes(content);
                //设置提交的相关参数
                HttpWebRequest req = (HttpWebRequest)HttpWebRequest.Create(url);
                req.Method = "POST";
                req.ContentType = "application/json;charset=utf-8";
                req.ContentLength = bs.Length;
                //将Cookie放入CookieContainer，然后再将CookieContainer添加到HttpWebRequest
                CookieContainer cc = new CookieContainer();
                cc.Add(new Uri(host), new Cookie("username", ht["username"].ToString()));
                cc.Add(new Uri(host), new Cookie("id", ht["id"].ToString()));
                req.CookieContainer = cc;
                //提交请求数据
                Stream reqStream = req.GetRequestStream();
                reqStream.Write(bs, 0, bs.Length);
                reqStream.Close();
                //接收返回的页面，必须的，不能省略
                WebResponse wr = req.GetResponse();
                System.IO.Stream respStream = wr.GetResponseStream();
                System.IO.StreamReader reader = new System.IO.StreamReader(respStream, System.Text.Encoding.GetEncoding("utf-8"));
                string t = reader.ReadToEnd();
                System.Web.HttpContext.Current.Response.Write(t);
                wr.Close();
            }
            catch (Exception ex)
            {
                System.Web.HttpContext.Current.Response.Write("异常在getPostRespone:" + ex.Source + ":" + ex.Message);
            }

        }

第二种，每次打开采集程序时，需要先到被采集的网站模拟登录一次，获取CookieContainer，然后再采集。看代码：

protected void Page_Load(object sender, EventArgs e)
        {
            try
            {
                CookieContainer cookieContainer = new CookieContainer();
                string formatString = "username={0}&password={1}";//***************
                string postString = string.Format(formatString, "youradminaccount", "yourpassword");
                //将提交的字符串数据转换成字节数组
                byte[] postData = Encoding.UTF8.GetBytes(postString);
                //设置提交的相关参数
                string URI = "http://www.ibest100.com/登录页面";//***************
                HttpWebRequest request = WebRequest.Create(URI) as HttpWebRequest;
                request.Method = "POST";
                request.KeepAlive = false;
                request.ContentType = "application/x-www-form-urlencoded";
                request.CookieContainer = cookieContainer;
                request.ContentLength = postData.Length;
                // 提交请求数据
                System.IO.Stream outputStream = request.GetRequestStream();
                outputStream.Write(postData, 0, postData.Length);
                outputStream.Close();
                //接收返回的页面，必须的，不能省略
                HttpWebResponse response = request.GetResponse() as HttpWebResponse;
                System.IO.Stream responseStream = response.GetResponseStream();
                System.IO.StreamReader reader = new System.IO.StreamReader(responseStream, Encoding.GetEncoding("gb2312"));
                string srcString = reader.ReadToEnd();
                //打开您要访问的页面
                URI = "http://www.ibest100.com/需要登录后才能采集的页面";//***************
                request = WebRequest.Create(URI) as HttpWebRequest;
                request.Method = "GET";
                request.KeepAlive = false;
                request.CookieContainer = cookieContainer;
                // 接收返回的页面
                response = request.GetResponse() as HttpWebResponse;
                responseStream = response.GetResponseStream();
                reader = new System.IO.StreamReader(responseStream, Encoding.GetEncoding("gb2312"));
                srcString = reader.ReadToEnd();
                //输出获取的页面或者处理
                Response.Write(srcString);
            }
            catch (WebException we)
            {
                string msg = we.Message;
                Response.Write(msg);
            }
        }

 

也许有人会问，如果对方登录的时候要验证码怎么办？那你就用第一种方式吧，只不过需要你分析对方的Cookie。

应用范围：采集数据、论坛发帖、博客发文。