首先說明：代碼片段是從網絡獲取，然後自己修改。我想好的東西應該拿來分享。
先說下原理：當我們采集頁面的時候，如果被采集的網站需要登錄才能采集。不管是基於Cookie還是基於Session，我們都會首先發送一個Http請求頭，這個Http請求頭裡面就包含了網站需要的Cookie信息。當網站接收到發送過來的Http請求頭時，會從Http請求頭獲取相關的Cookie或者Session信息，然後由程序來處理，決定你是否有權限訪問當前頁面。
好了，原理搞清楚了，就好辦了。我們所要做的僅僅是在采集的時候（或者說HttpWebRequest提交數據的時候），將Cookie信息放入Http請求頭裡面就可以了。
在這裡我提供2種方法。
第一種，直接將Cookie信息放入HttpWebRequest的CookieContainer裡。看代碼：
protected void Page_Load(object sender, EventArgs e)
{
//設置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/需要登錄後才能采集的頁面";
string host = "http://www.ibest100.com";
try
{
//獲取提交的字節
byte[] bs = Encoding.UTF8.GetBytes(content);
//設置提交的相關參數
HttpWebRequest req = (HttpWebRequest)HttpWebRequest.Create(url);
req.Method = "POST";
req.ContentType = "application/json;charset=utf-8";
req.ContentLength = bs.Length;
//將Cookie放入CookieContainer，然後再將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;
//提交請求數據
Stream reqStream = req.GetRequestStream();
reqStream.Write(bs, 0, bs.Length);
reqStream.Close();
//接收返回的頁面，必須的，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("異常在getPostRespone:" + ex.Source + ":" + ex.Message);
}
}
第二種，每次打開采集程序時，需要先到被采集的網站模擬登錄一次，獲取CookieContainer，然後再采集。看代碼：
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");
//將提交的字符串數據轉換成字節數組
byte[] postData = Encoding.UTF8.GetBytes(postString);
//設置提交的相關參數
string URI = "http://www.ibest100.com/登錄頁面";//***************
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;
// 提交請求數據
System.IO.Stream outputStream = request.GetRequestStream();
outputStream.Write(postData, 0, postData.Length);
outputStream.Close();
//接收返回的頁面，必須的，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();
//打開您要訪問的頁面
URI = "http://www.ibest100.com/需要登錄後才能采集的頁面";//***************
request = WebRequest.Create(URI) as HttpWebRequest;
request.Method = "GET";
request.KeepAlive = false;
request.CookieContainer = cookieContainer;
// 接收返回的頁面
response = request.GetResponse() as HttpWebResponse;
responseStream = response.GetResponseStream();
reader = new System.IO.StreamReader(responseStream, Encoding.GetEncoding("gb2312"));
srcString = reader.ReadToEnd();
//輸出獲取的頁面或者處理
Response.Write(srcString);
}
catch (WebException we)
{
string msg = we.Message;
Response.Write(msg);
}
}
也許有人會問，如果對方登錄的時候要驗證碼怎麼辦？那你就用第一種方式吧，只不過需要你分析對方的Cookie。
應用范圍：采集數據、論壇發帖、博客發文。
感謝來自網絡 的文章 編輯:dezai
轉載自:http://www.aspnetjia.com
