c# 獲取網頁源碼

C#獲取指定網頁HTML原代碼可使用 WebClient WebRequest HttpWebRequest 三種方式來實現。

當然也可使用webBrowse！在此就不研究webBrowse如何獲取了。

WebClient

private string GetWebClient(string url)

{

string strHTML = "";

WebClient myWebClient = new WebClient();

Stream myStream = myWebClient.OpenRead(url);

StreamReader sr = new StreamReader(myStream, System.Text.Encoding.GetEncoding("utf-8"));

strHTML = sr.ReadToEnd();

myStream.Close();

return strHTML;

}

WebRequest

private string GetWebRequest(string url)

{

Uri uri = new Uri(url);

WebRequest myReq = WebRequest.Create(uri);

WebResponse result = myReq.GetResponse();

Stream receviceStream = result.GetResponseStream();

StreamReader readerOfStream = new StreamReader(receviceStream, System.Text.Encoding.GetEncoding("utf-8"));

string strHTML = readerOfStream.ReadToEnd();

readerOfStream.Close();

receviceStream.Close();

result.Close();

return strHTML;

}

HttpWebRequest

private string GetHttpWebRequest(string url)

{

Uri uri = new Uri(url);

HttpWebRequest myReq = (HttpWebRequest)WebRequest.Create(uri);

myReq.UserAgent = "User-Agent:Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.2; .NET CLR 1.0.3705";

myReq.Accept = "*/*";

myReq.KeepAlive = true;

myReq.Headers.Add("Accept-Language", "zh-cn,en-us;q=0.5");

HttpWebResponse result = (HttpWebResponse)myReq.GetResponse();

Stream receviceStream = result.GetResponseStream();

StreamReader readerOfStream = new StreamReader(receviceStream, System.Text.Encoding.GetEncoding("utf-8"));

string strHTML = readerOfStream.ReadToEnd();

readerOfStream.Close();

receviceStream.Close();

result.Close();

return strHTML;

}

注意"utf-8"應與指定網頁的編碼對應。

總結

可以看到HttpWebRequest 方式最復雜，但確提供了更多的選擇性。

有的網站檢測客戶端的UserAgent！如163.com，你如果使用WebClient WebRequest方式獲取時，將獲取到的是錯誤提示頁面內容。

而通過HttpWebRequest 就沒問題。

源碼下載：http://files.cnblogs.com/zjfree/GetHTML.rar

測試環境：WIN2003 + VS2005 + C# + winForm

歡迎轉載，轉載請注明：轉載自[ http://hovertree.com/ ]