在C# Winform 應用程序中,獲取某網頁的源文件,可以用以下方法:
首先引入名稱空間
using System.IO;
using System.Net;
WebClient MyWebClient = new WebClient(); MyWebClient.Credentials = CredentialCache.DefaultCredentials;//獲取或設置用于向Internet資源的請求進行身份驗證的網絡憑據Byte[] pageData = MyWebClient.DownloadData("http://www.baidu.com");//string pageHtml = Encoding.Default.GetString(pageData); FileStream file = new FileStream("C://test.html", FileMode.Create); file.Write(pageData, 0, pageData.Length);
附,c# 獲取網頁源碼的代碼舉例。
C# 獲取指定網頁HTML原代碼可使用:WebClient WebRequest HttpWebRequest 三種方式。
當然也可使用webBrowse,有興趣的朋友,可以自己研究下。
1,WebClient方式
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;}
2,WebRequest方式
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;}
3,HttpWebRequest方式
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
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,如果使用WebClient WebRequest方式獲取,將獲取到的是錯誤提示頁面的內容。
HttpWebRequest沒有這個問題。
測試環境:WIN2003 + VS2005 + C# + winForm
新聞熱點
疑難解答