C# 获取网页内容
C#通常有三种方法获取网页内容,使用WebClient、WebBrowser或者HttpWebRequest/HttpWebResponse。
一. 使用WebClient
1 using System; 2 using System.Collections.Generic; 3 using System.IO; 4 using System.Linq; 5 using System.Net; 6 using System.Text; 7 using System.Threading.Tasks; 8 9 namespace day0917 10 { 11 class Program 12 { 13 static void Main(string[] args) 14 { 15 try 16 { 17 WebClient MyWebClient = new WebClient(); 18 //获取或设置用于向Internet资源的请求进行身份验证的网络凭据 19 MyWebClient.Credentials = CredentialCache.DefaultCredentials; 20 //从指定网站下载数据 21 Byte[] pageData = MyWebClient.DownloadData("http://www.163.com"); 22 //如果获取网站页面采用的是GB2312,则使用这句 23 string pageHtml = Encoding.Default.GetString(pageData); 24 //string pageHtml = Encoding.UTF8.GetString(pageData); 25 //如果获取网站页面采用的是UTF-8,则使用这句 26 //在控制台输入获取的内容 27 Console.WriteLine(pageHtml); 28 var file = AppDomain.CurrentDomain.BaseDirectory; 29 //将获取的内容写入文本 30 using (StreamWriter sw = new StreamWriter(@"E:课程总代码抓取数据day0917day0917A.txt")) 31 { 32 sw.Write(pageHtml); 33 } 34 Console.ReadLine(); //让控制台暂停,否则一闪而过了 35 } 36 catch (WebException webEx) 37 { 38 Console.WriteLine(webEx.Message.ToString()); 39 } 40 Console.ReadKey(); 41 } 42 } 43 }
二.使用WebBrowser
1 WebBrowser web = new WebBrowser(); 2 web.Navigate("http://www.xjflcp.com/ssc/"); 3 web.DocumentCompleted += new WebBrowserDocumentCompletedEventHandler(web_DocumentCompleted); 4 void web_DocumentCompleted(object sender, WebBrowserDocumentCompletedEventArgs e) 5 { 6 WebBrowser web = (WebBrowser)sender; 7 HtmlElementCollection ElementCollection = web.Document.GetElementsByTagName("Table"); 8 foreach (HtmlElement item in ElementCollection) 9 { 10 File.AppendAllText("Kaijiang_xj.txt", item.InnerText); 11 } 12 }