C# 获取网页内容

 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\day0917\day0917\A.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 }

 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         }

 1 HttpWebRequest httpReq; 
 2 HttpWebResponse httpResp; 
 3 
 4 string strBuff = ""; 
 5 char[] cbuffer = new char[256]; 
 6 int byteRead = 0; 
 7 
 8 string filename = @"c:\log.txt"; 
 9 ///定义写入流操作 
10 public void WriteStream() 
11 { 
12 Uri httpURL = new Uri(txtURL.Text);
13 
14 ///HttpWebRequest类继承于WebRequest，并没有自己的构造函数，需通过WebRequest的Creat方法 建立，并进行强制的类型转换 
15       httpReq = (HttpWebRequest)WebRequest.Create(httpURL); 
16 ///通过HttpWebRequest的GetResponse()方法建立HttpWebResponse,强制类型转换
17 
18    httpResp = (HttpWebResponse) httpReq.GetResponse(); 
19 ///GetResponseStream()方法获取HTTP响应的数据流,并尝试取得URL中所指定的网页内容
20 
21      ///若成功取得网页的内容，则以System.IO.Stream形式返回，若失败则产生ProtoclViolationException错 误。在此正确的做法应将以下的代码放到一个try块中处理。这里简单处理 
22 Stream respStream = httpResp.GetResponseStream();
23 
24 ///返回的内容是Stream形式的，所以可以利用StreamReader类获取GetResponseStream的内容，并以
25 
26 StreamReader类的Read方法依次读取网页源程序代码每一行的内容，直至行尾（读取的编码格式：UTF8） 
27 StreamReader respStreamReader = new StreamReader(respStream,Encoding.UTF8);
28 
29 byteRead = respStreamReader.Read(cbuffer,0,256); 
30 
31 while (byteRead != 0) 
32 { 
33 string strResp = new string(cbuffer,0,byteRead); 
34                   strBuff = strBuff + strResp; 
35                   byteRead = respStreamReader.Read(cbuffer,0,256); 
36 } 
37 
38 respStream.Close(); 
39 txtHTML.Text = strBuff; 
40 }