C#网页数据采集（三）HttpWebRequest

1. <span style="font-family: Arial, Helvetica, sans-serif; background-color: rgb(255, 255, 255);">截取到网页数据是js加载完以后的</span>  

 

 

 

[csharp] view plain copy

 

1. <span style="white-space:pre">    </span>    HtmlWeb webClient = new HtmlWeb();  
2.           string _url = "http://news.baidu.com/";  
3.           HtmlAgilityPack.HtmlDocument html1 = webClient.Load(_url);//是你需要解析的url  
4.           var end3 = html1.Encoding.BodyName;//获取页面编码格式  
5.           string _htmlSource = GetHtmlSource(_url, System.Text.Encoding.GetEncoding(end3));//还是需要设置一次编码格式避免乱码 调用<span style="font-family: Arial, Helvetica, sans-serif;">GetHtmlSource方法</span>  

 

[csharp] view plain copy

 

1. public static string GetHtmlSource(string url, Encoding charset)  
2.         {  
3.             string _html = string.Empty;  
4.             try  
5.             {  
6.                 HttpWebRequest _request = (HttpWebRequest)WebRequest.Create(url);  
7.                 HttpWebResponse _response = (HttpWebResponse)_request.GetResponse();  
8.                 using (Stream _stream = _response.GetResponseStream())  
9.                 {  
10.                     using (StreamReader _reader = new StreamReader(_stream, charset))  
11.                     {  
12.                         _html = _reader.ReadToEnd();  
13.                     }  
14.                 }  
15.             }  
16.             catch (WebException ex)  
17.             {  
18.                 using (StreamReader sr = new StreamReader(ex.Response.GetResponseStream()))  
19.                 {  
20.                     _html = sr.ReadToEnd();  
21.                 }  
22.             }  
23.             catch (Exception ex)  
24.             {  
25.                 _html = ex.Message;  
26.             }  
27.             return _html;  
28.         }