获取网页内容的几种方法

获取网页内容的几种方法

  (2012-10-14 21:01:09)

转载▼

标签：  杂谈

this.tbUrl.Text = "http://www.baidu.com";

1、使用WebClient类
 

 WebClient MyWebClient = new WebClient();
 MyWebClient.Credentials = CredentialCache.DefaultCredentials;     //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
 Byte[] pageData = MyWebClient.DownloadData(tbUrl.Text);           //从指定网站下载数据
 string pageHtml = Encoding.Default.GetString(pageData);           //把字节转化为字符串，注意编码方式
 
2、使用WebBrowser控件
 //通过WebBrowser空间访问网页，然后获取网页数据
 WebBrowser web = new WebBrowser();
 web.Navigate(tbUrl.Text);
 web.DocumentCompleted += new WebBrowserDocumentCompletedEventHandler(web_DocumentCompleted);       //当网页加载完成时触发该事件，获取网页数据
 
 void web_DocumentCompleted(object sender, WebBrowserDocumentCompletedEventArgs e)
 {
     //获取该html页面内的Table标签的内容
     WebBrowser web = (WebBrowser)sender;
     HtmlElementCollection ElementCollection = web.Document.getElementsByTagName_r("Table");
     foreach (HtmlElement item in ElementCollection) 
    {
        textBox1.AppendText(item.InnerText + "\n");
    } 
 }
 
3、使用HttpWebRequest/HttpWebResponse
 HttpWebRequest httpReq;
 HttpWebResponse httpResp;
 
 Uri httpURL = new Uri(this.tbUrl.Text);
 httpReq = (HttpWebRequest)WebRequest.Create(httpURL);
 httpResp = (HttpWebResponse)httpReq.GetResponse();
 
 Stream respStream = httpResp.GetResponseStream();      //得到数据流，再把数据流转化为特定的数据（图片，文本。。。）
   
 //如果是图片流
 pictureBox1.Image = Image.FromStream(respStream);
 
 //如果是文本流
 byte[] cbuffer = new byte[256];
 StreamReader respStreamReader = new StreamReader(respStream,Encoding.UTF8);  //编码为utf8
 byteRead = respStreamReader.Read(cbuffer,0,256);   //读取256个字节
 string strResp = new string(cbuffer,0,byteRead);