C#获取网页内容的三种方式 – Luke Zhang – 博客园

搜索网络,发现C#通常有三种方法获取网页内容,使用WebClient、WebBrowser或者HttpWebRequest/HttpWebResponse。。。

方法一:使用WebClient (引用自:http://fbljava.blog.163.com/blog/static/265211742008712105145244/)

 

static void Main(string[] args)

{

try {

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(“http://www.163.com”); //从指定网站下载数据

string pageHtml = Encoding.Default.GetString(pageData);  //如果获取网站页面采用的是GB2312,则使用这句

//string pageHtml = Encoding.UTF8.GetString(pageData); //如果获取网站页面采用的是UTF-8,则使用这句

Console.WriteLine(pageHtml);//在控制台输入获取的内容

using (StreamWriter sw = new StreamWriter(“c:\\test\\ouput.html”))//将获取的内容写入文本

{

sw.Write(pageHtml);

}

Console.ReadLine(); //让控制台暂停,否则一闪而过了

}

catch(WebException webEx) {

Console.WriteLine(webEx.Message.ToString());

}

}

 

方法二:使用WebBrowser (引用自:http://topic.csdn.net/u/20091225/14/4ea221cd-4c1e-4931-a6db-1fd4ee7398ef.html)

 

WebBrowser web = new WebBrowser();
web.Navigate(“http://www.xjflcp.com/ssc/”);
web.DocumentCompleted += new WebBrowserDocumentCompletedEventHandler(web_DocumentCompleted);
void web_DocumentCompleted(object sender, WebBrowserDocumentCompletedEventArgs e)
{
WebBrowser web = (WebBrowser)sender;
HtmlElementCollection ElementCollection = web.Document.GetElementsByTagName(“Table”);
foreach (HtmlElement item in ElementCollection)
{
File.AppendAllText(“Kaijiang_xj.txt”, item.InnerText);
}
}

 

方法三:使用HttpWebRequest/HttpWebResponse (引用自:http://hi.baidu.com/onlyafar/blog/item/7ac4c6bf92d4810019d81f98.html)

 

HttpWebRequest httpReq;
HttpWebResponse httpResp;

string strBuff = “”;
char[] cbuffer = new char[256];
int byteRead = 0;

string filename = @”c:\log.txt”;
///定义写入流操作
public void WriteStream()
{
Uri httpURL = new Uri(txtURL.Text);

///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
httpReq = (HttpWebRequest)WebRequest.Create(httpURL);
///通过HttpWebRequest的GetResponse()方法建立HttpWebResponse,强制类型转换

httpResp = (HttpWebResponse) httpReq.GetResponse();
///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

///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
Stream respStream = httpResp.GetResponseStream();

///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

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)
StreamReader respStreamReader = new StreamReader(respStream,Encoding.UTF8);

byteRead = respStreamReader.Read(cbuffer,0,256);

while (byteRead != 0)
{
string strResp = new string(cbuffer,0,byteRead);
strBuff = strBuff + strResp;
byteRead = respStreamReader.Read(cbuffer,0,256);
}

respStream.Close();
txtHTML.Text = strBuff;
}

来源URL:http://www.cnblogs.com/ceachy/articles/CSharp_Retrive_Page_Document.html