通过代理服务器验证后在抓取网页内容

 

C#用HttpWebRequest通过代理服务器验证后抓取网页内容 。。。。。

string urlStr = "http://www.domain.com";                            //設定要獲取的地址
HttpWebRequest hwr = (HttpWebRequest)HttpWebRequest.Create(urlStr);    //建立HttpWebRequest對象
hwr.Timeout = 60000;                                                //定義服務器超時時間
WebProxy proxy = new WebProxy();                                    //定義一個網關對象
proxy.Address = new Uri("http://proxy.domain.com:3128");            //網關服務器:端口
proxy.Credentials = new NetworkCredential("f3210316", "6978233");    //用戶名,密碼
hwr.UseDefaultCredentials = true;                                    //啟用網關認証
hwr.Proxy = proxy;                                                    //設置網關
HttpWebResponse hwrs = (HttpWebResponse)hwr.GetResponse();            //取得回應
Stream s = hwrs.GetResponseStream();                                //得到回應的流對象
StreamReader sr = new StreamReader(s, Encoding.UTF8);                //以UTF-8編碼讀取流
StringBuilder content = new StringBuilder();                        //
while (sr.Peek() != -1)                                                //每次讀取一行,直到
{                                                                    //下一個字節沒有內容
    content.Append(sr.ReadLine()+"/r/n");                            //返回為止
}                                                                    //
return content.ToString() ;                                            //返回得到的字符串

posted on 2007-07-14 17:56 Fooo 阅读(558) 评论(1)  编辑  收藏 所属分类: webBrowser

评论

//创建一个HTTP请求
HttpWebRequest req = (HttpWebRequest)WebRequest.Create("http://某家网站的验证码服务器/getimage?0.4283556984309326");
//设置一个代理
WebProxy myproxy = new WebProxy("202.101.6.85",8080);
req.Proxy = myproxy;
//获取代理服务器的回应
HttpWebResponse res = null;
try
{
res = (HttpWebResponse)req.GetResponse();
}
catch
{
MessageBox.Show("无法连接代理！");
return;
}
//判断HTTP响应状态
if(res.StatusCode != HttpStatusCode.OK)
{
MessageBox.Show("访问失败！");
res.Close();
return;
}
//获取应答流
System.IO.Stream stream = res.GetResponseStream();
//直接加载到图片（可以直接显示到图片控件）
System.Drawing.Bitmap bp = new Bitmap(stream);
//关闭应答流和服务器的应答
stream.Close();
res.Close();
//输出所有的Header（当然包括服务器输出的Cookie）
for(int ii=0;ii<res.Headers.Count;ii++)
{
MessageBox.Show(res.Headers.GetKey(ii)+"："+res.Headers[ii]);
}

#1楼 [楼主] 2007-07-14 18:14 Fooo