精彩奥运热点赛事的实时采集 - CSkin博客

东京奥运会正在如火如荼的进行中，中国健儿目前获取的金牌数已经超过约奥运会的金牌总数，同时大家也不再聚焦于取得奖牌的项目，苏炳添创造的历史、女篮取得不错的成绩、女排的遗憾都值得大家的关心。那么接下来还有哪些精彩赛事呢，通过爬虫程序抓取奥运网站分析之后可以更快的了解实时信息如下：

[C#] 纯文本查看 复制代码

// 要访问的目标页面

string targetUrl = "https://olympics.com/zh/";





// 代理服务器(产品官网 www.16yun.cn)

string proxyHost = "http://t.16yun.cn";

string proxyPort = "31111";



// 代理验证信息

string proxyUser = "username";

string proxyPass = "password";



// 设置代理服务器

WebProxy proxy = new WebProxy(string.Format("{0}:{1}", proxyHost, proxyPort), true);





ServicePointManager.Expect100Continue = false;



var request = WebRequest.Create(targetUrl) as HttpWebRequest;



request.AllowAutoRedirect = true;

request.KeepAlive = true;

request.Method    = "GET";

request.Proxy     = proxy;



//request.Proxy.Credentials = CredentialCache.DefaultCredentials;



request.Proxy.Credentials = new System.Net.NetworkCredential(proxyUser, proxyPass);



// 设置Proxy Tunnel

// Random ran=new Random();

// int tunnel =ran.Next(1,10000);

// request.Headers.Add("Proxy-Tunnel", String.valueOf(tunnel));





//request.Timeout = 20000;

//request.ServicePoint.ConnectionLimit = 512;

//request.UserAgent = "Mozilla/5.0 (Windows NT 6.3; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/48.0.2564.82 Safari/537.36";

//request.Headers.Add("Cache-Control", "max-age=0");

//request.Headers.Add("DNT", "1");





//String encoded = System.Convert.ToBase64String(System.Text.Encoding.GetEncoding("ISO-8859-1").GetBytes(proxyUser + ":" + proxyPass));

//request.Headers.Add("Proxy-Authorization", "Basic " + encoded);



using (var response = request.GetResponse() as HttpWebResponse)

using (var sr = new StreamReader(response.GetResponseStream(), Encoding.UTF8))

{

    string htmlStr = sr.ReadToEnd();

}