最近1直在思考着如何通过代码去假装或实现人工自然阅读网页的效果,起初能想到的是用WebBrowser实现这1效果,需要到达的功能料想有以下几点:
1、自动刷新
2、摹拟人工下拉转动条并停留1段时间;
3、可以刷IP、刷流量;
4、可以增加任意来访域名;
5、自动随机点击站内页面;
6、自动随机点击站内广告;
7、自动清除Cookie、Session;
8、能够摹拟搜索引擎搜索关键字并点击到指导页面;
1、WebBrowser中获得Cookie生成CookieContainer
1.在WebBrowser中获得Cookie CookieContainer myCookieContainer = new CookieContainer(); string cookieStr = webBrowser1.Document.Cookie; string[] cookstr = cookieStr.Split(';'); foreach (string str in cookstr) { string[] cookieNameValue = str.Split('='); Cookie ck = new Cookie(cookieNameValue[0].Trim ().ToString(), cookieNameValue[1].Trim ().ToString()); ck.Domain = "www.google.com"; myCookieContainer.Add(ck); } WebClient设置cookie! WebClient wc = new WebClient(); wc.Headers.Add("Cookie", "PHPSESSID=" + cookie + ";"); // 注意,这里是Cookie,不是Set-Cookie byte[] re = wc.UploadData(Global.RootPath + "test.php", new byte[0]); System.Text.UTF8Encoding converter = new System.Text.UTF8Encoding(); string str = converter.GetString(re); 2. 在WebBrowser中设置Cookie public partial class WebBrowserControl : Form { private String url; [DllImport("wininet.dll", CharSet = CharSet.Auto, SetLastError = true)] public static extern bool InternetSetCookie(string lpszUrlName, string lbszCookieName, string lpszCookieData); public WebBrowserControl(String path) { this.url = path; InitializeComponent(); // set cookie InternetSetCookie(url, "JSESSIONID", Globals.ThisDocument.sessionID); // navigate webBrowser.Navigate(url); } } 3.将WebBrowser的cookie信息传给HttpWebRequest 先建1个"CookieContainer" 把WebBrowser中的Cookie保存在里面 //在WebBrowser中登录cookie保存在WebBrowser.Document.Cookie中 CookieContainer myCookieContainer = new CookieContainer(); //String 的Cookie 要转成 Cookie型的 并放入CookieContainer中 string cookieStr = webBrowser1.Document.Cookie; string[] cookstr = cookieStr.Split(';'); foreach (string str in cookstr) { string[] cookieNameValue = str.Split('='); Cookie ck = new Cookie(cookieNameValue[0].Trim().ToString(), cookieNameValue[1].Trim().ToString()); ck.Domain = "www.abc.com";//必须写对 myCookieContainer.Add(ck); } HttpWebRequest hreq = (HttpWebRequest)HttpWebRequest.Create("http://www.abc.com/search.asp"); hreq.Method = "POST"; hreq.ContentType = "application/x-www-form-urlencoded"; //自己创建的CookieContainer hreq.CookieContainer = myCookieContainer; string postdata = "id=2005&action=search&name="; byte[] byte1 = Encoding.ASCII.GetBytes(postdata); hreq.ContentLength = byte1.Length; Stream poststream = hreq.GetRequestStream(); poststream.Write(byte1, 0, byte1.Length); poststream.Close(); HttpWebResponse hres = (HttpWebResponse)hreq.GetResponse();
2、Webbrowser清除Cookie及session
//方法1:调用 wininet.dll清除cookie (推荐) SuppressWininetBehavior(); //方法2:删除用户登录后的信息,这里相当于阅读器的注销功能,使用的是ie自带的功能 (推荐) HtmlDocument document = wb.Document; document.ExecCommand("ClearAuthenticationCache", false, null); //方法3:删除本机cookie 此方法会弹出ie清除cookie的弹出框 //Temporary Internet Files (Internet临时文件) //RunDll32.exe InetCpl.cpl,ClearMyTracksByProcess 8 //Cookies //RunDll32.exe InetCpl.cpl,ClearMyTracksByProcess 2 //History (历史记录) //RunDll32.exe InetCpl.cpl,ClearMyTracksByProcess 1 //Form. Data (表单数据) //RunDll32.exe InetCpl.cpl,ClearMyTracksByProcess 16 //Passwords (密码) //RunDll32.exe InetCpl.cpl,ClearMyTracksByProcess 32 //Delete All (全部删除) //ShellExecute(IntPtr.Zero, "open", "rundll32.exe", " InetCpl.cpl,ClearMyTracksByProcess 2", "", ShowCommands.SW_HIDE); ShellExecute(IntPtr.Zero, "open", "rundll32.exe", " InetCpl.cpl,ClearMyTracksByProcess 255", "", ShowCommands.SW_HIDE); //方法4:使用webbrowser自带的清coookie的方法 (不推荐,清不掉session,实测无效) wb.Document.Cookie.Remove(0, (wb.Document.Cookie.Count() - 1)); //方法5:使用js清除cookie (不推荐,清不掉session) wb.Navigate("javascript:void((function(){var a,b,c,e,f;f=0;a=document.cookie.split('; ');for(e=0;e<a.length&&a[e];e++){f++;for(b='.'+location.host;b;b=b.replace(/^(?:%5C.|[^%5C.]+)/,'')){for(c=location.pathname;c;c=c.replace(/.$/,'')){document.cookie=(a[e]+'; domain='+b+'; path='+c+'; expires='+new Date((new Date()).getTime()⑴e11).toGMTString());}}}})())"); //var a,b,c,e,f; //f=0; //a=document.cookie.split('; '); //b='.'+'baidu.com'; ////b='.'+'www.baidu.com'; //for(e=0;e<a.length;e++){ // //b='.'+location.host; // b=b.replace(/^(?:%5C.|[^%5C.]+)/,''); // c=location.pathname; // c=c.replace(/.$/,''); // ck = a[e]+'; domain='+b+'; path='+c+'; expires='+new Date((new Date()).getTime()⑴e11).toGMTString(); // console.log(ck); // document.cookie=ck; //} //方法6:使用InternetSetCookie给cookie赋null值 (不推荐) //也能够给此Cookie赋空值:InternetSetCookie //InternetSetCookie("http://.qq.com/", NULL, "uin=; PATH=/; DOMAIN=qq.com");
注:删除Cookie在测试中1直效果不是很好,最少没法在cnzz统计中刷新到独立访客,当制止了IE中的Cookie时,IP数与独立访客数就能够同时增长啦。
其实8爪鱼招标网每天正面临着流量的问题,同时百度权重也希望能够在1定时间内得能够提升,所以想做1个好的招标网站,而且还是个免费招标网站是1件非常不容易的事情。