winform怎么实现登陆一个网站并抓取这个网站的数据

Question

特别是怎么实现用户登陆网站后抓取登陆的页面数据，想知道怎么实现程序登陆。做过的朋友可以指点下给，谢谢！

Answer 1

你可以用HttpWebRequest
他可以模拟登陆
下面我自己的网站里的例子
用来实现模拟提交获取违章查询的...
希望对你有用
网址是  http://www.yocs.cn/Weizhang.aspxprivate string a(string filename)
        {
            HttpWebRequest request = WebRequest.Create("http://www.csjxj.com/validateimg.php") as HttpWebRequest;
            request.Referer = "http://www.csjxj.com/wzcx.php";
            request.UserAgent = "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.0; SLCC1)";
            request.Method = WebRequestMethods.File.DownloadFile;
            request.ContentType = "application/x-www-form-urlencoded";
            request.Accept = "image/gif, image/x-xbitmap, image/jpeg, image/pjpeg, application/vnd.ms-excel, application/vnd.ms-powerpoint, application/msword, application/x-shockwave-flash, */*";
            request.CookieContainer = new CookieContainer();
            HttpWebResponse response = request.GetResponse() as HttpWebResponse;
            Stream stream = response.GetResponseStream();
           
            FileStream FS = new FileStream(Server.MapPath(filename), FileMode.Create, FileAccess.ReadWrite);
            BinaryWriter write = new BinaryWriter(FS, Encoding.Default);
            BinaryReader reader = new BinaryReader(stream, Encoding.Default);
            byte[] bs = new byte[256];
            while (reader.Read(bs, 0, 256) > 0)
            {
                write.Write(bs);
            }
            reader.Close();
            write.Close();
            FS.Close();
            FS.Dispose();
            stream.Close();
            response.Close();
            return request.CookieContainer.GetCookieHeader(new Uri("http://www.csjxj.com"));
        }[AcceptVerbs(HttpVerbs.Get)]
        public ActionResult Weizhang()
        {
            string filename = "/Weizhang/" + Guid.NewGuid().ToString().Replace("-", String.Empty) + ".bmp";
            ViewData["iCodePath"] = filename;
            //CookieContainer _CookieContainer = request.CookieContainer.;
            TempData["YOCS_COOKIE"] = a(filename);
            ViewData["Content"] = "";
            return View();
        }        [AcceptVerbs(HttpVerbs.Post)]
        public ActionResult Weizhang(FormCollection form)
        {
            HttpWebRequest request = WebRequest.Create("http://www.csjxj.com/wzcx.php") as HttpWebRequest;            string postString = String.Format(@"cp={0}&type={1}&cj={2}&s_validate={3}&Submit2={4}",
                                            HttpUtility.UrlEncode(form["fChepai"], Encoding.GetEncoding("GB2312")),
                                            form["fType"],
                                            form["fFadongji"],
                                            form["fCode"],
                                            HttpUtility.UrlEncode("提交", Encoding.GetEncoding("GB2312")));
            byte[] postData = Encoding.ASCII.GetBytes(postString);
            request.ContentLength = postData.Length;            request.KeepAlive = true;
            request.AllowAutoRedirect = false;
            request.CookieContainer = new CookieContainer();
            request.CookieContainer.SetCookies(new Uri("http://www.csjxj.com/wzcx.php"), TempData["YOCS_COOKIE"].ToString());
            request.Accept = "application/x-ms-application, image/jpeg, application/xaml+xml, image/gif, image/pjpeg, application/x-ms-xbap, application/x-shockwave-flash, application/x-silverlight, application/vnd.ms-excel, application/vnd.ms-powerpoint, application/msword, */*";
            request.Method = "post";
            request.Referer = "http://www.csjxj.com/wzcx.php";
            request.UserAgent = "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.2; Trident/4.0; .NET CLR 1.1.4322; .NET CLR 2.0.50727; .NET CLR 3.0.04506.648; .NET CLR 3.5.21022; .NET CLR 3.0.4506.2152; .NET CLR 3.5.30729; CIBA; .NET4.0C; .NET4.0E)";
            request.ContentType = "application/x-www-form-urlencoded";            Stream S = request.GetRequestStream();
            S.Write(postData, 0, postData.Length);
            S.Close();            HttpWebResponse response = request.GetResponse() as HttpWebResponse;
            
            Stream ST = response.GetResponseStream();
            StreamReader r = new StreamReader(ST, Encoding.GetEncoding("GB2312"));
            String content = r.ReadToEnd();
            string source = content;
            response.Close();
            content = Regex.Match(content, @"<td colspan=5>([\s\S]+?)</td>", RegexOptions.IgnoreCase).Groups[1].Value;            if (content.IsEmpty() || content.IsMatch(@"^\s*$"))
            {
                content = Regex.Match(source, @"<table width=""510"" border=1 align=""center"" style=""word-break:break-all;"" cellspacing=""1"" bordercolorlight=""#FFFFFF"" bordercolordark=""#03599C"" cellpadding=""1"" height=""20"">[\s\S]+?</table>", RegexOptions.IgnoreCase).Value;
            }
            ViewData["Content"] = content;
            string filename = "/Weizhang/" + Guid.NewGuid().ToString().Replace("-", String.Empty) + ".bmp";
            ViewData["iCodePath"] = filename;
            //CookieContainer _CookieContainer = request.CookieContainer.;
            TempData["YOCS_COOKIE"] = a(filename);            return View();
        }

Answer 2

忘记说了.....
他需要你访问后的session的
所以,这个,和你登陆也是一样的道理的.....你只要加一个networkcreditial就行了

Answer 3

他那个是用asp.net mvc做的，这个和本问题没有直接联系

Answer 4

using System.Web;/// <summary>
    /// 根据链接地址 获取 Html文本
    /// </summary>
    public static string Get_Html(string Url)
    {
        System.Net.WebClient wc = new System.Net.WebClient();
        Byte[] pageData = wc.DownloadData(Url );
        wc.Credentials = System.Net.CredentialCache.DefaultCredentials;
        return System.Text.Encoding.Default.GetString(pageData);
    }

Answer 5

http://topic.csdn.net/u/20100529/12/6ff4d5cb-995a-4723-83e4-883cb54c3f0c.html
我写的！
不过没写完！
懒的写了！
可以看怎么抓数据！

Answer 6

【zhao_zps】如果需要登陆的网站该怎么实现呢？

Answer 7

你可以传COOKIE进去
http://hi.baidu.com/panyuan1988/blog/item/b1904e955538d46154fb96f7.html