C#-HttpWebRequest获取数据下一页问题 [英] C# - HttpWebRequest Get Data Next Page(s) Issue

查看:85
本文介绍了C#-HttpWebRequest获取数据下一页问题的处理方法,对大家解决问题具有一定的参考价值,需要的朋友们下面随着小编来一起学习吧!

问题描述

我尝试使用httpwebrequest从网站中提取数据.我无法从第一个页面"中提取数据,但是当我尝试将数据获取到下一页或上一页时,出现错误.

Im try to extract data from a website with httpwebrequest. Im able to extract data from the first "Page" but when i try to get data to the next or previous page i get a error.

下一页操作-单击数字页

要查看Post参数,我使用Fiddler来比较我的代码和网站中的Post Request标头.

To see the Post parameters i use Fiddler to compare the Post Request Header from my Code and the website.

发布请求-标头2ºPage

我的实际C#代码如下:

My actual C# code its this:

string URI = "https://www.citius.mj.pt/Portal/consultas/ConsultaVendaAnuncios.aspx";                

CookieContainer cc = new CookieContainer();
HttpWebRequest h = (HttpWebRequest)WebRequest.Create(URI);
h.CookieContainer = cc;
HttpWebResponse hr = (HttpWebResponse)h.GetResponse();
using (var s = hr.GetResponseStream())
{
    using (var r = new StreamReader(s, Encoding.UTF8))
    {
        string html = r.ReadToEnd();                        

        Match mVS = Regex.Match(html, "id=\"__VIEWSTATE\" value=\"(.*?)\"", RegexOptions.Singleline);                        
        Match mEV = Regex.Match(html, "id=\"__EVENTVALIDATION\" value=\"(.*?)\"", RegexOptions.Singleline);

        ///////////////////////////////////////SEARCH///////////////////////////////////////////////////

        Dictionary<string, string> param = new Dictionary<string, string>();
        param.Add("ctl00$ContentPlaceHolder1$ScriptManager1", "ctl00$ContentPlaceHolder1$ScriptManager1|ctl00$ContentPlaceHolder1$btnSearch");                        
        param.Add("__EVENTTARGET", "");
        param.Add("__EVENTARGUMENT", "");
        param.Add("__LASTFOCUS", "");
        param.Add("__VIEWSTATE", mVS.Groups[1].Value);                        
        param.Add("__EVENTVALIDATION", mEV.Groups[1].Value);
        param.Add("ctl00$ContentPlaceHolder1$rbtlTribunais", "False");
        param.Add("ctl00$ContentPlaceHolder1$ddlTribunais", "- Todos os Tribunais -");
        param.Add("ctl00$ContentPlaceHolder1$rblDias", "todos");
        param.Add("__ASYNCPOST", "true");
        param.Add("ctl00$ContentPlaceHolder1$btnSearch", "Pesquisar");

        string post = "";
        foreach (var i in param)
        {
            post += WebUtility.UrlEncode(i.Key) + "=" + WebUtility.UrlEncode(i.Value) + "&";
        }

        var data = Encoding.UTF8.GetBytes(post);                        

        HttpWebRequest request = (HttpWebRequest)WebRequest.Create(URI);
        request.CookieContainer = cc;
        request.Referer = URI;
        request.Method = "POST";                        
        request.Headers.Add("Cache-Control", "no-cache");
        request.Accept = "*/*";                                                
        request.Headers.Add("Accept-Language", "pt-PT,pt;q=0.8,en-US;q=0.6,en;q=0.4,es;q=0.2");
        request.UserAgent = "Mozilla/5.0 (Windows NT 6.3) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/48.0.2564.116 Safari/537.36";
        request.ContentLength = data.Length;
        request.ContentType = "application/x-www-form-urlencoded; charset=UTF-8";
        request.Headers.Add("Origin", "https://www.citius.mj.pt");
        request.Headers.Add("X-Requested-With", "XMLHttpRequest");
        request.Headers.Add("X-MicrosoftAjax: Delta=true");

        using (var stream = request.GetRequestStream())
        {
            stream.Write(data, 0, data.Length);
        }

        HttpWebResponse response = (HttpWebResponse)request.GetResponse();                        

        var responseString = new StreamReader(response.GetResponseStream()).ReadToEnd();                        

        int x = 1;

        ////////////////////////////////////////////NEXT PAGE//////////////////////////////////////////

        param.Clear();

        param.Add("ctl00$ContentPlaceHolder1$ScriptManager1", "ctl00$ContentPlaceHolder1$upResultados|ctl00$ContentPlaceHolder1$Pager1$lnkNext");
        param.Add("ctl00$ContentPlaceHolder1$rbtlTribunais", "False");
        param.Add("ctl00$ContentPlaceHolder1$ddlTribunais", "- Todos os Tribunais -");
        param.Add("ctl00$ContentPlaceHolder1$rblDias", "todos");
        param.Add("__EVENTTARGET", "ctl00$ContentPlaceHolder1$Pager1$lnkNext");
        param.Add("__EVENTARGUMENT", "");
        param.Add("__LASTFOCUS", "");
        param.Add("__VIEWSTATE", mVS.Groups[1].Value);
        param.Add("__EVENTVALIDATION", mEV.Groups[1].Value);
        param.Add("__ASYNCPOST", "true");

        post = "";
        foreach (var i in param)
        {
            post += WebUtility.UrlEncode(i.Key) + "=" + WebUtility.UrlEncode(i.Value) + "&";
        }

        data = Encoding.UTF8.GetBytes(post);

        request = (HttpWebRequest)WebRequest.Create(URI);
        request.CookieContainer = cc;
        request.Referer = URI;
        request.Method = "POST";
        request.Headers.Add("Cache-Control", "no-cache");
        request.Accept = "*/*";
        request.Headers.Add("Accept-Language", "pt-PT,pt;q=0.8,en-US;q=0.6,en;q=0.4,es;q=0.2");
        request.UserAgent = "Mozilla/5.0 (Windows NT 6.3) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/48.0.2564.116 Safari/537.36";
        request.ContentLength = data.Length;
        request.ContentType = "application/x-www-form-urlencoded; charset=UTF-8";
        request.Headers.Add("Origin", "https://www.citius.mj.pt");
        request.Headers.Add("X-Requested-With", "XMLHttpRequest");
        request.Headers.Add("X-MicrosoftAjax: Delta=true");

        using (var stream = request.GetRequestStream())
        {
            stream.Write(data, 0, data.Length);
        }

        response = (HttpWebResponse)request.GetResponse();

        responseString = new StreamReader(response.GetResponseStream()).ReadToEnd();

        int y = 1;

    }
}

当我尝试获取下一页数据时得到的结果如下: 提琴手的结果

The result i get when i trying to get nextpage data its: Result from fiddler

比较我的代码和网站调用之间的标头,唯一的区别是我看到的是"_EVENTEVALUATION".

Comparing the header between calls from my code and the website the only difference i see its the "_EVENTEVALUATION".

我在做什么错了?

推荐答案

如我所建议的,您应该拆分响应字符串.

As I suggest, you should split response string.

string URI = "https://www.citius.mj.pt/Portal/consultas/ConsultaVendaAnuncios.aspx";

CookieContainer cc = new CookieContainer();
HttpWebRequest h = (HttpWebRequest)WebRequest.Create(URI);
h.CookieContainer = cc;
HttpWebResponse hr = (HttpWebResponse)h.GetResponse();
using (var s = hr.GetResponseStream())
{
    using (var r = new StreamReader(s, Encoding.UTF8))
    {
        string html = r.ReadToEnd();

        Match mVS = Regex.Match(html, "id=\"__VIEWSTATE\" value=\"(.*?)\"", RegexOptions.Singleline);
        Match mEV = Regex.Match(html, "id=\"__EVENTVALIDATION\" value=\"(.*?)\"", RegexOptions.Singleline);

        ///////////////////////////////////////SEARCH///////////////////////////////////////////////////

        Dictionary<string, string> param = new Dictionary<string, string>();
        param.Add("ctl00$ContentPlaceHolder1$ScriptManager1", "ctl00$ContentPlaceHolder1$ScriptManager1|ctl00$ContentPlaceHolder1$btnSearch");
        param.Add("__EVENTTARGET", "");
        param.Add("__EVENTARGUMENT", "");
        param.Add("__LASTFOCUS", "");
        param.Add("__VIEWSTATE", mVS.Groups[1].Value);
        param.Add("__EVENTVALIDATION", mEV.Groups[1].Value);
        param.Add("ctl00$ContentPlaceHolder1$rbtlTribunais", "False");
        param.Add("ctl00$ContentPlaceHolder1$ddlTribunais", "- Todos os Tribunais -");
        param.Add("ctl00$ContentPlaceHolder1$rblDias", "todos");
        param.Add("__ASYNCPOST", "true");
        param.Add("ctl00$ContentPlaceHolder1$btnSearch", "Pesquisar");

        string post = "";
        foreach (var i in param)
        {
            post += WebUtility.UrlEncode(i.Key) + "=" + WebUtility.UrlEncode(i.Value) + "&";
        }

        var data = Encoding.UTF8.GetBytes(post);

        HttpWebRequest request = (HttpWebRequest)WebRequest.Create(URI);
        request.CookieContainer = cc;
        request.Referer = URI;
        request.Method = "POST";
        request.Headers.Add("Cache-Control", "no-cache");
        request.Accept = "*/*";
        request.Headers.Add("Accept-Language", "pt-PT,pt;q=0.8,en-US;q=0.6,en;q=0.4,es;q=0.2");
        request.UserAgent = "Mozilla/5.0 (Windows NT 6.3) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/48.0.2564.116 Safari/537.36";
        request.ContentLength = data.Length;
        request.ContentType = "application/x-www-form-urlencoded; charset=UTF-8";
        request.Headers.Add("Origin", "https://www.citius.mj.pt");
        request.Headers.Add("X-Requested-With", "XMLHttpRequest");
        request.Headers.Add("X-MicrosoftAjax: Delta=true");

        using (var stream = request.GetRequestStream())
        {
            stream.Write(data, 0, data.Length);
        }

        HttpWebResponse response = (HttpWebResponse)request.GetResponse();

        var responseString = new StreamReader(response.GetResponseStream()).ReadToEnd();

        File.WriteAllText("D:\\tmp1.txt", responseString);

        ////////////////////////////////////////////NEXT PAGE//////////////////////////////////////////

        param.Clear();

        string[] split = responseString.Split('|');
        for (int i = 0; i < split.Length; i++)
        {
            if (split[i] == "__VIEWSTATE") param.Add("__VIEWSTATE", split[i + 1]);
            if (split[i] == "__EVENTVALIDATION") param.Add("__EVENTVALIDATION", split[i + 1]);
        }
        param.Add("ctl00$ContentPlaceHolder1$ScriptManager1", "ctl00$ContentPlaceHolder1$upResultados|ctl00$ContentPlaceHolder1$Pager1$lnkNext");
        param.Add("ctl00$ContentPlaceHolder1$rbtlTribunais", "False");
        param.Add("ctl00$ContentPlaceHolder1$ddlTribunais", "- Todos os Tribunais -");
        param.Add("ctl00$ContentPlaceHolder1$rblDias", "todos");
        param.Add("__EVENTTARGET", "ctl00$ContentPlaceHolder1$Pager1$lnkNext");
        param.Add("__EVENTARGUMENT", "");
        param.Add("__LASTFOCUS", "");
        //param.Add("__VIEWSTATE", mVS.Groups[1].Value);
        //param.Add("__EVENTVALIDATION", mEV.Groups[1].Value);
        param.Add("__ASYNCPOST", "true");

        post = "";
        foreach (var i in param)
        {
            post += WebUtility.UrlEncode(i.Key) + "=" + WebUtility.UrlEncode(i.Value) + "&";
        }

        data = Encoding.UTF8.GetBytes(post);

        request = (HttpWebRequest)WebRequest.Create(URI);
        request.CookieContainer = cc;
        request.Referer = URI;
        request.Method = "POST";
        request.Headers.Add("Cache-Control", "no-cache");
        request.Accept = "*/*";
        request.Headers.Add("Accept-Language", "pt-PT,pt;q=0.8,en-US;q=0.6,en;q=0.4,es;q=0.2");
        request.UserAgent = "Mozilla/5.0 (Windows NT 6.3) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/48.0.2564.116 Safari/537.36";
        request.ContentLength = data.Length;
        request.ContentType = "application/x-www-form-urlencoded; charset=UTF-8";
        request.Headers.Add("Origin", "https://www.citius.mj.pt");
        request.Headers.Add("X-Requested-With", "XMLHttpRequest");
        request.Headers.Add("X-MicrosoftAjax: Delta=true");

        using (var stream = request.GetRequestStream())
        {
            stream.Write(data, 0, data.Length);
        }

        response = (HttpWebResponse)request.GetResponse();

        responseString = new StreamReader(response.GetResponseStream()).ReadToEnd();

        File.WriteAllText("D:\\tmp2.txt", responseString);
        int y = 1;

    }
}

这篇关于C#-HttpWebRequest获取数据下一页问题的文章就介绍到这了,希望我们推荐的答案对大家有所帮助,也希望大家多多支持IT屋!

查看全文
登录 关闭
扫码关注1秒登录
发送“验证码”获取 | 15天全站免登陆