【发布时间】:2016-02-29 01:04:27
【问题描述】:
我尝试使用 httpwebrequest 从网站中提取数据。我能够从第一个“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。
Next Page Action - Click on the number page
要查看 Post 参数,我使用 Fiddler 来比较我的代码和网站中的 Post Request Header。
我的实际 C# 代码是这样的:
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: Result from fiddler
比较来自我的代码和网站的调用之间的标头,我看到它的唯一区别是“_EVENTEVALUATION”。
我做错了什么?
【问题讨论】:
-
这两个值是由 javascript 计算出来的。这是给你的建议:响应字符串是由
|字符连接的字符串数组。您必须找到它(不要使用拆分功能)。有些元素是字符串,有些是数字,其余的是整数,描述字符串的长度(可能包含|)跟随该整数。然后您使用 chrome(或其他工具)调试页面以查找页面如何计算两个这些值。 -
@Sakura 我更新了代码。我尝试使用 $InkNext(单击数字)而不是使用 btnNextPage。我认为这是一种简单的方法,而且我的参数更少。不幸的是,我没有得到我需要的结果。任何想法为什么这不起作用?我知道该网站制作了 __doPostBack('ctl00$ContentPlaceHolder1$Pager1$lnkNext','')
标签: c# post httpwebrequest