很久没有写新的东西了,今天在工作中遇到的一个问题,感觉很有用,有种想记下来的冲动。
这篇文章是有关模拟登录网站方面的。
实现步骤;
- 启用一个web会话
- 发送模拟数据请求(POST或者GET)
- 获取会话的CooKie 并根据该CooKie继续访问登录后的页面,获取后续访问的页面数据。
我们以登录人人网为例,首先需要分析人人网登录时POST的数据格式,这个可以通过IE9中只带的F12快捷键,调出开发人员工具。如下图:
通过开始捕获得到POST的地址和POST的数据
POST数据:
[email protected]&password=111&icode=&origURL=http%3A%2F%2Fwww.renren.com%2Fhome&domain=renren.com&key_id=1&_rtk=90484476
POST地址:
http://www.renren.com/PLogin.do
下面就是代码示例来得到登录后页面(http://guide.renren.com/guide)的数据
HTMLHelper类
using System; using System.Collections.Generic; using System.Linq; using System.Text; using System.Net; using System.IO; using System.Threading;
namespace Test { public class HTMLHelper { /// <summary> /// 获取CooKie /// </summary> /// <param name="loginUrl"></param> /// <param name="postdata"></param> /// <param name="header"></param> /// <returns></returns> public static CookieContainer GetCooKie(string loginUrl, string postdata, HttpHeader header) { HttpWebRequest request = null; HttpWebResponse response = null; try { CookieContainer cc = new CookieContainer(); request = (HttpWebRequest)WebRequest.Create(loginUrl); request.Method = header.method; request.ContentType = header.contentType; byte[] postdatabyte = Encoding.UTF8.GetBytes(postdata); request.ContentLength = postdatabyte.Length; request.AllowAutoRedirect = false; request.CookieContainer = cc; request.KeepAlive = true;
//提交请求 Stream stream; stream = request.GetRequestStream(); stream.Write(postdatabyte, 0, postdatabyte.Length); stream.Close();
//接收响应 response = (HttpWebResponse)request.GetResponse(); response.Cookies = request.CookieContainer.GetCookies(request.RequestUri);
CookieCollection cook = response.Cookies; //Cookie字符串格式 string strcrook = request.CookieContainer.GetCookieHeader(request.RequestUri);
return cc; } catch (Exception ex) {
throw ex; } }
/// <summary> /// 获取html /// </summary> /// <param name="getUrl"></param> /// <param name="cookieContainer"></param> /// <param name="header"></param> /// <returns></returns> public static string GetHtml(string getUrl, CookieContainer cookieContainer,HttpHeader header) { Thread.Sleep(1000); HttpWebRequest httpWebRequest = null; HttpWebResponse httpWebResponse = null; try { httpWebRequest = (HttpWebRequest)HttpWebRequest.Create(getUrl); httpWebRequest.CookieContainer = cookieContainer; httpWebRequest.ContentType = header.contentType; httpWebRequest.ServicePoint.ConnectionLimit = header.maxTry; httpWebRequest.Referer = getUrl; httpWebRequest.Accept = header.accept; httpWebRequest.UserAgent = header.userAgent; httpWebRequest.Method = "GET"; httpWebResponse = (HttpWebResponse)httpWebRequest.GetResponse(); Stream responseStream = httpWebResponse.GetResponseStream(); StreamReader streamReader = new StreamReader(responseStream, Encoding.UTF8); string html = streamReader.ReadToEnd(); streamReader.Close(); responseStream.Close(); httpWebRequest.Abort(); httpWebResponse.Close(); return html; } catch (Exception e) { if (httpWebRequest != null) httpWebRequest.Abort(); if (httpWebResponse != null) httpWebResponse.Close(); return string.Empty; } } }
public class HttpHeader { public string contentType { get; set; }
public string accept { get; set; }
public string userAgent { get; set; }
public string method{get;set;}
public int maxTry { get; set; } } }
测试用例:
HttpHeader header = new HttpHeader(); header.accept = "image/gif, image/x-xbitmap, image/jpeg, image/pjpeg, application/x-shockwave-flash, application/x-silverlight, application/vnd.ms-excel, application/vnd.ms-powerpoint, application/msword, application/x-ms-application, application/x-ms-xbap, application/vnd.ms-xpsdocument, application/xaml+xml, application/x-silverlight-2-b1, */*"; header.contentType = "application/x-www-form-urlencoded"; header.method = "POST"; header.userAgent = "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; .NET CLR 2.0.50727; .NET CLR 3.0.04506.648; .NET CLR 3.5.21022)"; header.maxTry = 300;
string html = HTMLHelper.GetHtml("http://guide.renren.com/guide", HTMLHelper.GetCooKie("http://www.renren.com/PLogin.do", "[email protected]&password=111&icode=&origURL=http%3A%2F%2Fwww.renren.com%2Fhome&domain=renren.com&key_id=1&_rtk=90484476", header), header);
Console.WriteLine(html);
Console.ReadLine();
|
请发表评论