C#HttpHelper实现了C#HttpWebRequest抓取时无视编码，无视证书，无视Cookie，并且实现的代理的功能，使用它您可以进行Get和Post请求，可以很方便 的设置Cookie，证书，代理，编码问题您不用管，因为类会自动为您识别网页的编码。 HttpHelper类，用来实现Http访问，Post或者Get方式的，直接访问，带Cookie的，带证书的等方式，可以设置代理。
using System;using System.Collections.Generic;using System.Text;using System.Net;using System.IO;using System.Text.RegularExpressions;using System.IO.Compression;using System.Security.Cryptography.X509Certificates;using System.Net.Security;namespace DotNet4.Utilities{ /// <summary> /// Http连接操作帮助类 /// </summary> public class HttpHelper { #region 预定义方法或者变更 //默认的编码 private Encoding encoding = Encoding.Default; //Post数据编码 private Encoding postencoding = Encoding.Default; //HttpWebRequest对象用来发起请求 private HttpWebRequest request = null; //获取影响流的数据对象 private HttpWebResponse response = null; /// <summary> /// 根据相传入的数据，得到相应页面数据 /// </summary> /// <param name="item">参数类对象</param> /// <returns>返回HttpResult类型</returns> public HttpResult GetHtml(HttpItem item) { //返回参数 HttpResult result = new HttpResult(); try { //准备参数 SetRequest(item); } catch (Exception ex) { return new HttpResult() { Cookie = string.Empty, Header = null, Html = ex.Message, StatusDescription = "配置参数时出错：" ex.Message }; } try { #region 得到请求的response using (response = (HttpWebResponse)request.GetResponse()) { result.StatusCode = response.StatusCode; result.StatusDescription = response.StatusDescription; result.Header = response.Headers; if (response.Cookies != null) result.CookieCollection = response.Cookies; if (response.Headers["set-cookie"] != null) result.Cookie = response.Headers["set-cookie"]; byte[] ResponseByte = null; using (MemoryStream _stream = new MemoryStream()) { //GZIIP处理 if (response.ContentEncoding != null && response.ContentEncoding.Equals("gzip", StringComparison.InvariantCultureIgnoreCase)) { //开始读取流并设置编码方式 new GZipStream(response.GetResponseStream(), CompressionMode.Decompress).CopyTo(_stream, 10240); } else { //开始读取流并设置编码方式 response.GetResponseStream().CopyTo(_stream, 10240); } //获取Byte ResponseByte = _stream.ToArray(); } if (ResponseByte != null & ResponseByte.Length > 0) { //是否返回Byte类型数据 if (item.ResultType == ResultType.Byte) result.ResultByte = ResponseByte; //从这里开始我们要无视编码了 if (encoding == null) { Match meta = Regex.Match(Encoding.Default.GetString(ResponseByte), "<meta([^<]*)charset=([^<]*)[\"']", RegexOptions.IgnoreCase); string c = (meta.Groups.Count > 1) ? meta.Groups[2].Value.ToLower().Trim() : string.Empty; if (c.Length > 2) { try { if (c.IndexOf(" ") > 0) c = c.Substring(0, c.IndexOf(" ")); encoding = Encoding.GetEncoding(c.Replace("\"", "").Replace("'", "").Replace(";", "").Replace("iso-8859-1", "gbk").Trim()); } catch { if (string.IsNullOrEmpty(response.CharacterSet)) encoding = Encoding.UTF8; else encoding = Encoding.GetEncoding(response.CharacterSet); } } else { if (string.IsNullOrEmpty(response.CharacterSet)) encoding = Encoding.UTF8; else encoding = Encoding.GetEncoding(response.CharacterSet); } } //得到返回的HTML result.Html = encoding.GetString(ResponseByte); } else { //得到返回的HTML result.Html = "本次请求并未返回任何数据"; } } #endregion } catch (WebException ex) { //这里是在发生异常时返回的错误信息 response = (HttpWebResponse)ex.Response; result.Html = ex.Message; if (response != null) { result.StatusCode = response.StatusCode; result.StatusDescription = response.StatusDescription; } } catch (Exception ex) { result.Html = ex.Message; } if (item.IsToLower) result.Html = result.Html.ToLower(); return result; } /// <summary> /// 为请求准备参数 /// </summary> ///<param name="item">参数列表</param> private void SetRequest(HttpItem item) { // 验证证书 SetCer(item); //设置Header参数 if (item.Header != null && item.Header.Count > 0) foreach (string key in item.Header.AllKeys) { request.Headers.Add(key, item.Header[key]); } // 设置代理 SetProxy(item); if (item.ProtocolVersion != null) request.ProtocolVersion = item.ProtocolVersion; request.ServicePoint.Expect100Continue = item.Expect100Continue; //请求方式Get或者Post request.Method = item.Method; request.Timeout = item.Timeout; request.KeepAlive = item.KeepAlive; request.ReadWriteTimeout = item.ReadWriteTimeout; if (!string.IsNullOrWhiteSpace(item.Host)) { request.Host = item.Host; } //Accept request.Accept = item.Accept; //ContentType返回类型 request.ContentType = item.ContentType; //UserAgent客户端的访问类型，包括浏览器版本和操作系统信息 request.UserAgent = item.UserAgent; // 编码 encoding = item.Encoding; //设置安全凭证 request.Credentials = item.ICredentials; //设置Cookie SetCookie(item); //来源地址 request.Referer = item.Referer; //是否执行跳转功能 request.AllowAutoRedirect = item.Allowautoredirect; //设置Post数据 SetPostData(item); //设置最大连接 if (item.Connectionlimit > 0) request.ServicePoint.ConnectionLimit = item.Connectionlimit; } /// <summary> /// 设置证书 /// </summary> /// <param name="item"></param> private void SetCer(HttpItem item) { if (!string.IsNullOrWhiteSpace(item.CerPath)) { //这一句一定要写在创建连接的前面。使用回调的方法进行证书验证。 ServicePointManager.ServerCertificateValidationCallback = new System.Net.Security.RemoteCertificateValidationCallback(CheckValidationResult); //初始化对像，并设置请求的URL地址 request = (HttpWebRequest)WebRequest.Create(item.URL); SetCerList(item); //将证书添加到请求里 request.ClientCertificates.Add(new X509Certificate(item.CerPath)); } else { //初始化对像，并设置请求的URL地址 request = (HttpWebRequest)WebRequest.Create(item.URL); SetCerList(item); } } /// <summary> /// 设置多个证书 /// </summary> /// <param name="item"></param> private void SetCerList(HttpItem item) { if (item.ClentCertificates != null && item.ClentCertificates.Count > 0) { foreach (X509Certificate c in item.ClentCertificates) { request.ClientCertificates.Add(c); } } } /// <summary> /// 设置Cookie /// </summary> /// <param name="item">Http参数</param> private void SetCookie(HttpItem item) { if (!string.IsNullOrEmpty(item.Cookie)) request.Headers[HttpRequestHeader.Cookie] = item.Cookie; //设置CookieCollection if (item.ResultCookieType == ResultCookieType.CookieCollection) { request.CookieContainer = new CookieContainer(); if (item.CookieCollection != null && item.CookieCollection.Count > 0) request.CookieContainer.Add(item.CookieCollection); } } /// <summary> /// 设置Post数据 /// </summary> /// <param name="item">Http参数</param> private void SetPostData(HttpItem item) { //验证在得到结果时是否有传入数据 if (request.Method.Trim().ToLower().Contains("post")) { if (item.PostEncoding != null) { postencoding = item.PostEncoding; } byte[] buffer = null; //写入Byte类型 if (item.PostDataType == PostDataType.Byte && item.PostdataByte != null && item.PostdataByte.Length > 0) { //验证在得到结果时是否有传入数据 buffer = item.PostdataByte; }//写入文件 else if (item.PostDataType == PostDataType.FilePath && !string.IsNullOrWhiteSpace(item.Postdata)) { StreamReader r = new StreamReader(item.Postdata, postencoding); buffer = postencoding.GetBytes(r.ReadToEnd()); r.Close(); } //写入字符串 else if (!string.IsNullOrWhiteSpace(item.Postdata)) { buffer = postencoding.GetBytes(item.Postdata); } if (buffer != null) { request.ContentLength = buffer.Length; request.GetRequestStream().Write(buffer, 0, buffer.Length); } } } /// <summary> /// 设置代理 /// </summary> /// <param name="item">参数对象</param> private void SetProxy(HttpItem item) { bool isIeProxy = false; if (!string.IsNullOrWhiteSpace(item.ProxyIp)) { isIeProxy = item.ProxyIp.ToLower().Contains("ieproxy"); } if (!string.IsNullOrWhiteSpace(item.ProxyIp) && !isIeProxy) { //设置代理服务器 if (item.ProxyIp.Contains(":")) { string[] plist = item.ProxyIp.Split(':'); WebProxy myProxy = new WebProxy(plist[0].Trim(), Convert.ToInt32(plist[1].Trim())); //建议连接 myProxy.Credentials = new NetworkCredential(item.ProxyUserName, item.ProxyPwd); //给当前请求对象 request.Proxy = myProxy; } else { WebProxy myProxy = new WebProxy(item.ProxyIp, false); //建议连接 myProxy.Credentials = new NetworkCredential(item.ProxyUserName, item.ProxyPwd); //给当前请求对象 request.Proxy = myProxy; } } else if (isIeProxy) { //设置为IE代理 } else { request.Proxy = item.WebProxy; } } /// <summary> /// 回调验证证书问题 /// </summary> /// <param name="sender">流对象</param> /// <param name="certificate">证书</param> /// <param name="chain">X509Chain</param> /// <param name="errors">SslPolicyErrors</param> /// <returns>bool</returns> public bool CheckValidationResult(object sender, X509Certificate certificate, X509Chain chain, SslPolicyErrors errors) { return true; } #endregion } /// <summary> /// Http请求参考类 /// </summary> public class HttpItem { /// <summary> /// 请求URL必须填写 /// </summary> public string URL { get; set; } string _Method = "GET"; /// <summary> /// 请求方式默认为GET方式,当为POST方式时必须设置Postdata的值 /// </summary> public string Method { get { return _Method; } set { _Method = value; } } int _Timeout = 100000; /// <summary> /// 默认请求超时时间 /// </summary> public int Timeout { get { return _Timeout; } set { _Timeout = value; } } int _ReadWriteTimeout = 30000; /// <summary> /// 默认写入Post数据超时间 /// </summary> public int ReadWriteTimeout { get { return _ReadWriteTimeout; } set { _ReadWriteTimeout = value; } } /// <summary> /// 设置Host的标头信息 /// </summary> public string Host { get; set; } Boolean _KeepAlive = true; /// <summary> /// 获取或设置一个值，该值指示是否与 Internet 资源建立持久性连接默认为true。 /// </summary> public Boolean KeepAlive { get { return _KeepAlive; } set { _KeepAlive = value; } } string _Accept = "text/html, application/xhtml xml, */*"; /// <summary> /// 请求标头值 默认为text/html, application/xhtml xml, */* /// </summary> public string Accept { get { return _Accept; } set { _Accept = value; } } string _ContentType = "text/html"; /// <summary> /// 请求返回类型默认 text/html /// </summary> public string ContentType { get { return _ContentType; } set { _ContentType = value; } } string _UserAgent = "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Trident/5.0)"; /// <summary> /// 客户端访问信息默认Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Trident/5.0) /// </summary> public string UserAgent { get { return _UserAgent; } set { _UserAgent = value; } } /// <summary> /// 返回数据编码默认为NUll,可以自动识别,一般为utf-8,gbk,gb2312 /// </summary> public Encoding Encoding { get; set; } private PostDataType _PostDataType = PostDataType.String; /// <summary> /// Post的数据类型 /// </summary> public PostDataType PostDataType { get { return _PostDataType; } set { _PostDataType = value; } } /// <summary> /// Post请求时要发送的字符串Post数据 /// </summary> public string Postdata { get; set; } /// <summary> /// Post请求时要发送的Byte类型的Post数据 /// </summary> public byte[] PostdataByte { get; set; } /// <summary> /// Cookie对象集合 /// </summary> public CookieCollection CookieCollection { get; set; } /// <summary> /// 请求时的Cookie /// </summary> public string Cookie { get; set; } /// <summary> /// 来源地址，上次访问地址 /// </summary> public string Referer { get; set; } /// <summary> /// 证书绝对路径 /// </summary> public string CerPath { get; set; } /// <summary> /// 设置代理对象，不想使用IE默认配置就设置为Null，而且不要设置ProxyIp /// </summary> public WebProxy WebProxy { get; set; } private Boolean isToLower = false; /// <summary> /// 是否设置为全文小写，默认为不转化 /// </summary> public Boolean IsToLower { get { return isToLower; } set { isToLower = value; } } private Boolean allowautoredirect = false; /// <summary> /// 支持跳转页面，查询结果将是跳转后的页面，默认是不跳转 /// </summary> public Boolean Allowautoredirect { get { return allowautoredirect; } set { allowautoredirect = value; } } private int connectionlimit = 1024; /// <summary> /// 最大连接数 /// </summary> public int Connectionlimit { get { return connectionlimit; } set { connectionlimit = value; } } /// <summary> /// 代理Proxy 服务器用户名 /// </summary> public string ProxyUserName { get; set; } /// <summary> /// 代理 服务器密码 /// </summary> public string ProxyPwd { get; set; } /// <summary> /// 代理 服务IP,如果要使用IE代理就设置为ieproxy /// </summary> public string ProxyIp { get; set; } private ResultType resulttype = ResultType.String; /// <summary> /// 设置返回类型String和Byte /// </summary> public ResultType ResultType { get { return resulttype; } set { resulttype = value; } } private WebHeaderCollection header = new WebHeaderCollection(); /// <summary> /// header对象 /// </summary> public WebHeaderCollection Header { get { return header; } set { header = value; } } //....省略苦干部分代码}
评论