/// <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)
{
result.Cookie = string.Empty;
result.Header = null;
result.Html = ex.Message;
result.StatusDescription = "配置参数时出错：" + ex.Message;
//配置参数时出错
return result;
}
try
{
//请求数据
using (response = (HttpWebResponse)request.GetResponse())
{
GetData(item, result);
}
}
catch (WebException ex)
{
if (ex.Response != null)
{
using (response = (HttpWebResponse)ex.Response)
{
GetData(item, result);
}
}
else
{
result.Html = ex.Message;
}
}
catch (Exception ex)
{
result.Html = ex.Message;
}
if (item.IsToLower) result.Html = result.Html.ToLower();
return result;
}
protected string Test(string ip)
{
// ip = ip.Replace(":", "：");
HttpHelper http = new HttpHelper();
ServicePointManager.DefaultConnectionLimit = 1000;
HttpItem item = new HttpItem()
{
URL = "https://www.taobao.com/",//URL 必需项
Encoding = null,//编码格式（utf-8,gb2312,gbk） 可选项 默认类会自动识别
Method = "get",//URL 可选项 默认为Get
Timeout = 250000,//连接超时时间 可选项默认为100000
ReadWriteTimeout = 30000,//写入Post返回结果超时时间 可选项默认为30000
KeepAlive = false,
ProtocolVersion = HttpVersion.Version10,
IsToLower = false,//得到的HTML代码是否转成小写 可选项默认转小写
//Cookie = "",//字符串Cookie 可选项
//UserAgent = "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Trident/5.0)",//用户的浏览器类型，版本，操作系统 可选项有默认值
//Accept = "text/html, application/xhtml+xml, */*",// 可选项有默认值
ContentType = "text/html",//返回类型 可选项有默认值
Referer = "http://www.ip.cn/",//来源URL 可选项
CerPath = "taobao.cer",
ResultType = ResultType.Byte ,
//Allowautoredirect = true,//是否根据３０１跳转 可选项
Connectionlimit = 1024,//最大连接数 可选项 默认为1024
ProxyIp = ip,//代理服务器ID 端口可以直接加到后面以：分开就行了 可选项 不需要代理 时可以不设置这三个参数
// ResultType = ResultType.String,//返回返回结果类型，是Byte还是String
CookieCollection = new System.Net.CookieCollection(),//可以直接传一个Cookie集合进来
};
//item.Header.Add("测试Key1", "测试Value1");
//item.Header.Add("测试Key2", "测试Value2");
//得到HTML代码
HttpResult result = http.GetHtml(item);
//取出返回的Cookie
string cookie = result.Cookie;
//返回的Html内容
string html = result.Html;
if (result.StatusCode == System.Net.HttpStatusCode.OK)
{
}
//表示StatusCode的文字说明与描述
string statusCodeDescription = result.StatusDescription;
return html;
}
/// <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("get"))
{
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.IsNullOrEmpty(item.Postdata))
{
StreamReader r = new StreamReader(item.Postdata, postencoding);
buffer = postencoding.GetBytes(r.ReadToEnd());
r.Close();
} //写入字符串
else if (!string.IsNullOrEmpty(item.Postdata))
{
buffer = postencoding.GetBytes(item.Postdata);
}
if (buffer != null)
{
request.ContentLength = buffer.Length;
request.GetRequestStream().Write(buffer, 0, buffer.Length);
}
}
}
/// <summary>
/// 设置编码
/// </summary>
/// <param name="item">HttpItem</param>
/// <param name="result">HttpResult</param>
/// <param name="ResponseByte">byte[]</param>
private void SetEncoding(HttpItem item, HttpResult result, byte[] ResponseByte)
{
//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 = string.Empty;
if (meta != null && meta.Groups.Count > 0)
{
c = meta.Groups[1].Value.ToLower().Trim();
}
if (c.Length > 2)
{
try
{
encoding = Encoding.GetEncoding(c.Replace("\"", string.Empty).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);
}
}
}
}
/// <summary>
/// 设置代理
/// </summary>
/// <param name="objhttpItem">参数对象</param>
private void SetProxy(HttpItem objhttpItem)
{
if (string.IsNullOrEmpty(objhttpItem.ProxyUserName) && string.IsNullOrEmpty(objhttpItem.ProxyPwd) && string.IsNullOrEmpty(objhttpItem.ProxyIp))
{
//不需要设置
}
else
{
//设置代理服务器
WebProxy myProxy = new WebProxy(objhttpItem.ProxyIp, false);
//建议连接
myProxy.Credentials = new NetworkCredential(objhttpItem.ProxyUserName, objhttpItem.ProxyPwd);
//给当前请求对象
request.Proxy = myProxy;
//设置安全凭证
request.Credentials = CredentialCache.DefaultNetworkCredentials;
}
}
/// <summary>
/// 设置Cookie
/// </summary>
/// <param name="objhttpItem">Http参数</param>
private void SetCookie(HttpItem objhttpItem)
{
if (!string.IsNullOrEmpty(objhttpItem.Cookie))
{
//Cookie
request.Headers[HttpRequestHeader.Cookie] = objhttpItem.Cookie;
}
//设置Cookie
if (objhttpItem.CookieCollection != null)
{
request.CookieContainer = new CookieContainer();
request.CookieContainer.Add(objhttpItem.CookieCollection);
}
}
/// <summary>
/// 设置证书
/// </summary>
/// <param name="objhttpItem"></param>
private void SetCer(HttpItem objhttpItem)
{
if (!string.IsNullOrEmpty(objhttpItem.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(GetUrl(objhttpItem.URL));
//创建证书文件
X509Certificate objx509 = new X509Certificate(objhttpItem.CerPath);
//添加到请求里
request.ClientCertificates.Add(objx509);
}
else
{
//初始化对像，并设置请求的URL地址
request = (HttpWebRequest)WebRequest.Create(GetUrl(objhttpItem.URL));
}
}
/// <summary>
/// 根据相传入的数据，得到相应页面数据
/// </summary>
/// <param name="strPostdata">传入的数据Post方式,get方式传NUll或者空字符串都可以</param>
/// <returns>string类型的响应数据</returns>
private HttpResult GetHttpRequestData(HttpItem objhttpitem)
{
//返回参数
HttpResult result = new HttpResult();
try
{
#region 得到请求的response
using (response = (HttpWebResponse)request.GetResponse())
{
result.Header = response.Headers;
if (response.Cookies != null)
{
result.CookieCollection = response.Cookies;
}
if (response.Headers["set-cookie"] != null)
{
result.Cookie = response.Headers["set-cookie"];
}
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);
//.net4.0以下写法
_stream = GetMemoryStream(new GZipStream(response.GetResponseStream(), CompressionMode.Decompress));
}
else
{
//开始读取流并设置编码方式
//response.GetResponseStream().CopyTo(_stream, 10240);
//.net4.0以下写法
_stream = GetMemoryStream(response.GetResponseStream());
}
//获取Byte
byte[] RawResponse = _stream.ToArray();
//是否返回Byte类型数据
if (objhttpitem.ResultType == ResultType.Byte)
{
result.ResultByte = RawResponse;
}
//从这里开始我们要无视编码了
if (encoding == null)
{
string temp = Encoding.Default.GetString(RawResponse, 0, RawResponse.Length);
//<meta(.*?)charset([\s]?)=[^>](.*?)>
Match meta = Regex.Match(temp, "<meta([^<]*)charset=([^<]*)[\"']", RegexOptions.IgnoreCase | RegexOptions.Multiline);
string charter = (meta.Groups.Count > 2) ? meta.Groups[2].Value : string.Empty;
charter = charter.Replace("\"", string.Empty).Replace("'", string.Empty).Replace(";", string.Empty);
if (charter.Length > 0)
{
charter = charter.ToLower().Replace("iso-8859-1", "gbk");
encoding = Encoding.GetEncoding(charter);
}
else
{
if (response.CharacterSet.ToLower().Trim() == "iso-8859-1")
{
encoding = Encoding.GetEncoding("gbk");
}
else
{
if (string.IsNullOrEmpty(response.CharacterSet.Trim()))
{
encoding = Encoding.UTF8;
}
else
{
encoding = Encoding.GetEncoding(response.CharacterSet);
}
}
}
}
//得到返回的HTML
result.Html = encoding.GetString(RawResponse);
//最后释放流
_stream.Close();
}
#endregion
}
catch (WebException ex)
{
//这里是在发生异常时返回的错误信息
result.Html = "String Error";
response = (HttpWebResponse)ex.Response;
}
if (objhttpitem.IsToLower)
{
result.Html = result.Html.ToLower();
}
return result;
}
/// <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)
{
result = new HttpResult();
result.Cookie = string.Empty;
result.Header = null;
result.Html = ex.Message;
result.StatusDescription = "配置参数时出错：" + ex.Message;
return result;
}
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"];
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);
//.net4.0以下写法
_stream = GetMemoryStream(new GZipStream(response.GetResponseStream(), CompressionMode.Decompress));
}
else
{
//开始读取流并设置编码方式
//response.GetResponseStream().CopyTo(_stream, 10240);
//.net4.0以下写法
_stream = GetMemoryStream(response.GetResponseStream());
}
//获取Byte
byte[] ResponseByte = _stream.ToArray();
_stream.Close();
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="objhttpItem">参数列表</param>
private void SetRequest(HttpItem objhttpItem)
{
//设置安全协议
ServicePointManager.SecurityProtocol = objhttpItem.SecurityProtocolType;
// 验证证书
SetCer(objhttpItem);
//设置Header参数
if (objhttpItem.Header != null && objhttpItem.Header.Count > 0) foreach (string item in objhttpItem.Header.AllKeys)
{
request.Headers.Add(item, objhttpItem.Header[item]);
}
// 设置代理
SetProxy(objhttpItem);
if (objhttpItem.ProtocolVersion != null) request.ProtocolVersion = objhttpItem.ProtocolVersion;
request.ServicePoint.Expect100Continue = objhttpItem.Expect100Continue;
//请求方式Get或者Post
request.Method = objhttpItem.Method;
request.Timeout = objhttpItem.Timeout;
request.ReadWriteTimeout = objhttpItem.ReadWriteTimeout;
//Accept
request.Accept = objhttpItem.Accept;
//ContentType返回类型
request.ContentType = objhttpItem.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 = objhttpItem.UserAgent;
// 编码
encoding = objhttpItem.Encoding;
//设置Cookie
SetCookie(objhttpItem);
//来源地址
request.Referer = objhttpItem.Referer;
//是否执行跳转功能
request.AllowAutoRedirect = objhttpItem.Allowautoredirect;
//设置Post数据
SetPostData(objhttpItem);
//设置最大连接
if (objhttpItem.Connectionlimit > 0) request.ServicePoint.ConnectionLimit = objhttpItem.Connectionlimit;
}
/// <summary>
/// 设置多个证书
/// </summary>
/// <param name="objhttpItem"></param>
private void SetCerList(HttpItem objhttpItem)
{
if (objhttpItem.ClentCertificates != null && objhttpItem.ClentCertificates.Count > 0)
{
foreach (X509Certificate item in objhttpItem.ClentCertificates)
{
request.ClientCertificates.Add(item);
}
}
}
/// <summary>
/// 根据相传入的数据，得到相应页面数据
/// </summary>
/// <param name="strPostdata">传入的数据Post方式,get方式传NUll或者空字符串都可以</param>
/// <returns>string类型的响应数据</returns>
private HttpResult GetHttpRequestData(HttpItem objhttpitem)
{
//返回参数
HttpResult result = new HttpResult();
try
{
#region 得到请求的response
using (response = (HttpWebResponse)request.GetResponse())
{
result.Header = response.Headers;
if (response.Cookies != null)
{
result.CookieCollection = response.Cookies;
}
if (response.Headers["set-cookie"] != null)
{
result.Cookie = response.Headers["set-cookie"];
}
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);
//.net4.0以下写法
_stream = GetMemoryStream(new GZipStream(response.GetResponseStream(), CompressionMode.Decompress));
}
else
{
//开始读取流并设置编码方式
//response.GetResponseStream().CopyTo(_stream, 10240);
//.net4.0以下写法
_stream = GetMemoryStream(response.GetResponseStream());
}
//获取Byte
byte[] RawResponse = _stream.ToArray();
//是否返回Byte类型数据
if (objhttpitem.ResultType == ResultType.Byte)
{
result.ResultByte = RawResponse;
}
//从这里开始我们要无视编码了
if (encoding == null)
{
string temp = Encoding.Default.GetString(RawResponse, 0, RawResponse.Length);
//<meta(.*?)charset([\s]?)=[^>](.*?)>
Match meta = Regex.Match(temp, "<meta([^<]*)charset=([^<]*)[\"']", RegexOptions.IgnoreCase | RegexOptions.Multiline);
string charter = (meta.Groups.Count > 2) ? meta.Groups[2].Value : string.Empty;
charter = charter.Replace("\"", string.Empty).Replace("'", string.Empty).Replace(";", string.Empty);
if (charter.Length > 0)
{
charter = charter.ToLower().Replace("iso-8859-1", "gbk");
encoding = Encoding.GetEncoding(charter);
}
else
{
if (response.CharacterSet.ToLower().Trim() == "iso-8859-1")
{
encoding = Encoding.GetEncoding("gbk");
}
else
{
if (string.IsNullOrEmpty(response.CharacterSet.Trim()))
{
encoding = Encoding.UTF8;
}
else
{
encoding = Encoding.GetEncoding(response.CharacterSet);
}
}
}
}
//得到返回的HTML
result.Html = encoding.GetString(RawResponse);
//最后释放流
_stream.Close();
}
#endregion
}
catch (WebException ex)
{
//这里是在发生异常时返回的错误信息
result.Html = "String Error";
response = (HttpWebResponse)ex.Response;
}
if (objhttpitem.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);
if (item.IPEndPoint != null)
{
_IPEndPoint = item.IPEndPoint;
//设置本地的出口ip和端口
request.ServicePoint.BindIPEndPointDelegate = new BindIPEndPoint(BindIPEndPointCallback);
}
//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 (item.IfModifiedSince != null)
{
request.IfModifiedSince = Convert.ToDateTime(item.IfModifiedSince);
}
//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;
if (item.MaximumAutomaticRedirections > 0)
{
request.MaximumAutomaticRedirections = item.MaximumAutomaticRedirections;
}
//设置Post数据
SetPostData(item);
//设置最大连接
if (item.Connectionlimit > 0)
{
request.ServicePoint.ConnectionLimit = item.Connectionlimit;
}
}
/// <summary>
/// 根据相传入的数据，得到相应页面数据
/// </summary>
/// <param name="objhttpitem">参数类对象</param>
/// <returns>返回HttpResult类型</returns>
public HttpResult GetHtml(HttpItem objhttpitem)
{
//返回参数
HttpResult result = new HttpResult();
try
{
//准备参数
SetRequest(objhttpitem);
}
catch (Exception ex)
{
result = new HttpResult()
{
Cookie = "",
Header = null,
Html = ex.Message,
StatusDescription = "配置参数时出错：" + ex.Message
};
return(result);
}
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"];
}
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);
//.net4.0以下写法
_stream = GetMemoryStream(new GZipStream(response.GetResponseStream(), CompressionMode.Decompress));
}
else
{
//开始读取流并设置编码方式
//response.GetResponseStream().CopyTo(_stream, 10240);
//.net4.0以下写法
_stream = GetMemoryStream(response.GetResponseStream());
}
//获取Byte
byte[] RawResponse = _stream.ToArray();
_stream.Close();
//是否返回Byte类型数据
if (objhttpitem.ResultType == ResultType.Byte)
{
result.ResultByte = RawResponse;
}
//从这里开始我们要无视编码了
if (encoding == null)
{
Match meta = Regex.Match(Encoding.Default.GetString(RawResponse), "<meta([^<]*)charset=([^<]*)[\"']", RegexOptions.IgnoreCase);
string charter = (meta.Groups.Count > 1) ? meta.Groups[2].Value.ToLower() : string.Empty;
if (charter.Length > 2)
{
encoding = Encoding.GetEncoding(charter.Trim().Replace("\"", "").Replace("'", "").Replace(";", "").Replace("iso-8859-1", "gbk"));
}
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(RawResponse);
}
#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 (objhttpitem.IsToLower)
{
result.Html = result.Html.ToLower();
}
return(result);
}
/// <summary>
/// 设置代理
/// </summary>
/// <param name="item">参数对象</param>
private void SetProxy(HttpItem item)
{
bool isIeProxy = false;
if (!string.IsNullOrEmpty(item.ProxyIp))
{
isIeProxy = item.ProxyIp.ToLower().Contains("ieproxy");
}
if (!string.IsNullOrEmpty(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>
/// 设置代理
/// </summary>
/// <param name="item">参数对象</param>
private void SetProxy(HttpItem item)
{
if (!string.IsNullOrEmpty(item.ProxyIp))
{
//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;
}
//设置安全凭证
request.Credentials = CredentialCache.DefaultCredentials;
}
else if (item.WebProxy != null)
{
request.Proxy = item.WebProxy;
}
}
/// <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);
if (item.IPEndPoint != null)
{
_IPEndPoint = item.IPEndPoint;
//设置本地的出口ip和端口
request.ServicePoint.BindIPEndPointDelegate = new BindIPEndPoint(BindIPEndPointCallback);
}
//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 (item.IfModifiedSince != null) request.IfModifiedSince = Convert.ToDateTime(item.IfModifiedSince);
//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;
if (item.MaximumAutomaticRedirections > 0)
{
request.MaximumAutomaticRedirections = item.MaximumAutomaticRedirections;
}
//设置Post数据
SetPostData(item);
//设置最大连接
if (item.Connectionlimit > 0) request.ServicePoint.ConnectionLimit = item.Connectionlimit;
}
/// <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;
//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>
/// 为请求准备参数
/// </summary>
///<param name="objhttpItem">参数列表</param>
/// <param name="_Encoding">读取数据时的编码方式</param>
private void SetRequest(HttpItem objhttpItem)
{
// 验证证书
SetCer(objhttpItem);
// 设置代理
SetProxy(objhttpItem);
//请求方式Get或者Post
request.Method = objhttpItem.Method;
request.Timeout = objhttpItem.Timeout;
request.ReadWriteTimeout = objhttpItem.ReadWriteTimeout;
//Accept
request.Accept = objhttpItem.Accept;
//ContentType返回类型
request.ContentType = objhttpItem.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 = objhttpItem.UserAgent;
// 编码
SetEncoding(objhttpItem);
//设置Cookie
SetCookie(objhttpItem);
//来源地址
request.Referer = objhttpItem.Referer;
//是否执行跳转功能
request.AllowAutoRedirect = objhttpItem.Allowautoredirect;
//设置Post数据
SetPostData(objhttpItem);
//设置最大连接
if (objhttpItem.Connectionlimit > 0)
{
request.ServicePoint.ConnectionLimit = objhttpItem.Connectionlimit;
}
}
/// <summary>
/// 获取数据的并解析的方法
/// </summary>
/// <param name="item"></param>
/// <param name="result"></param>
private void GetData(HttpItem item, HttpResult result)
{
#region base
//获取StatusCode
result.StatusCode = response.StatusCode;
//获取StatusDescription
result.StatusDescription = response.StatusDescription;
//获取最后访问的URl
result.ResponseUri = response.ResponseUri.ToString();
//获取Headers
result.Header = response.Headers;
//获取CookieCollection
if (response.Cookies != null) result.CookieCollection = response.Cookies;
//获取set-cookie
if (response.Headers["set-cookie"] != null) result.Cookie = response.Headers["set-cookie"];
#endregion
#region byte
//处理网页Byte
byte[] ResponseByte = GetByte();
#endregion
#region Html
if (ResponseByte != null & ResponseByte.Length > 0)
{
//设置编码
SetEncoding(item, result, ResponseByte);
//得到返回的HTML
result.Html = encoding.GetString(ResponseByte);
}
else
{
//没有返回任何Html代码
result.Html = string.Empty;
}
#endregion
}
/// <summary>
/// 设置编码
/// </summary>
/// <param name="objhttpItem">Http参数</param>
private void SetEncoding(HttpItem objhttpItem)
{
if (string.IsNullOrEmpty(objhttpItem.Encoding) || objhttpItem.Encoding.ToLower().Trim() == "null")
{
//读取数据时的编码方式
encoding = null;
}
else
{
//读取数据时的编码方式
encoding = System.Text.Encoding.GetEncoding(objhttpItem.Encoding);
}
}
/// <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Post数据
/// </summary>
/// <param name="objhttpItem">Http参数</param>
private void SetPostData(HttpItem objhttpItem)
{
//验证在得到结果时是否有传入数据
if (request.Method.Trim().ToLower().Contains("post"))
{
//写入Byte类型
if (objhttpItem.PostDataType == PostDataType.Byte)
{
//验证在得到结果时是否有传入数据
if (objhttpItem.PostdataByte != null && objhttpItem.PostdataByte.Length > 0)
{
request.ContentLength = objhttpItem.PostdataByte.Length;
request.GetRequestStream().Write(objhttpItem.PostdataByte, 0, objhttpItem.PostdataByte.Length);
}
}//写入文件
else if (objhttpItem.PostDataType == PostDataType.FilePath)
{
StreamReader r = new StreamReader(objhttpItem.Postdata, encoding);
byte[] buffer = Encoding.Default.GetBytes(r.ReadToEnd());
r.Close();
request.ContentLength = buffer.Length;
request.GetRequestStream().Write(buffer, 0, buffer.Length);
}
else
{
//验证在得到结果时是否有传入数据
if (!string.IsNullOrEmpty(objhttpItem.Postdata))
{
byte[] buffer = Encoding.Default.GetBytes(objhttpItem.Postdata);
request.ContentLength = buffer.Length;
request.GetRequestStream().Write(buffer, 0, buffer.Length);
}
}
}
}
/// <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>
///采用https协议访问网络,根据传入的URl地址，得到响应的数据字符串。
///</summary>
///<param name="objhttpItem">参数列表</param>
///<returns>String类型的数据</returns>
public HttpResult GetHtml(HttpItem objhttpItem)
{
//准备参数
SetRequest(objhttpItem);
//调用专门读取数据的类
return GetHttpRequestData(objhttpItem);
}
static void Main(string[] args)
{
//List<Thread> threads = new List<Thread>();
while (true)
{
Console.WriteLine("请输入关键词：");
String keyWord = Console.ReadLine().Trim();
if (!string.IsNullOrEmpty(keyWord.Trim()))
{
//
Thread t = new Thread(() =>
{
#region 抓取任务开始
String start = "";
string taskKeyWord = keyWord;
HttpHelper http = new HttpHelper();
//每一次抓取
//大于totalItems/48时停止
Int32 count = 1;
Random random = new Random();
while (true)
{
start = (48 * count).ToString();
HttpItem item = new HttpItem()
{
URL = "http://pic.sogou.com/pics?query=" + taskKeyWord + "&mood=0&picformat=0&mode=1&di=0&clusterfilter=off&p=40230504&dp=1&start=" + start + "&reqType=ajax&tn=0&reqFrom=result",//URL 必需项
Method = "get",//URL 可选项 默认为Get
IsToLower = false,//得到的HTML代码是否转成小写 可选项默认转小写
Referer = "",//来源URL 可选项
Postdata = "",//Post数据 可选项GET时不需要写
Timeout = 100000,//连接超时时间 可选项默认为100000
ReadWriteTimeout = 30000,//写入Post数据超时时间 可选项默认为30000
UserAgent = "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Trident/5.0)",//用户的浏览器类型，版本，操作系统 可选项有默认值
ContentType = "text/html",//返回类型 可选项有默认值
Allowautoredirect = false,//是否根据301跳转 可选项
//CerPath = "d:\123.cer",//证书绝对路径 可选项不需要证书时可以不写这个参数
//Connectionlimit = 1024,//最大连接数 可选项 默认为1024
ResultType = ResultType.String
};
HttpResult result = http.GetHtml(item);
string html = result.Html;
string cookie = result.Cookie;
//Console.WriteLine("【" + Thread.CurrentThread.ManagedThreadId + "】-" + html);
//解析结果，得到停止条件
System.Web.Script.Serialization.JavaScriptSerializer js = new System.Web.Script.Serialization.JavaScriptSerializer();
SouGouImgModel model = js.Deserialize<SouGouImgModel>(html);
if (Convert.ToInt32(start) >= Convert.ToInt32(model.totalItems.Replace(",", "")))
//if (model.items.Count==0)
{
Console.WriteLine("结束时间：【" + DateTime.Now + "】-任务关键字：" + taskKeyWord);
break;
}
Console.WriteLine("当前个数："+model.items.Count+"==请求总个数："+start+"==MaxEnd："+model.maxEnd+"==总个数："+model.totalItems);
//下一轮
int span = random.Next(3000, 10000);
Thread.Sleep(span);
//Console.WriteLine(count);
count++;
}
#endregion
});
//threads.Add(t);
t.Start();
Console.WriteLine("开始时间：【" + DateTime.Now + "】-任务关键字：" + keyWord);
}
}
}
