C# HttpWebRequest 绝技 根据URL地址获取网页信息
如果要使用中间的方法的话，可以访问我的帮助类完全免费开源：C# HttpHelper,帮助类,真正的Httprequest请求时无视编码，无视证书，无视Cookie,网页抓取
1.第一招，根据URL地址获取网页信息
先来看一下代码
get方法
public
static
string
GetUrltoHtml(
string
Url,
string
type)
{
try
{
System.Net.WebRequest wReq = System.Net.WebRequest.Create(Url);
// Get the response instance.
System.Net.WebResponse wResp = wReq.GetResponse();
System.IO.Stream respStream = wResp.GetResponseStream();
// Dim reader As StreamReader = New StreamReader(respStream)
using (System.IO.StreamReader reader = new System.IO.StreamReader(respStream, Encoding.GetEncoding(type)))
{
return reader.ReadToEnd();
}
}
catch (System.Exception ex)
{
// errorMsg = ex.Message;
}
return "" ;
}
{
try
{
System.Net.WebRequest wReq = System.Net.WebRequest.Create(Url);
// Get the response instance.
System.Net.WebResponse wResp = wReq.GetResponse();
System.IO.Stream respStream = wResp.GetResponseStream();
// Dim reader As StreamReader = New StreamReader(respStream)
using (System.IO.StreamReader reader = new System.IO.StreamReader(respStream, Encoding.GetEncoding(type)))
{
return reader.ReadToEnd();
}
}
catch (System.Exception ex)
{
// errorMsg = ex.Message;
}
return "" ;
}
post方法
///
<summary>
/// 采用https协议访问网络
/// </summary>
/// <param name="URL"> url地址 </param>
/// <param name="strPostdata"> 发送的数据 </param>
/// <returns></returns>
public string OpenReadWithHttps( string URL, string strPostdata, string strEncoding)
{
Encoding encoding = Encoding.Default;
HttpWebRequest request = (HttpWebRequest)WebRequest.Create(URL);
request.Method = " post " ;
request.Accept = " text/html, application/xhtml+xml, */* " ;
request.ContentType = " application/x-www-form-urlencoded " ;
byte [] buffer = encoding.GetBytes(strPostdata);
request.ContentLength = buffer.Length;
request.GetRequestStream().Write(buffer, 0 , buffer.Length);
HttpWebResponse response = (HttpWebResponse)request.GetResponse();
using( StreamReader reader = new StreamReader(response.GetResponseStream(), System.Text.Encoding.GetEncoding(strEncoding)))
/// 采用https协议访问网络
/// </summary>
/// <param name="URL"> url地址 </param>
/// <param name="strPostdata"> 发送的数据 </param>
/// <returns></returns>
public string OpenReadWithHttps( string URL, string strPostdata, string strEncoding)
{
Encoding encoding = Encoding.Default;
HttpWebRequest request = (HttpWebRequest)WebRequest.Create(URL);
request.Method = " post " ;
request.Accept = " text/html, application/xhtml+xml, */* " ;
request.ContentType = " application/x-www-form-urlencoded " ;
byte [] buffer = encoding.GetBytes(strPostdata);
request.ContentLength = buffer.Length;
request.GetRequestStream().Write(buffer, 0 , buffer.Length);
HttpWebResponse response = (HttpWebResponse)request.GetResponse();
using( StreamReader reader = new StreamReader(response.GetResponseStream(), System.Text.Encoding.GetEncoding(strEncoding)))
{
return reader.ReadToEnd();
return reader.ReadToEnd();
}
}
}
这招是入门第一式， 特点：
1.最简单最直观的一种，入门课程。
2.适应于明文，无需登录，无需任何验证就可以进入的页面。
3.获取的数据类型为HTML文档。
4.请求方法为Get/Post
2.第二招，根据URL地址获取需要验证证书才能访问的网页信息
先来看一下代码
get方法
//
回调验证证书问题
public bool CheckValidationResult( object sender, X509Certificate certificate, X509Chain chain, SslPolicyErrors errors)
{ // 总是接受
return true ;
}
/// <summary>
/// 传入URL返回网页的html代码
/// </summary>
/// <param name="Url"> URL </param>
/// <returns></returns>
public string GetUrltoHtml( string Url)
{
StringBuilder content = new StringBuilder();
try
{
// 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);
// 与指定URL创建HTTP请求
HttpWebRequest request = (HttpWebRequest)WebRequest.Create(Url);
// 创建证书文件
X509Certificate objx509 = new X509Certificate(Application.StartupPath + " \\123.cer " );
// 添加到请求里
request.ClientCertificates.Add(objx509);
// 获取对应HTTP请求的响应
HttpWebResponse response = (HttpWebResponse)request.GetResponse();
// 获取响应流
Stream responseStream = response.GetResponseStream();
// 对接响应流(以"GBK"字符集)
StreamReader sReader = new StreamReader(responseStream, Encoding.GetEncoding( " utf-8 " ));
// 开始读取数据
Char[] sReaderBuffer = new Char[ 256 ];
int count = sReader.Read(sReaderBuffer, 0 , 256 );
while (count > 0 )
{
String tempStr = new String(sReaderBuffer, 0 , count);
content.Append(tempStr);
count = sReader.Read(sReaderBuffer, 0 , 256 );
}
// 读取结束
sReader.Close();
}
catch (Exception)
{
content = new StringBuilder( " Runtime Error " );
}
return content.ToString();
}
public bool CheckValidationResult( object sender, X509Certificate certificate, X509Chain chain, SslPolicyErrors errors)
{ // 总是接受
return true ;
}
/// <summary>
/// 传入URL返回网页的html代码
/// </summary>
/// <param name="Url"> URL </param>
/// <returns></returns>
public string GetUrltoHtml( string Url)
{
StringBuilder content = new StringBuilder();
try
{
// 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);
// 与指定URL创建HTTP请求
HttpWebRequest request = (HttpWebRequest)WebRequest.Create(Url);
// 创建证书文件
X509Certificate objx509 = new X509Certificate(Application.StartupPath + " \\123.cer " );
// 添加到请求里
request.ClientCertificates.Add(objx509);
// 获取对应HTTP请求的响应
HttpWebResponse response = (HttpWebResponse)request.GetResponse();
// 获取响应流
Stream responseStream = response.GetResponseStream();
// 对接响应流(以"GBK"字符集)
StreamReader sReader = new StreamReader(responseStream, Encoding.GetEncoding( " utf-8 " ));
// 开始读取数据
Char[] sReaderBuffer = new Char[ 256 ];
int count = sReader.Read(sReaderBuffer, 0 , 256 );
while (count > 0 )
{
String tempStr = new String(sReaderBuffer, 0 , count);
content.Append(tempStr);
count = sReader.Read(sReaderBuffer, 0 , 256 );
}
// 读取结束
sReader.Close();
}
catch (Exception)
{
content = new StringBuilder( " Runtime Error " );
}
return content.ToString();
}
post方法
//
回调验证证书问题
public bool CheckValidationResult( object sender, X509Certificate certificate, X509Chain chain, SslPolicyErrors errors)
{
// 总是接受
return true ;
}
/// <summary>
/// 采用https协议访问网络
/// </summary>
/// <param name="URL"> url地址 </param>
/// <param name="strPostdata"> 发送的数据 </param>
/// <returns></returns>
public string OpenReadWithHttps( string URL, string strPostdata, string strEncoding)
{
// 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);
Encoding encoding = Encoding.Default;
HttpWebRequest request = (HttpWebRequest)WebRequest.Create(URL);
// 创建证书文件
X509Certificate objx509 = new X509Certificate(Application.StartupPath + " \\123.cer " );
// 加载Cookie
request.CookieContainer = new CookieContainer();
// 添加到请求里
request.ClientCertificates.Add(objx509);
request.Method = " post " ;
request.Accept = " text/html, application/xhtml+xml, */* " ;
request.ContentType = " application/x-www-form-urlencoded " ;
byte [] buffer = encoding.GetBytes(strPostdata);
request.ContentLength = buffer.Length;
request.GetRequestStream().Write(buffer, 0 , buffer.Length);
HttpWebResponse response = (HttpWebResponse)request.GetResponse();
using (StreamReader reader = new StreamReader(response.GetResponseStream(), System.Text.Encoding.GetEncoding(strEncoding)))
public bool CheckValidationResult( object sender, X509Certificate certificate, X509Chain chain, SslPolicyErrors errors)
{
// 总是接受
return true ;
}
/// <summary>
/// 采用https协议访问网络
/// </summary>
/// <param name="URL"> url地址 </param>
/// <param name="strPostdata"> 发送的数据 </param>
/// <returns></returns>
public string OpenReadWithHttps( string URL, string strPostdata, string strEncoding)
{
// 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);
Encoding encoding = Encoding.Default;
HttpWebRequest request = (HttpWebRequest)WebRequest.Create(URL);
// 创建证书文件
X509Certificate objx509 = new X509Certificate(Application.StartupPath + " \\123.cer " );
// 加载Cookie
request.CookieContainer = new CookieContainer();
// 添加到请求里
request.ClientCertificates.Add(objx509);
request.Method = " post " ;
request.Accept = " text/html, application/xhtml+xml, */* " ;
request.ContentType = " application/x-www-form-urlencoded " ;
byte [] buffer = encoding.GetBytes(strPostdata);
request.ContentLength = buffer.Length;
request.GetRequestStream().Write(buffer, 0 , buffer.Length);
HttpWebResponse response = (HttpWebResponse)request.GetResponse();
using (StreamReader reader = new StreamReader(response.GetResponseStream(), System.Text.Encoding.GetEncoding(strEncoding)))
{
return reader.ReadToEnd();
return reader.ReadToEnd();
}
}
}
这招是学会算是进了大门了，凡是需要验证证书才能进入的页面都可以使用这个方法进入，我使用的是证书回调验证的方式，证书验证是否通过在客户端验证，这样的话我们就可以使用自己定义一个方法来验证了，有的人会说那也不清楚是怎么样验证的啊，其它很简单，代码是自己写的为什么要那么难为自己呢，直接返回一个True不就完了，永远都是验证通过，这样就可以无视证书的存在了， 特点：
1.入门前的小难题，初级课程。
2.适应于无需登录，明文但需要验证证书才能访问的页面。
3.获取的数据类型为HTML文档。
4.请求方法为Get/Post
3.第三招，根据URL地址获取需要登录才能访问的网页信息
我们先来分析一下这种类型的网页，需要登录才能访问的网页，其它呢也是一种验证，验证什么呢，验证客户端是否登录，是否具用相应的凭证，需要登录的都要验证SessionID这是每一个需要登录的页面都需要验证的，那我们怎么做的，我们第一步就是要得存在Cookie里面的数据包括SessionID，那怎么得到呢，这个方法很多，使用ID9或者是火狐浏览器很容易就能得到，可以参考我的文章
提供一个网页抓取hao123手机号码归属地的例子 这里面针对ID9有详细的说明。
如果我们得到了登录的Cookie信息之后那个再去访问相应的页面就会非常的简单了，其它说白了就是把本地的Cookie信息在请求的时候捎带过去就行了。
看代码
get方法
View Code
///
<summary>
/// 传入URL返回网页的html代码带有证书的方法
/// </summary>
/// <param name="Url"> URL </param>
/// <returns></returns>
public string GetUrltoHtml( string Url)
{
StringBuilder content = new StringBuilder();
try
{
// 与指定URL创建HTTP请求
HttpWebRequest request = (HttpWebRequest)WebRequest.Create(Url);
request.UserAgent = " Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Trident/5.0; BOIE9;ZHCN) " ;
request.Method = " GET " ;
request.Accept = " */* " ;
// 如果方法验证网页来源就加上这一句如果不验证那就可以不写了
request.Referer = " http://sufei.cnblogs.com " ;
CookieContainer objcok = new CookieContainer();
objcok.Add( new Uri( " http://sufei.cnblogs.com " ), new Cookie( " 键 " , " 值 " ));
objcok.Add( new Uri( " http://sufei.cnblogs.com " ), new Cookie( " 键 " , " 值 " ));
objcok.Add( new Uri( " http://sufei.cnblogs.com " ), new Cookie( " sidi_sessionid " , " 360A748941D055BEE8C960168C3D4233 " ));
request.CookieContainer = objcok;
// 不保持连接
request.KeepAlive = true ;
// 获取对应HTTP请求的响应
HttpWebResponse response = (HttpWebResponse)request.GetResponse();
// 获取响应流
Stream responseStream = response.GetResponseStream();
// 对接响应流(以"GBK"字符集)
StreamReader sReader = new StreamReader(responseStream, Encoding.GetEncoding( " gb2312 " ));
// 开始读取数据
Char[] sReaderBuffer = new Char[ 256 ];
int count = sReader.Read(sReaderBuffer, 0 , 256 );
while (count > 0 )
{
String tempStr = new String(sReaderBuffer, 0 , count);
content.Append(tempStr);
count = sReader.Read(sReaderBuffer, 0 , 256 );
}
// 读取结束
sReader.Close();
}
catch (Exception)
{
content = new StringBuilder( " Runtime Error " );
}
return content.ToString();
}
/// 传入URL返回网页的html代码带有证书的方法
/// </summary>
/// <param name="Url"> URL </param>
/// <returns></returns>
public string GetUrltoHtml( string Url)
{
StringBuilder content = new StringBuilder();
try
{
// 与指定URL创建HTTP请求
HttpWebRequest request = (HttpWebRequest)WebRequest.Create(Url);
request.UserAgent = " Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Trident/5.0; BOIE9;ZHCN) " ;
request.Method = " GET " ;
request.Accept = " */* " ;
// 如果方法验证网页来源就加上这一句如果不验证那就可以不写了
request.Referer = " http://sufei.cnblogs.com " ;
CookieContainer objcok = new CookieContainer();
objcok.Add( new Uri( " http://sufei.cnblogs.com " ), new Cookie( " 键 " , " 值 " ));
objcok.Add( new Uri( " http://sufei.cnblogs.com " ), new Cookie( " 键 " , " 值 " ));
objcok.Add( new Uri( " http://sufei.cnblogs.com " ), new Cookie( " sidi_sessionid " , " 360A748941D055BEE8C960168C3D4233 " ));
request.CookieContainer = objcok;
// 不保持连接
request.KeepAlive = true ;
// 获取对应HTTP请求的响应
HttpWebResponse response = (HttpWebResponse)request.GetResponse();
// 获取响应流
Stream responseStream = response.GetResponseStream();
// 对接响应流(以"GBK"字符集)
StreamReader sReader = new StreamReader(responseStream, Encoding.GetEncoding( " gb2312 " ));
// 开始读取数据
Char[] sReaderBuffer = new Char[ 256 ];
int count = sReader.Read(sReaderBuffer, 0 , 256 );
while (count > 0 )
{
String tempStr = new String(sReaderBuffer, 0 , count);
content.Append(tempStr);
count = sReader.Read(sReaderBuffer, 0 , 256 );
}
// 读取结束
sReader.Close();
}
catch (Exception)
{
content = new StringBuilder( " Runtime Error " );
}
return content.ToString();
}
post方法。
View Code
///
<summary>
/// 采用https协议访问网络
/// </summary>
/// <param name="URL"> url地址 </param>
/// <param name="strPostdata"> 发送的数据 </param>
/// <returns></returns>
public string OpenReadWithHttps( string URL, string strPostdata)
{
Encoding encoding = Encoding.Default;
HttpWebRequest request = (HttpWebRequest)WebRequest.Create(URL);
request.Method = " post " ;
request.Accept = " text/html, application/xhtml+xml, */* " ;
request.ContentType = " application/x-www-form-urlencoded " ;
CookieContainer objcok = new CookieContainer();
objcok.Add( new Uri( " http://sufei.cnblogs.com " ), new Cookie( " 键 " , " 值 " ));
objcok.Add( new Uri( " http://sufei.cnblogs.com " ), new Cookie( " 键 " , " 值 " ));
objcok.Add( new Uri( " http://sufei.cnblogs.com " ), new Cookie( " sidi_sessionid " , " 360A748941D055BEE8C960168C3D4233 " ));
request.CookieContainer = objcok;
byte [] buffer = encoding.GetBytes(strPostdata);
request.ContentLength = buffer.Length;
request.GetRequestStream().Write(buffer, 0 , buffer.Length);
HttpWebResponse response = (HttpWebResponse)request.GetResponse();
StreamReader reader = new StreamReader(response.GetResponseStream(), System.Text.Encoding.GetEncoding( " utf-8 " ));
return reader.ReadToEnd();
}
/// 采用https协议访问网络
/// </summary>
/// <param name="URL"> url地址 </param>
/// <param name="strPostdata"> 发送的数据 </param>
/// <returns></returns>
public string OpenReadWithHttps( string URL, string strPostdata)
{
Encoding encoding = Encoding.Default;
HttpWebRequest request = (HttpWebRequest)WebRequest.Create(URL);
request.Method = " post " ;
request.Accept = " text/html, application/xhtml+xml, */* " ;
request.ContentType = " application/x-www-form-urlencoded " ;
CookieContainer objcok = new CookieContainer();
objcok.Add( new Uri( " http://sufei.cnblogs.com " ), new Cookie( " 键 " , " 值 " ));
objcok.Add( new Uri( " http://sufei.cnblogs.com " ), new Cookie( " 键 " , " 值 " ));
objcok.Add( new Uri( " http://sufei.cnblogs.com " ), new Cookie( " sidi_sessionid " , " 360A748941D055BEE8C960168C3D4233 " ));
request.CookieContainer = objcok;
byte [] buffer = encoding.GetBytes(strPostdata);
request.ContentLength = buffer.Length;
request.GetRequestStream().Write(buffer, 0 , buffer.Length);
HttpWebResponse response = (HttpWebResponse)request.GetResponse();
StreamReader reader = new StreamReader(response.GetResponseStream(), System.Text.Encoding.GetEncoding( " utf-8 " ));
return reader.ReadToEnd();
}
特点：
1.还算有点水类型的，练习成功后可以小牛一把。
2.适应于需要登录才能访问的页面。
3.获取的数据类型为HTML文档。
4.请求方法为Get/Post
总结一下，其它基本的技能就这几个部分，如果再深入的话那就是基本技能的组合了
比如，
1. 先用Get或者Post方法登录然后取得Cookie再去访问页面得到信息，这种其它也是上面技能的组合，
这里需要以请求后做这样一步
response.Cookies
这就是在你请求后可以得到当次Cookie的方法，直接取得返回给上一个方法使用就行了，上面我们都是自己构造的，在这里直接使用这个Cookie就可以了。
2.如果我们碰到需要登录而且还要验证证书的网页怎么办，其它这个也很简单把我们上面的方法综合 一下就行了
如下代码这里我以Get为例子Post例子也是同样的方法
View Code
///
<summary>
/// 传入URL返回网页的html代码
/// </summary>
/// <param name="Url"> URL </param>
/// <returns></returns>
public string GetUrltoHtml( string Url)
{
StringBuilder content = new StringBuilder();
try
{
// 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);
// 与指定URL创建HTTP请求
HttpWebRequest request = (HttpWebRequest)WebRequest.Create(Url);
// 创建证书文件
X509Certificate objx509 = new X509Certificate(Application.StartupPath + " \\123.cer " );
// 添加到请求里
request.ClientCertificates.Add(objx509);
CookieContainer objcok = new CookieContainer();
objcok.Add( new Uri( " http://www.cnblogs.com " ), new Cookie( " 键 " , " 值 " ));
objcok.Add( new Uri( " http://www.cnblogs.com " ), new Cookie( " 键 " , " 值 " ));
objcok.Add( new Uri( " http://www.cnblogs.com " ), new Cookie( " sidi_sessionid " , " 360A748941D055BEE8C960168C3D4233 " ));
request.CookieContainer = objcok;
// 获取对应HTTP请求的响应
HttpWebResponse response = (HttpWebResponse)request.GetResponse();
// 获取响应流
Stream responseStream = response.GetResponseStream();
// 对接响应流(以"GBK"字符集)
StreamReader sReader = new StreamReader(responseStream, Encoding.GetEncoding( " utf-8 " ));
// 开始读取数据
Char[] sReaderBuffer = new Char[ 256 ];
int count = sReader.Read(sReaderBuffer, 0 , 256 );
while (count > 0 )
{
String tempStr = new String(sReaderBuffer, 0 , count);
content.Append(tempStr);
count = sReader.Read(sReaderBuffer, 0 , 256 );
}
// 读取结束
sReader.Close();
}
catch (Exception)
{
content = new StringBuilder( " Runtime Error " );
}
return content.ToString();
}
/// 传入URL返回网页的html代码
/// </summary>
/// <param name="Url"> URL </param>
/// <returns></returns>
public string GetUrltoHtml( string Url)
{
StringBuilder content = new StringBuilder();
try
{
// 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);
// 与指定URL创建HTTP请求
HttpWebRequest request = (HttpWebRequest)WebRequest.Create(Url);
// 创建证书文件
X509Certificate objx509 = new X509Certificate(Application.StartupPath + " \\123.cer " );
// 添加到请求里
request.ClientCertificates.Add(objx509);
CookieContainer objcok = new CookieContainer();
objcok.Add( new Uri( " http://www.cnblogs.com " ), new Cookie( " 键 " , " 值 " ));
objcok.Add( new Uri( " http://www.cnblogs.com " ), new Cookie( " 键 " , " 值 " ));
objcok.Add( new Uri( " http://www.cnblogs.com " ), new Cookie( " sidi_sessionid " , " 360A748941D055BEE8C960168C3D4233 " ));
request.CookieContainer = objcok;
// 获取对应HTTP请求的响应
HttpWebResponse response = (HttpWebResponse)request.GetResponse();
// 获取响应流
Stream responseStream = response.GetResponseStream();
// 对接响应流(以"GBK"字符集)
StreamReader sReader = new StreamReader(responseStream, Encoding.GetEncoding( " utf-8 " ));
// 开始读取数据
Char[] sReaderBuffer = new Char[ 256 ];
int count = sReader.Read(sReaderBuffer, 0 , 256 );
while (count > 0 )
{
String tempStr = new String(sReaderBuffer, 0 , count);
content.Append(tempStr);
count = sReader.Read(sReaderBuffer, 0 , 256 );
}
// 读取结束
sReader.Close();
}
catch (Exception)
{
content = new StringBuilder( " Runtime Error " );
}
return content.ToString();
}
3.如果我们碰到那种需要验证网页来源的方法应该怎么办呢，这种情况其它是有些程序员会想到你可能会使用程序，自动来获取网页信息，为了防止就使用页面来源来验证，就是说只要不是从他们所在页面或是域名过来的请求就不接受，有的是直接验证来源的IP，这些都可以使用下面一句来进入，这主要是这个地址是可以直接伪造的
request.Referer
=
"
http://sufei.cnblogs.com
"
;
呵呵其它很简单因为这个地址可以直接修改。但是如果服务器上验证的是来源的URL那就完了，我们就得去修改数据包了，这个有点难度暂时不讨论。
4.提供一些与这个例子相配置的方法
过滤HTML标签的方法
View Code
///
<summary>
/// 过滤html标签
/// </summary>
/// <param name="strHtml"> html的内容 </param>
/// <returns></returns>
public static string StripHTML( string stringToStrip)
{
// paring using RegEx //
stringToStrip = Regex.Replace(stringToStrip, " </p(?:\\s*)>(?:\\s*)<p(?:\\s*)> " , " \n\n " , RegexOptions.IgnoreCase | RegexOptions.Compiled);
stringToStrip = Regex.Replace(stringToStrip, " <br(?:\\s*)/> " , " \n " , RegexOptions.IgnoreCase | RegexOptions.Compiled);
stringToStrip = Regex.Replace(stringToStrip, " \" " , " '' " , RegexOptions.IgnoreCase | RegexOptions.Compiled);
stringToStrip = StripHtmlXmlTags(stringToStrip);
return stringToStrip;
}
private static string StripHtmlXmlTags( string content)
{
return Regex.Replace(content, " <[^>]+> " , "" , RegexOptions.IgnoreCase | RegexOptions.Compiled);
}
/// 过滤html标签
/// </summary>
/// <param name="strHtml"> html的内容 </param>
/// <returns></returns>
public static string StripHTML( string stringToStrip)
{
// paring using RegEx //
stringToStrip = Regex.Replace(stringToStrip, " </p(?:\\s*)>(?:\\s*)<p(?:\\s*)> " , " \n\n " , RegexOptions.IgnoreCase | RegexOptions.Compiled);
stringToStrip = Regex.Replace(stringToStrip, " <br(?:\\s*)/> " , " \n " , RegexOptions.IgnoreCase | RegexOptions.Compiled);
stringToStrip = Regex.Replace(stringToStrip, " \" " , " '' " , RegexOptions.IgnoreCase | RegexOptions.Compiled);
stringToStrip = StripHtmlXmlTags(stringToStrip);
return stringToStrip;
}
private static string StripHtmlXmlTags( string content)
{
return Regex.Replace(content, " <[^>]+> " , "" , RegexOptions.IgnoreCase | RegexOptions.Compiled);
}
URL转化的方法
#region
转化 URL
public static string URLDecode( string text)
{
return HttpUtility.UrlDecode(text, Encoding.Default);
}
public static string URLEncode( string text)
{
return HttpUtility.UrlEncode(text, Encoding.Default);
}
#endregion
public static string URLDecode( string text)
{
return HttpUtility.UrlDecode(text, Encoding.Default);
}
public static string URLEncode( string text)
{
return HttpUtility.UrlEncode(text, Encoding.Default);
}
#endregion
提供一个实际例子，这个是使用IP138来查询手机号码归属地的方法，其它在我的上一次文章里都有，在这里我再放上来是方便大家阅读，这方面的技术其它研究起来很有意思，希望大家多提建议，我相信应该还有更多更好，更完善的方法，在这里给大家提供一个参考吧。感谢支持
上例子
///
<summary>
/// 输入手机号码得到归属地信息
/// </summary>
/// <param name="number"> 手机号码 </param>
/// <returns> 数组类型0为归属地，1卡类型，2区 号，3邮 编 </returns>
public static string [] getTelldate( string number)
{
try
{
string strSource = GetUrltoHtml( " http://www.ip138.com:8080/search.asp?action=mobile&mobile= " + number.Trim());
// 归属地
strSource = strSource.Substring(strSource.IndexOf(number));
strSource = StripHTML(strSource);
strSource = strSource.Replace( " \r " , "" );
strSource = strSource.Replace( " \n " , "" );
strSource = strSource.Replace( " \t " , "" );
strSource = strSource.Replace( " " , "" );
strSource = strSource.Replace( " --> " , "" );
string [] strnumber = strSource.Split( new string [] { " 归属地 " , " 卡类型 " , " 邮 编 " , " 区 号 " , " 更详细 " , " 卡号 " }, StringSplitOptions.RemoveEmptyEntries);
string [] strnumber1 = null ;
if (strnumber.Length > 4 )
{
strnumber1 = new string [] { strnumber[ 1 ].Trim(), strnumber[ 2 ].Trim(), strnumber[ 3 ].Trim(), strnumber[ 4 ].Trim() };
}
return strnumber1;
}
catch (Exception)
{
return null ;
}
}
/// 输入手机号码得到归属地信息
/// </summary>
/// <param name="number"> 手机号码 </param>
/// <returns> 数组类型0为归属地，1卡类型，2区 号，3邮 编 </returns>
public static string [] getTelldate( string number)
{
try
{
string strSource = GetUrltoHtml( " http://www.ip138.com:8080/search.asp?action=mobile&mobile= " + number.Trim());
// 归属地
strSource = strSource.Substring(strSource.IndexOf(number));
strSource = StripHTML(strSource);
strSource = strSource.Replace( " \r " , "" );
strSource = strSource.Replace( " \n " , "" );
strSource = strSource.Replace( " \t " , "" );
strSource = strSource.Replace( " " , "" );
strSource = strSource.Replace( " --> " , "" );
string [] strnumber = strSource.Split( new string [] { " 归属地 " , " 卡类型 " , " 邮 编 " , " 区 号 " , " 更详细 " , " 卡号 " }, StringSplitOptions.RemoveEmptyEntries);
string [] strnumber1 = null ;
if (strnumber.Length > 4 )
{
strnumber1 = new string [] { strnumber[ 1 ].Trim(), strnumber[ 2 ].Trim(), strnumber[ 3 ].Trim(), strnumber[ 4 ].Trim() };
}
return strnumber1;
}
catch (Exception)
{
return null ;
}
}
这个例子写是不怎么样，些地方是可以简化的，这个接口而且可以直接使用Xml得到，但我在这里的重点是让一些新手看看方法和思路风凉啊，呵呵
第四招，通过Socket访问
------------------------------------------------------------------------------------------------------------
///<summary> /// 请求的公共类用来向服务器发送请求 ///</summary> ///<param name="strSMSRequest">发送请求的字符串</param> ///<returns>返回的是请求的信息</returns> private static string SMSrequest(string strSMSRequest) { byte[] data = new byte[1024]; string stringData = null; IPHostEntry gist = Dns.GetHostByName("www.110.cn"); IPAddress ip = gist.AddressList[0]; //得到IP IPEndPoint ipEnd = new IPEndPoint(ip, 3121); //默认80端口号 Socket socket = new Socket(AddressFamily.InterNetwork, SocketType.Stream, ProtocolType.Tcp); //使用tcp协议 stream类型 try { socket.Connect(ipEnd); } catch (SocketException ex) { return "Fail to connect server\r\n" + ex.ToString(); } string path = strSMSRequest.ToString().Trim(); StringBuilder buf = new StringBuilder(); //buf.Append("GET ").Append(path).Append(" HTTP/1.0\r\n"); //buf.Append("Content-Type: application/x-www-form-urlencoded\r\n"); //buf.Append("\r\n"); byte[] ms = System.Text.UTF8Encoding.UTF8.GetBytes(buf.ToString()); //提交请求的信息 socket.Send(ms); //接收返回 string strSms = ""; int recv = 0; do { recv = socket.Receive(data); stringData = Encoding.ASCII.GetString(data, 0, recv); //如果请求的页面meta中指定了页面的encoding为gb2312则需要使用对应的Encoding来对字节进行转换() strSms = strSms + stringData; //strSms += recv.ToString(); } while (recv != 0); socket.Shutdown(SocketShutdown.Both); socket.Close(); return strSms; }