当前位置: 首页 > 图文教程 > 网络编程 > ASP.NET > asp.net HttpWebRequest自动识别网页编码

ASP.NET
LINQ学习笔记:元素操作符
LINQ学习笔记:聚合方法
LINQ学习笔记:量词
LINQ学习笔记:创建方法
LINQ学习笔记:LINQ to XML
LINQ学习笔记:X-DOM概览
LINQ学习笔记:实例化一个X-DOM
LINQ学习笔记:导航和查询X-DOM
LINQ学习笔记:更新一个X-DOM
LINQ学习笔记:string类型的Value属性
LINQ学习笔记:XML命名空间
LINQ学习笔记:投射到X-DOM
C#教程:声明和调用扩展方法
C#教程:没有扩展方法的日子
C#教程:lambda表达式转换成表达式树
C#教程:编程方式构建表达式树
C#教程:使用lambda表达式记录事件日志
C#教程:作为委托的Lambda表达式
C#教程:关于匿名类型的特性
C#教程:隐式类型数组

ASP.NET 中的 asp.net HttpWebRequest自动识别网页编码


出处:互联网   整理: 软晨网(RuanChen.com)   发布: 2009-09-13   浏览: 231 ::
收藏到网摘: n/a

HttpWebRequest获取网页源代码时自动识别网页编码,通过读取页面中的charset和读取http头中的编码信息获取页面的编码,基本可以正确获取网页编码

复制代码 代码如下:

static string GetEncoding(string url)
{
HttpWebRequest request = null;
HttpWebResponse response = null;
StreamReader reader = null;
try
{
request = (HttpWebRequest)WebRequest.Create(url);
request.Timeout = 20000;
request.AllowAutoRedirect = false;
response = (HttpWebResponse)request.GetResponse();
if (response.StatusCode == HttpStatusCode.OK && response.ContentLength < 1024 * 1024)
{
if (response.ContentEncoding != null && response.ContentEncoding.Equals("gzip", StringComparison.InvariantCultureIgnoreCase))
reader = new StreamReader(new GZipStream(response.GetResponseStream(), CompressionMode.Decompress));
else
reader = new StreamReader(response.GetResponseStream(), Encoding.ASCII);
string html = reader.ReadToEnd();
Regex reg_charset = new Regex(@"charset\b\s*=\s*(?<charset>[^""]*)");
if (reg_charset.IsMatch(html))
{
return reg_charset.Match(html).Groups["charset"].Value;
}
else if (response.CharacterSet != string.Empty)
{
return response.CharacterSet;
}
else
return Encoding.Default.BodyName;
}
}
catch
{
}
finally
{
if (response != null)
{
response.Close();
response = null;
}
if (reader != null)
reader.Close();
if (request != null)
request = null;
}
return Encoding.Default.BodyName;
}
/// <summary>
/// 获取源代码
/// </summary>
/// <param name="url"></param>
/// <returns></returns>
static string GetHtml(string url, Encoding encoding)
{
HttpWebRequest request = null;
HttpWebResponse response = null;
StreamReader reader = null;
try
{
request = (HttpWebRequest)WebRequest.Create(url);
request.Timeout = 20000;
request.AllowAutoRedirect = false;
response = (HttpWebResponse)request.GetResponse();
if (response.StatusCode == HttpStatusCode.OK && response.ContentLength < 1024 * 1024)
{
if (response.ContentEncoding != null && response.ContentEncoding.Equals("gzip", StringComparison.InvariantCultureIgnoreCase))
reader = new StreamReader(new GZipStream(response.GetResponseStream(), CompressionMode.Decompress), encoding);
else
reader = new StreamReader(response.GetResponseStream(), encoding);
string html = reader.ReadToEnd();
return html;
}
}
catch
{
}
finally
{
if (response != null)
{
response.Close();
response = null;
}
if (reader != null)
reader.Close();
if (request != null)
request = null;
}
return string.Empty;
}