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
运行时修改Web.config中的元素值
优秀的Architect之路(入门)
提问的智慧(HowToAskQuestionsTheSmartWay)
C#数据结构篇(3队列类)
现在就可下载WTL7.0和.NETSP1
在.NET中开发组件
使用.NET远程处理访问其他应用程序域中的对象
使用ADO.NET访问数据库
承载.NET公共语言运行库
在.NET运行时了解类型信息(2)
在.NET运行时了解类型信息(3)
智能客户端(SmartClient)
获取数据库表结构
Visual Studio 2005 分包下载
为DataGrid中的行增加序号
关于HttpContext的Items属性
[推荐].NET XML Best Practices - Choosing an XML API
在 XML Schema和WSDL中使用名称空间
在论坛里为什么不能发问题
AspectSharp例子分析

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: 164 ::
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;
}