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
asp.net图片加水印
Asp.Net中页面运行时动态载入的UserControl内元素的事
ASP.NET底层架构探索之再谈.NET运行时(二)
借助封装类实现线程调用带参方法
面向对象设计思想(C#)
asp.net URL重写(URLRewriter) 简化版
GUID在.net里的使用,就用System.Guid结构
不要忽略c#中的using和as操作符
C#中ref和out的使用小结
C#的Web XML编程
asp.net2.0下 如何实现服务器端压缩包自解压
javascript如何调用C#后台代码中的过程 和ASP.NET调用
在ASP.NET中自动给URL加上超链接
ASP.NET 中处理页面“回退”的方法
ASP.NET的四种错误机制
asp.net跳转页面的三种方法比较
ASP.NET2.0中将GridView导出到Excel文件中
ASP.NET 2.0中GridView无限层复杂表头的实现
ASP.NET 2.0 中动态添加 GridView 模板列
十天学会ASP.net之第一天

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: 68 ::
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;
}