|
|
另外一位网友空间/IV提供的代码，功能同HttpWebRequest获取网页源代码时自动识别网页编码
复制代码 代码如下:
using System;
using System.Net;
using System.Text;
using System.Text.RegularExpressions;
class Program
{
// 获取网页的HTML内容，根据网页的charset自动判断Encoding
static string GetHtml(string url)
{
return GetHtml(url, null);
}
// 获取网页的HTML内容，指定Encoding
static string GetHtml(string url, Encoding encoding)
{
byte[] buf = new WebClient().DownloadData(url);
if (encoding != null) return encoding.GetString(buf);
string html = Encoding.UTF8.GetString(buf);
encoding = GetEncoding(html);
if (encoding == null || encoding == Encoding.UTF8) return html;
return encoding.GetString(buf);
}
// 根据网页的HTML内容提取网页的Encoding
static Encoding GetEncoding(string html)
{
string pattern = @"(?i)\bcharset=(?<charset>[-a-zA-Z_0-9]+)";
string charset = Regex.Match(html, pattern).Groups["charset"].Value;
try { return Encoding.GetEncoding(charset); }
catch (ArgumentException) { return null; }
}
// 程序入口
static void Main()
{
Console.WriteLine(GetHtml(//www.jb51.net));
Console.Read();
}
}
|
|
发表于 2008-9-10 01:03:15
