获取页面编码的方法

1,通过分析Header提取编码。

WebRequest webRequest = WebRequest.Create(url);
HttpWebResponse webResponse = (HttpWebResponse)webRequest.GetResponse();
Regex reg_charset = new Regex(@"charsets*=s*(?<charset>[^""]*)") ;
WebHeaderCollection headers = webResponse.Headers;
string encodingName = string.Empty;
string contentType = headers["Content-Type"];
if (contentType.IndexOf("charset") > 0 && reg_charset.IsMatch(ContentType))
{
       encodingName = reg_charset.Match(contentType).Groups["charset"].Value;
}

引用地址 http://blog.useasp.net/default.aspx

2. 通过网页分析

//获取页面
                            string strResult = Encoding.Default.GetString(e.Result);
 
                            const string regCharset = "(<meta[^>]*charset=(?<charset>[^>'"]*)[\s\S]*?>)|(xml[^>]+encoding=("|')*(?<charset>[^>'"]*)[\s\S]*?>)";

                            var r = new Regex(regCharset, RegexOptions.IgnoreCase);
                            var m1 = r.Match(strResult);
                            string encodingName = (m1.Captures.Count != 0) ? m1.Groups["charset"].Value : "";

                            if (string.IsNullOrEmpty(encodingName))
                            {
                                //如果未获取  这手动替换判断
                                string str = m1.Groups[1].Value;
                                const string pattern = "<meta charset="|">|" />";
                                encodingName = Regex.Replace(str, pattern, "");

                            }