采集项目中,因为经常会碰到中文的url,需要对整个url进行编码
呵呵,代码最能说明问题,大家看吧
System.Text.RegularExpressions.MatchEvaluator me = new System.Text.RegularExpressions.MatchEvaluator(cnUrlEncode);
string url = "http://community.csdn.net/中国人/Expert/中topic/5114/国5114234.xml?temp=.4305384人";
string urla = "http://community.csdn.net/Expert/topic/5114/5114234.xml?temp=.4305384";
url = System.Text.RegularExpressions.Regex.Replace(url, "([\u4e00-\u9fa5])",me);
string url = "http://community.csdn.net/中国人/Expert/中topic/5114/国5114234.xml?temp=.4305384人";
string urla = "http://community.csdn.net/Expert/topic/5114/5114234.xml?temp=.4305384";
url = System.Text.RegularExpressions.Regex.Replace(url, "([\u4e00-\u9fa5])",me);
委托
private string cnUrlEncode(System.Text.RegularExpressions.Match m)
{
return System.Web.HttpUtility.UrlEncode(m.Groups[1].Value, System.Text.Encoding.Default);
}
{
return System.Web.HttpUtility.UrlEncode(m.Groups[1].Value, System.Text.Encoding.Default);
}