c#通用正则解析代码,抓取数据无需再写正则_I Miss You AS I love Yo...

来源:百度文库 编辑:神马文学网 时间:2024/04/29 07:33:00
2010-05-05 22:00

比如一段html:

t1
t2
t3

我们想取出与之间的值,使用如下捕获组正则即可达到要求:
调用:GetHtmls(“”, “”, html)

/// 
/// 返回匹配多个的集合值
///

/// 开始html tag
/// 结束html tag
/// html
///
public static List GetHtmls(string start, string end, string html)
{
IList list = new List();
try
{
string pattern = string.Format("{0}(?(.|[\r\n])+?){1}", start, end);//匹配URL的模式,并分组
MatchCollection mc = Regex.Matches(html, pattern);//满足pattern的匹配集合
if (mc.Count != 0)
{
foreach (Match match in mc)
{
GroupCollection gc = match.Groups;
list.Add(gc["g"].Value);
}
}
}
catch {}
return list;
}

对于单组,可以:

public static string GetHtml(string start, string end, string html)
{
string ret = string.Empty;
try
{
string pattern = string.Format("{0}(?(.|[\r\n])+?)?{1}", start, end);//匹配URL的模式,并分组
ret= Regex.Match(html, pattern).Groups["g"].Value;

}
catch { }

return ret;
}
 
http://www.cnblogs.com/changyou/archive/2010/01/09/1643200.html