c#通用正则解析代码，抓取数据无需再写正则

比如一段html:

<td>t1</td>
<td>t2</td>
<td>t3</td>

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

/// <summary>
        /// 返回匹配多个的集合值
        /// </summary>
        /// <param name="start">开始html tag</param>
        /// <param name="end">结束html tag</param>
        /// <param name="html">html</param>
        /// <returns></returns>
        public static List<string> GetHtmls(string start, string end, string html)
        {
            IList list = new List<string>();
            try
            {
                string pattern = string.Format("{0}(?<g>(.|[\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}(?<g>(.|[\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;
        }

转载于:https://www.cnblogs.com/changyou/archive/2010/01/09/1643200.html