Asp.Net正则获取页面a标签里的内容

Asp.Net正则获取页面a标签里的内容

　　　　string url = "http://www.114369.com";
        string html = MyCLib.NetClass.SendUrl(url,System.Text.Encoding.UTF8);
        List<string> keywords = new List<string>();
        Regex reg = new Regex(@"(?is)<a[^>]*?href=(['""]?)(?<url>[^'""s>]+)1[^>]*>(?<text>(?:(?!</?a).)*)</a>");
        MatchCollection mc = reg.Matches(html);
        foreach (Match m in mc)
        {
            //richTextBox2.Text += m.Groups["url"].Value + "
";
            string keyword = Regex.Replace(m.Groups["text"].Value, "<[^>]*>", string.Empty).Replace("..", "").Replace("·", "").Replace("&nbsp;", "");

            if (keyword.Length > 0 && !keywords.Contains(keyword)) 
            {
                keywords.Add(keyword);
            }
        }
        for (int i = 0; i < keywords.Count; i++)
        {
            Response.Write(keywords[i]);
            Response.Write("<br>");
        }

 Asp.Net正则过滤超链接a

string s = "<a href="#">我们是中国人</a><a class='xxx' href="#">我们是中国人2</a>";
        Regex reg = new Regex(@"<as*[^>]*>([sS]+?)</a>", RegexOptions.IgnoreCase);
        s = reg.Replace(s, "$1");
        Response.Write(s);//结果：我们是中国人我们是中国人2

js正则过滤超链接a

string s = "<a href="#">我们是中国人</a><a class='xxx' href="#">我们是中国人2</a>";

s = s.replace(/(</?a[^>]*>)(?!.*1)/ig,"");