C#提取网页数据正则表达式二

            string regstr = @"(?i)(?<=<td.*?.*?>)[^<]+(?=</td>)"; //提取td的文字           
            string regstr = @"<a\s+href=(?<url>.+?)>(?<content>.+?)</a>";   //提取链接的内容
            string regstr = @"<td.+?><a\s+href=(?<url>.+?)>(?<content>.+?)</a></td>";  //提取TD中链接的内容
            string regstr = @"<td.+?><span.+?>(?<content>.+?)</span></td>";  //提取TD中span的内容
            string regstr = @"<td.+?>(?<content>.+?)</td>";   //获取TD之间所有的内容
            string regstr = @"<td>(?<content>.+?)-<font color=#0000ff>推荐</font></td>"; //获取内容

正则替换：

一循环内替换：

            string regstr = @"(?i)[\<]td.*?[\>].*?(</td>)"; //提取页面所有TD内容
            string regReplace = @"(?i)[\<]td.*?[\>]";    //将所有<td......> 替换成<td>

            Regex reg = new Regex(regstr, RegexOptions.IgnoreCase | RegexOptions.Singleline);
            MatchCollection mc = reg.Matches(data);
            foreach (Match m in mc)
            {
                Console.WriteLine(m.Groups[0].ToString());
                Console.WriteLine("------------------------------");
                string s = Regex.Replace(m.Groups[0].ToString(), regReplace, "<td>", RegexOptions.IgnoreCase);
             Console.WriteLine(s);
               
            }

二统一替换

                 string regstr = @"(?i)[\<]td.*?[\>].*?(</td>)"; //提取页面所有TD内容
            string regReplace = @"(?i)[\<]td.*?[\>]";    //将所有<td......> 替换成<td>

            Regex reg = new Regex(regstr, RegexOptions.IgnoreCase | RegexOptions.Singleline);           
            string s = Regex.Replace(data, regReplace, "<td>", RegexOptions.IgnoreCase);
            MatchCollection mc = reg.Matches(s);
            foreach (Match m in mc)
            {
             
                Console.WriteLine(m.Groups[0].ToString());
                Console.WriteLine("------------------------------");
               
                       
            }