求一正则表达式

Question

<table width="100%" cellpadding="0" cellspacing="1" class="grid">
  <tr align="center">
    <td width="20%" class="head">文章名称</td>
    <td width="40%" class="head">最新章节</td>
    <td width="15%" class="head">作者</td>
<td width="9%" class="head">字数</td>
    <td width="10%" class="head">更新</td>
    <td width="6%" class="head">状态</td>
  </tr>
    <tr>
    <td class="odd"><a href="http://www.33sy.com/shuyuan_info/30/30355.htm">网王同人之三生有幸</a></td>
    <td class="even"><a href="http://www.33sy.com/files/article/book/30/30355/index.html" target="_blank">正文 第一卷 第九章</a></td>
    <td class="odd">嘟小離</td>
<td class="even">17K</td>
    <td class="odd" align="center">09-04-10</td>
    <td class="even" align="center">连载</td>
  </tr>
    <tr>
    <td class="odd"><a href="http://www.33sy.com/shuyuan_info/29/29197.htm">红楼奇梦</a></td>
    <td class="even"><a href="http://www.33sy.com/files/article/book/29/29197/index.html" target="_blank">正文 四十七章</a></td>
    <td class="odd">江南鱼翁</td>
<td class="even">93K</td>
    <td class="odd" align="center">09-04-10</td>
    <td class="even" align="center">连载</td>
  </tr>
    <tr>
    <td class="odd"><a href="http://www.33sy.com/shuyuan_info/30/30539.htm">《狐狸，你在干嘛》</a></td>
    <td class="even"><a href="http://www.33sy.com/files/article/book/30/30539/index.html" target="_blank">正文 第九章 谁是小狗</a></td>
    <td class="odd">笨笨菩提</td>
<td class="even">22K</td>
    <td class="odd" align="center">09-04-10</td>
    <td class="even" align="center">连载</td>
  </tr>
    <tr>
    <td class="odd"><a href="http://www.33sy.com/shuyuan_info/28/28610.htm">&lt;&lt;擦肩而过&gt;&gt;</a></td>
    <td class="even"><a href="http://www.33sy.com/files/article/book/28/28610/index.html" target="_blank">正文 第四十二章 道歉</a></td>
    <td class="odd">kamzxj</td>
<td class="even">91K</td>
    <td class="odd" align="center">09-04-10</td>
    <td class="even" align="center">连载</td>
  </tr>
    <tr>
    <td class="odd"><a href="http://www.33sy.com/shuyuan_info/31/31162.htm">绫罗绸缎</a></td>
    <td class="even"><a href="http://www.33sy.com/files/article/book/31/31162/index.html" target="_blank">正文 民女陌然</a></td>
    <td class="odd">月千寒</td>
<td class="even">3K</td>
    <td class="odd" align="center">09-04-10</td>
    <td class="even" align="center">连载</td>
  </tr>
    <tr>
    <td class="odd"><a href="http://www.33sy.com/shuyuan_info/29/29745.htm">倾世红颜</a></td>
    <td class="even"><a href="http://www.33sy.com/files/article/book/29/29745/index.html" target="_blank">正文 【王显献计策】1</a></td>
    <td class="odd">玉宫</td>
<td class="even">128K</td>
    <td class="odd" align="center">09-04-10</td>
    <td class="even" align="center">连载</td>
  </tr>
    <tr>
    <td class="odd"><a href="http://www.33sy.com/shuyuan_info/29/29552.htm">凤凰错</a></td>
    <td class="even"><a href="http://www.33sy.com/files/article/book/29/29552/index.html" target="_blank">正文 0049</a></td>
    <td class="odd">雨痕愁雾</td>
<td class="even">95K</td>
    <td class="odd" align="center">09-04-10</td>
    <td class="even" align="center">连载</td>
  </tr>
    <tr>
    <td class="odd"><a href="http://www.33sy.com/shuyuan_info/29/29947.htm">绝情龙帝的小七宠妃</a></td>
    <td class="even"><a href="http://www.33sy.com/files/article/book/29/29947/index.html" target="_blank">正文 第042章</a></td>
    <td class="odd">刷新的墙壁</td>
<td class="even">73K</td>
    <td class="odd" align="center">09-04-10</td>
    <td class="even" align="center">连载</td>
  </tr>
    <tr>
    <td class="odd"><a href="http://www.33sy.com/shuyuan_info/30/30429.htm">双猫传奇</a></td>
    <td class="even"><a href="http://www.33sy.com/files/article/book/30/30429/index.html" target="_blank">正文 第十章 谁最温柔？</a></td>
    <td class="odd">猫的温柔</td>
<td class="even">40K</td>
    <td class="odd" align="center">09-04-10</td>
    <td class="even" align="center">连载</td>
  </tr>
    
</table>
我要滤出每一个表格的第一列网址以上表格中有10条附合,但不知道表达式怎么写
<td class="odd"><a href="http://www.33sy.com/shuyuan_info/30/30355.htm">网王同人之三生有幸</a></td>就是将每一行的第一列的网址滤出来如上,要的结果是http://www.33sy.com/shuyuan_info/30/30355.htm

Answer 1

"(?<=<tr[^>]*>\\s*<td[^>]*>\\s*<a.*?href=\")[^\"]+(?=\">)"  // 应该有九个吧

Answer 2

"(?is)(?<=<tr[^>]*>\\s*<td[^>]*>\\s*<a.*?href=\")[^\"]+(?=\">)"  
// 应该有九个吧

Answer 3

一定要正则吗?
我以前一个处理HTTP代码用的.你看看string[] fileUrl = Exstring.GetInsideStr("代码文件","<td class=\"odd\"> <a href=\"","\">");
    /// <summary>
    /// 扩展字符串处理
    /// </summary>
    public class ExString
    {
        /// <summary>
        /// 获取该文字出现的次数
        /// </summary>
        /// <param name="str">需要查找的主体文档</param>
        /// <param name="pointStr">关键文字</param>
        /// <returns>次数</returns>
        public static int GetStrTime(string str,string pointStr)
        {
            int result = -1;//统计总数
            int nowpoint = 0;//计算当前位置
            while (nowpoint != -1)
            {
                result++;
                if (nowpoint == 0)
                    nowpoint = str.IndexOf(pointStr);
                else
                    nowpoint = str.IndexOf(pointStr, nowpoint + 1);
            }
            return result;
        }        #region 获取某两个字符串里面的所有字符串
        /// <summary>
        /// 获取某两个字符串里面的所有字符串
        /// 前后标志字符不可一样
        /// </summary>
        /// <param name="str">主体文档</param>
        /// <param name="strA">前面的字符串</param>
        /// <param name="strB">后面的字符串</param>
        /// <returns>夹在中间的字符串集</returns>
        public static string[] GetInsideStr(string str, string strA, string strB)
        {
            int A = 0, B = 0;
            int AL = strA.Length;
            int BL = strB.Length;
            System.Collections.ArrayList forsave = new System.Collections.ArrayList();
            while (true)
            {
                if (B == 0) 
                    A = str.IndexOf(strA);
                else
                    A = str.IndexOf(strA, B + BL);//从上个B结尾处开始找A                
                if (A != -1)//有可能A为-1
                {
                    B = str.IndexOf(strB, A + AL);//从上面的A后面开始找B
                    if (B != -1)
                    {
                        A = str.LastIndexOf(strA, B);//从B往前找A 位置确定AB间
                        forsave.Add(str.Substring(A + AL, B - A - AL));
                    }
                    else
                        break;
                }
                else
                    break;
            }
            string[] result = (string[])forsave.ToArray(typeof(string));
            return result;
        }
        /// <summary>
        /// 获取某两个字符串里面的所有字符串
        /// 前后标志字符不可一样
        /// </summary>
        /// <param name="str">主体文档</param>
        /// <param name="strA">前面的字符串</param>
        /// <param name="offsetA">前面的偏移位置数(往右)</param>
        /// <param name="strB">后面的字符串</param>
        /// <param name="offsetB">后面的偏移位置数(往右)</param>
        /// <returns>夹在中间的字符串集</returns>
        public static string[] GetInsideStr(string str, string strA, int offsetA, string strB, int offsetB)
        {
            int A = 0, B = 0;
            int AL = strA.Length + offsetA;
            int BL = strB.Length + offsetB;
            System.Collections.ArrayList forsave = new System.Collections.ArrayList();
            while (true)
            {
                if (B == 0)
                    A = str.IndexOf(strA);
                else
                    A = str.IndexOf(strA, B + BL);//从上个B结尾处开始找A
                if (A != -1)//有可能A为-1
                {
                    B = str.IndexOf(strB, A + AL);//从上面的A后面开始找B
                    if (B != -1)
                    {
                        A = str.LastIndexOf(strA, B);//从B往前找A 位置确定AB间
                        forsave.Add(str.Substring(A + AL, B - A - AL));
                    }
                    else
                        break;
                }
                else
                    break;
            }
            string[] result = (string[])forsave.ToArray(typeof(string));
            return result;
        }
        /// <summary>
        /// 获取某两个字符串里面的所有字符串
        /// 前后标志字符不可一样
        /// </summary>
        /// <param name="getindex">获取第几个匹配的字符(无则返回null)</param>
        /// <param name="str">主体文档</param>
        /// <param name="strA">前面的字符串</param>
        /// <param name="strB">后面的字符串</param>
        /// <returns>夹在中间的字符串集</returns>
        public static string GetInsideStr(int getindex,string str, string strA, string strB)
        {
            int A = 0, B = 0;
            int AL = strA.Length;
            int BL = strB.Length;
            System.Collections.ArrayList forsave = new System.Collections.ArrayList();
            while (true)
            {
                if (B == 0)
                    A = str.IndexOf(strA);
                else
                    A = str.IndexOf(strA, B + BL);//从上个B结尾处开始找A                
                if (A != -1)//有可能A为-1
                {
                    B = str.IndexOf(strB, A + AL);//从上面的A后面开始找B
                    if (B != -1)
                    {
                        A = str.LastIndexOf(strA, B);//从B往前找A 位置确定AB间
                        forsave.Add(str.Substring(A + AL, B - A - AL));
                    }
                    else
                        break;
                }
                else
                    break;
            }
            string[] result = (string[])forsave.ToArray(typeof(string));
            try
            {
                return result[getindex - 1];
            }
            catch
            {
                return null;
            }
        }
        /// <summary>
        /// 获取某两个字符串里面的所有字符串
        /// 前后标志字符不可一样
        /// </summary>
        /// <param name="str">主体文档</param>
        /// <param name="getindex">获取第几个匹配的字符(无则返回null)</param>
        /// <param name="strA">前面的字符串</param>
        /// <param name="offsetA">前面的偏移位置数(往右)</param>
        /// <param name="strB">后面的字符串</param>
        /// <param name="offsetB">后面的偏移位置数(往右)</param>
        /// <returns>夹在中间的字符串集</returns>
        public static string GetInsideStr(int getindex, string str, string strA
            , int offsetA, string strB, int offsetB)
        {
            int A = 0, B = 0;
            int AL = strA.Length + offsetA;
            int BL = strB.Length + offsetB;
            System.Collections.ArrayList forsave = new System.Collections.ArrayList();
            while (true)
            {
                if (B == 0)
                    A = str.IndexOf(strA);
                else
                    A = str.IndexOf(strA, B + BL);//从上个B结尾处开始找A
                if (A != -1)//有可能A为-1
                {
                    B = str.IndexOf(strB, A + AL);//从上面的A后面开始找B
                    if (B != -1)
                    {
                        A = str.LastIndexOf(strA, B);//从B往前找A 位置确定AB间
                        forsave.Add(str.Substring(A + AL, B - A - AL));
                    }
                    else
                        break;
                }
                else
                    break;
            }
            string[] result = (string[])forsave.ToArray(typeof(string));
            try
            {
                return result[getindex - 1];
            }
            catch
            {
                return null;
            }
        }
        #endregion
    }

Answer 4

            Regex re = new Regex("(?is)(?<=<tr[^>]*>\\s*<td[^>]*>\\s*<a.*?href=\")[^\"]+(?=\">)");
            Match m = re.Match(input);
            while (m.Success)
            {
                Console.WriteLine(m.Value);
                m = m.NextMatch();
            }// 我是这样用的 是可以的