随手正则写的 CSDN【只看楼主】功能

写这个的时候居然没有看到原来CSDN已经有这个功能了，写完代码了突然发现原来早就已经有了。

现把代码贴出来吧，虽然有很多解析HTML的开源类库如:http://htmlagilitypack.codeplex.com/，但我一直习惯于正则匹配。

截图：

呵呵，起码还能看吧@——#

private void button1_Click(object sender, EventArgs e)
        {
            if (!string.IsNullOrEmpty(txtCsdnUrl.Text.Trim()))
            {
                string url = txtCsdnUrl.Text.Trim();
                string htmlSource = string.Empty;
                htmlSource = GetHtmlSource(url);
                int pageCount = GetPageCount(htmlSource);
                string context = string.Empty;

                if (pageCount > 1)
                {
                    for (int i = 1; i <= pageCount; i++)
                    {
                        htmlSource = GetHtmlSource(url + "?page=" + i);

                       context+= GetLZArticle(htmlSource);
                    }
                }
                else
                {
                    context += GetLZArticle(htmlSource);
                }

                richTextBox1.Text = context;

            }
            else
            {
                MessageBox.Show("请输入地址");
            }
        }

        /// <summary>
        /// 获取源代码
        /// </summary>
        /// <param name="Url"></param>
        /// <returns></returns>
        public string GetHtmlSource(string Url)
        {
            WebClient client = new WebClient();
            client.Headers.Add("user-agent", "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.2; .NET CLR 1.0.3705;)");
            Stream data = client.OpenRead(Url);
            string result = string.Empty;
            using (StreamReader reader = new StreamReader(data, Encoding.UTF8))
            {
                result = reader.ReadToEnd();
            }

            return result;
        }

        /// <summary>
        /// 获取贴子总页数 URL格式:http://bbs.csdn.net/topics/390730011?page=2
        /// </summary>
        /// <returns>返回最大页数</returns>
        public int GetPageCount(string HtmlSource)
        {
            int pageCount = 0;

            Regex reg = new Regex("<select class="jumpMenu" name="jumpMenu">(?<val>.*?)</select>", RegexOptions.Singleline | RegexOptions.IgnoreCase);
            string htmlSource = HtmlSource;
            Regex reg1 = new Regex("<option.*?>(?<val>.*?)</option>", RegexOptions.Singleline | RegexOptions.IgnoreCase);
            int count = reg1.Matches(reg.Match(htmlSource).Groups["val"].Value).Count;

            int.TryParse(reg1.Matches(reg.Match(htmlSource).Groups["val"].Value)[count - 1].Groups["val"].Value,
                         out pageCount);

            return pageCount;
        }

        /// <summary>
        /// 获取文章标题
        /// </summary>
        /// <param name="HtmlSource">网页内容</param>
        /// <returns></returns>
        public string GetArticleTitle(string HtmlSource)
        {
            string title = string.Empty;

            Regex reg = new Regex("<span class="title text_overflow">(?<title>.*?)</span>", RegexOptions.Singleline | RegexOptions.IgnoreCase);

            title = reg.Match(HtmlSource).Groups["title"].Value;

            return title;
        }


        public string GetAuthorName(string HtmlSource)
        {
            string result = string.Empty;

            Regex regex = new Regex("<a class="p-author" href="#">(?<value>.*?)</a>");

            result = regex.Match(HtmlSource).Groups["value"].Value;

            return result;
        }

        public string GetLZArticle(string HtmlSource)
        {

            string result = string.Empty;
            string authorName = GetAuthorName(HtmlSource);

            Regex regex = new Regex("<td valign="top" class="post_info .*?" data-username="" + authorName + "".*?>.*?<div class="post_body">(?<value>.*?)</div>.*?</td>", RegexOptions.Singleline | RegexOptions.IgnoreCase);

            for (int i = 0; i < regex.Matches(HtmlSource).Count; i++)
            {
                result += regex.Matches(HtmlSource)[i].Groups["value"].Value;
                result += "--------------------分隔线--------------------";
            }
            return result.Trim().Replace("<br />","
");
        }

代码都在这里了。