<div class="post_item">
="digg">
    ="diggit" onclick="DiggIt(3439076,120879,1)"> 
    span ="diggnum" id="digg_count_3439076">4</spandiv="clear"></@H_108_404@>    
    id="digg_tip_3439076" class="digg_tip">      
="post_item_body"h3><a ="titlelnk" href="http://www.cnblogs.com/swq6413/p/3439076.html" target="_blank">分享完整的项目工程目录结构a>                   
    p ="post_item_summary"href="http://www.cnblogs.com/swq6413/"img width="48" height="pfs" src="http://pic.cnitblog.com/face/142964/20131116170946.png" alt=""/></@H_108_404@>    在项目开发过程中，如何有序的保存项目中的各类数据文件，建立一个分类清晰、方便管理的目录结构是非常重要的。 综合以前的项目和一些朋友的项目结构，我整理了一份我觉得还不错的项目目录结构。 在这里分享给大家，欢迎各位提出你宝贵的意见和建议。如果喜欢请“推荐”则个，感激万分！！ 整个目录设置到4级子目录，实... 
    p>              
    ="post_item_foot">                    
    ="lightblue">七少爷> 
    发布于 2013-11-23 15:48 
    ="article_comment"="http://www.cnblogs.com/swq6413/p/3439076.html#commentform" title="2013-11-23 16:40"="gray">
        评论(4)="article_view">阅读(206)>

    class Program
    {
        static void Main(string[] args)
        {
         
            string content = HttpUtility.HttpGetHtml();
            HttpUtility.GetArticles(content);
        }
    }

    internal class HttpUtility
    {
        //默认获取第一页数据
        public string HttpGetHtml()
        {
            HttpWebRequest request = (HttpWebRequest)WebRequest.Create("http://www.cnblogs.com/");
            request.Accept = text/plain,*/*; q=0.01";
            request.Method = GET";
            request.Headers.Add(Accept-Language",zh-cn,zh;q=0.8,en-us;q=0.5,en;q=0.3");
            request.ContentLength = 0;
           
            request.Host = www.cnblogs.com";
            request.UserAgent = Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.1 (KHTML,like Gecko) Maxthon/4.1.3.5000 Chrome/26.0.1410.43 Safari/537.1";
            HttpWebResponse response = (HttpWebResponse)request.GetResponse();
            Stream responStream = response.GetResponseStream();
            StreamReader reader = new StreamReader(responStream,Encoding.UTF8);
            string content = reader.ReadToEnd();
            return content;

        }

        static List<Article> GetArticles(string htmlString)
        {
            List<Article> articleList = new List<Article>();
            Regex regex = null;
            Article article = null;
            regex = new Regex(<div class=\"post_item\">(?<content>.*?)(?=<div class=\"clear\">" + @"</div>\s*</div>)",RegexOptions.Singleline);

            if (regex.IsMatch(htmlString))
            {
                MatchCollection aritcles = regex.Matches(htmlString);

                foreach (Match item in aritcles)
                {
                    article = new Article();
                    取推荐
                    regex =
                        new Regex(
                            <div class=\"digg\">.*<span.*>(?<digNum>.*)</span>" +
                            .*<div class=\"post_item_body\">digNum"].Value;

                    取文章标题 需要去除转义字符
                    regex = <h3>(?<a>.*)</h3>string a = regex.Match(item.Value).Groups[a"].Value;
                    regex = <a\\s.*href=\"(?<href>.*?)\".*>(?<summary>.*)</a>href"].Value;
                    article.AritcleTitle = regex.Match(a).Groups[summary取作者图片 
                    regex = <a.*>(?<img><img[^>].*>)</a>img取作者博客URL及链接的target属性
                    regex = <a\\s*?href=\"(?<href>.*)\"\\s*?target=\"(?<target>.*?)\">.*</a>"].Value;
                    string urlTarget = regex.Match(item.Value).Groups[target取文章简介
                    1 先取summary Div中所有内容
                    regex = <p class=\"post_item_summary\">(?<summary>.*)</p>@H_108_404@string summary = regex.Match(item.Value).Groups[2 取简介
                    regex = (?<indroduct>(?<=</a>).*)indroduct"].Value;


                    取发布人与发布时间
                    regex =
                        <div class=\"post_item_foot\">\\s*<a.*?>(?<publishName>.*)</a>(?<publishTime>.*)<span class=\"article_comment\">publishName"].Value;
                    article.PublishTime = regex.Match(item.Value).Groups[publishTime"].Value.Trim();

                    取评论数
                    regex =
                        <span class=\"article_comment\"><a.*>(?<comment>.*)</a></span><span class=\"article_view\">comment取阅读数
                    regex = <span\\s*class=\"article_view\"><a.*>(?<readNum>.*)</a>readNum"].Value;
                    articleList.Add(article);
                }

            }
            return articleList;
        }



        string ClearSpecialTag(string htmlString)
        {

            string htmlStr = Regex.Replace(htmlString,0); line-height:1.5!important">\n"",RegexOptions.IgnoreCase);
            htmlStr = Regex.Replace(htmlStr,0); line-height:1.5!important">\t\r\"'return htmlStr;
        }
    }

    class Article
    {
        /// <summary>
        /// 文章标题
        </summary>
        string AritcleTitle { get; set; }
         文章链接
        @H_108_404@string AritcleUrl {  文章简介
        @H_108_404@string AritcleInto {  作者名
        @H_108_404@string Author {  作者地址
        @H_108_404@string AuthorUrl {  作者图片
        @H_108_404@string AuthorImg {  发布时间
        @H_108_404@string PublishTime {  推荐数
        @H_108_404@string DiggNum { set; }

         评论数
        @H_108_404@string CommentNum {  阅读数
        @H_108_404@string ReadNum { set; }

    }