采集博客园asp.net的文章地址实例（上）

05

2013
05

在winform窗体中建立一个RichTextBox，用来显示文章标题和链接地址

private void Form1_Load(object sender, EventArgs e)
{
    //得到采集的全部文章
    List<Article> list = Articles.GetArticles();
    string TextStr = "";
    //通过循环将全部文章遍历
    if (list != null)
    {
        for (int i = 0; i < list.Count; i++)
        {
            Article temp = list[i];
            //将数据输出显示
            if (TextStr.Trim() != "")
            {
                TextStr += "\n";
            }
            TextStr += "标题:" + temp.Title;
            TextStr += "\n链接:" + temp.Url;
            TextStr += "\n阅读次数:" + temp.Views;
            TextStr += "\n作者:" + temp.Author + "\n";
        }
    }
    richTextBox1.Text = TextStr;
}

新建一个类来实现数据的采集，使用正则表达式进行采集！

/// <summary>
/// 文章信息操作类
/// </summary>
public class Articles
{
    #region 采集数据并返回一个集合
    /// <summary>
    /// 采集博客园asp.net文章地址实例（上）
    /// </summary>
    /// <returns>一个装有全部采集数据的集合对象</returns>
    public static List<Entity.Article> GetArticles()
    {
        //泛型集合，用来存入多篇文章信息
        List<Entity.Article> list = new List<Entity.Article>();

        #region 读取网页源代码并提取数据

        //网页操作对象,我用来获取网页源码
        HTML html = new HTML();

//对博客园每日排行数据进行采集
string htmlcode = html.GetHTML("http://www.cnblogs.com/cate/aspnet/","utf-8");

//提取博客园排行文章信息的正则表达式
//Regex regexarticles = new Regex(".+· <a\\s+id=\".+\" href=\"(?<url>.+)\"\\s+target=\"_blank\">(?<title>.+)</a> <span\\s+class=\".+\">\\(阅读:(?<views>\\d+)\\).*\\(评论:(?<reply>\\d+)\\).*\\((?<time>.+)\\)</span>\\s*</td>\\s*<td\\s+height=\"\\d+\">\\s+<a\\s+id=\".+\" href=\"(?<blog>.+)\">(?<author>.+)</a>");

//Regex regexarticles = new Regex("");
Regex regexarticles = new Regex("<div class=\"post_item_body\">\\s+<h3><a class=\"titlelnk\" href=\"(?<url>.+)\" target=\"_blank\">(?<title>.+)</a></h3>\\s+<p class=\"post_item_summary\">\\s+(?<ttt>.+)\\s+</p>\\s+<div class=\"post_item_foot\">\\s+<a href=\"(?<blog>.+)\" class=\"lightblue\">(?<author>.+)</a>\\s+发布于(?<time>.+)\r\\s+<span class=\"article_comment\"><a href=\"(?<url1>.+)\" title=\"(?<time>.+)\" class=\"gray\">\\s+评论((?<reply>.+))</a></span><span class=\"article_view\"><a href=\"(?<url>.+)\" class=\"gray\">阅读(?<views>.+)</a></span></div>\\s+</div>");

        //所有匹配表达式的内容
        MatchCollection marticles = regexarticles.Matches(htmlcode);
        ///遍历匹配内容
        foreach (Match m in marticles)
        {
            Entity.Article test = new Entity.Article();
            test.Category = "博客园asp.net文章";           //设置分类
            test.Title = m.Groups["title"].Value.Trim();       //设置标题
            test.Url = m.Groups["url"].Value.Trim();           //设置连接
            test.Url1 = m.Groups["url1"].Value.Trim();           //设置连接
            test.Views = int.Parse(m.Groups["views"].Value.Trim('(').Trim(')'));    //设置浏览次数
            test.Replys = int.Parse(m.Groups["reply"].Value.Trim('(').Trim(')'));  //设置评论次数
            test.Datatime = m.Groups["time"].Value.Trim();             //设置发布时间
            test.Author = m.Groups["author"].Value.Trim();             //设置作者
            test.Site = m.Groups["blog"].Value.Trim();                 //设置文章出处
            list.Add(test);
        }

Regex regexarticles1 = new Regex("<div class=\"post_item_body\">\\s+<h3><a class=\"titlelnk\" href=\"(?<url>.+)\" target=\"_blank\">(?<title>.+)</a></h3>\\s+<p class=\"post_item_summary\">\\s+(?<ttt>.+)\\s+</p>\\s+<div class=\"post_item_foot\">\\s+<a href=\"(?<blog>.+)\" class=\"lightblue\">(?<author>.+)</a>\\s+发布于(?<time>.+)\r\\s+<span class=\"article_comment\"><a href=\"(?<url1>.+)\" title=\"\" class=\"gray\">\\s+评论((?<reply>.+))</a></span><span class=\"article_view\"><a href=\"(?<url>.+)\" class=\"gray\">阅读(?<views>.+)</a></span></div>\\s+</div>");

        //所有匹配表达式的内容
        MatchCollection marticles1 = regexarticles1.Matches(htmlcode);
        ///遍历匹配内容
        foreach (Match m in marticles1)
        {
            Entity.Article test = new Entity.Article();
            test.Category = "博客园asp.net文章";           //设置分类
            test.Title = m.Groups["title"].Value.Trim();       //设置标题
            test.Url = m.Groups["url"].Value.Trim();           //设置连接
            test.Url1 = m.Groups["url1"].Value.Trim();           //设置阅读连接
            test.Views = int.Parse(m.Groups["views"].Value.Trim('(').Trim(')'));    //设置浏览次数
            test.Replys = int.Parse(m.Groups["reply"].Value.Trim('(').Trim(')'));  //设置评论次数
            test.Datatime = m.Groups["time"].Value.Trim();             //设置发布时间
            test.Author = m.Groups["author"].Value.Trim();             //设置作者
            test.Site = m.Groups["blog"].Value.Trim();                 //设置文章出处
            list.Add(test);
        }
        #endregion