.net处理页面的抓取数据

昵称10504424 2014-05-07

展开全文

//要抓取数据的页面路径
       string url = "http://www./banshi/used-car/lower-secondary-education/middle-school-list/1381286867.shtml";
       //将页面上的数据转换为HTML
        string html = Method.GetHtmlData(url);
        //   txt_content.Text = html;
        //找到需要的数据匹配正则 (?<name>.+?)
        string regex = @"<font size=""2"">(?<name>.+?)</td>";
        Regex listRegex = new Regex(regex, RegexOptions.Multiline | RegexOptions.IgnoreCase);
        //得到匹配的数据集合
        MatchCollection mc = listRegex.Matches(html);
        JCheng.Model.School Model = new JCheng.Model.School();
        //将得到的字符串分割存进数组
        string[] str = txt_content.Text.Substring(0, txt_content.Text.Length - 1).Replace("<br />", "").Split(',');
        //数据每六个为一个model类，如下循环添加入库。
        for (int i = 0; i < str.Length - 1; )
        {
            Model.sName = str[i];
            Model.sAddress = str[i + 1];
            Model.sPostCode = str[i + 2];
            Model.sPhone = str[i + 3];
            Model.sEmail = str[i + 4];
            Model.sClass = str[i + 5];
            new JCheng.BLL.School().Add(Model);
            i += 6;
        }