一个简单的网页爬虫例子!

html代码:

<head runat="server">
    <title>c#爬网</title>
</head>
<body>
    <form id="form1" runat="server">
    <div style="margin:0 auto;width:700px">
        <asp:TextBox ID="></asp:TextBox>
        <asp:Button ID="btnStart" runat="server" Text="开始" onclick="btnStart_Click" /><br /><br />
        <textarea id=" runat="server" style="width:700px;height:500px"></textarea>
    </div>
    </form>
</body>
</html>

后台代码:

public partial class _Default : System.Web.UI.Page
    {
        protected void Page_Load(object sender, EventArgs e)
        {
        }
        protected void btnStart_Click(object sender, EventArgs e)
        {
            string url = this.txtUrl.Text.Trim();

            if (!string.IsNullOrEmpty(url))
            {
                WebRequest request = WebRequest.Create(url);
                WebResponse response = request.GetResponse();

                StreamReader reader = new StreamReader(response.GetResponseStream(), Encoding.UTF8);
                string htmlCode = reader.ReadToEnd();//获取整个页面的源码

                //正则,获取<form></form>标签间的内容
                Regex reg = new Regex("(?is)<form[^>]*>(?<form>.*?)</form>");
                this.htmlStr.Value = reg.Match(htmlCode).Groups["form"].Value;
            }
        }
    }

运行效果:

这里输入url地址是本地的

c#网页爬虫初探-LMLPHP

可以看到获取了<form></form>标签间的内容(当然还包括viewstate)。

04-28 17:13