asp.net 抓取新闻
前台页面：
<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd"> <html xmlns="http://www.w3.org/1999/xhtml"> <head id="Head1" runat="server"> <title></title> <script type="text/javascript" src="http://code.jquery.com/jquery-1.7.2.js"></script> </head> <body> <form id="form1" runat="server"> <div> <asp:Panel ID="Panel1" runat="server"> 网址：<asp:TextBox ID="txtUrl" runat="server"></asp:TextBox> <asp:Button ID="btnGet" runat="server" Text="RSS" OnClick="btnGet_Click" /> </asp:Panel> </div> </form> </body> </html>
后台代码：
using System;
using System.Collections.Generic;
using System.Linq;
using System.Web;
using System.Web.UI;
using System.Web.UI.WebControls;
using System.Text;
using System.Net;
using System.Text.RegularExpressions;
public partial class Default7 : System.Web.UI.Page
{
protected void Page_Load(object sender, EventArgs e)
{
}
protected void btnGet_Click(object sender, EventArgs e)
{
string strurl = txtUrl.Text.ToString(); //欲获取的网页地址 要 http://
WebClient myWebClient = new WebClient(); //创建WebClient实例myWebClient
//获取或设置用于对向 Internet 资源的请求进行身份验证的网络凭据。
myWebClient.Credentials = CredentialCache.DefaultCredentials;
//从资源下载数据并返回字节数组。（加@是因为网址中间有"/"符号）
byte[] pagedata = myWebClient.DownloadData(@strurl);
//string result = Encoding.Default.GetString(pagedata); //如果获取网站页面采用的是GB2312，则使用这句
string result = Encoding.GetEncoding("GB2312").GetString(pagedata); //如果获取网站页面采用的是UTF-8，则使用这句
Regex regex = new Regex("<div class=\"mark\">([\\s\\S]*)</div>([\\s\\S]*)<div id=\"ajax_page\">", RegexOptions.Compiled);
Match match= regex.Match(result);
if (match.Success)
{
result = match.Groups[0].Value;
}
Response.Write(result); //在WEB页中显示获取的内容
Panel1.Visible = false;
}
/// <summary>
/// 返回分析数据
/// </summary>
/// <param name="regexString">正则</param>
/// <param name="html">HTML</param>
/// <param name="group">分组长度</param>
/// <returns>数据</returns>
//public List<string> GetData(string regexString, string html, int group)
//{
// List<string> result = new List<string>();
// Regex regex = new Regex(regexString, RegexOptions.IgnoreCase);
// MatchCollection mc = regex.Matches(html);
// for (int count = 0; count < mc.Count; count++)
// {
// Match m = mc[count];
// for (int index = 0; m.Groups[index].Value != ""; index++)
// {
// string value = m.Groups[index].Value;
// if (count % group != 2)
// value = Regex.Replace(value, "&", "");
// if (value == "")
// {
// result.RemoveRange((result.Count / group) * group, result.Count % group);
// count = (count / group) * group + group - 1;
// break;
// }
// result.Add(value);
// }
// }
// return result;
//}
/// <summary>
/// 返回分析数据
/// </summary>
/// <param name="regexString">正则</param>
/// <param name="html">HTML</param>
/// <returns>数据</returns>
public List<string> GetData(string regexString, string html)
{
List<string> result = new List<string>();
Regex regex = new Regex(regexString, RegexOptions.IgnoreCase);
MatchCollection mc = regex.Matches(html);
for (int count = 0; count < mc.Count; count++)
{
Match m = mc[count];
for (int index = 0; m.Groups[index].Value != ""; index++)
{
result.Add(m.Groups[index].Value);
}
}
return result;
}
}
