今天闲着没事看了看使用正则的使用,之前只是用来做验证,第一次用来抓取网页,
抓去了博客园首页几个分页的推荐文章列表。。。。
代码很简单就不做解释了,肯定做得不严谨,主要是熟悉下几个正则类和用于抓取网页内容的方法。。。
using System;using System.Web;using System.Web.UI;using System.Text.RegularExpressions;using System.Net;using System.IO;public partial class test : Page {public int g=0;public string dfdf = "";void Page_Load(object sender, System.EventArgs e) {for (int i = 2; i <10; i++) { WebRequest rque = WebRequest.Create("http://www.cnblogs.com/p"+i.ToString()); WebResponse utxt = rque.GetResponse(); Stream str = utxt.GetResponseStream(); StreamReader sread = new StreamReader(str, System.Text.Encoding.UTF8);string pram = @"<h3><a class=""titlelnk"" href=""(.*?)"" target=""_blank"">(.*?)</a>"; MatchCollection m = Regex.Matches(sread.ReadToEnd(), pram);foreach (Match ms in m) { g += 1; dfdf = dfdf + ms.Groups[1].Value.ToString() + ms.Groups[2].Value.ToString() + "<br/><br/><br/><br/><br/>"; } } Response.Write("总记录数:"+g.ToString()+"<br/>"+dfdf); }}转载于:https://www.cnblogs.com/sishahu/archive/2012/01/18/2325326.html
