步步为营-19-正则表达式的简单应用
说明:现在我想查看博客园中,我都写了哪些随笔,都是什么时间写的.做一个数据的采集分析
using System; using System.Collections.Generic; using System.Linq; using System.Net; using System.Text; using System.Text.RegularExpressions; using System.Threading.Tasks; namespace 博客园统计 { class Program { static void Main(string[] args) { WebClient web = new WebClient(); byte[] buffer = web.DownloadData(@"http://www.cnblogs.com/YK2012/"); string html = Encoding.UTF8.GetString(buffer); MatchCollection mc = Regex.Matches(html, @"<a.+?homepage1.+?DayList.+?html.+?>(?<title>.+)</a>"); MatchCollection name = Regex.Matches(html,@"@\s(?<time>.+)逍遥小天狼"); Console.WriteLine("一共有{0}篇文章",mc.Count); for (int i = 0; i < mc.Count; i++) { if (mc.Count>0 && name.Count>0) { Console.WriteLine(mc[i].Groups["title"]); Console.WriteLine(name[i].Groups["time"]); } } Console.Read(); } } }