网页抠图(正则表达式)
using System; using System.Collections.Generic; using System.Linq; using System.Net; using System.Text; using System.Text.RegularExpressions; using System.Threading.Tasks; using System.IO; namespace 网页抠图 { class Program { static void Main(string[] args) { WebClient wc = new WebClient(); for (int i = 0; i < 9; i++) { string page = ""; if (i > 0) { page = "_" + i; } string html = wc.DownloadString("http://gb.cri.cn/42071/2015/03/25/7211s4912740" + page + ".htm"); MatchCollection Matchs = Regex.Matches(html, "<IMG\\ssrc=\"(/mmsource/images/2015/03/25/[0-9]{2}/(\\w+.jpg))\">"); string url = "http://gb.cri.cn"; foreach (Match item in Matchs) { if (item.Success) { //Console.WriteLine(item); //Console.WriteLine(url+item.Groups[1].Value); //Console.WriteLine(Path.Combine(@"E:\img",item.Groups[2].Value)); wc.DownloadFile(url + item.Groups[1].Value, Path.Combine(@"E:\img", item.Groups[2].Value)); Console.Write("*"); } } } Console.WriteLine("下载完成"); Console.ReadKey(); } } }