基本信息
源码名称:C# 通过正则采集某网站的图片数据
源码大小:0.04M
文件格式:.rar
开发语言:C#
更新时间:2017-11-03
   友情提示:(无需注册或充值,赞助后即可获取资源下载链接)

     嘿,亲!知识可是无价之宝呢,但咱这精心整理的资料也耗费了不少心血呀。小小地破费一下,绝对物超所值哦!如有下载和支付问题,请联系我们QQ(微信同号):78630559

本次赞助数额为: 2 元 
   源码介绍


using System;
using System.Collections.Generic;
using System.IO;
using System.Linq;
using System.Net;
using System.Text;
using System.Text.RegularExpressions;
using System.Threading.Tasks;

namespace 正则提取
{
    class Program
    {
        private static HttpWebRequest myHttpWebRequest;
        static void Main(string[] args)
        {

            //采集部分
            Console.WriteLine("编号");
            int t = int.Parse(Console.ReadLine());
            Console.WriteLine("开始页");
            int i = int.Parse(Console.ReadLine());
            Console.WriteLine("结束页");
            int n = int.Parse(Console.ReadLine());

            for (int x = i; i < n; i  )
            {
                string strURL = "https://bbs.xd.com/thread-"   t   "-"   i   "-1.html";
                myHttpWebRequest = (HttpWebRequest)WebRequest.Create(strURL);
                myHttpWebRequest.Timeout = 20 * 1000; //连接超时
                myHttpWebRequest.Accept = "text / html,application / xhtml   xml,application / xml; q = 0.9,*/*;q=0.8";
                myHttpWebRequest.UserAgent = "Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 5.1; Trident/4.0;)";
                //myHttpWebRequest.Headers.Add("Cookie", "UM_distinctid = 15b917f117652c - 0e0f802cc2344a8 - 13646e4a - 1fa400 - 15b917f117751c; CNZZDATA1254852923 = 818605592 - 1492791763 - http% 253A % 252F % 252Fsgk.fbisb.com % 252F % 7C1492850579");
                //myHttpWebRequest.Host = "s.70sec.com";
                //myHttpWebRequest.Referer = "http://s.70sec.com/";
                HttpWebResponse myHttpWebResponse = (HttpWebResponse)myHttpWebRequest.GetResponse();
                StreamReader myreader = new StreamReader(myHttpWebResponse.GetResponseStream(), Encoding.UTF8);
                string responseText = myreader.ReadToEnd();
                string[] lines = responseText.Split('\n');//new added
                myHttpWebResponse.Close();
                myreader.Close();

                //提取部分

                foreach (string line in lines)
                // while ((line = sr.ReadLine()) != null)//修改处
                    {

                    int index = line.IndexOf("static/image/siteicon/v4/xd.png");
                    if (index > -1)

                    {
                        // Console.WriteLine(line);
                        Match mc = Regex.Match(line, @"(?<=nowrap;""> )(.*?)(?=<img class=""uc_platform_icon"" src=""static/image/siteicon/v4/xd.png)", RegexOptions.Multiline);
                        string href1 = mc.Groups[1].Value;
                        Console.WriteLine("{1}获取到内容{0}:", x,href1);
                        string href = href1   "\r\n";
                        StreamWriter sw = File.AppendText("1.txt");
                        sw.Write(href);
                        sw.Close();
                    }

                }
            }
        }
    }
}