C# 简单的图片爬虫 专爬美女图片

 先把网页Down下来，看看图片包含在哪个标签里面

 简单粗暴的识别方法，用'进行分割

var url = pageHtml.Split('\'');
int index = url[i].IndexOf(".jpeg");
if(index == (url[i].Length - 5))

得到的Url，然后拿着Url进行下载即可，有的网站有反扒，不让直接下载怎么办，上工具 internet download manager，复制全部的Url打开工具软件

复制Url后选择，从剪切板中添加批量下载 

 

哇塞，好美

 

代码在下面 

using RestSharp;
using RestSharp.Extensions;
using System;
using System.Collections.Generic;
using System.Drawing;
using System.IO;
using System.Linq;
using System.Net;
using System.Net.Http;
using System.Text;
using System.Threading.Tasks;

namespace PictureSpider
{
    public class Program
    {
        public static void Main(string[] args)
        {
            try
            {
                WebClient webClient = new WebClient();
                webClient.Credentials = CredentialCache.DefaultCredentials;
                webClient.Headers.Add("Accept", "image/gif, image/x-xbitmap, image/jpeg, image/pjpeg, */*");
                webClient.Headers.Add("Accept-Language", "zh-CN");
                webClient.Headers.Add("Host", "");
                webClient.Headers.Add("User-Agent", "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.2; SV1)");
                webClient.Headers.Add("Content-Type", "application/x-www-form-urlencoded");
                webClient.Credentials = CredentialCache.DefaultCredentials;//获取或设置用于向Internet资源的请求进行身份验证的网络凭据
                Byte[] pageData = webClient.DownloadData("https://www.vmgirls.com/15298.html"); //从指定网站下载数据
                string pageHtml = Encoding.Default.GetString(pageData);  //如果获取网站页面采用的是GB2312，则使用这句    
                using (System.IO.StreamWriter file = new System.IO.StreamWriter(@"html.txt", true))
                {
                    file.WriteLine(pageHtml);
                }
                //找到'进行分割
                var url = pageHtml.Split('\'');
                List<string> urls = new List<string>();
                for(int i=0;i< url.Length;i++)
                {
                    int index = url[i].IndexOf(".jpeg");
                    if(index == (url[i].Length - 5))
                    {
                        string pictrueUrl = "https:" + url[i];
                        urls.Add(pictrueUrl);
                        Console.WriteLine(pictrueUrl);
                        try
                        {
                            byte[] Bytes = webClient.DownloadData(pictrueUrl);
                            using (MemoryStream ms = new MemoryStream(Bytes))
                            {
                                Image outputImg = Image.FromStream(ms);
                                outputImg.Save($"{i.ToString()}.jpeg");
                            }
                        }
                        catch (Exception ex)
                        {
                            Console.WriteLine(ex.ToString());
                        }
                    }
                }
                using (System.IO.StreamWriter file = new System.IO.StreamWriter(@"url.txt", true))
                {
                    for (int i = 0; i < urls.Count(); i++)
                    {
                        file.WriteLine(urls[i]);
                    }
                }
            }
            catch (WebException webEx)
            {
                Console.WriteLine(webEx.Message.ToString());
            }

            Console.ReadLine();
        }
    }
}