C#采用vony.Html.AIO插件批量爬MM网站图片

//需要定义一个list用来存放所有的页面链接 
static List categoryUrl = new List();

//加载url到文档
  IHtmlDocument source = new JumonyParser().LoadDocument("https://www.mntup.com/XiuRen.html", System.Text.Encoding.GetEncoding("utf-8"));
     
            //获取所有class=dana的的a标签
            var divLinks = source.Find(".dana a");
            foreach (var aLink in divLinks)
            {
                var categoryName = aLink.Attribute("href").Value(); //获取a中的链接
                categoryUrl.Add(categoryName);
            }

   
foreach (var url in categoryUrl)
            {
               //获取图片也的的文档
                IHtmlDocument html = new JumonyParser().LoadDocument($"{address}{url}", System.Text.Encoding.GetEncoding("utf-8"));

                //获取每个分页面并下载
                var pageLink = html.Find(".page a");
                foreach (var alingk in pageLink)
                {
                    string href = alingk.Attribute("href").Value();
                    Console.WriteLine($"获取分页地址{href}");

                }
            }

  
//获取每一个分页的文档模型
 IHtmlDocument htm2 = new JumonyParser().LoadDocument($"{address}{href}", System.Text.Encoding.GetEncoding("utf-8"));

                    //获取class=img的div下的img标签
                    var aLink = htm2.Find(".img img");

                    foreach (var link in aLink)
                    {
                        var imgsrc = link.Attribute("src").Value();
                        Console.WriteLine("获取到图片路径" + imgsrc);
                        Console.WriteLine($"开始下载图片{imgsrc}>>>>>>>");
                        DownLoadImg(new Image { Address = address + imgsrc, Title = url });
                        
                    }
                }

        /// 

        /// 异不下载图片
        /// 
        /// 
        async static void DownLoadImg(Image image)
        {
            using (WebClient client = new WebClient())
            {
                try
                {
                    int start = image.Address.LastIndexOf("/") + 1;
    
                    string fileName = image.Address.Substring(start, image.Address.Length - start);
                  //图片目录采用页面地址作为文件名
                    string directory = "c:/images/" + image.Title.Replace("/", "-").Replace("html", "") + "/";                
                    if (!Directory.Exists(directory))
                    {
                        Directory.CreateDirectory(directory);
                    }
                    await client.DownloadFileTaskAsync(new Uri(image.Address), directory + fileName);
                }
                catch (Exception)
                {
                    Console.WriteLine($"{image.Address}下载失败");
                    File.AppendText(@"c:/log.txt");
                }
                Console.WriteLine($"{image.Address}下载成功");
            }

        }