HtmlAgilityPack爬虫

1.获取连接内容

            var webGet = new HtmlWeb();
            var document = webGet.Load(url);
            var contentNode = document.DocumentNode;

2.获取某个部分信息

  var title = contentNode.SelectSingleNode("/html/body/div[4]/div[1]/h1");

3.获得图片

 var imgNodes = imgNodes.SelectNodes(".//img");
                foreach (var item in imgNodes)
                {
                    var imageUrl = item.Attributes["src"]?.Value;
                    if (!string.IsNullOrWhiteSpace(imageUrl))
                    {
                        imageUrl = "https:" + imageUrl.Replace("https:", "").Replace("http:", "");
                        var imgurl = FileUploadHelper.DownloadFile(imageUrl);
                    }
                }