用NSoup解析HTML

1.在NuGet程序包中添加NSoup包

public static void TestNSoup(string urlStr)
        {
            WebClient wc = new WebClient();
            byte[] htmlByte = wc.DownloadData(urlStr);
            string html = Encoding.UTF8.GetString(htmlByte);
            //声明Document对象
            Document doc = NSoupClient.Parse(html);

            //直接通过url来获取Document对象
            Document doc1 = NSoupClient.Connect(urlStr).Get();

            Elements div = doc1.GetElementById("标签id").GetElementsByTag("标签名如,div");

            //通过id获取元素
            Element userNames = doc.GetElementById("标签id");
            //通过标签名获取元素
            Elements p = doc.GetElementsByTag("p");

            //通过类样式获取元素 
            Elements btnNews = doc.GetElementsByClass("btn-news");

            //通过属性获取
            Elements attrstyle = doc.GetElementsByAttribute("style");

            //遍历获取到的标签
            foreach (Element item in div)
            {
                Console.WriteLine(item.Html());
            }
        }

 

posted @ 2019-08-29 16:12  杜子烟  阅读(870)  评论(0编辑  收藏  举报