html解析

private void button1_Click(object sender, EventArgs e)
        {
            //采用开源HtmlAgilityPack解析类，解析Html文档
            byte[] buffer;
            WebClient webClient = new WebClient();
            buffer= webClient.DownloadData(@"可以下载字节也可以是string
            MemoryStream ms = new MemoryStream(buffer);
            HtmlAgilityPack.HtmlDocument htmlDoc = new HtmlAgilityPack.HtmlDocument();
            htmlDoc.Load(ms); //如果是loadHtml参数就是string
            //选取的是节点集合，要对集合进行遍历
            HtmlNodeCollection collection =  htmlDoc.DocumentNode.SelectNodes(".//a[@href]");//采用xpath的方式选取

            foreach (var item in collection)
            {
                HtmlAttribute att = item.Attributes["href"]; //查看这个节点的 href属性
                if (att != null) //如果有href属性
                {
                    if (att.Value.StartsWith("http")) //这个属性是否是http开头的
                    {
                        listBox1.Items.Add(att.Value);
                    }
                }
            }
            ms.Close();
            ms.Dispose();
            webClient.Dispose();
 
        }