使用Html Agility Pack快速解析Html内容

 ???????/// <summary> ???????/// 获取网页内容 ???????/// </summary> ???????/// <returns></returns> ???????private static string GetHtml() ???????{ ???????????string html = string.Empty; ???????????string url = "http://quote.eastmoney.com/stocklist.html"; ???????????using (var client = new HttpClient()) ???????????{ ???????????????client.BaseAddress = new Uri(url); ???????????????//关键代码1：设置请求头采用GZip和deflate两种压缩算法 ???????????????client.DefaultRequestHeaders.Add("Accept-Encoding", "gzip, deflate"); ???????????????var response = client.GetAsync(url).Result; ???????????????var fileStream = response.Content.ReadAsStreamAsync().Result; ???????????????//关键代码2：对文件流采用GZip算法解压 ???????????????GZipStream gzip = new GZipStream(fileStream, CompressionMode.Decompress); ???????????????using (StreamReader reader = new StreamReader(gzip, Encoding.GetEncoding("gb2312")))//中文编码处理 ???????????????{ ???????????????????html = reader.ReadToEnd(); ???????????????????//File.WriteAllText(@"C:\stock.html", reader.ReadToEnd(), Encoding.Default); ???????????????} ???????????} ???????????return html; ???????}

 ???????static void Main(string[] args) ???????{ ???????????string html= GetHtml(); ???????????var doc = new HtmlDocument(); ???????????doc.LoadHtml(html); ???????????//查找dom节点div的Id为quotesearch下所有ul下的li下的所有a节点 ???????????var nodes = doc.DocumentNode.SelectNodes("//div[@id=‘quotesearch‘]/ul/li/a"); ???????????foreach (var node in nodes) ???????????{ ???????????????var arrays=node.InnerText.Split(‘(‘); ???????????????Console.WriteLine(string.Format("股票名称：{0}，股票代码：{1}", arrays[0], arrays[1].Replace(")",""))); ???????????} ???????????//File.WriteAllText(@"C:\stock.html", matches.ToString(), Encoding.Default); ???????????Console.ReadKey(); ???????}