httphtml+XPath采集

C#版本的网络爬虫感觉还是很好用的。

HttpHelper http = new HttpHelper();
            HttpItem item = new HttpItem() { URL = "http://www.cnblogs.com/danielWise/archive/2011/02/28/1966808.html" };
            HtmlDocument html = new HtmlDocument();
            string resultHtml = http.GetHtml(item).Html;
            html.LoadHtml(resultHtml);

            HtmlAgilityPack.HtmlNode htmlNode = html.DocumentNode;
            //要取出的Xpath标签
            HtmlAgilityPack.HtmlNode div = htmlNode.SelectSingleNode(".//*[@id="cnblogs_post_body"]");
            //Console.WriteLine(div.Elements("p").Count());
            foreach (var mydiv in div.Elements("p"))
            {
                Console.WriteLine(mydiv.InnerText);
            }
            Console.ReadKey();