Html Agility Pack 使用 XPath 选择器

想做一个爬虫程序，以前用的一直使用CSS选择器的html解析插件，最近做的项目想使用 Html Agility Pack 来做解析

Html Agility Pack使用 XPath 和 Linq 来做Html解析，我使用Xpath中记录

解析网页：http://txzhanshang.zhankoo.com/tt

列表下一页：//*[contains(@class, 'pagination-right')]/a[text()='下一页']

文章地址：//*[@class='zsinfo']/li/a[@href]

 

        // GET: Test
        public ActionResult Index()
        {
            var crawlerConfigList = _crawlerConfigService.GetCrawlerConfigs();
            foreach (var crawlerConfig in crawlerConfigList)
            {
                GetList(crawlerConfig);
            }
            ViewBag.UrlList = urlList;
            return View(crawlerConfigList);
        }

        private void GetList(CrawlerConfig crawlerConfig)
        {
            var web = new HtmlWeb();
            var htmlDoc = web.Load(crawlerConfig.CrawlerUrl);
            var node = htmlDoc.DocumentNode.SelectNodes(crawlerConfig.ASelector);
            node.ForEach(x =>
            {
                urlList.Add(x.Attributes["href"].Value);
            });

            //下一页
            var nextpageNode = htmlDoc.DocumentNode.SelectSingleNode(crawlerConfig.ListNextPageSelector);
            if (nextpageNode != null)
            {
                var nextpage = nextpageNode.Attributes["href"].Value;
                if (!string.IsNullOrEmpty(nextpage))
                {
                    crawlerConfig.CrawlerUrl = crawlerConfig.CrawlerDomain + nextpage;
                    GetList(crawlerConfig);
                }
            }
        }

 移除某个节点

var url = "http://txzhanshang.zhankoo.com/detail/12709.html";
            var web = new HtmlWeb();
            var htmlDoc = web.Load(url);
            var node = htmlDoc.DocumentNode.SelectSingleNode("//*[@class='inner-wrap']");
            //移除某个节点
            foreach (var rm in node.SelectNodes("//*[@class='newsContenttip']"))
            {
                rm.Remove();
            }
            var ss = node.InnerText;
            var sss = node.InnerHtml;