C#使用xpath简单爬取网站的内容

       public static void Get()

        {

            // string xpathtrI = "//*[@id='classify-list']/dl/dd/a/cite/span/i";

            #region 获取首页的分类

            ////主页的html地址

            //string urlHome = "http://www.qidian.com/";

            //HtmlWeb web = new HtmlWeb();

            //HtmlAgilityPack.HtmlDocument htmlDoc = web.Load(urlHome);

            ////创建html的节点

            //HtmlNode rootNode1 = htmlDoc.DocumentNode;

            //string xpathtrA = "//*[@id='classify-list']/dl/dd";

            //HtmlNodeCollection classList = rootNode1.SelectNodes(xpathtrA);

            //List<string> listINode = new List<string>();

            //foreach (HtmlNode item in classList)

            //{

            //    //获取分类

            //    string inode = item.SelectSingleNode("//a/cite/span/i").InnerText;

            //    listINode.Add(inode);

            //}

            #endregion

            #region 分类及明细

            //string urlDetail = "http://xuanhuan.qidian.com/";

            //List<string> urlList = new List<string>();

            //urlList.Add("http://xuanhuan.qidian.com/");

            //urlList.Add("http://qihuan.qidian.com/");

            //urlList.Add("http://wuxia.qidian.com/");

            //urlList.Add("http://xianxia.qidian.com/");

            //urlList.Add("http://dushi.qidian.com/");

            //urlList.Add("http://zhichang.qidian.com/");

            //urlList.Add("http://junshi.qidian.com/");

            //urlList.Add("http://lishi.qidian.com/");

            //urlList.Add("http://youxi.qidian.com/");

            //urlList.Add("http://tiyu.qidian.com/");

            //urlList.Add("http://kehuan.qidian.com/");

            //urlList.Add("http://lingyi.qidian.com/");//foreach (string url in urlList)

            //{

            //    HtmlAgilityPack.HtmlDocument htmlDetail = web.Load(url);

            //    HtmlNode rootNode2 = htmlDetail.DocumentNode;

            //    string a = "//*[@class='book-info']";

            //    HtmlNodeCollection classList2 = rootNode2.SelectNodes(a);

            //    List<string> listINode2 = new List<string>();

            //    foreach (HtmlNode item in classList2)

            //    {

            //        //获取分类

            //        string inode = item.InnerHtml;

            //        listINode2.Add(inode);

            //    }

            //}

            #endregion

            #region 文章内容

            HtmlWeb web = new HtmlWeb();

            string u = "http://read.qidian.com/chapter/zOGI9RYmNdFhO--gcH8iFg2/h3iHSEH1cSpMs5iq0oQwLQ2";

            HtmlAgilityPack.HtmlDocument htmlDocment = web.Load(u);

            //创建html的节点

            HtmlNode htmlNode = htmlDocment.DocumentNode;

            string x = "//*[@class='read-content j_readContent']";

            HtmlNode htmlNodeP = htmlNode.SelectSingleNode(x);

            string htmlD = htmlNodeP.InnerText;

            #endregion

        }
只是拿一个例子而已。
秒客网

C#使用xpath简单爬取网站的内容

相关文章
