C# HtmlDocument和HtmlNode的使用以及节点的模糊查询
C#HtmlAgilityPack.HtmlDocument和HtmlAgilityPack.HtmlNode的使用
HtmlAgilityPack.HtmlDocument response = null; //HtmlAgilityPack.HtmlNode类和HtmlAgilityPack.HtmlDocument类的使用! HtmlAgilityPack.HtmlNode responseNew = null; HtmlDocument doc = new HtmlDocument(); wc.Encoding = Encoding.UTF8; string html= wc.DownloadString(url); doc.LoadHtml(html); responseNew = doc.DocumentNode.SelectSingleNode("/html/body"); //根据XPath查找节点,跟XmlNode差不多 HtmlNodeCollection categoryNodeList = responseNew.SelectNodes("div[3]/div[1]/div[1]/div[1]/ul[1]/li"); foreach (HtmlNode item in categoryNodeList) //foreach (HtmlNode item in ulS2.ChildNodes) { var xpath = item.XPath; if (k % 2 != 0) { number = number + 1; xpath = xpath.Replace("/#text[" + number + "]", "/li");//替换字符串 } k=k+1; string titleName, infourl, company, city, date, salary, salary_em, source; titleName = item.SelectSingleNode(xpath + "/div/div/span/a").InnerText;// infourl = item.SelectSingleNode(xpath + "/div/div/span/a").Attributes["href"].Value; //url }
XML节点的模糊查询:contains(@属性,'模糊查询的值')
ulS = response.DocumentNode.SelectNodes("//*[@id='resultList']/div[contains(@class,'el')]");
XML节点的等值查询
ulS = response.DocumentNode.SelectNodes("//*[@id='resultList']/div[@class='el']"); for (int i = 2; i < ulS.Count; i++) { var item = ulS[i]; var xpath = item.XPath; string titleName; titleName = item.SelectSingleNode(xpath + "/p/span/a").InnerText; }