HtmlAgilityPack 总结（一）

“//comment()”在XPath中表示“所有注释节点”

1、获取网页title：doc.DocumentNode.SelectSingleNode(“//title”).InnerText;
解释：XPath中“//title”表示所有title节点。SelectSingleNode用于获取满足条件的唯一的节点。

2、获取所有的超链接：doc.DocumentNode.Descendants(“a”)

3、获取name为kw的input，也就是相当于getElementsByName()：
            var kwBox = doc.DocumentNode.SelectSingleNode(“//input[@name=’kw’]”);

解释：”//input[@name=’kw’]”也是XPath的语法，表示：name属性等于kw的input标签。

//li/h3/a[@href]：所有li下面的h3包含a超级链接有href属性才符合。有的a可能是支持的js事件

//div[starts-with(@class,’content_single’)]：所有符合条件的div，并且它的class是由字符串content_single 开头的。

                HtmlAgilityPack.HtmlWeb hw = new HtmlAgilityPack.HtmlWeb();

                HtmlAgilityPack.HtmlDocument doccc = hw.Load(url);//是你需要解析的url

                ArrayList ImagePtahs = GetHrefs(doccc);

              WebProxy proxyObject = new WebProxy(IP, port);//这里我是用的代理。

                //向指定地址发送请求

               HttpWebRequest HttpWReq = (HttpWebRequest)WebRequest.Create(url);

                HttpWReq.Proxy = proxyObject;

                HttpWReq.Timeout = 10000;

                HttpWebResponse HttpWResp = (HttpWebResponse)HttpWReq.GetResponse();              

                StreamReader sr = new StreamReader(HttpWResp.GetResponseStream(), System.Text.Encoding.GetEncoding(“UTF-8”));             

                //注意上面的编码了吗？？

                HtmlAgilityPack.HtmlDocument doc = new HtmlAgilityPack.HtmlDocument();

                doc.Load(sr);

                int res = CheckIsGoodProxy(doc); //这是我解析的函数，还没到那一步。不解释了。

                sr.Close();

                HttpWResp.Close();

                HttpWReq.Abort();

HtmlWeb webClient = new HtmlWeb();

HtmlAgilityPack.HtmlWeb.PreRequestHandler handler = delegate(HttpWebRequest request)

{

       request.Headers[HttpRequestHeader.AcceptEncoding] = “gzip, deflate”;

       request.AutomaticDecompression = DecompressionMethods.Deflate | DecompressionMethods.GZip;

       request.CookieContainer = new System.Net.CookieContainer();

       return true;

};

webClient.PreRequest += handler;

HtmlDocument doc = webClient.Load(this.getUrl());

    private ArrayList GetHrefs(HtmlAgilityPack.HtmlDocument _doc)

        {

            try

            {

                Images = new ArrayList();

                HtmlNodeCollection hrefs = _doc.DocumentNode.SelectNodes(“//li/h3/a[@href]”);

                   HtmlNodeCollection hrefs2 = _doc.DocumentNode.SelectNodes(“//div[starts-with(@class,’content_single’)]”);

                if (hrefs == null)

                    return new ArrayList();

                foreach (HtmlNode href in hrefs)

                {

                    //  Images.Add(href.Attributes[“src”].Value);

                    string hreff = href.Attributes[“href”].Value;// 排除  博海拾贝第二百零二期】吃完薯条寂寞了

                    string title = href.Attributes[“title”].Value;

                  if (title.IndexOf(“邪恶”) >= 0)

                    {

                        continue;

                    }

                    if (title.IndexOf(“恶搞”) >= 0)

                    {

                        continue;

                    }

                    if (title.IndexOf(“雷人”) >= 0)

                    {

                        continue;

                    }

                    ///执行数据保存的逻辑

                }

}

catch (Exception ex)

            {

                ShowLogMsg(“出错了：”+ex.Message+ex.StackTrace);

                return new ArrayList();

            }

        }