"//comment()"在XPath中表示“所有注釋節點”

1、獲取網頁title：doc.DocumentNode.SelectSingleNode("//title").InnerText;? 解釋：XPath中“//title”表示所有title節點。SelectSingleNode用于獲取滿足條件的唯一的節點。

2、獲取所有的超鏈接：doc.DocumentNode.Descendants("a")

3、獲取name為kw的input，也就是相當于getElementsByName()： ????????????var?kwBox?=?doc.DocumentNode.SelectSingleNode("//input[@name='kw']");

解釋："//input[@name='kw']"也是XPath的語法，表示：name屬性等于kw的input標簽。

//li/h3/a[@href]：所有li下面的h3包含a超級鏈接有href屬性才符合。有的a可能是支持的js事件

//div[starts-with(@class,'content_single')]：所有符合條件的div，并且它的class是由字符串content_single?開頭的。

????????????????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);//這里我是用的代理。

????????????????//向指定地址發送請求

???????????????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"));??????????????

????????????????//注意上面的編碼了嗎？？

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

????????????????doc.Load(sr);

????????????????int?res?=?CheckIsGoodProxy(doc);?//這是我解析的函數，還沒到那一步。不解釋了。

????????????????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??博海拾貝第二百零二期】吃完薯條寂寞了?

????????????????????string?title?=?href.Attributes["title"].Value;

??????????????????if?(title.IndexOf("邪惡")?>=?0)

????????????????????{

????????????????????????continue;

????????????????????}

????????????????????if?(title.IndexOf("惡搞")?>=?0)

????????????????????{

????????????????????????continue;

????????????????????}

????????????????????if?(title.IndexOf("雷人")?>=?0)

????????????????????{

????????????????????????continue;

????????????????????}

????????????????????///執行數據保存的邏輯

????????????????}

}

?catch?(Exception?ex)

????????????{

????????????????ShowLogMsg("出錯了："+ex.Message+ex.StackTrace);

????????????????return?new?ArrayList();

????????????}

????????}