爬虫

提取页面HTML代码

方法一：采用 WebClient ，代码如下
using System.Net;
{
   string strurl="网址";
   WebClient aWebClient = new WebClient();
   aWebClient.Encoding = System.Text.Encoding.UTF8;
   string htmlcode = aWebClient.DownloadString(strurl);
   txtbox.Text=htmlcode;//txtbox为一个文本框
}
方法二：采用 HttpWebRequest HttpWebResponse ，代码如下
using System.Net;
{
 string strurl = "http://www.weather.com.cn/weather/101310101.shtml?from=cn";
 HttpWebRequest myReq = (HttpWebRequest)WebRequest.Create(strurl);
    myReq.Accept = "Accept-Languat:zh-cn";
    myReq.AllowAutoRedirect = true;
    myReq.MaximumAutomaticRedirections = 1;
    myReq.Referer = "weather";
    HttpWebResponse myResponse = (HttpWebResponse)myReq.GetResponse();
    Stream myStream = myResponse.GetResponseStream();
    StreamReader myReader = new StreamReader(myStream, System.Text.Encoding.UTF8);
    txtbox.Text = myReader.ReadToEnd();//txtbox为一个文本框

}

 2.添加引用

Winista.HtmlParser.dll

static void Main(string[] args)
        {
            string strurl = "http://hq.cnpc/cwb/news/bnxx/Pages/20171228_C1852.aspx ";
            WebClient aWebClient = new WebClient();
            aWebClient.Encoding = System.Text.Encoding.UTF8;
            string htmlcode = aWebClient.DownloadString(strurl);
            //Console.WriteLine(htmlcode);
            Parser parser = Parser.CreateParser(htmlcode, "utf-8");//GBK
            HtmlPage page = new HtmlPage(parser);
            HasAttributeFilter filter = new HasAttributeFilter("id", "contentText");
            NodeList result = parser.Parse(filter);
            TagNode tag = (TagNode)result[0];

            Console.WriteLine(result.ToHtml().ToString());
            Console.WriteLine(tag.GetAttribute("id"));
            Console.ReadKey();
        }

　　3.输出：