推荐订阅源

转：http://www.cnblogs.com/chuncn/archive/2009/09/07/1561564.html

登录的处理。因为有些网页数据需要登陆后才能提取。这里要使用ieHTTPHeaders来提取登录时的提交信息。

抓取网页

 HtmlAgilityPack.HtmlDocument htmlDoc;

            if (!string.IsNullOrEmpty(登录URL))
            {
                htmlDoc = htmlWeb.Load(登录URL, 提交的用户验证信息, 获取数据的网页URL);
            }
            else
            {
                htmlDoc = htmlWeb.Load(获取数据的网页URL);
            }
        

-------------------------------------------------------------------------------------------

using System;

using System.Collections.Generic;

using System.Text;

using Microsoft.VisualStudio.TestTools.WebTesting;

using HtmlAgilityPack;

public class WebTest1Coded : WebTest

{

public override IEnumerator<WebTestRequest> GetRequestEnumerator()

{

WebTestRequest request1 = new WebTestRequest("http://www.microsoft.com/");

request1.ValidateResponse += new EventHandler<ValidationEventArgs>(request1_ValidateResponse);

yield return request1;

}

void request1_ValidateResponse(object sender, ValidationEventArgs e)

{

//load the response body string as an HtmlAgilityPack.HtmlDocument

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

doc.LoadHtml(e.Response.BodyString);

//locate the "Nav" element

HtmlNode navNode = doc.GetElementbyId("Nav");

//pick the first <li> element

HtmlNode firstNavItemNode = navNode.SelectSingleNode(".//li");

//validate the first list item in the Nav element says "Windows"

e.IsValid = firstNavItemNode.InnerText == "Windows";

}

}