HtmlAgilityPack XPath返回HtmlAgilityPack.HtmlNodeCollection

我试图抓取一个网站，以获取它的数据。到目前为止，我得到它至少连接到网站，但现在当我尝试设置与数据的文本框的文本，我只是得到了一堆：HtmlAgilityPack XPath返回HtmlAgilityPack.HtmlNodeCollection

HtmlAgilityPack.HtmlNodeCollection

有相同数量的有数据的HtmlAgilityPack.HtmlNodeCollection。这里是我的代码（我知道这是有点马虎）：

using System.Collections.Generic; 
using System.Linq; 
using System.Net; 
using System.Text.RegularExpressions; 
using System.Windows.Forms; 
using System; 
using HtmlAgilityPack; 

namespace WindowsFormsApplication1 
{ 
public partial class Form1 : Form 
{ 
    string choice; 

    public Form1() 
    { 
     InitializeComponent(); 
    } 

    public void comboBox1_SelectedIndexChanged(object sender, System.EventArgs e) 
    { 

    } 

    public void button1_Click(object sender, System.EventArgs e) 
    { 
     HtmlAgilityPack.HtmlDocument htmlDoc = new HtmlAgilityPack.HtmlDocument(); 
     htmlDoc.OptionFixNestedTags = true; 

     string urlToLoad = "http://www.nbcwashington.com/weather/school-closings/"; 
     HttpWebRequest request = HttpWebRequest.Create(urlToLoad) as HttpWebRequest; 
     request.Method = "GET"; 

     Console.WriteLine(request.RequestUri.AbsoluteUri); 
     WebResponse response = request.GetResponse(); 

     htmlDoc.Load(response.GetResponseStream(), true); 
     if (htmlDoc.DocumentNode != null) 
     { 
      var articleNodes = htmlDoc.DocumentNode.SelectNodes("/html/body/div/div/div/div/div/div/p"); 



      if (articleNodes != null && articleNodes.Any()) 
      { 
       foreach (var articleNode in articleNodes) 
       { 

        textBox1.AppendText(htmlDoc.DocumentNode.SelectNodes("/html/body/div/div/div/div/div/div/p").ToString()); 

       } 
      } 
     } 

     Console.ReadLine(); 
    } 

    private void listBox1_SelectedIndexChanged(object sender, System.EventArgs e) 
    { 
     choice = listBox1.SelectedItem.ToString(); 
    } 



} 
}

所以我在这里错过/做错了什么？数据应该返回类似于：

Warren County Public Schools Closed 
Washington Adventist University Closing at Noon

感谢您关注此问题。

来源

2016-01-23 informative

转换为字符串的反应，看HTML，我们会告诉你什么是错的。此外，大多数这种检查为零是不需要的。 – mybirthname

没关系，找到了问题。我想我试图抓住文档节点而不是内部文本...这里是代码，以防万一任何人想要它。

using System.Collections.Generic; 
using System.Linq; 
using System.Net; 
using System.Text.RegularExpressions; 
using System.Windows.Forms; 
using System; 
using HtmlAgilityPack; 

namespace WindowsFormsApplication1 
{ 
public partial class Form1 : Form 
{ 
    string choice; 

    public Form1() 
    { 
     InitializeComponent(); 
    } 

    public void comboBox1_SelectedIndexChanged(object sender, System.EventArgs e) 
    { 

    } 

    public void button1_Click(object sender, System.EventArgs e) 
    { 
     HtmlAgilityPack.HtmlDocument htmlDoc = new HtmlAgilityPack.HtmlDocument(); 
     htmlDoc.OptionFixNestedTags = true; 

     string urlToLoad = "http://www.nbcwashington.com/weather/school-closings/"; 
     HttpWebRequest request = HttpWebRequest.Create(urlToLoad) as HttpWebRequest; 
     request.Method = "GET"; 

     Console.WriteLine(request.RequestUri.AbsoluteUri); 
     WebResponse response = request.GetResponse(); 

     htmlDoc.Load(response.GetResponseStream(), true); 
     if (htmlDoc.DocumentNode != null) 
     { 
      var articleNodes = htmlDoc.DocumentNode.SelectNodes("/html/body/div/div/div/div/div/div/p"); 



      if (articleNodes != null && articleNodes.Any()) 
      { 
       int k = 0; 
       foreach (var articleNode in articleNodes) 
       { 


        textBox1.AppendText(articleNode.InnerText + "\n"); 

       } 
      } 
     } 

     Console.ReadLine(); 
    } 

    private void listBox1_SelectedIndexChanged(object sender, System.EventArgs e) 
    { 
     choice = listBox1.SelectedItem.ToString(); 
    } 



}

}

来源

2016-01-23 00:33:07 informative

由于articleNodes已经包含了你感兴趣的节点，就没有必要再打电话SelectNodes()一个循环中。

此外，您不需要检查null，因为articleNodes是一个集合。它可能是空，但不应该是null。

试试这个，访问InnerHtml（或InnerText）属性，而不是：

var articleNodes = htmlDoc.DocumentNode.SelectNodes("/html/body/div/div/div/div/div/div/p"); 

var result = articleNodes.Select(x => x.InnerHtml.Replace("<br><span>", " ") 
               .Replace(" </span>", "")).ToList();

来源

2016-01-23 00:33:44

HtmlAgilityPack XPath返回HtmlAgilityPack.HtmlNodeCollection

回答

相关问题