通过 html 敏捷包获取标题标签

Question

我正在尝试使用 htmlagility 包来获取结果的链接和标题
我有这个代码

using HtmlAgilityPack;
using System;
using System.Collections.Generic;
using System.ComponentModel;
using System.Data;
using System.Drawing;
using System.IO;
using System.Linq;
using System.Net;
using System.ServiceModel.Syndication;
using System.Text;
using System.Threading.Tasks;
using System.Windows.Forms;
using System.Xml;

namespace Search
{
public partial class Form1 : Form
{
    // load snippet
    HtmlAgilityPack.HtmlDocument htmlSnippet = new HtmlAgilityPack.HtmlDocument();

    public Form1()
    {
        InitializeComponent();
    }

    private void btn1_Click(object sender, EventArgs e)
    {
        listBox1.Items.Clear();
        StringBuilder sb = new StringBuilder();
        byte[] ResultsBuffer = new byte[8192];
        string SearchResults = "http://google.com/search?q=" + txtKeyWords.Text.Trim();
        HttpWebRequest request = (HttpWebRequest)WebRequest.Create(SearchResults);
        HttpWebResponse response = (HttpWebResponse)request.GetResponse();

        Stream resStream = response.GetResponseStream();
        string tempString = null;
        int count = 0;
        do
        {
            count = resStream.Read(ResultsBuffer, 0, ResultsBuffer.Length);
            if (count != 0)
            {
                tempString = Encoding.ASCII.GetString(ResultsBuffer, 0, count);
                sb.Append(tempString);
            }
        }

        while (count > 0);
        string sbb = sb.ToString();

        HtmlAgilityPack.HtmlDocument html = new HtmlAgilityPack.HtmlDocument();
        html.OptionOutputAsXml = true;
        html.LoadHtml(sbb);
        HtmlNode doc = html.DocumentNode;

        foreach (HtmlNode link in doc.SelectNodes("//a[@href]"))
        {
            //HtmlAttribute att = link.Attributes["href"];
            string hrefValue = link.GetAttributeValue("href", string.Empty);
            if (!hrefValue.ToString().ToUpper().Contains("GOOGLE") && hrefValue.ToString().Contains("/url?q=") && hrefValue.ToString().ToUpper().Contains("HTTP://"))
            {
                int index = hrefValue.IndexOf("&");
                if (index > 0)
                {
                    hrefValue = hrefValue.Substring(0, index);
                    listBox1.Items.Add(hrefValue.Replace("/url?q=", ""));
                }
            }
        }
    }
}

}

此代码返回查询的结果链接我也想获得每个链接的标题标签 我怎样才能获得每个链接的标题？
有人可以帮忙吗？

Answer 1

如果“标题”是指链接的显示文本，那么您可以从每个HtmlNode link InnerText属性中获取它：

foreach (HtmlNode link in doc.SelectNodes("//a[@href]"))
{
    .....
    var title = link.InnerText.Trim();
}

Answer 2

这将给出输出：链接和链接的标题。 这不会返回链接的锚文本。 您将只获得每个链接的标题。

foreach (HtmlNode link in doc.SelectNodes("//a[@href]"))
{
   HtmlWeb htmlWeb = new HtmlWeb();
   HtmlAgilityPack.HtmlDocument htmlDocument = htmlWeb.Load(link);
   var title = htmlDocument.DocumentNode.SelectSingleNode("html/head/title").InnerText;
}