HtmlAgilityPack使用XPath语法，尽管许多人认为它的文档记录很差，但在XPath文档https://www.w3schools.com/xml/xpath_syntax.asp的帮助下，我使用它没有任何困难

解析

<h2>
  <a href="">Jack</a>
</h2>
<ul>
  <li class="tel">
    <a href="">81 75 53 60</a>
  </li>
</ul>
<h2>
  <a href="">Roy</a>
</h2>
<ul>
  <li class="tel">
    <a href="">44 52 16 87</a>
  </li>
</ul>

我是这样做的:

string url = "http://website.com";
var Webget = new HtmlWeb();
var doc = Webget.Load(url);
foreach (HtmlNode node in doc.DocumentNode.SelectNodes("//h2//a"))
{
  names.Add(node.ChildNodes[0].InnerHtml);
}
foreach (HtmlNode node in doc.DocumentNode.SelectNodes("//li[@class='tel']//a"))
{
  phones.Add(node.ChildNodes[0].InnerHtml);
}

HtmlAgilityPack使用XPath语法，尽管许多人认为它的文档记录很差，但在XPath文档https://www.w3schools.com/xml/xpath_syntax.asp的帮助下，我使用它没有任何困难

解析

<h2>
  <a href="">Jack</a>
</h2>
<ul>
  <li class="tel">
    <a href="">81 75 53 60</a>
  </li>
</ul>
<h2>
  <a href="">Roy</a>
</h2>
<ul>
  <li class="tel">
    <a href="">44 52 16 87</a>
  </li>
</ul>

我是这样做的:

string url = "http://website.com";
var Webget = new HtmlWeb();
var doc = Webget.Load(url);
foreach (HtmlNode node in doc.DocumentNode.SelectNodes("//h2//a"))
{
  names.Add(node.ChildNodes[0].InnerHtml);
}
foreach (HtmlNode node in doc.DocumentNode.SelectNodes("//li[@class='tel']//a"))
{
  phones.Add(node.ChildNodes[0].InnerHtml);
}

我不知道这对您是否有任何帮助，但我已经写了几篇介绍基础知识的文章。

HtmlAgilityPack文章系列 htmllagilitypack库简介 使用HtmlAgilityPack轻松从html片段中提取链接

下一篇文章已经完成了95%，我只需要对我所编写的最后几部分代码进行解释。如果你感兴趣，那么当我发布它时，我会尽量记得在这里发布。

入门- HTML敏捷包

// From File
var doc = new HtmlDocument();
doc.Load(filePath);

// From String
var doc = new HtmlDocument();
doc.LoadHtml(html);

// From Web
var url = "http://html-agility-pack.net/";
var web = new HtmlWeb();
var doc = web.Load(url);

主要HTMLAgilityPack相关代码如下

using System;
using System.Net;
using System.Web;
using System.Web.Services;
using System.Web.Script.Services;
using System.Text.RegularExpressions;
using HtmlAgilityPack;

namespace GetMetaData
{
    /// <summary>
    /// Summary description for MetaDataWebService
    /// </summary>
    [WebService(Namespace = "http://tempuri.org/")]
    [WebServiceBinding(ConformsTo = WsiProfiles.BasicProfile1_1)]
    [System.ComponentModel.ToolboxItem(false)]
    // To allow this Web Service to be called from script, using ASP.NET AJAX, uncomment the following line.
    [System.Web.Script.Services.ScriptService]
    public class MetaDataWebService: System.Web.Services.WebService
    {
        [WebMethod]
        [ScriptMethod(UseHttpGet = false)]
        public MetaData GetMetaData(string url)
        {
            MetaData objMetaData = new MetaData();

            //Get Title
            WebClient client = new WebClient();
            string sourceUrl = client.DownloadString(url);

            objMetaData.PageTitle = Regex.Match(sourceUrl, @
            "\<title\b[^>]*\>\s*(?<Title>[\s\S]*?)\</title\>", RegexOptions.IgnoreCase).Groups["Title"].Value;

            //Method to get Meta Tags
            objMetaData.MetaDescription = GetMetaDescription(url);
            return objMetaData;
        }

        private string GetMetaDescription(string url)
        {
            string description = string.Empty;

            //Get Meta Tags
            var webGet = new HtmlWeb();
            var document = webGet.Load(url);
            var metaTags = document.DocumentNode.SelectNodes("//meta");

            if (metaTags != null)
            {
                foreach(var tag in metaTags)
                {
                    if (tag.Attributes["name"] != null && tag.Attributes["content"] != null && tag.Attributes["name"].Value.ToLower() == "description")
                    {
                        description = tag.Attributes["content"].Value;
                    }
                }
            } 
            else
            {
                description = string.Empty;
            }
            return description;
        }
    }
}

    public string HtmlAgi(string url, string key)
    {

        var Webget = new HtmlWeb();
        var doc = Webget.Load(url);
        HtmlNode ourNode = doc.DocumentNode.SelectSingleNode(string.Format("//meta[@name='{0}']", key));

        if (ourNode != null)
        {


                return ourNode.GetAttributeValue("content", "");

        }
        else
        {
            return "not fount";
        }

    }