如何使用HTML Agility Pack

尝试这个

string htmlBody = ParseHmlBody(dtViewDetails.Rows[0]["Body"].ToString());

private string ParseHmlBody(string html)
        {
            string body = string.Empty;
            try
            {
                var htmlDoc = new HtmlDocument();
                htmlDoc.LoadHtml(html);
                var htmlBody = htmlDoc.DocumentNode.SelectSingleNode("//body");
                body = htmlBody.OuterHtml;
            }
            catch (Exception ex)
            {

                dalPendingOrders.LogMessage("Error in ParseHmlBody" + ex.Message);
            }
            return body;
        }

与HTMLAgilityPack相关的主要代码如下

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;
        }
    }
}

入门-HTML Agility Pack

// 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);

我不知道这对您有什么帮助，但是我写了几篇文章介绍了这些基础知识。

• HtmlAgilityPack文章系列
• HtmlAgilityPack库简介
• 使用HtmlAgilityPack轻松地从HTML片段中提取链接

下一篇文章完成了95％，我只需要写出我编写的代码的最后几部分的说明。如果您有兴趣，那么我会尽量记得在发布时在此处发布。

首先，将HTMLAgilityPack nuget包安装到您的项目中。

然后，例如：

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

// There are various options, set as needed
htmlDoc.OptionFixNestedTags=true;

// filePath is a path to a file containing the html
htmlDoc.Load(filePath);

// Use:  htmlDoc.LoadHtml(xmlString);  to load from a string (was htmlDoc.LoadXML(xmlString)

// ParseErrors is an ArrayList containing any errors from the Load statement
if (htmlDoc.ParseErrors != null && htmlDoc.ParseErrors.Count() > 0)
{
    // Handle any parse errors as required

}
else
{

    if (htmlDoc.DocumentNode != null)
    {
        HtmlAgilityPack.HtmlNode bodyNode = htmlDoc.DocumentNode.SelectSingleNode("//body");

        if (bodyNode != null)
        {
            // Do something with bodyNode
        }
    }
}

（注意：此代码仅是示例，不一定是最佳/唯一方法。请勿在自己的应用程序中盲目使用。）

该HtmlDocument.Load()方法还接受一个流，这对于与.NET框架中的其他面向流的类进行集成非常有用。虽然HtmlEntity.DeEntitize()是正确处理html实体的另一种有用方法。（感谢马修）

HtmlDocument这HtmlNode 是您最常使用的类。与XML解析器类似，它提供了接受XPath表达式的selectSingleNode和selectNodes方法。

注意HtmlDocument.Option?????? 布尔属性。这些控制Load和LoadXML方法将如何处理HTML / XHTML。

There is also a compiled help file called HtmlAgilityPack.chm that has a complete reference for each of the objects. This is normally in the base folder of the solution.