C#使用AngleSharp库解析html文档

var config = Configuration.Default.WithDefaultLoader();
var address = "https://en.wikipedia.org/wiki/List_of_The_Big_Bang_Theory_episodes";
var context = BrowsinGContext.New(config);
var document = await context.OpenAsync(address);
var cellSelector = "tr.vevent td:nth-child(3)";
var cells = document.QuerySelectorAll(cellSelector);
var titles = cells.Select(m => m.TextContent);

//创建一个（可重用）解析器前端
var parser = new HtmlParser();
//html DOM节点
var source = "
<h1>Some example source</h1>
<p>This is a paragraph element</p>
";

//解析源文件
var document = parser.Parse(source);
//创建P标签
var p = document.CreateElement("p");
p.TextContent = "This is another paragraph.";
//添加到DOM
document.Body.AppendChild(p);
//返回完整html
var html = document.DocumentElement.OuterHtml;
ViewData["html"] = html;

var parser = new HtmlParser();
 //为以下源代码生成HTML DOM
var document = parser.Parse("
<ul>
<li>First element</li>
<li>Second element</li>
<li>third</li>
<li class='bla'>Last</li>
</ul>
");
//获取所有li元素并将test属性设置为值测试
var elements = document.QuerySelectorAll("li").Attr("test", "test");
 //元素仍然包含所有li元素
ViewData["html"] = document.DocumentElement.OuterHtml;

var parser = new HtmlParser();
var document = parser.ParseDocument(text);
using (var writer = new StringWriter())
{
    document.ToHtml(writer, new PrettyMarkupFORMatter
                            {
                                Indentation = "\t",
                                NewLine = "\n"
                            });
    var indentedText = writer.ToString();
}

var requester = new DefaultHttpRequester("Mozilla/5.0 (windows NT 10.0; WOW64) AppleWEBKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.100 Safari/537.36");
requester.Headers.Add("Accept", "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8");
requester.Headers.Add("Referer", "");
requester.Headers.Add("Accept-Language", "zh-Hans-CN,zh-Hans;q=0.8,en-US;q=0.5,en;q=0.3");
var context = BrowsingContext.New(Configuration.Default.WithLocaleBasedEncoding().WithDefaultLoader().WithDefaultCookies().With(requester));
//根据虚拟请求/响应模式创建文档
var document = context.OpenAsync(url).Result;
using (var writer = new StringWriter())
{
    document.ToHtml(writer, new PrettyMarkupFormatter
                            {
                                Indentation = "\t",
                                NewLine = "\n"
                            });
    var indentedText = writer.ToString();
}

/// 
/// 解析html
/// 
public class Belle
{
        /// 
        /// 标题
        /// 
        public string Title { get; set; }
        /// 
        /// 图片地址
        /// 
        public string ImageUrl { get; set; }
}

// 设置配置以支持文档加载
var config = Configuration.Default.WithDefaultLoader();
// 豆瓣地址
var address = "https://www.dbmeinv.com/dbgroup/show.htm?cid=4";
// 请求豆辨网
var document =  BrowsingContext.New(config).OpenAsync(address);
// 根据class获取html元素
var cells = document.Result.QuerySelectorAll(".panel-body li");
// We are only interested in the text - select it with LINQ
List list = new List();
foreach (var item in cells)
{
     var belle = new Belle
     {
         Title= item.QuerySelector("img").GetAttribute("title"),
         ImageUrl= item.QuerySelector("img").GetAttribute("src")
     };
     list.Add(belle);
 }
ViewData["html"] = list;