1、通过NuGet获取AngleSharp
1)使用Nuget管理控制台
将AngleSharp集成到项目中的最简单方法是使用NuGet。您可以通过打开包管理器控制台(PM)并键入以下语句来安装AngleSharp:
Install-Package AngleSharp
2)使用Nuget图形管理器
使用Nuget的界面的管理器搜索"AngleSharp
"=> 找到点出点击"安装
"。
相关文档:VS(Visual Studio)中Nuget的使用
2、使用AngleSharp解析html的示例
var source = @" <!DOCTYPE html> <html lang=en> <meta charset=utf-8> <meta name=viewport content=""initial-scale=1, minimum-scale=1, width=device-width""> <title>Error 404 (Not Found)!!1</title> <style> *{margin:0;padding:0}html,code{font:15px/22px arial,sans-serif}html{background:#fff;color:#222;padding:15px}body{margin:7% auto 0;max-width:390px;min-height:180px;padding:30px 0 15px}* > body{background:url(//www.google.com/images/errors/robot.png) 100% 5px no-repeat;padding-right:205px}p{margin:11px 0 22px;overflow:hidden}ins{color:#777;text-decoration:none}a img{border:0}@media screen and (max-width:772px){body{background:none;margin-top:0;max-width:none;padding-right:0}}#logo{background:url(//www.google.com/images/errors/logo_sm_2.png) no-repeat}@media only screen and (min-resolution:192dpi){#logo{background:url(//www.google.com/images/errors/logo_sm_2_hr.png) no-repeat 0% 0%/100% 100%;-moz-border-image:url(//www.google.com/images/errors/logo_sm_2_hr.png) 0}}@media only screen and (-webkit-min-device-pixel-ratio:2){#logo{background:url(//www.google.com/images/errors/logo_sm_2_hr.png) no-repeat;-webkit-background-size:100% 100%}}#logo{display:inline-block;height:55px;width:150px} </style> www.google.com/> <p><b>404.</b> <ins>That’s an error.</ins> <p>The requested URL <code>/error</code> was not found on this server. <ins>That’s all we know.</ins>"; //使用AngleSharp的默认配置 var config = Configuration.Default; //使用给定的配置创建用于评估web页面的新上下文 var context = BrowsingContext.New(config); //只需要获得DOM表示 var document = await context.OpenAsync(req => req.Content(source)); //将其序列化回控制台 Console.WriteLine(document.DocumentElement.OuterHtml);
3、简单操作document(Dom文档)
static async Task FirstExample() { //使用AngleSharp的默认配置 var config = Configuration.Default; //使用给定的配置创建用于评估web页面的新上下文 var context = BrowsingContext.New(config); //从响应的内容解析文档到虚拟请求 var document = await context.OpenAsync(req => req.Content("<h1>Some example source</h1><p>This is a paragraph element")); //对文档执行如下操作 Console.WriteLine("Serializing the (original) document:"); Console.WriteLine(document.DocumentElement.OuterHtml); var p = document.CreateElement("p"); p.TextContent = "This is another paragraph."; Console.WriteLine("Inserting another element in the body ..."); document.Body.AppendChild(p); Console.WriteLine("Serializing the document again:"); Console.WriteLine(document.DocumentElement.OuterHtml); }
4、获取html中的元素
static async Task UsingLinq() { //使用默认配置创建一个用于评估web页面的新上下文 var context = BrowsingContext.New(Configuration.Default); //根据虚拟请求/响应模式创建文档 var document = await context.OpenAsync(req => req.Content("<ul><li>First item<li>Second item<li class='blue'>Third item!<li class='blue red'>Last item!</ul>")); //对LINQ做点什么 var blueListItemsLinq = document.All.Where(m => m.LocalName == "li" && m.ClassList.Contains("blue")); //或者直接使用CSS选择器 var blueListItemsCssSelector = document.QuerySelectorAll("li.blue"); Console.WriteLine("Comparing both ways ..."); Console.WriteLine(); Console.WriteLine("LINQ:"); foreach (var item in blueListItemsLinq) { Console.WriteLine(item.Text()); } Console.WriteLine(); Console.WriteLine("CSS:"); foreach (var item in blueListItemsCssSelector) { Console.WriteLine(item.Text()); } } static async Task SingleElements() { //使用默认配置创建一个用于评估web页面的新上下文 var context = BrowsingContext.New(Configuration.Default); //创建一个新文档 var document = await context.OpenAsync(req => req.Content("<b><i>This is some <em> bold <u>and</u> italic </em> text!</i></b>")); var emphasize = document.QuerySelector("em"); Console.WriteLine("Difference between several ways of getting text:"); Console.WriteLine(); Console.WriteLine("Only from C# / AngleSharp:"); Console.WriteLine(); Console.WriteLine(emphasize.ToHtml()); //<em> bold <u>and</u> italic </em> Console.WriteLine(emphasize.Text()); // bold and italic Console.WriteLine(); Console.WriteLine("From the DOM:"); Console.WriteLine(); Console.WriteLine(emphasize.InnerHtml); // bold <u>and</u> italic Console.WriteLine(emphasize.OuterHtml); //<em> bold <u>and</u> italic </em> Console.WriteLine(emphasize.TextContent);// bold and italic }