{"id":1245,"date":"2025-01-25T23:54:27","date_gmt":"2025-01-25T15:54:27","guid":{"rendered":"https:\/\/www.laixuexila.com\/?p=1245"},"modified":"2025-01-25T23:54:28","modified_gmt":"2025-01-25T15:54:28","slug":"%e5%a6%82%e4%bd%95%e5%9c%a8-c-%e4%b8%ad%e6%9c%89%e6%95%88%e8%a7%a3%e6%9e%90-html","status":"publish","type":"post","link":"https:\/\/www.laixuexila.com\/index.php\/2025\/01\/25\/%e5%a6%82%e4%bd%95%e5%9c%a8-c-%e4%b8%ad%e6%9c%89%e6%95%88%e8%a7%a3%e6%9e%90-html\/","title":{"rendered":"\u5982\u4f55\u5728 C# \u4e2d\u6709\u6548\u89e3\u6790 HTML"},"content":{"rendered":"\n

\u5728 C# \u4e2d\uff0c\u89e3\u6790 HTML \u901a\u5e38\u9700\u8981\u4f9d\u8d56\u7b2c\u4e09\u65b9\u5e93\u6765\u7b80\u5316\u5de5\u4f5c\u3002\u56e0\u4e3a C# \u6807\u51c6\u5e93\u5e76\u4e0d\u76f4\u63a5\u63d0\u4f9b\u4e13\u95e8\u7684 HTML \u89e3\u6790\u5de5\u5177\uff0c\u6240\u4ee5\u4f7f\u7528\u6d41\u884c\u7684\u5e93\u5982 HtmlAgilityPack<\/strong> \u548c AngleSharp<\/strong> \u53ef\u4ee5\u6709\u6548\u5730\u89e3\u6790\u548c\u64cd\u4f5c HTML \u5185\u5bb9\u3002\u4ee5\u4e0b\u662f\u51e0\u79cd\u5e38\u89c1\u7684\u65b9\u5f0f\u6765\u89e3\u6790 HTML\uff1a<\/p>\n\n\n\n

1. \u4f7f\u7528 HtmlAgilityPack<\/strong><\/h3>\n\n\n\n

HtmlAgilityPack \u662f\u4e00\u4e2a\u529f\u80fd\u5f3a\u5927\u7684 .NET \u5e93\uff0c\u7528\u4e8e\u89e3\u6790 HTML \u6587\u4ef6\u5e76\u5141\u8bb8\u4f60\u901a\u8fc7 DOM \u64cd\u4f5c HTML \u5185\u5bb9\u3002\u5b83\u53ef\u4ee5\u5904\u7406\u4e0d\u89c4\u8303\u7684 HTML\uff0c\u7279\u522b\u662f\u5728\u6293\u53d6\u7f51\u9875\u65f6\u5e38\u89c1\u7684\u9519\u8bef\u3002<\/p>\n\n\n\n

\u5b89\u88c5 HtmlAgilityPack<\/h4>\n\n\n\n

\u9996\u5148\uff0c\u4f60\u9700\u8981\u901a\u8fc7 NuGet \u5b89\u88c5 HtmlAgilityPack\uff1a<\/p>\n\n\n\n

Install-Package HtmlAgilityPack<\/code><\/pre>\n\n\n\n
\u793a\u4f8b\u4ee3\u7801\uff1a\u89e3\u6790 HTML \u5e76\u63d0\u53d6\u6570\u636e<\/h4>\n\n\n\n
using HtmlAgilityPack;\nusing System;\n\npublic class HtmlParser\n{\n    public static void Main()\n    {\n        \/\/ \u521b\u5efa\u4e00\u4e2a HtmlDocument \u5bf9\u8c61\n        var web = new HtmlWeb();\n\n        \/\/ \u52a0\u8f7d HTML \u6587\u6863\n        var doc = web.Load(\"https:\/\/example.com\");\n\n        \/\/ \u83b7\u53d6\u7f51\u9875\u4e2d\u7684\u6240\u6709\u94fe\u63a5\n        foreach (var link in doc.DocumentNode.SelectNodes(\"\/\/a[@href]\"))\n        {\n            Console.WriteLine(link.GetAttributeValue(\"href\", \"\"));\n        }\n    }\n}<\/code><\/pre>\n\n\n\n
\u5728\u8fd9\u4e2a\u4f8b\u5b50\u4e2d\uff0c\u6211\u4eec\u4f7f\u7528 HtmlWeb<\/code> \u7c7b\u4ece URL \u52a0\u8f7d HTML\uff0c\u7136\u540e\u4f7f\u7528 SelectNodes<\/code> \u65b9\u6cd5\u6765\u67e5\u627e\u9875\u9762\u4e2d\u6240\u6709 <a><\/code> \u6807\u7b7e\u7684 href<\/code> \u5c5e\u6027\u3002<\/p>\n\n\n\n
2. \u4f7f\u7528 AngleSharp<\/strong><\/h3>\n\n\n\n
AngleSharp \u662f\u53e6\u4e00\u4e2a\u529f\u80fd\u5f3a\u5927\u7684 HTML \u89e3\u6790\u5e93\uff0c\u4e13\u4e3a\u6d4f\u89c8\u5668\u7c7b\u7684 DOM \u64cd\u4f5c\u8bbe\u8ba1\uff0c\u53ef\u4ee5\u89e3\u6790 HTML\u3001CSS \u548c JavaScript\u3002<\/p>\n\n\n\n
\u5b89\u88c5 AngleSharp<\/h4>\n\n\n\n
\u4f60\u53ef\u4ee5\u901a\u8fc7 NuGet \u5b89\u88c5 AngleSharp\uff1a<\/p>\n\n\n\n
Install-Package AngleSharp<\/code><\/pre>\n\n\n\n
\u793a\u4f8b\u4ee3\u7801\uff1a\u89e3\u6790 HTML \u5e76\u63d0\u53d6\u6570\u636e<\/h4>\n\n\n\n
using AngleSharp;\nusing AngleSharp.Dom;\nusing System;\nusing System.Threading.Tasks;\n\npublic class HtmlParser\n{\n    public static async Task Main()\n    {\n        \/\/ \u521b\u5efa\u4e00\u4e2a\u6d4f\u89c8\u5668\u4e0a\u4e0b\u6587\n        var config = Configuration.Default.WithDefaultLoader();\n        var document = await BrowsingContext.New(config).OpenAsync(\"https:\/\/example.com\");\n\n        \/\/ \u83b7\u53d6\u6240\u6709\u94fe\u63a5\n        var links = document.QuerySelectorAll(\"a\");\n\n        foreach (var link in links)\n        {\n            Console.WriteLine(link.GetAttribute(\"href\"));\n        }\n    }\n}<\/code><\/pre>\n\n\n\n
AngleSharp \u5141\u8bb8\u4f60\u4ee5\u5f02\u6b65\u7684\u65b9\u5f0f\u52a0\u8f7d\u7f51\u9875\uff0c\u8fd9\u5bf9\u4e8e\u9700\u8981\u6293\u53d6\u5927\u91cf\u7f51\u9875\u5185\u5bb9\u7684\u5e94\u7528\u7a0b\u5e8f\u7279\u522b\u6709\u7528\u3002<\/p>\n\n\n\n
3. \u4f7f\u7528 .NET \u5185\u7f6e\u7684 HtmlDocument<\/code><\/strong><\/h3>\n\n\n\n
\u5982\u679c\u4f60\u53ea\u9700\u8981\u8fdb\u884c\u7b80\u5355\u7684 HTML \u89e3\u6790\uff0c\u800c\u4e0d\u60f3\u5f15\u5165\u989d\u5916\u7684\u5e93\uff0c\u4e5f\u53ef\u4ee5\u4f7f\u7528 System.Windows.Forms<\/code> \u4e2d\u7684 HtmlDocument<\/code> \u7c7b\uff08\u9002\u7528\u4e8e Windows Forms \u5e94\u7528\u7a0b\u5e8f\uff09\u3002<\/p>\n\n\n\n
\u793a\u4f8b\u4ee3\u7801\uff1a<\/h4>\n\n\n\n
using System;\nusing System.Windows.Forms;\n\npublic class HtmlParser\n{\n    public static void Main()\n    {\n        var htmlDoc = new HtmlDocument();\n\n        \/\/ \u52a0\u8f7d HTML \u5b57\u7b26\u4e32\n        htmlDoc.LoadHtml(\"<html><body><a href='https:\/\/example.com'>Click here<\/a><\/body><\/html>\");\n\n        \/\/ \u83b7\u53d6\u94fe\u63a5\n        var link = htmlDoc.DocumentNode.SelectSingleNode(\"\/\/a\");\n        Console.WriteLine(link.GetAttributeValue(\"href\", \"\"));\n    }\n}<\/code><\/pre>\n\n\n\n
\u4e0d\u8fc7\u9700\u8981\u6ce8\u610f\u7684\u662f\uff0cHtmlDocument<\/code> \u7c7b\u662f\u9488\u5bf9 Windows Forms \u5e94\u7528\u7a0b\u5e8f\u8bbe\u8ba1\u7684\uff0c\u9002\u7528\u4e8e\u8f83\u7b80\u5355\u7684 HTML \u89e3\u6790\u9700\u6c42\u3002<\/p>\n\n\n\n
4. \u89e3\u6790 HTML \u5b57\u7b26\u4e32\u4e0e\u6b63\u5219\u8868\u8fbe\u5f0f<\/strong><\/h3>\n\n\n\n
\u5c3d\u7ba1\u4e0d\u63a8\u8350\uff0c\u4f46\u6709\u65f6\u53ef\u4ee5\u901a\u8fc7\u6b63\u5219\u8868\u8fbe\u5f0f\u89e3\u6790\u7b80\u5355\u7684 HTML \u5185\u5bb9\u3002\u5bf9\u4e8e\u590d\u6742\u7684 HTML \u7ed3\u6784\uff0c\u6b63\u5219\u8868\u8fbe\u5f0f\u53ef\u80fd\u4e0d\u591f\u7075\u6d3b\u548c\u5f3a\u5927\u3002<\/p>\n\n\n\n
\u793a\u4f8b\u4ee3\u7801\uff1a<\/h4>\n\n\n\n
using System;\nusing System.Text.RegularExpressions;\n\npublic class HtmlParser\n{\n    public static void Main()\n    {\n        string htmlContent = \"<html><body><a href='https:\/\/example.com'>Click here<\/a><\/body><\/html>\";\n\n        \/\/ \u4f7f\u7528\u6b63\u5219\u8868\u8fbe\u5f0f\u63d0\u53d6 href \u5c5e\u6027\n        var match = Regex.Match(htmlContent, @\"href\\s*=\\s*['\"\"](?<url>.*?)['\"\"]\");\n\n        if (match.Success)\n        {\n            Console.WriteLine(match.Groups[\"url\"].Value);\n        }\n    }\n}<\/code><\/pre>\n\n\n\n
\u867d\u7136\u6b63\u5219\u8868\u8fbe\u5f0f\u53ef\u4ee5\u7528\u4e8e\u7b80\u5355\u7684 HTML \u63d0\u53d6\uff0c\u4f46\u5b83\u5728\u5904\u7406\u590d\u6742\u6216\u4e0d\u89c4\u8303\u7684 HTML \u65f6\u5bb9\u6613\u5931\u8d25\u3002<\/p>\n\n\n\n
\u603b\u7ed3\uff1a<\/h3>\n\n\n\n
    \n
  1. HtmlAgilityPack<\/strong>\uff1a\u9002\u7528\u4e8e\u89e3\u6790\u4e0d\u89c4\u8303\u6216\u590d\u6742\u7684 HTML\uff0c\u5e38\u7528\u4e8e\u7f51\u9875\u6293\u53d6\u3002<\/li>\n\n\n\n
  2. AngleSharp<\/strong>\uff1a\u66f4\u73b0\u4ee3\u5316\uff0c\u652f\u6301\u66f4\u5b8c\u6574\u7684\u6d4f\u89c8\u5668\u98ce\u683c\u89e3\u6790\uff0c\u5c24\u5176\u9002\u7528\u4e8e\u9700\u8981\u5f02\u6b65\u52a0\u8f7d\u7684\u573a\u666f\u3002<\/li>\n\n\n\n
  3. .NET \u5185\u7f6e HtmlDocument<\/code><\/strong>\uff1a\u9002\u5408\u7b80\u5355\u9700\u6c42\uff0c\u9002\u7528\u4e8e Windows Forms \u5e94\u7528\u7a0b\u5e8f\u3002<\/li>\n\n\n\n
  4. \u6b63\u5219\u8868\u8fbe\u5f0f<\/strong>\uff1a\u7528\u4e8e\u975e\u5e38\u7b80\u5355\u7684 HTML \u89e3\u6790\uff0c\u901a\u5e38\u4e0d\u63a8\u8350\u7528\u4e8e\u590d\u6742\u573a\u666f\u3002<\/li>\n<\/ol>\n\n\n\n
    \u63a8\u8350\u4f7f\u7528 HtmlAgilityPack<\/strong> \u6216 AngleSharp<\/strong>\uff0c\u5b83\u4eec\u63d0\u4f9b\u4e86\u5f3a\u5927\u800c\u7075\u6d3b\u7684\u529f\u80fd\uff0c\u9002\u7528\u4e8e\u5927\u591a\u6570 HTML \u89e3\u6790\u9700\u6c42\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"
    \u5728 C# \u4e2d\uff0c\u89e3\u6790 HTML \u901a\u5e38\u9700\u8981\u4f9d\u8d56\u7b2c\u4e09\u65b9\u5e93\u6765\u7b80\u5316\u5de5\u4f5c\u3002\u56e0\u4e3a C# \u6807\u51c6\u5e93\u5e76\u4e0d\u76f4\u63a5\u63d0\u4f9b\u4e13\u95e8\u7684 HTML  […]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[59],"tags":[],"class_list":["post-1245","post","type-post","status-publish","format-standard","hentry","category-c"],"_links":{"self":[{"href":"https:\/\/www.laixuexila.com\/index.php\/wp-json\/wp\/v2\/posts\/1245","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.laixuexila.com\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.laixuexila.com\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.laixuexila.com\/index.php\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.laixuexila.com\/index.php\/wp-json\/wp\/v2\/comments?post=1245"}],"version-history":[{"count":1,"href":"https:\/\/www.laixuexila.com\/index.php\/wp-json\/wp\/v2\/posts\/1245\/revisions"}],"predecessor-version":[{"id":1246,"href":"https:\/\/www.laixuexila.com\/index.php\/wp-json\/wp\/v2\/posts\/1245\/revisions\/1246"}],"wp:attachment":[{"href":"https:\/\/www.laixuexila.com\/index.php\/wp-json\/wp\/v2\/media?parent=1245"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.laixuexila.com\/index.php\/wp-json\/wp\/v2\/categories?post=1245"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.laixuexila.com\/index.php\/wp-json\/wp\/v2\/tags?post=1245"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}