{"id":2159,"date":"2026-04-23T23:08:30","date_gmt":"2026-04-23T15:08:30","guid":{"rendered":"http:\/\/www.preluna.xyz\/?p=2159"},"modified":"2026-04-24T14:41:02","modified_gmt":"2026-04-24T06:41:02","slug":"htmlparser-%e7%9a%84%e4%bd%bf%e7%94%a8","status":"publish","type":"post","link":"http:\/\/www.preluna.xyz\/index.php\/2026\/04\/23\/htmlparser-%e7%9a%84%e4%bd%bf%e7%94%a8\/preluna\/text\/","title":{"rendered":"HTMLParser \u7684\u4f7f\u7528"},"content":{"rendered":"\n<figure class=\"wp-block-image size-large\"><div class='fancybox-wrapper lazyload-container-unload' data-fancybox='post-images' href='http:\/\/www.preluna.xyz\/wp-content\/uploads\/2026\/04\/HTMLParser-\u7684\u4f7f\u7528-877x1024.png'><img class=\"lazyload lazyload-style-1\" src=\"data:image\/svg+xml;base64,PCEtLUFyZ29uTG9hZGluZy0tPgo8c3ZnIHdpZHRoPSIxIiBoZWlnaHQ9IjEiIHhtbG5zPSJodHRwOi8vd3d3LnczLm9yZy8yMDAwL3N2ZyIgc3Ryb2tlPSIjZmZmZmZmMDAiPjxnPjwvZz4KPC9zdmc+\"  loading=\"lazy\" decoding=\"async\" width=\"877\" height=\"1024\" data-original=\"http:\/\/www.preluna.xyz\/wp-content\/uploads\/2026\/04\/HTMLParser-\u7684\u4f7f\u7528-877x1024.png\" src=\"data:image\/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAAAXNSR0IArs4c6QAAAARnQU1BAACxjwv8YQUAAAAJcEhZcwAADsQAAA7EAZUrDhsAAAANSURBVBhXYzh8+PB\/AAffA0nNPuCLAAAAAElFTkSuQmCC\" alt=\"\" class=\"wp-image-2160\"  sizes=\"auto, (max-width: 877px) 100vw, 877px\" \/><\/div><\/figure>\n\n\n\n<h2 class=\"wp-block-heading\">\u9898\u76ee\u8003\u70b9<\/h2>\n\n\n\n<p>\u8fd9\u9053\u9898\u4e3b\u8981\u8003\u7684\u662f\u4e0b\u9762\u51e0\u4e2a\u70b9\uff1a<\/p>\n\n\n\n<ol class=\"wp-block-list\">\n<li><code>HTMLParser<\/code> \u7684\u4f7f\u7528<\/li>\n\n\n\n<li>\u7ee7\u627f\u7c7b\u5e76\u91cd\u5199\u56de\u8c03\u65b9\u6cd5<\/li>\n\n\n\n<li>\u5b57\u7b26\u4e32\u5224\u65ad\uff0c\u6bd4\u5982\u662f\u5426\u5305\u542b\u6362\u884c\u7b26 <code>\\n<\/code><\/li>\n\n\n\n<li>\u8f93\u5165\u5904\u7406\uff1a\u628a\u591a\u884c HTML \u4ee3\u7801\u8bfb\u8fdb\u6765<\/li>\n\n\n\n<li>\u6309\u9898\u76ee\u8981\u6c42\u683c\u5f0f\u8f93\u51fa<\/li>\n<\/ol>\n\n\n\n<p>\u8fd9\u9898\u672c\u8d28\u4e0a\u4e0d\u662f\u8ba9\u4f60\u201c\u81ea\u5df1\u786c\u5199\u4e00\u4e2a HTML \u89e3\u6790\u5668\u201d\uff0c\u800c\u662f\u8ba9\u4f60\u5b66\u4f1a\u7528 Python \u5df2\u7ecf\u63d0\u4f9b\u597d\u7684 <code>HTMLParser<\/code>\u3002<\/p>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h2 class=\"wp-block-heading\">\u5ba1\u9898<\/h2>\n\n\n\n<p>\u6211\u4eec\u5148\u628a\u9898\u76ee\u7ffb\u8bd1\u6210\u66f4\u5bb9\u6613\u4e0b\u624b\u7684\u8bdd\u3002<\/p>\n\n\n\n<p>\u9898\u76ee\u7ed9\u4f60\u4e00\u6bb5\u5305\u542b <code>N<\/code> \u884c\u7684 HTML \u4ee3\u7801\uff0c\u8981\u6c42\u4f60\u6309\u51fa\u73b0\u987a\u5e8f\u8f93\u51fa\u4e09\u7c7b\u5185\u5bb9\uff1a<\/p>\n\n\n\n<ol class=\"wp-block-list\">\n<li>\u5355\u884c\u6ce8\u91ca<\/li>\n\n\n\n<li>\u591a\u884c\u6ce8\u91ca<\/li>\n\n\n\n<li>\u6570\u636e\u5185\u5bb9<\/li>\n<\/ol>\n\n\n\n<p>\u8fd9\u91cc\u6700\u5173\u952e\u7684\u662f\u8981\u5206\u6e05\uff1a<\/p>\n\n\n\n<h3 class=\"wp-block-heading\">\u4ec0\u4e48\u662f\u6ce8\u91ca<\/h3>\n\n\n\n<p>HTML \u6ce8\u91ca\u957f\u8fd9\u6837\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>&lt;!-- \u6ce8\u91ca\u5185\u5bb9 --&gt;\n<\/code><\/pre>\n\n\n\n<p>\u5982\u679c\u6ce8\u91ca\u5185\u5bb9\u8de8\u4e86\u591a\u884c\uff0c\u5c31\u662f\u591a\u884c\u6ce8\u91ca\uff1b\u5982\u679c\u53ea\u5728\u4e00\u884c\u91cc\uff0c\u5c31\u662f\u5355\u884c\u6ce8\u91ca\u3002<\/p>\n\n\n\n<h3 class=\"wp-block-heading\">\u4ec0\u4e48\u662f\u6570\u636e<\/h3>\n\n\n\n<p>\u6807\u7b7e\u91cc\u9762\u771f\u6b63\u7684\u6587\u672c\u5185\u5bb9\u5c31\u662f data\uff0c\u4f8b\u5982\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>&lt;div&gt;Welcome to HackerRank&lt;\/div&gt;\n<\/code><\/pre>\n\n\n\n<p>\u8fd9\u91cc\u7684 data \u5c31\u662f\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>Welcome to HackerRank\n<\/code><\/pre>\n\n\n\n<h3 class=\"wp-block-heading\">\u5bb9\u6613\u5ffd\u7565\u7684\u70b9<\/h3>\n\n\n\n<p>\u9898\u76ee\u7279\u522b\u63d0\u9192\uff1a<\/p>\n\n\n\n<blockquote class=\"wp-block-quote is-layout-flow wp-block-quote-is-layout-flow\">\n<p>\u5982\u679c <code>data == '\\n'<\/code>\uff0c\u4e0d\u8981\u6253\u5370\u3002<\/p>\n<\/blockquote>\n\n\n\n<p>\u4e5f\u5c31\u662f\u8bf4\uff0c\u6709\u4e9b\u201c\u6570\u636e\u201d\u5176\u5b9e\u53ea\u662f\u4e00\u4e2a\u6362\u884c\u7b26\uff0c\u8fd9\u79cd\u65e0\u6548\u5185\u5bb9\u8981\u8df3\u8fc7\u3002<\/p>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h2 class=\"wp-block-heading\">\u601d\u8def\u63d0\u793a<\/h2>\n\n\n\n<p>\u5148\u4e0d\u8981\u6025\u7740\u5199\u4ee3\u7801\uff0c\u5148\u60f3\u505a\u6cd5\u3002<\/p>\n\n\n\n<p>\u8fd9\u9898\u7684\u5173\u952e\u601d\u8def\u662f\uff1a<\/p>\n\n\n\n<h3 class=\"wp-block-heading\">\u7b2c\u4e00\u6b65\uff1a\u4e0d\u8981\u81ea\u5df1\u624b\u52a8\u627e\u6ce8\u91ca\u548c\u6570\u636e<\/h3>\n\n\n\n<p>\u56e0\u4e3a HTML \u7ed3\u6784\u81ea\u5df1\u5904\u7406\u4f1a\u5f88\u9ebb\u70e6\uff0c\u6240\u4ee5\u76f4\u63a5\u4f7f\u7528 Python \u7684 <code>HTMLParser<\/code>\u3002<\/p>\n\n\n\n<h3 class=\"wp-block-heading\">\u7b2c\u4e8c\u6b65\uff1a\u8ba9\u89e3\u6790\u5668\u5e2e\u6211\u4eec\u201c\u78b0\u5230\u4ec0\u4e48\u5c31\u544a\u8bc9\u6211\u4eec\u201d<\/h3>\n\n\n\n<p><code>HTMLParser<\/code> \u5728\u89e3\u6790 HTML \u65f6\uff1a<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li>\u9047\u5230\u6ce8\u91ca\uff0c\u4f1a\u8c03\u7528\u4e00\u4e2a\u65b9\u6cd5<\/li>\n\n\n\n<li>\u9047\u5230\u666e\u901a\u6587\u672c\u6570\u636e\uff0c\u4e5f\u4f1a\u8c03\u7528\u4e00\u4e2a\u65b9\u6cd5<\/li>\n<\/ul>\n\n\n\n<p>\u6240\u4ee5\u6211\u4eec\u53ea\u9700\u8981\u628a\u8fd9\u4e9b\u65b9\u6cd5\u6539\u5199\u6389\uff0c\u5728\u91cc\u9762\u6309\u9898\u76ee\u683c\u5f0f\u6253\u5370\u5373\u53ef\u3002<\/p>\n\n\n\n<h3 class=\"wp-block-heading\">\u7b2c\u4e09\u6b65\uff1a\u5224\u65ad\u5355\u884c\u8fd8\u662f\u591a\u884c<\/h3>\n\n\n\n<p>\u5f53\u89e3\u6790\u5668\u628a\u6ce8\u91ca\u5185\u5bb9\u4f20\u7ed9\u6211\u4eec\u65f6\uff1a<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li>\u5982\u679c\u5185\u5bb9\u91cc\u6709 <code>\\n<\/code>\uff0c\u8bf4\u660e\u5b83\u8de8\u884c\u4e86\uff0c\u662f\u591a\u884c\u6ce8\u91ca<\/li>\n\n\n\n<li>\u5426\u5219\u5c31\u662f\u5355\u884c\u6ce8\u91ca<\/li>\n<\/ul>\n\n\n\n<h3 class=\"wp-block-heading\">\u7b2c\u56db\u6b65\uff1a\u5904\u7406 data<\/h3>\n\n\n\n<p>\u5982\u679c data \u53ea\u662f\u4e00\u4e2a\u6362\u884c\u7b26 <code>'\\n'<\/code>\uff0c\u8df3\u8fc7\uff1b<br>\u5426\u5219\u8f93\u51fa\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>&gt;&gt;&gt; Data\n\u5177\u4f53\u5185\u5bb9\n<\/code><\/pre>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h2 class=\"wp-block-heading\">\u5b8c\u6574\u8bbe\u8ba1\u601d\u8def<\/h2>\n\n\n\n<p>\u73b0\u5728\u628a\u6574\u4e2a\u8fc7\u7a0b\u5c55\u5f00\u6210\u6e05\u6670\u6b65\u9aa4\u3002<\/p>\n\n\n\n<h3 class=\"wp-block-heading\">\u7b2c\u4e00\u6b65\uff1a\u5b9a\u4e49\u4e00\u4e2a\u65b0\u7684\u89e3\u6790\u5668\u7c7b<\/h3>\n\n\n\n<p>\u6211\u4eec\u7ee7\u627f <code>HTMLParser<\/code>\uff0c\u6bd4\u5982\u5199\u6210\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>class MyHTMLParser(HTMLParser):\n<\/code><\/pre>\n\n\n\n<p>\u7136\u540e\u91cd\u5199\u4e24\u4e2a\u65b9\u6cd5\uff1a<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li><code>handle_comment(self, data)<\/code>\uff1a\u5904\u7406\u6ce8\u91ca<\/li>\n\n\n\n<li><code>handle_data(self, data)<\/code>\uff1a\u5904\u7406\u6570\u636e<\/li>\n<\/ul>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h3 class=\"wp-block-heading\">\u7b2c\u4e8c\u6b65\uff1a\u5728 <code>handle_comment()<\/code> \u91cc\u5206\u7c7b\u8f93\u51fa<\/h3>\n\n\n\n<p>\u89e3\u6790\u5668\u9047\u5230\u6ce8\u91ca\u65f6\uff0c\u4f1a\u628a\u6ce8\u91ca\u5185\u90e8\u7684\u5185\u5bb9\u4f20\u7ed9 <code>data<\/code>\u3002<\/p>\n\n\n\n<p>\u6bd4\u5982\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>&lt;!--&#91;if IE 9]&gt;IE9-specific content&lt;!&#91;endif]--&gt;\n<\/code><\/pre>\n\n\n\n<p>\u4f20\u8fdb\u6765\u7684 <code>data<\/code> \u5b9e\u9645\u662f\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>&#91;if IE 9]&gt;IE9-specific content&lt;!&#91;endif]\n<\/code><\/pre>\n\n\n\n<p>\u8fd9\u65f6\u5019\u6211\u4eec\u5224\u65ad\uff1a<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li><code>'\\n' in data<\/code>\uff1a\u591a\u884c\u6ce8\u91ca<\/li>\n\n\n\n<li>\u5426\u5219\uff1a\u5355\u884c\u6ce8\u91ca<\/li>\n<\/ul>\n\n\n\n<p>\u7136\u540e\u6309\u9898\u76ee\u8981\u6c42\u6253\u5370\u3002<\/p>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h3 class=\"wp-block-heading\">\u7b2c\u4e09\u6b65\uff1a\u5728 <code>handle_data()<\/code> \u91cc\u5904\u7406\u6587\u672c\u5185\u5bb9<\/h3>\n\n\n\n<p>\u5982\u679c data \u662f\u666e\u901a\u6587\u672c\uff0c\u5c31\u8f93\u51fa\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>&gt;&gt;&gt; Data\ndata\n<\/code><\/pre>\n\n\n\n<p>\u4f46\u6709\u4e00\u4e2a\u4f8b\u5916\uff1a<\/p>\n\n\n\n<p>\u5982\u679c <code>data == '\\n'<\/code>\uff0c\u8bf4\u660e\u53ea\u662f\u6362\u884c\uff0c\u4e0d\u8f93\u51fa\u3002<\/p>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h3 class=\"wp-block-heading\">\u7b2c\u56db\u6b65\uff1a\u628a\u8f93\u5165\u7684 N \u884c HTML \u8bfb\u8fdb\u6765<\/h3>\n\n\n\n<p>\u9898\u76ee\u4f1a\u5148\u7ed9\u4e00\u4e2a\u6574\u6570 <code>N<\/code>\uff0c\u8868\u793a\u540e\u9762\u6709\u591a\u5c11\u884c HTML\u3002<\/p>\n\n\n\n<p>\u6240\u4ee5\u5148\u8bfb\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>n = int(input())\n<\/code><\/pre>\n\n\n\n<p>\u7136\u540e\u5faa\u73af\u8bfb\u5165 <code>n<\/code> \u884c\u3002<\/p>\n\n\n\n<p>\u8fd9\u91cc\u5efa\u8bae\u628a\u6240\u6709\u884c\u62fc\u63a5\u6210\u4e00\u4e2a\u5b8c\u6574\u5b57\u7b26\u4e32\uff0c\u518d\u4e00\u6b21\u6027\u4ea4\u7ed9\u89e3\u6790\u5668\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>html = \"\\n\".join(...)\n<\/code><\/pre>\n\n\n\n<p>\u4e3a\u4ec0\u4e48\u8fd9\u6837\u505a\uff1f<\/p>\n\n\n\n<p>\u56e0\u4e3a\u591a\u884c\u6ce8\u91ca\u672c\u6765\u5c31\u53ef\u80fd\u8de8\u5f88\u591a\u884c\uff0c\u5982\u679c\u4f60\u4e00\u884c\u4e00\u884c\u5355\u72ec\u5582\u7ed9\u89e3\u6790\u5668\uff0c\u867d\u7136\u6709\u65f6\u4e5f\u80fd\u8fc7\uff0c\u4f46\u4ece\u6574\u4f53\u4e0a\u62fc\u6210\u4e00\u6bb5 HTML \u518d\u89e3\u6790\uff0c\u66f4\u7b26\u5408\u201c\u8fd9\u662f\u4e00\u4e2a\u5b8c\u6574 HTML \u7247\u6bb5\u201d\u7684\u601d\u8def\uff0c\u4e5f\u66f4\u7a33\u3002<\/p>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h2 class=\"wp-block-heading\">\u4ee3\u7801\u5b9e\u73b0<\/h2>\n\n\n\n<p>\u4e0b\u9762\u662f\u9002\u5408\u521d\u5b66\u8005\u7406\u89e3\u7684\u5199\u6cd5\u3002<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>from html.parser import HTMLParser\n\n\nclass MyHTMLParser(HTMLParser):\n    def handle_comment(self, data):\n        if '\\n' in data:\n            print(\">>> Multi-line Comment\")\n        else:\n            print(\">>> Single-line Comment\")\n        print(data)\n\n    def handle_data(self, data):\n        if data == '\\n':\n            return\n        print(\">>> Data\")\n        print(data)\n\n\nn = int(input())\nhtml_lines = &#91;]\n\nfor _ in range(n):\n    html_lines.append(input())\n\nhtml = '\\n'.join(html_lines)  \n\nparser = MyHTMLParser()\nparser.feed(html)\n<\/code><\/pre>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h2 class=\"wp-block-heading\">\u8fd0\u884c\u6f14\u793a<\/h2>\n\n\n\n<p>\u6211\u4eec\u7528\u9898\u76ee\u7684\u6837\u4f8b\u6765\u624b\u52a8\u8d70\u4e00\u904d\u3002<\/p>\n\n\n\n<h3 class=\"wp-block-heading\">\u8f93\u5165<\/h3>\n\n\n\n<pre class=\"wp-block-code\"><code>4\n&lt;!--&#91;if IE 9]&gt;IE9-specific content\n&lt;!&#91;endif]--&gt;\n&lt;div&gt; Welcome to HackerRank&lt;\/div&gt;\n&lt;!--&#91;if IE 9]&gt;IE9-specific content&lt;!&#91;endif]--&gt;\n<\/code><\/pre>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h3 class=\"wp-block-heading\">\u7b2c\u4e00\u6b65\uff1a\u8bfb\u5165 HTML<\/h3>\n\n\n\n<p>\u524d 4 \u884c HTML \u4f1a\u88ab\u62fc\u6210\u4e00\u4e2a\u5b8c\u6574\u5b57\u7b26\u4e32\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>&lt;!--&#91;if IE 9]&gt;IE9-specific content\n&lt;!&#91;endif]--&gt;\n&lt;div&gt; Welcome to HackerRank&lt;\/div&gt;\n&lt;!--&#91;if IE 9]&gt;IE9-specific content&lt;!&#91;endif]--&gt;\n<\/code><\/pre>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h3 class=\"wp-block-heading\">\u7b2c\u4e8c\u6b65\uff1a\u89e3\u6790\u7b2c\u4e00\u6bb5\u6ce8\u91ca<\/h3>\n\n\n\n<p>\u524d\u4e24\u884c\u7ec4\u6210\u4e00\u4e2a\u6ce8\u91ca\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>&lt;!--&#91;if IE 9]&gt;IE9-specific content\n&lt;!&#91;endif]--&gt;\n<\/code><\/pre>\n\n\n\n<p>\u6ce8\u91ca\u5185\u5bb9\u91cc\u6709\u6362\u884c\u7b26\uff0c\u6240\u4ee5\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>'\\n' in data\n<\/code><\/pre>\n\n\n\n<p>\u4e3a\u771f\uff0c\u56e0\u6b64\u8f93\u51fa\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>&gt;&gt;&gt; Multi-line Comment\n&#91;if IE 9]&gt;IE9-specific content\n&lt;!&#91;endif]\n<\/code><\/pre>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h3 class=\"wp-block-heading\">\u7b2c\u4e09\u6b65\uff1a\u89e3\u6790 <code>&lt;div&gt;<\/code> \u91cc\u7684\u6587\u672c<\/h3>\n\n\n\n<pre class=\"wp-block-code\"><code>&lt;div&gt; Welcome to HackerRank&lt;\/div&gt;\n<\/code><\/pre>\n\n\n\n<p>\u6807\u7b7e\u4e2d\u7684\u6587\u672c\u662f\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code> Welcome to HackerRank\n<\/code><\/pre>\n\n\n\n<p>\u8fd9\u4e0d\u662f\u5355\u72ec\u7684 <code>'\\n'<\/code>\uff0c\u6240\u4ee5\u8f93\u51fa\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>&gt;&gt;&gt; Data\n Welcome to HackerRank\n<\/code><\/pre>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h3 class=\"wp-block-heading\">\u7b2c\u56db\u6b65\uff1a\u89e3\u6790\u6700\u540e\u4e00\u4e2a\u6ce8\u91ca<\/h3>\n\n\n\n<pre class=\"wp-block-code\"><code>&lt;!--&#91;if IE 9]&gt;IE9-specific content&lt;!&#91;endif]--&gt;\n<\/code><\/pre>\n\n\n\n<p>\u8fd9\u6b21\u6ca1\u6709\u6362\u884c\u7b26\uff0c\u6240\u4ee5\u662f\u5355\u884c\u6ce8\u91ca\uff0c\u8f93\u51fa\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>&gt;&gt;&gt; Single-line Comment\n&#91;if IE 9]&gt;IE9-specific content&lt;!&#91;endif]\n<\/code><\/pre>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h2 class=\"wp-block-heading\">\u65b9\u6cd5\u603b\u7ed3<\/h2>\n\n\n\n<p>\u8fd9\u7c7b\u9898\u4ee5\u540e\u53ef\u4ee5\u8fd9\u6837\u8bc6\u522b\u3001\u8fd9\u6837\u4e0b\u624b\u3002<\/p>\n\n\n\n<h3 class=\"wp-block-heading\">\u770b\u5230\u201c\u89e3\u6790 HTML \/ XML \/ \u6807\u7b7e\u201d\u65f6\u5148\u60f3\uff1a<\/h3>\n\n\n\n<p>\u4e0d\u8981\u81ea\u5df1\u624b\u52a8\u5207\u5b57\u7b26\u4e32\uff0c\u4f18\u5148\u60f3\u6709\u6ca1\u6709\u73b0\u6210\u89e3\u6790\u5de5\u5177\u3002<\/p>\n\n\n\n<p>\u5728 Python \u91cc\uff0c\u548c HTML \u76f8\u5173\u7684\u9898\uff0c\u5e38\u89c1\u5de5\u5177\u5c31\u662f\uff1a<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li><code>HTMLParser<\/code><\/li>\n<\/ul>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h3 class=\"wp-block-heading\">\u8fd9\u9898\u7684\u901a\u7528\u5957\u8def<\/h3>\n\n\n\n<p>\u9047\u5230\u8fd9\u79cd\u201c\u89e3\u6790\u8fc7\u7a0b\u4e2d\u78b0\u5230\u4ec0\u4e48\u5c31\u505a\u4ec0\u4e48\u201d\u7684\u9898\uff0c\u901a\u5e38\u6309\u8fd9\u4e2a\u6a21\u5f0f\u505a\uff1a<\/p>\n\n\n\n<ol class=\"wp-block-list\">\n<li>\u7ee7\u627f\u7cfb\u7edf\u63d0\u4f9b\u7684\u89e3\u6790\u5668\u7c7b<\/li>\n\n\n\n<li>\u91cd\u5199\u5bf9\u5e94\u7684\u5904\u7406\u51fd\u6570<\/li>\n\n\n\n<li>\u5728\u5904\u7406\u51fd\u6570\u91cc\u5b8c\u6210\u8f93\u51fa\u6216\u7edf\u8ba1<\/li>\n\n\n\n<li>\u6700\u540e\u628a\u6574\u6bb5\u5185\u5bb9\u4ea4\u7ed9\u89e3\u6790\u5668\u53bb\u626b<\/li>\n<\/ol>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h3 class=\"wp-block-heading\">\u8fd9\u9898\u771f\u6b63\u96be\u70b9\u4e0d\u662f\u4ee3\u7801\uff0c\u800c\u662f\u5ba1\u9898<\/h3>\n\n\n\n<p>\u4f60\u8981\u6293\u4f4f\u4e24\u4e2a\u5224\u65ad\u6761\u4ef6\uff1a<\/p>\n\n\n\n<ol class=\"wp-block-list\">\n<li>\u6ce8\u91ca\u91cc\u6709\u6ca1\u6709 <code>\\n<\/code>\n<ul class=\"wp-block-list\">\n<li>\u6709\uff1a\u591a\u884c\u6ce8\u91ca<\/li>\n\n\n\n<li>\u6ca1\u6709\uff1a\u5355\u884c\u6ce8\u91ca<\/li>\n<\/ul>\n<\/li>\n\n\n\n<li>\u6570\u636e\u662f\u4e0d\u662f\u521a\u597d\u7b49\u4e8e <code>'\\n'<\/code>\n<ul class=\"wp-block-list\">\n<li>\u662f\uff1a\u4e0d\u8f93\u51fa<\/li>\n\n\n\n<li>\u4e0d\u662f\uff1a\u8f93\u51fa data<\/li>\n<\/ul>\n<\/li>\n<\/ol>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h3 class=\"wp-block-heading\">\u672c\u8282\u5c0f\u7ed3<\/h3>\n\n\n\n<p>\u8fd9\u9898\u6700\u6838\u5fc3\u7684\u4e00\u53e5\u8bdd\u5c31\u662f\uff1a<\/p>\n\n\n\n<p><strong>\u4e0d\u7528\u81ea\u5df1\u5206\u6790 HTML \u7ed3\u6784\uff0c\u800c\u662f\u501f\u52a9 <code>HTMLParser<\/code>\uff0c\u5728\u201c\u6ce8\u91ca\u56de\u8c03\u201d\u548c\u201c\u6570\u636e\u56de\u8c03\u201d\u91cc\u6309\u89c4\u5219\u6253\u5370\u3002<\/strong><\/p>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h2 class=\"wp-block-heading\">\u7ec3\u4e60<\/h2>\n\n\n\n<p>\u4f60\u53ef\u4ee5\u5148\u81ea\u5df1\u505a\u8fd9\u4e00\u9898\uff0c\u4e0d\u8981\u6025\u7740\u770b\u7b54\u6848\u3002<\/p>\n\n\n\n<h3 class=\"wp-block-heading\">\u7ec3\u4e60\u9898<\/h3>\n\n\n\n<p>\u7ed9\u5b9a\u4e0b\u9762\u8fd9\u6bb5 HTML\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>&lt;!--hello--&gt;\n&lt;p&gt;Python&lt;\/p&gt;\n&lt;!--line1\nline2--&gt;\n<\/code><\/pre>\n\n\n\n<p>\u8bf7\u6309\u9898\u76ee\u540c\u6837\u7684\u89c4\u5219\u8f93\u51fa\u7ed3\u679c\u3002<\/p>\n\n\n\n<h3 class=\"wp-block-heading\">\u63d0\u793a<\/h3>\n\n\n\n<p>\u4f60\u53ef\u4ee5\u5148\u81ea\u5df1\u5224\u65ad\uff1a<\/p>\n\n\n\n<ol class=\"wp-block-list\">\n<li>\u7b2c\u4e00\u6bb5\u6ce8\u91ca\u662f\u5355\u884c\u8fd8\u662f\u591a\u884c\uff1f<\/li>\n\n\n\n<li><code>&lt;p&gt;Python&lt;\/p&gt;<\/code> \u91cc\u9762\u7684 data \u662f\u4ec0\u4e48\uff1f<\/li>\n\n\n\n<li>\u6700\u540e\u4e00\u6bb5\u6ce8\u91ca\u91cc\u6709\u6ca1\u6709 <code>\\n<\/code>\uff1f<\/li>\n<\/ol>\n\n\n\n<h2 class=\"wp-block-heading\">\u8fd9\u6b21\u6211\u4eec\u4e0d\u76f4\u63a5\u770b\u7b54\u6848\uff0c\u800c\u662f\u4ece\u7a7a\u767d\u5f00\u59cb\u642d\u51fa\u6765<\/h2>\n\n\n\n<p>\u8fd9\u9053\u9898\u5f88\u9002\u5408\u7ec3\u4e00\u79cd\u80fd\u529b\uff1a<strong>\u5148\u628a\u7a0b\u5e8f\u9aa8\u67b6\u642d\u8d77\u6765\uff0c\u518d\u4e00\u70b9\u70b9\u628a\u7ec6\u8282\u586b\u8fdb\u53bb<\/strong>\u3002<br>\u4f60\u4ee5\u540e\u505a\u9898\u65f6\uff0c\u5982\u679c\u603b\u89c9\u5f97\u201c\u6211\u77e5\u9053\u5927\u6982\u5728\u8003\u4ec0\u4e48\uff0c\u4f46\u5c31\u662f\u5199\u4e0d\u51fa\u6765\u201d\uff0c\u90a3\u5c31\u7279\u522b\u9700\u8981\u8fd9\u79cd\u8bad\u7ec3\u65b9\u5f0f\u3002<\/p>\n\n\n\n<p>\u8fd9\u6b21\u6211\u4eec\u5c31\u4e25\u683c\u6309\u4f60\u8bf4\u7684\u987a\u5e8f\u6765\uff1a<\/p>\n\n\n\n<ol class=\"wp-block-list\">\n<li>\u5148\u5199\u7c7b<\/li>\n\n\n\n<li>\u518d\u5199\u65b9\u6cd5<\/li>\n\n\n\n<li>\u6700\u540e\u5199\u4e3b\u7a0b\u5e8f<\/li>\n<\/ol>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h2 class=\"wp-block-heading\">\u5148\u60f3\u6e05\u695a\uff1a\u8fd9\u9053\u9898\u7684\u7a0b\u5e8f\u957f\u4ec0\u4e48\u6837<\/h2>\n\n\n\n<p>\u8fd9\u9898\u4e0d\u662f\u666e\u901a\u7684\u201c\u8bfb\u5165\u6570\u5b57\u7136\u540e\u8ba1\u7b97\u201d\u7684\u9898\uff0c\u5b83\u66f4\u50cf\u662f\uff1a<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li>\u6211\u4eec\u5148\u9020\u4e00\u4e2a\u201c\u4f1a\u89e3\u6790 HTML \u7684\u5bf9\u8c61\u201d<\/li>\n\n\n\n<li>\u8fd9\u4e2a\u5bf9\u8c61\u5728\u9047\u5230\u6ce8\u91ca\u65f6\uff0c\u81ea\u52a8\u8c03\u7528\u4e00\u4e2a\u65b9\u6cd5<\/li>\n\n\n\n<li>\u5728\u9047\u5230\u6587\u672c\u6570\u636e\u65f6\uff0c\u81ea\u52a8\u8c03\u7528\u53e6\u4e00\u4e2a\u65b9\u6cd5<\/li>\n\n\n\n<li>\u6211\u4eec\u53ea\u9700\u8981\u5728\u8fd9\u4e24\u4e2a\u65b9\u6cd5\u91cc\u5199\u201c\u600e\u4e48\u8f93\u51fa\u201d<\/li>\n<\/ul>\n\n\n\n<p>\u6240\u4ee5\u6574\u4e2a\u7a0b\u5e8f\u7ed3\u6784\u5176\u5b9e\u5f88\u56fa\u5b9a\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>from html.parser import HTMLParser\n\nclass MyHTMLParser(HTMLParser):\n    # \u5199\u5904\u7406\u6ce8\u91ca\u7684\u65b9\u6cd5\n    # \u5199\u5904\u7406\u6570\u636e\u7684\u65b9\u6cd5\n\n# \u4e3b\u7a0b\u5e8f\n# \u8bfb\u5165 n\n# \u8bfb\u5165 n \u884c html\n# \u521b\u5efa\u89e3\u6790\u5668\u5bf9\u8c61\n# \u5582\u7ed9\u5b83 html\n<\/code><\/pre>\n\n\n\n<p>\u4f60\u5148\u4e0d\u8981\u7ba1\u65b9\u6cd5\u91cc\u9762\u600e\u4e48\u5199\uff0c\u5148\u628a\u8fd9\u4e2a\u6574\u4f53\u9aa8\u67b6\u8bb0\u4f4f\u3002<\/p>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h2 class=\"wp-block-heading\">\u7b2c\u4e00\u6b65\uff1a\u5148\u628a\u7c7b\u5199\u51fa\u6765<\/h2>\n\n\n\n<p>\u5148\u5199\u5bfc\u5165\uff0c\u518d\u5199\u4e00\u4e2a\u7ee7\u627f <code>HTMLParser<\/code> \u7684\u7c7b\u3002<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>from html.parser import HTMLParser\n\n\nclass MyHTMLParser(HTMLParser):\n    pass\n<\/code><\/pre>\n\n\n\n<h3 class=\"wp-block-heading\">\u8fd9\u91cc\u5728\u5e72\u4ec0\u4e48<\/h3>\n\n\n\n<p><code>HTMLParser<\/code> \u662f Python \u5df2\u7ecf\u5199\u597d\u7684 HTML \u89e3\u6790\u5668\u3002<br>\u6211\u4eec\u73b0\u5728\u4e0d\u662f\u4ece\u96f6\u9020\u8f6e\u5b50\uff0c\u800c\u662f\u201c\u7ee7\u627f\u201d\u5b83\uff0c\u7136\u540e\u5728\u5b83\u539f\u6709\u80fd\u529b\u4e0a\u52a0\u81ea\u5df1\u7684\u5904\u7406\u903b\u8f91\u3002<\/p>\n\n\n\n<h3 class=\"wp-block-heading\">\u4e3a\u4ec0\u4e48\u5148\u5199 <code>pass<\/code><\/h3>\n\n\n\n<p>\u56e0\u4e3a\u6211\u4eec\u73b0\u5728\u53ea\u662f\u5148\u628a\u7c7b\u7684\u6846\u67b6\u642d\u51fa\u6765\u3002<br><code>pass<\/code> \u7684\u610f\u601d\u53ef\u4ee5\u7406\u89e3\u6210\uff1a<\/p>\n\n\n\n<blockquote class=\"wp-block-quote is-layout-flow wp-block-quote-is-layout-flow\">\n<p>\u8fd9\u4e2a\u4f4d\u7f6e\u5148\u5360\u7740\uff0c\u540e\u9762\u518d\u8865\u5185\u5bb9\u3002<\/p>\n<\/blockquote>\n\n\n\n<p>\u8fd9\u4e00\u6b65\u7684\u76ee\u6807\u4e0d\u662f\u201c\u5199\u5b8c\u201d\uff0c\u800c\u662f\u5148\u628a\u7a0b\u5e8f\u7684\u5927\u6846\u67b6\u7acb\u8d77\u6765\u3002<\/p>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h2 class=\"wp-block-heading\">\u7b2c\u4e8c\u6b65\uff1a\u5148\u8865\u7b2c\u4e00\u4e2a\u65b9\u6cd5 <code>handle_comment<\/code><\/h2>\n\n\n\n<p>\u8fd9\u9898\u8981\u6c42\u8f93\u51fa\u6ce8\u91ca\uff0c\u6240\u4ee5\u6211\u4eec\u5148\u628a\u201c\u5904\u7406\u6ce8\u91ca\u201d\u7684\u65b9\u6cd5\u5199\u51fa\u6765\u3002<\/p>\n\n\n\n<p>\u5728 <code>HTMLParser<\/code> \u91cc\uff0c\u9047\u5230 HTML \u6ce8\u91ca\u65f6\uff0c\u4f1a\u81ea\u52a8\u8c03\u7528\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>handle_comment(self, data)\n<\/code><\/pre>\n\n\n\n<p>\u6240\u4ee5\u6211\u4eec\u628a\u5b83\u52a0\u5230\u7c7b\u91cc\u3002<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>from html.parser import HTMLParser\n\n\nclass MyHTMLParser(HTMLParser):\n    def handle_comment(self, data):\n        pass\n<\/code><\/pre>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h2 class=\"wp-block-heading\">\u7b2c\u4e09\u6b65\uff1a\u60f3\u6e05\u695a <code>handle_comment<\/code> \u91cc\u9762\u8981\u505a\u4ec0\u4e48<\/h2>\n\n\n\n<p>\u5148\u4e0d\u8981\u6025\u7740\u5199\u4ee3\u7801\uff0c\u5148\u60f3\u903b\u8f91\u3002<\/p>\n\n\n\n<p>\u9898\u76ee\u8981\u6c42\uff1a<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li>\u5982\u679c\u6ce8\u91ca\u662f\u5355\u884c\u7684\uff0c\u8f93\u51fa <code>&gt;&gt;&gt; Single-line Comment<\/code><\/li>\n\n\n\n<li>\u5982\u679c\u6ce8\u91ca\u662f\u591a\u884c\u7684\uff0c\u8f93\u51fa <code>&gt;&gt;&gt; Multi-line Comment<\/code><\/li>\n\n\n\n<li>\u7136\u540e\u518d\u8f93\u51fa\u6ce8\u91ca\u5185\u5bb9\u672c\u8eab<\/li>\n<\/ul>\n\n\n\n<p>\u90a3\u4e48\u95ee\u9898\u5c31\u53d8\u6210\uff1a<\/p>\n\n\n\n<p><strong>\u600e\u4e48\u5224\u65ad\u5355\u884c\u8fd8\u662f\u591a\u884c\uff1f<\/strong><\/p>\n\n\n\n<p>\u7b54\u6848\u5c31\u662f\u770b\u6ce8\u91ca\u5185\u5bb9\u91cc\u6709\u6ca1\u6709\u6362\u884c\u7b26 <code>\\n<\/code>\u3002<\/p>\n\n\n\n<p>\u4e5f\u5c31\u662f\u8bf4\uff1a<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li>\u5982\u679c <code>'\\n' in data<\/code>\uff0c\u5c31\u662f\u591a\u884c\u6ce8\u91ca<\/li>\n\n\n\n<li>\u5426\u5219\u5c31\u662f\u5355\u884c\u6ce8\u91ca<\/li>\n<\/ul>\n\n\n\n<p>\u6240\u4ee5\u8fd9\u4e00\u6bb5\u7684\u903b\u8f91\u53ef\u4ee5\u5148\u5199\u6210\u201c\u4e2d\u6587\u601d\u8def\u201d\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>def handle_comment(self, data):\n    \u5982\u679c data \u91cc\u6709 \\n:\n        \u6253\u5370\u591a\u884c\u6ce8\u91ca\u6807\u9898\n    \u5426\u5219:\n        \u6253\u5370\u5355\u884c\u6ce8\u91ca\u6807\u9898\n\n    \u6253\u5370\u6ce8\u91ca\u5185\u5bb9\n<\/code><\/pre>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h2 class=\"wp-block-heading\">\u7b2c\u56db\u6b65\uff1a\u628a <code>handle_comment<\/code> \u771f\u6b63\u5199\u6210\u4ee3\u7801<\/h2>\n\n\n\n<p>\u73b0\u5728\u628a\u521a\u624d\u7684\u601d\u8def\u7ffb\u8bd1\u6210 Python\u3002<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>from html.parser import HTMLParser\n\n\nclass MyHTMLParser(HTMLParser):\n    def handle_comment(self, data):\n        if '\\n' in data:\n            print(\"&gt;&gt;&gt; Multi-line Comment\")\n        else:\n            print(\"&gt;&gt;&gt; Single-line Comment\")\n        print(data)\n<\/code><\/pre>\n\n\n\n<h3 class=\"wp-block-heading\">\u8fd9\u4e00\u6b65\u4e3a\u4ec0\u4e48\u8fd9\u6837\u5199<\/h3>\n\n\n\n<p>\u8fd9\u91cc\u6700\u91cd\u8981\u7684\u662f\u8fd9\u4e2a\u5224\u65ad\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>if '\\n' in data:\n<\/code><\/pre>\n\n\n\n<p>\u5b83\u7684\u610f\u601d\u662f\uff1a<\/p>\n\n\n\n<blockquote class=\"wp-block-quote is-layout-flow wp-block-quote-is-layout-flow\">\n<p>\u5982\u679c\u5b57\u7b26\u4e32 <code>data<\/code> \u91cc\u9762\u5305\u542b\u6362\u884c\u7b26\uff0c\u5c31\u8bf4\u660e\u8fd9\u4e2a\u6ce8\u91ca\u8de8\u4e86\u591a\u884c\u3002<\/p>\n<\/blockquote>\n\n\n\n<p>\u7136\u540e\u65e0\u8bba\u662f\u5355\u884c\u8fd8\u662f\u591a\u884c\uff0c\u6700\u540e\u90fd\u8981\u8f93\u51fa\u6ce8\u91ca\u5185\u5bb9\u672c\u8eab\uff0c\u6240\u4ee5\u540e\u9762\u7edf\u4e00\u5199\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>print(data)\n<\/code><\/pre>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h2 class=\"wp-block-heading\">\u7b2c\u4e94\u6b65\uff1a\u518d\u8865\u7b2c\u4e8c\u4e2a\u65b9\u6cd5 <code>handle_data<\/code><\/h2>\n\n\n\n<p>\u9898\u76ee\u9664\u4e86\u6ce8\u91ca\uff0c\u8fd8\u8981\u8f93\u51fa\u6570\u636e\u5185\u5bb9\u3002<br>\u6240\u4ee5\u6211\u4eec\u8fd8\u9700\u8981\u5904\u7406\u201c\u6807\u7b7e\u4e2d\u7684\u666e\u901a\u6587\u672c\u201d\u3002<\/p>\n\n\n\n<p>\u5728 <code>HTMLParser<\/code> \u91cc\uff0c\u9047\u5230\u666e\u901a\u6587\u672c\u65f6\uff0c\u4f1a\u81ea\u52a8\u8c03\u7528\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>handle_data(self, data)\n<\/code><\/pre>\n\n\n\n<p>\u6240\u4ee5\u6211\u4eec\u5148\u628a\u8fd9\u4e2a\u65b9\u6cd5\u52a0\u4e0a\u3002<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>from html.parser import HTMLParser\n\n\nclass MyHTMLParser(HTMLParser):\n    def handle_comment(self, data):\n        if '\\n' in data:\n            print(\"&gt;&gt;&gt; Multi-line Comment\")\n        else:\n            print(\"&gt;&gt;&gt; Single-line Comment\")\n        print(data)\n\n    def handle_data(self, data):\n        pass\n<\/code><\/pre>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h2 class=\"wp-block-heading\">\u7b2c\u516d\u6b65\uff1a\u60f3\u6e05\u695a <code>handle_data<\/code> \u91cc\u9762\u8981\u505a\u4ec0\u4e48<\/h2>\n\n\n\n<p>\u8fd9\u4e00\u90e8\u5206\u4e5f\u5148\u522b\u6025\u7740\u5199\u4ee3\u7801\u3002<\/p>\n\n\n\n<p>\u9898\u76ee\u8981\u6c42\uff1a<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li>\u8f93\u51fa\u6570\u636e\u524d\u5148\u6253\u5370 <code>&gt;&gt;&gt; Data<\/code><\/li>\n\n\n\n<li>\u7136\u540e\u6253\u5370\u6570\u636e\u5185\u5bb9<\/li>\n\n\n\n<li>\u4f46\u662f\u5982\u679c <code>data == '\\n'<\/code>\uff0c\u5c31\u4e0d\u8981\u6253\u5370<\/li>\n<\/ul>\n\n\n\n<p>\u8fd9\u8bf4\u660e <code>handle_data<\/code> \u7684\u903b\u8f91\u662f\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>def handle_data(self, data):\n    \u5982\u679c data == '\\n':\n        \u4ec0\u4e48\u4e5f\u4e0d\u505a\uff0c\u76f4\u63a5\u7ed3\u675f\n    \u5426\u5219:\n        \u5148\u6253\u5370 &gt;&gt;&gt; Data\n        \u518d\u6253\u5370 data\n<\/code><\/pre>\n\n\n\n<p>\u8fd9\u91cc\u7684\u5173\u952e\u70b9\u662f\uff1a<\/p>\n\n\n\n<h3 class=\"wp-block-heading\">\u4e3a\u4ec0\u4e48\u8981\u8df3\u8fc7 <code>'\\n'<\/code><\/h3>\n\n\n\n<p>HTML \u4e2d\u6709\u65f6\u6807\u7b7e\u4e0e\u6807\u7b7e\u4e4b\u95f4\u672c\u6765\u5c31\u4f1a\u6709\u6362\u884c\u3002<br>\u89e3\u6790\u5668\u770b\u5230\u8fd9\u4e9b\u6362\u884c\uff0c\u4e5f\u4f1a\u628a\u5b83\u4eec\u5f53\u6210 data\u3002<br>\u4f46\u9898\u76ee\u8bf4\u4e86\uff0c\u8fd9\u79cd\u53ea\u6709\u4e00\u4e2a\u6362\u884c\u7b26\u7684\u5185\u5bb9\u4e0d\u7b97\u6709\u6548\u6570\u636e\uff0c\u6240\u4ee5\u8981\u5ffd\u7565\u3002<\/p>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h2 class=\"wp-block-heading\">\u7b2c\u4e03\u6b65\uff1a\u628a <code>handle_data<\/code> \u771f\u6b63\u5199\u51fa\u6765<\/h2>\n\n\n\n<pre class=\"wp-block-code\"><code>from html.parser import HTMLParser\n\n\nclass MyHTMLParser(HTMLParser):\n    def handle_comment(self, data):\n        if '\\n' in data:\n            print(\"&gt;&gt;&gt; Multi-line Comment\")\n        else:\n            print(\"&gt;&gt;&gt; Single-line Comment\")\n        print(data)\n\n    def handle_data(self, data):\n        if data == '\\n':\n            return\n        print(\"&gt;&gt;&gt; Data\")\n        print(data)\n<\/code><\/pre>\n\n\n\n<h3 class=\"wp-block-heading\">\u4e3a\u4ec0\u4e48\u8fd9\u91cc\u7528 <code>return<\/code><\/h3>\n\n\n\n<pre class=\"wp-block-code\"><code>if data == '\\n':\n    return\n<\/code><\/pre>\n\n\n\n<p>\u610f\u601d\u662f\uff1a<\/p>\n\n\n\n<blockquote class=\"wp-block-quote is-layout-flow wp-block-quote-is-layout-flow\">\n<p>\u5982\u679c\u8fd9\u6b21\u8bfb\u5230\u7684\u6570\u636e\u53ea\u662f\u4e00\u4e2a\u6362\u884c\u7b26\uff0c\u90a3\u8fd9\u4e2a\u65b9\u6cd5\u5c31\u7acb\u523b\u7ed3\u675f\uff0c\u540e\u9762\u7684\u6253\u5370\u4ee3\u7801\u90fd\u4e0d\u6267\u884c\u3002<\/p>\n<\/blockquote>\n\n\n\n<p>\u8fd9\u662f\u4e00\u79cd\u5f88\u5e38\u89c1\u7684\u5199\u6cd5\u3002<br>\u5148\u628a\u201c\u4e0d\u9700\u8981\u5904\u7406\u7684\u60c5\u51b5\u201d\u6392\u9664\u6389\uff0c\u540e\u9762\u4ee3\u7801\u5c31\u66f4\u6e05\u695a\u3002<\/p>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h2 class=\"wp-block-heading\">\u5230\u8fd9\u91cc\uff0c\u7c7b\u5df2\u7ecf\u5199\u5b8c\u4e86<\/h2>\n\n\n\n<p>\u4f60\u73b0\u5728\u5df2\u7ecf\u5b8c\u6210\u4e86\u8fd9\u9898\u6700\u6838\u5fc3\u7684\u90e8\u5206\u3002<\/p>\n\n\n\n<p>\u4e5f\u5c31\u662f\u8bf4\uff0c\u8fd9\u4e00\u6bb5\u5df2\u7ecf\u4e0d\u662f\u201c\u534a\u6210\u54c1\u201d\u4e86\uff0c\u800c\u662f\u4e00\u4e2a\u771f\u6b63\u80fd\u5de5\u4f5c\u7684\u89e3\u6790\u5668\u7c7b\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>from html.parser import HTMLParser\n\n\nclass MyHTMLParser(HTMLParser):\n    def handle_comment(self, data):\n        if '\\n' in data:\n            print(\"&gt;&gt;&gt; Multi-line Comment\")\n        else:\n            print(\"&gt;&gt;&gt; Single-line Comment\")\n        print(data)\n\n    def handle_data(self, data):\n        if data == '\\n':\n            return\n        print(\"&gt;&gt;&gt; Data\")\n        print(data)\n<\/code><\/pre>\n\n\n\n<p>\u63a5\u4e0b\u6765\u8981\u505a\u7684\u4e8b\u60c5\u5176\u5b9e\u53ea\u662f\uff1a<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li>\u628a\u8f93\u5165\u8bfb\u8fdb\u6765<\/li>\n\n\n\n<li>\u628a\u8bfb\u5230\u7684 HTML \u4ea4\u7ed9\u8fd9\u4e2a\u89e3\u6790\u5668<\/li>\n<\/ul>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h2 class=\"wp-block-heading\">\u7b2c\u516b\u6b65\uff1a\u5f00\u59cb\u5199\u4e3b\u7a0b\u5e8f\uff0c\u5148\u8bfb\u5165 n<\/h2>\n\n\n\n<p>\u4e3b\u7a0b\u5e8f\u7b2c\u4e00\u6b65\u5f88\u7b80\u5355\uff0c\u5148\u8bfb\u9898\u76ee\u7ed9\u7684\u884c\u6570\u3002<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>n = int(input())\n<\/code><\/pre>\n\n\n\n<h3 class=\"wp-block-heading\">\u8fd9\u91cc\u662f\u4ec0\u4e48\u610f\u601d<\/h3>\n\n\n\n<ul class=\"wp-block-list\">\n<li><code>input()<\/code> \u8bfb\u5165\u4e00\u884c\u5185\u5bb9\uff0c\u7ed3\u679c\u662f\u5b57\u7b26\u4e32<\/li>\n\n\n\n<li><code>int(...)<\/code> \u628a\u5b57\u7b26\u4e32\u8f6c\u6210\u6574\u6570<\/li>\n<\/ul>\n\n\n\n<p>\u6240\u4ee5\u8fd9\u53e5\u7684\u4f5c\u7528\u5c31\u662f\uff1a<\/p>\n\n\n\n<blockquote class=\"wp-block-quote is-layout-flow wp-block-quote-is-layout-flow\">\n<p>\u8bfb\u5165 HTML \u603b\u5171\u6709\u591a\u5c11\u884c\u3002<\/p>\n<\/blockquote>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h2 class=\"wp-block-heading\">\u7b2c\u4e5d\u6b65\uff1a\u51c6\u5907\u4e00\u4e2a\u5217\u8868\uff0c\u5b58\u4e0b\u8fd9 n \u884c HTML<\/h2>\n\n\n\n<p>\u56e0\u4e3a\u540e\u9762\u6709\u591a\u884c\u8f93\u5165\uff0c\u6240\u4ee5\u901a\u5e38\u5148\u51c6\u5907\u4e00\u4e2a\u5217\u8868\u3002<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>html_lines = &#91;]\n<\/code><\/pre>\n\n\n\n<p>\u8fd9\u4e2a\u5217\u8868\u540e\u9762\u7528\u6765\u5b58\u6bcf\u4e00\u884c HTML\u3002<\/p>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h2 class=\"wp-block-heading\">\u7b2c\u5341\u6b65\uff1a\u5faa\u73af\u8bfb\u5165 n \u884c<\/h2>\n\n\n\n<pre class=\"wp-block-code\"><code>for _ in range(n):\n    html_lines.append(input())\n<\/code><\/pre>\n\n\n\n<h3 class=\"wp-block-heading\">\u8fd9\u91cc\u8981\u4f1a\u8bfb<\/h3>\n\n\n\n<p>\u8fd9\u6bb5\u4ee3\u7801\u7684\u610f\u601d\u662f\uff1a<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li>\u5faa\u73af <code>n<\/code> \u6b21<\/li>\n\n\n\n<li>\u6bcf\u6b21\u8bfb\u5165\u4e00\u884c HTML<\/li>\n\n\n\n<li>\u653e\u5230 <code>html_lines<\/code> \u8fd9\u4e2a\u5217\u8868\u91cc<\/li>\n<\/ul>\n\n\n\n<p>\u6bd4\u5982\u5982\u679c\u8f93\u5165\u662f\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>4\n&lt;!--&#91;if IE 9]&gt;IE9-specific content\n&lt;!&#91;endif]--&gt;\n&lt;div&gt; Welcome to HackerRank&lt;\/div&gt;\n&lt;!--&#91;if IE 9]&gt;IE9-specific content&lt;!&#91;endif]--&gt;\n<\/code><\/pre>\n\n\n\n<p>\u90a3\u4e48\u6700\u540e <code>html_lines<\/code> \u91cc\u5b58\u7684\u5927\u6982\u5c31\u662f\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>&#91;\n    \"&lt;!--&#91;if IE 9]&gt;IE9-specific content\",\n    \"&lt;!&#91;endif]--&gt;\",\n    \"&lt;div&gt; Welcome to HackerRank&lt;\/div&gt;\",\n    \"&lt;!--&#91;if IE 9]&gt;IE9-specific content&lt;!&#91;endif]--&gt;\"\n]\n<\/code><\/pre>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h2 class=\"wp-block-heading\">\u7b2c\u5341\u4e00\u6b65\uff1a\u628a\u8fd9\u51e0\u884c\u62fc\u6210\u4e00\u4e2a\u5b8c\u6574\u7684 HTML \u5b57\u7b26\u4e32<\/h2>\n\n\n\n<p>\u8fd9\u4e00\u6b65\u5f88\u91cd\u8981\u3002<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>html = '\\n'.join(html_lines)\n<\/code><\/pre>\n\n\n\n<h3 class=\"wp-block-heading\">\u4e3a\u4ec0\u4e48\u8981\u62fc\u63a5<\/h3>\n\n\n\n<p>\u56e0\u4e3a\u9898\u76ee\u7ed9\u7684\u662f\u4e00\u4e2a\u201cHTML \u7247\u6bb5\u201d\uff0c\u5b83\u672c\u6765\u5c31\u662f\u591a\u884c\u7684\u3002<br>\u6211\u4eec\u5e0c\u671b\u628a\u5b83\u6062\u590d\u6210\u5b8c\u6574\u6587\u672c\uff0c\u518d\u4ea4\u7ed9\u89e3\u6790\u5668\u7edf\u4e00\u5904\u7406\u3002<\/p>\n\n\n\n<h3 class=\"wp-block-heading\">\u4e3a\u4ec0\u4e48\u4e2d\u95f4\u8981\u7528 <code>'\\n'<\/code><\/h3>\n\n\n\n<p>\u56e0\u4e3a\u539f\u672c\u6bcf\u4e00\u884c\u4e4b\u95f4\u5c31\u662f\u6362\u884c\u5173\u7cfb\u3002<br>\u5982\u679c\u4f60\u76f4\u63a5\u5199\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>html = ''.join(html_lines)\n<\/code><\/pre>\n\n\n\n<p>\u90a3\u591a\u884c\u6ce8\u91ca\u5c31\u4f1a\u88ab\u9519\u8bef\u5730\u8fde\u5728\u4e00\u8d77\uff0c\u6362\u884c\u4fe1\u606f\u4e22\u4e86\u3002<\/p>\n\n\n\n<p>\u6240\u4ee5\u5fc5\u987b\u5199\u6210\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>html = '\\n'.join(html_lines)\n<\/code><\/pre>\n\n\n\n<p>\u8fd9\u6837\u624d\u80fd\u4fdd\u7559\u539f\u59cb\u7ed3\u6784\u3002<\/p>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h2 class=\"wp-block-heading\">\u7b2c\u5341\u4e8c\u6b65\uff1a\u521b\u5efa\u89e3\u6790\u5668\u5bf9\u8c61<\/h2>\n\n\n\n<p>\u524d\u9762\u7c7b\u5df2\u7ecf\u5199\u597d\u4e86\uff0c\u73b0\u5728\u5c31\u53ef\u4ee5\u201c\u5b9e\u4f8b\u5316\u201d\u5b83\u3002<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>parser = MyHTMLParser()\n<\/code><\/pre>\n\n\n\n<p>\u8fd9\u53e5\u53ef\u4ee5\u7406\u89e3\u6210\uff1a<\/p>\n\n\n\n<blockquote class=\"wp-block-quote is-layout-flow wp-block-quote-is-layout-flow\">\n<p>\u6309\u7167 <code>MyHTMLParser<\/code> \u8fd9\u4e2a\u7c7b\uff0c\u771f\u6b63\u9020\u51fa\u4e00\u4e2a\u89e3\u6790\u5668\u5bf9\u8c61\u3002<\/p>\n<\/blockquote>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h2 class=\"wp-block-heading\">\u7b2c\u5341\u4e09\u6b65\uff1a\u628a HTML \u5582\u7ed9\u89e3\u6790\u5668<\/h2>\n\n\n\n<p>\u6700\u540e\u4e00\u6b65\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>parser.feed(html)\n<\/code><\/pre>\n\n\n\n<h3 class=\"wp-block-heading\">\u8fd9\u53e5\u662f\u6574\u9898\u7684\u6267\u884c\u5f00\u5173<\/h3>\n\n\n\n<p><code>feed(html)<\/code> \u7684\u610f\u601d\u662f\uff1a<\/p>\n\n\n\n<blockquote class=\"wp-block-quote is-layout-flow wp-block-quote-is-layout-flow\">\n<p>\u628a\u8fd9\u4e00\u5927\u6bb5 HTML \u4ea4\u7ed9\u89e3\u6790\u5668\uff0c\u8bf7\u4f60\u5f00\u59cb\u89e3\u6790\u3002<\/p>\n<\/blockquote>\n\n\n\n<p>\u7136\u540e\u89e3\u6790\u5668\u5c31\u4f1a\u81ea\u52a8\u626b\u63cf\u8fd9\u6bb5 HTML\uff1a<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li>\u9047\u5230\u6ce8\u91ca\uff0c\u5c31\u8c03\u7528 <code>handle_comment<\/code><\/li>\n\n\n\n<li>\u9047\u5230\u6587\u672c\u6570\u636e\uff0c\u5c31\u8c03\u7528 <code>handle_data<\/code><\/li>\n<\/ul>\n\n\n\n<p>\u6240\u4ee5\u6211\u4eec\u524d\u9762\u5199\u7684\u65b9\u6cd5\uff0c\u8fd9\u65f6\u624d\u771f\u6b63\u5f00\u59cb\u53d1\u6325\u4f5c\u7528\u3002<\/p>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h2 class=\"wp-block-heading\">\u628a\u4e3b\u7a0b\u5e8f\u8865\u5b8c\u6574<\/h2>\n\n\n\n<p>\u73b0\u5728\u628a\u521a\u624d\u7684\u51e0\u6b65\u8fde\u8d77\u6765\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>n = int(input())\nhtml_lines = &#91;]\n\nfor _ in range(n):\n    html_lines.append(input())\n\nhtml = '\\n'.join(html_lines)\n\nparser = MyHTMLParser()\nparser.feed(html)\n<\/code><\/pre>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h2 class=\"wp-block-heading\">\u6700\u7ec8\u5b8c\u6574\u4ee3\u7801<\/h2>\n\n\n\n<p>\u73b0\u5728\u628a\u201c\u7c7b + \u4e3b\u7a0b\u5e8f\u201d\u5408\u8d77\u6765\uff0c\u5c31\u662f\u5b8c\u6574\u7b54\u6848\u3002<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>from html.parser import HTMLParser\n\n\nclass MyHTMLParser(HTMLParser):\n    def handle_comment(self, data):\n        if '\\n' in data:\n            print(\"&gt;&gt;&gt; Multi-line Comment\")\n        else:\n            print(\"&gt;&gt;&gt; Single-line Comment\")\n        print(data)\n\n    def handle_data(self, data):\n        if data == '\\n':\n            return\n        print(\"&gt;&gt;&gt; Data\")\n        print(data)\n\n\nn = int(input())\nhtml_lines = &#91;]\n\nfor _ in range(n):\n    html_lines.append(input())\n\nhtml = '\\n'.join(html_lines)\n\nparser = MyHTMLParser()\nparser.feed(html)\n<\/code><\/pre>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h2 class=\"wp-block-heading\">\u518d\u5e26\u4f60\u624b\u52a8\u8d70\u4e00\u904d\u6267\u884c\u8fc7\u7a0b<\/h2>\n\n\n\n<p>\u6211\u4eec\u8fd8\u662f\u770b\u6837\u4f8b\u8f93\u5165\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>4\n&lt;!--&#91;if IE 9]&gt;IE9-specific content\n&lt;!&#91;endif]--&gt;\n&lt;div&gt; Welcome to HackerRank&lt;\/div&gt;\n&lt;!--&#91;if IE 9]&gt;IE9-specific content&lt;!&#91;endif]--&gt;\n<\/code><\/pre>\n\n\n\n<h3 class=\"wp-block-heading\">\u7b2c 1 \u6b65\uff1a\u8bfb\u5165 <code>n<\/code><\/h3>\n\n\n\n<pre class=\"wp-block-code\"><code>n = 4\n<\/code><\/pre>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h3 class=\"wp-block-heading\">\u7b2c 2 \u6b65\uff1a\u8bfb\u5165 4 \u884c HTML<\/h3>\n\n\n\n<pre class=\"wp-block-code\"><code>html_lines = &#91;\n    \"&lt;!--&#91;if IE 9]&gt;IE9-specific content\",\n    \"&lt;!&#91;endif]--&gt;\",\n    \"&lt;div&gt; Welcome to HackerRank&lt;\/div&gt;\",\n    \"&lt;!--&#91;if IE 9]&gt;IE9-specific content&lt;!&#91;endif]--&gt;\"\n]\n<\/code><\/pre>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h3 class=\"wp-block-heading\">\u7b2c 3 \u6b65\uff1a\u62fc\u63a5<\/h3>\n\n\n\n<pre class=\"wp-block-code\"><code>html = \"&lt;!--&#91;if IE 9]&gt;IE9-specific content\\n&lt;!&#91;endif]--&gt;\\n&lt;div&gt; Welcome to HackerRank&lt;\/div&gt;\\n&lt;!--&#91;if IE 9]&gt;IE9-specific content&lt;!&#91;endif]--&gt;\"\n<\/code><\/pre>\n\n\n\n<p>\u6ce8\u610f\u7b2c\u4e00\u6bb5\u6ce8\u91ca\u91cc\u9762\u4fdd\u7559\u4e86 <code>\\n<\/code>\uff0c\u8fd9\u5c31\u662f\u540e\u9762\u80fd\u5224\u65ad\u6210\u591a\u884c\u6ce8\u91ca\u7684\u539f\u56e0\u3002<\/p>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h3 class=\"wp-block-heading\">\u7b2c 4 \u6b65\uff1a\u5f00\u59cb\u89e3\u6790<\/h3>\n\n\n\n<pre class=\"wp-block-code\"><code>parser.feed(html)\n<\/code><\/pre>\n\n\n\n<p>\u89e3\u6790\u65f6\u4f1a\u53d1\u751f\u8fd9\u4e9b\u4e8b\uff1a<\/p>\n\n\n\n<h4 class=\"wp-block-heading\">\u5148\u9047\u5230\u7b2c\u4e00\u6bb5\u6ce8\u91ca<\/h4>\n\n\n\n<p>\u5b83\u7684\u5185\u5bb9\u662f\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>&#91;if IE 9]&gt;IE9-specific content\n&lt;!&#91;endif]\n<\/code><\/pre>\n\n\n\n<p>\u91cc\u9762\u6709 <code>\\n<\/code>\uff0c\u6240\u4ee5\u8f93\u51fa\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>&gt;&gt;&gt; Multi-line Comment\n&#91;if IE 9]&gt;IE9-specific content\n&lt;!&#91;endif]\n<\/code><\/pre>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h4 class=\"wp-block-heading\">\u7136\u540e\u9047\u5230 <code>&lt;div&gt;<\/code> \u91cc\u7684\u6587\u672c<\/h4>\n\n\n\n<p>\u6587\u672c\u5185\u5bb9\u662f\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code> Welcome to HackerRank\n<\/code><\/pre>\n\n\n\n<p>\u5b83\u4e0d\u662f\u5355\u72ec\u7684 <code>'\\n'<\/code>\uff0c\u6240\u4ee5\u8f93\u51fa\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>&gt;&gt;&gt; Data\n Welcome to HackerRank\n<\/code><\/pre>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h4 class=\"wp-block-heading\">\u6700\u540e\u9047\u5230\u5355\u884c\u6ce8\u91ca<\/h4>\n\n\n\n<p>\u5185\u5bb9\u662f\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>&#91;if IE 9]&gt;IE9-specific content&lt;!&#91;endif]\n<\/code><\/pre>\n\n\n\n<p>\u91cc\u9762\u6ca1\u6709 <code>\\n<\/code>\uff0c\u6240\u4ee5\u8f93\u51fa\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>&gt;&gt;&gt; Single-line Comment\n&#91;if IE 9]&gt;IE9-specific content&lt;!&#91;endif]\n<\/code><\/pre>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h2 class=\"wp-block-heading\">\u4f60\u73b0\u5728\u5e94\u8be5\u771f\u6b63\u8bb0\u4f4f\u7684\uff0c\u4e0d\u662f\u4ee3\u7801\uff0c\u800c\u662f\u201c\u5199\u9898\u987a\u5e8f\u201d<\/h2>\n\n\n\n<p>\u4ee5\u540e\u4f60\u518d\u9047\u5230\u8fd9\u79cd\u9898\uff0c\u4e0d\u8981\u4e00\u4e0a\u6765\u5c31\u76ef\u7740\u5b8c\u6574\u7b54\u6848\u53d1\u61f5\u3002<br>\u4f60\u8981\u6309\u8fd9\u4e2a\u987a\u5e8f\u601d\u8003\uff1a<\/p>\n\n\n\n<h3 class=\"wp-block-heading\">\u7b2c\u4e00\u6b65\uff1a\u5148\u770b\u8981\u4e0d\u8981\u81ea\u5b9a\u4e49\u4e00\u4e2a\u7c7b<\/h3>\n\n\n\n<p>\u8fd9\u9898\u8981\uff0c\u56e0\u4e3a\u8981\u7ee7\u627f <code>HTMLParser<\/code>\u3002<\/p>\n\n\n\n<h3 class=\"wp-block-heading\">\u7b2c\u4e8c\u6b65\uff1a\u5148\u628a\u7c7b\u7684\u7a7a\u58f3\u5199\u51fa\u6765<\/h3>\n\n\n\n<p>\u54ea\u6015\u5148\u5199 <code>pass<\/code>\uff0c\u4e5f\u6bd4\u5bf9\u7740\u7a7a\u767d\u53d1\u5446\u5f3a\u3002<\/p>\n\n\n\n<h3 class=\"wp-block-heading\">\u7b2c\u4e09\u6b65\uff1a\u4e00\u4e2a\u65b9\u6cd5\u4e00\u4e2a\u65b9\u6cd5\u8865<\/h3>\n\n\n\n<p>\u5148\u5199 <code>handle_comment<\/code>\uff0c\u518d\u5199 <code>handle_data<\/code>\u3002<\/p>\n\n\n\n<h3 class=\"wp-block-heading\">\u7b2c\u56db\u6b65\uff1a\u6700\u540e\u5199\u4e3b\u7a0b\u5e8f<\/h3>\n\n\n\n<p>\u4e3b\u7a0b\u5e8f\u901a\u5e38\u53ea\u662f\uff1a<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li>\u8bfb\u8f93\u5165<\/li>\n\n\n\n<li>\u6574\u7406\u8f93\u5165<\/li>\n\n\n\n<li>\u8c03\u7528\u524d\u9762\u5199\u597d\u7684\u7c7b<\/li>\n<\/ul>\n\n\n\n<p>\u8fd9\u5c31\u662f\u5f88\u591a\u9898\u90fd\u80fd\u901a\u7528\u7684\u201c\u642d\u9aa8\u67b6\u201d\u65b9\u6cd5\u3002<\/p>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h2 class=\"wp-block-heading\">\u8fd9\u9898\u7684\u6613\u9519\u70b9<\/h2>\n\n\n\n<h3 class=\"wp-block-heading\">\u6613\u9519\u70b9 1\uff1a\u5fd8\u4e86\u7ee7\u627f <code>HTMLParser<\/code><\/h3>\n\n\n\n<p>\u9519\u8bef\u5199\u6cd5\u50cf\u8fd9\u6837\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>class MyHTMLParser:\n<\/code><\/pre>\n\n\n\n<p>\u8fd9\u6837\u5c31\u6ca1\u6709\u89e3\u6790 HTML \u7684\u80fd\u529b\u4e86\u3002<br>\u5fc5\u987b\u5199\u6210\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>class MyHTMLParser(HTMLParser):\n<\/code><\/pre>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h3 class=\"wp-block-heading\">\u6613\u9519\u70b9 2\uff1a\u5fd8\u4e86\u8df3\u8fc7 <code>data == '\\n'<\/code><\/h3>\n\n\n\n<p>\u5982\u679c\u4e0d\u5199\u8fd9\u53e5\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>if data == '\\n':\n    return\n<\/code><\/pre>\n\n\n\n<p>\u8f93\u51fa\u91cc\u5c31\u4f1a\u591a\u51fa\u5f88\u591a\u6ca1\u610f\u4e49\u7684\u7a7a\u884c\u6570\u636e\u3002<\/p>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h3 class=\"wp-block-heading\">\u6613\u9519\u70b9 3\uff1a\u628a\u591a\u884c\u8f93\u5165\u76f4\u63a5\u8fde\u8d77\u6765\u4e86\uff0c\u6ca1\u6709\u52a0 <code>\\n<\/code><\/h3>\n\n\n\n<p>\u9519\u8bef\u5199\u6cd5\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>html = ''.join(html_lines)\n<\/code><\/pre>\n\n\n\n<p>\u8fd9\u6837\u4f1a\u628a\u539f\u6765\u7684\u6362\u884c\u5f04\u4e22\uff0c\u5f71\u54cd\u591a\u884c\u6ce8\u91ca\u5224\u65ad\u3002<\/p>\n\n\n\n<p>\u6b63\u786e\u5199\u6cd5\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>html = '\\n'.join(html_lines)\n<\/code><\/pre>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h3 class=\"wp-block-heading\">\u6613\u9519\u70b9 4\uff1a\u628a\u6ce8\u91ca\u6807\u7b7e\u4e00\u8d77\u6253\u5370\u51fa\u6765<\/h3>\n\n\n\n<p>\u9898\u76ee\u8981\u6253\u5370\u7684\u662f\u6ce8\u91ca\u5185\u5bb9\uff0c\u4e0d\u662f <code>&lt;!--<\/code> \u548c <code>--&gt;<\/code> \u672c\u8eab\u3002<br>\u597d\u5728 <code>HTMLParser<\/code> \u5df2\u7ecf\u5e2e\u4f60\u5904\u7406\u597d\u4e86\uff0c<code>handle_comment(self, data)<\/code> \u91cc\u7684 <code>data<\/code> \u53ea\u4f1a\u662f\u5185\u90e8\u5185\u5bb9\u3002<\/p>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h2 class=\"wp-block-heading\">\u672c\u8282\u5c0f\u7ed3<\/h2>\n\n\n\n<p>\u8fd9\u9898\u4ece\u7a7a\u767d\u5199\u51fa\u6765\uff0c\u5176\u5b9e\u5c31\u662f\u4e09\u4ef6\u4e8b\uff1a<\/p>\n\n\n\n<p>\u7b2c\u4e00\uff0c\u5148\u7ee7\u627f <code>HTMLParser<\/code>\uff0c\u5199\u4e00\u4e2a\u81ea\u5df1\u7684\u89e3\u6790\u5668\u7c7b\u3002<br>\u7b2c\u4e8c\uff0c\u5728\u7c7b\u91cc\u5199\u4e24\u4e2a\u65b9\u6cd5\uff1a\u4e00\u4e2a\u5904\u7406\u6ce8\u91ca\uff0c\u4e00\u4e2a\u5904\u7406\u6570\u636e\u3002<br>\u7b2c\u4e09\uff0c\u4e3b\u7a0b\u5e8f\u8d1f\u8d23\u8bfb\u5165 HTML\uff0c\u7136\u540e <code>feed<\/code> \u7ed9\u89e3\u6790\u5668\u3002<\/p>\n\n\n\n<p>\u771f\u6b63\u8981\u5b66\u4f1a\u7684\u662f\u8fd9\u79cd\u987a\u5e8f\uff1a<\/p>\n\n\n\n<p><strong>\u5148\u642d\u6846\u67b6\uff0c\u518d\u8865\u65b9\u6cd5\uff0c\u6700\u540e\u63a5\u4e3b\u7a0b\u5e8f\u3002<\/strong><\/p>\n\n\n\n<p>\u8fd9\u6bd4\u6b7b\u8bb0\u7b54\u6848\u6709\u7528\u5f97\u591a\u3002<\/p>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h2 class=\"wp-block-heading\">\u7ec3\u4e60<\/h2>\n\n\n\n<p>\u4f60\u73b0\u5728\u53ef\u4ee5\u81ea\u5df1\u8bd5\u7740\u4e0d\u770b\u4e0a\u9762\u7684\u5b8c\u6574\u4ee3\u7801\uff0c\u72ec\u7acb\u5199\u8fd9\u4e00\u9898\u7684\u201c\u7b80\u5316\u7248\u201d\u3002<\/p>\n\n\n\n<h3 class=\"wp-block-heading\">\u9898\u76ee<\/h3>\n\n\n\n<p>\u8f93\u5165\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>3\n&lt;!--hello--&gt;\n&lt;h1&gt;Title&lt;\/h1&gt;\n&lt;!--a\nb--&gt;\n<\/code><\/pre>\n\n\n\n<p>\u8bf7\u6309\u539f\u9898\u8981\u6c42\u8f93\u51fa\u7ed3\u679c\u3002<\/p>\n\n\n\n<h3 class=\"wp-block-heading\">\u63d0\u793a<\/h3>\n\n\n\n<p>\u4f60\u53ef\u4ee5\u6309\u4e0b\u9762\u987a\u5e8f\u81ea\u5df1\u505a\uff1a<\/p>\n\n\n\n<ol class=\"wp-block-list\">\n<li>\u5148\u5199 <code>class MyHTMLParser(HTMLParser):<\/code><\/li>\n\n\n\n<li>\u5148\u8865 <code>handle_comment<\/code><\/li>\n\n\n\n<li>\u518d\u8865 <code>handle_data<\/code><\/li>\n\n\n\n<li>\u4e3b\u7a0b\u5e8f\u8bfb\u5165 3 \u884c<\/li>\n\n\n\n<li>\u7528 <code>'\\n'.join(...)<\/code> \u62fc\u8d77\u6765<\/li>\n\n\n\n<li>\u6700\u540e <code>parser.feed(html)<\/code><\/li>\n<\/ol>\n\n\n\n<p><\/p>\n\n\n\n<p><\/p>\n","protected":false},"excerpt":{"rendered":"<p>\u9898\u76ee\u8003\u70b9 \u8fd9\u9053\u9898\u4e3b\u8981\u8003\u7684\u662f\u4e0b\u9762\u51e0\u4e2a\u70b9\uff1a \u8fd9\u9898\u672c\u8d28\u4e0a\u4e0d\u662f\u8ba9\u4f60\u201c\u81ea\u5df1\u786c\u5199\u4e00\u4e2a HTML \u89e3\u6790\u5668\u201d\uff0c\u800c\u662f\u8ba9\u4f60\u5b66\u4f1a\u7528  [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[54],"tags":[],"class_list":["post-2159","post","type-post","status-publish","format-standard","hentry","category-text"],"_links":{"self":[{"href":"http:\/\/www.preluna.xyz\/index.php\/wp-json\/wp\/v2\/posts\/2159","targetHints":{"allow":["GET"]}}],"collection":[{"href":"http:\/\/www.preluna.xyz\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"http:\/\/www.preluna.xyz\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"http:\/\/www.preluna.xyz\/index.php\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"http:\/\/www.preluna.xyz\/index.php\/wp-json\/wp\/v2\/comments?post=2159"}],"version-history":[{"count":2,"href":"http:\/\/www.preluna.xyz\/index.php\/wp-json\/wp\/v2\/posts\/2159\/revisions"}],"predecessor-version":[{"id":2166,"href":"http:\/\/www.preluna.xyz\/index.php\/wp-json\/wp\/v2\/posts\/2159\/revisions\/2166"}],"wp:attachment":[{"href":"http:\/\/www.preluna.xyz\/index.php\/wp-json\/wp\/v2\/media?parent=2159"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"http:\/\/www.preluna.xyz\/index.php\/wp-json\/wp\/v2\/categories?post=2159"},{"taxonomy":"post_tag","embeddable":true,"href":"http:\/\/www.preluna.xyz\/index.php\/wp-json\/wp\/v2\/tags?post=2159"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}