{"id":2168,"date":"2026-04-24T14:45:34","date_gmt":"2026-04-24T06:45:34","guid":{"rendered":"http:\/\/www.preluna.xyz\/?p=2168"},"modified":"2026-04-24T16:50:23","modified_gmt":"2026-04-24T08:50:23","slug":"html-parser-htmlparser","status":"publish","type":"post","link":"http:\/\/www.preluna.xyz\/index.php\/2026\/04\/24\/html-parser-htmlparser\/preluna\/text\/","title":{"rendered":"html.parser.HTMLParser"},"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\/html.parser.HTMLParser-648x1024.png'><img class=\"lazyload lazyload-style-1\" src=\"data:image\/svg+xml;base64,PCEtLUFyZ29uTG9hZGluZy0tPgo8c3ZnIHdpZHRoPSIxIiBoZWlnaHQ9IjEiIHhtbG5zPSJodHRwOi8vd3d3LnczLm9yZy8yMDAwL3N2ZyIgc3Ryb2tlPSIjZmZmZmZmMDAiPjxnPjwvZz4KPC9zdmc+\"  loading=\"lazy\" decoding=\"async\" width=\"648\" height=\"1024\" data-original=\"http:\/\/www.preluna.xyz\/wp-content\/uploads\/2026\/04\/html.parser.HTMLParser-648x1024.png\" src=\"data:image\/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAAAXNSR0IArs4c6QAAAARnQU1BAACxjwv8YQUAAAAJcEhZcwAADsQAAA7EAZUrDhsAAAANSURBVBhXYzh8+PB\/AAffA0nNPuCLAAAAAElFTkSuQmCC\" alt=\"\" class=\"wp-image-2169\"  sizes=\"auto, (max-width: 648px) 100vw, 648px\" \/><\/div><\/figure>\n\n\n\n<h2 class=\"wp-block-heading\">1. \u9898\u76ee\u8003\u70b9<\/h2>\n\n\n\n<p>\u8fd9\u9053\u9898\u4e3b\u8981\u8003\uff1a<\/p>\n\n\n\n<ol class=\"wp-block-list\">\n<li><strong>HTMLParser \u7684\u4f7f\u7528<\/strong><\/li>\n\n\n\n<li><strong>\u7c7b\u7684\u7ee7\u627f<\/strong><\/li>\n\n\n\n<li><strong>\u91cd\u5199\u65b9\u6cd5<\/strong><\/li>\n\n\n\n<li><strong>\u5b57\u7b26\u4e32\u5224\u65ad<\/strong><\/li>\n\n\n\n<li><strong>\u591a\u884c\u8f93\u5165\u62fc\u63a5<\/strong><\/li>\n\n\n\n<li><strong>\u6309\u9898\u76ee\u683c\u5f0f\u8f93\u51fa<\/strong><\/li>\n<\/ol>\n\n\n\n<p>\u8fd9\u9053\u9898\u4e0d\u662f\u8ba9\u6211\u4eec\u81ea\u5df1\u624b\u5199 HTML \u89e3\u6790\u5668\uff0c\u800c\u662f\u8ba9\u6211\u4eec\u4f7f\u7528 Python \u5df2\u7ecf\u63d0\u4f9b\u597d\u7684\u5de5\u5177\uff1a<code>html.parser.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\">2. \u5ba1\u9898<\/h2>\n\n\n\n<p>\u9898\u76ee\u7ed9\u4f60\u4e00\u6bb5 HTML \u4ee3\u7801\uff0c\u4e00\u5171\u6709 <code>N<\/code> \u884c\u3002<\/p>\n\n\n\n<p>\u4f60\u9700\u8981\u4ece\u8fd9\u6bb5 HTML \u4e2d\u627e\u51fa\u4e09\u7c7b\u5185\u5bb9\uff1a<\/p>\n\n\n\n<figure class=\"wp-block-table\"><table class=\"has-fixed-layout\"><thead><tr><th>\u5185\u5bb9\u7c7b\u578b<\/th><th>\u793a\u4f8b<\/th><th>\u8f93\u51fa\u6807\u9898<\/th><\/tr><\/thead><tbody><tr><td>\u5355\u884c\u6ce8\u91ca<\/td><td><code>&lt;!-- comment --&gt;<\/code><\/td><td><code>&gt;&gt;&gt; Single-line Comment<\/code><\/td><\/tr><tr><td>\u591a\u884c\u6ce8\u91ca<\/td><td><code>&lt;!-- line1\\nline2 --&gt;<\/code><\/td><td><code>&gt;&gt;&gt; Multi-line Comment<\/code><\/td><\/tr><tr><td>\u666e\u901a\u6570\u636e<\/td><td><code>&lt;div&gt;Hello&lt;\/div&gt;<\/code> \u91cc\u9762\u7684 <code>Hello<\/code><\/td><td><code>&gt;&gt;&gt; Data<\/code><\/td><\/tr><\/tbody><\/table><\/figure>\n\n\n\n<p>\u6ce8\u610f\u9898\u76ee\u8981\u6c42\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>Do not print data if data == '\\n'\n<\/code><\/pre>\n\n\n\n<p>\u610f\u601d\u662f\uff1a<\/p>\n\n\n\n<p>\u5982\u679c HTMLParser \u8bfb\u5230\u7684\u6570\u636e\u53ea\u662f\u4e00\u4e2a\u6362\u884c\u7b26 <code>'\\n'<\/code>\uff0c\u4e0d\u8981\u8f93\u51fa\u5b83\u3002<\/p>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h2 class=\"wp-block-heading\">3. \u601d\u8def\u63d0\u793a<\/h2>\n\n\n\n<p>\u8fd9\u9053\u9898\u6700\u5173\u952e\u7684\u70b9\u662f\uff1a<\/p>\n\n\n\n<p>\u4f60\u4e0d\u9700\u8981\u81ea\u5df1\u53bb\u5224\u65ad\u54ea\u91cc\u662f\u6807\u7b7e\u3001\u54ea\u91cc\u662f\u6ce8\u91ca\u3001\u54ea\u91cc\u662f\u6570\u636e\u3002<\/p>\n\n\n\n<p>Python \u7684 <code>HTMLParser<\/code> \u4f1a\u5e2e\u4f60\u89e3\u6790 HTML\u3002\u4f60\u53ea\u9700\u8981\u5199\u4e00\u4e2a\u7c7b\uff0c\u7ee7\u627f\u5b83\uff0c\u7136\u540e\u91cd\u5199\u5bf9\u5e94\u7684\u65b9\u6cd5\u3002<\/p>\n\n\n\n<p>HTMLParser \u5728\u89e3\u6790\u65f6\u4f1a\u81ea\u52a8\u8c03\u7528\u8fd9\u4e9b\u65b9\u6cd5\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>handle_comment(self, data)\n<\/code><\/pre>\n\n\n\n<p>\u9047\u5230\u6ce8\u91ca\u65f6\u81ea\u52a8\u8c03\u7528\u3002<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>handle_data(self, data)\n<\/code><\/pre>\n\n\n\n<p>\u9047\u5230\u666e\u901a\u6587\u672c\u6570\u636e\u65f6\u81ea\u52a8\u8c03\u7528\u3002<\/p>\n\n\n\n<p>\u6240\u4ee5\u6574\u4f53\u65b9\u5411\u662f\uff1a<\/p>\n\n\n\n<p>\u7b2c\u4e00\u6b65\uff0c\u5bfc\u5165 <code>HTMLParser<\/code>\u3002<\/p>\n\n\n\n<p>\u7b2c\u4e8c\u6b65\uff0c\u5b9a\u4e49\u4e00\u4e2a\u81ea\u5df1\u7684\u89e3\u6790\u5668\u7c7b\uff0c\u7ee7\u627f <code>HTMLParser<\/code>\u3002<\/p>\n\n\n\n<p>\u7b2c\u4e09\u6b65\uff0c\u91cd\u5199 <code>handle_comment()<\/code>\uff0c\u5224\u65ad\u6ce8\u91ca\u662f\u5355\u884c\u8fd8\u662f\u591a\u884c\u3002<\/p>\n\n\n\n<p>\u7b2c\u56db\u6b65\uff0c\u91cd\u5199 <code>handle_data()<\/code>\uff0c\u8f93\u51fa\u666e\u901a\u6570\u636e\u3002<\/p>\n\n\n\n<p>\u7b2c\u4e94\u6b65\uff0c\u628a\u8f93\u5165\u7684 N \u884c HTML \u62fc\u6210\u4e00\u4e2a\u5b8c\u6574\u5b57\u7b26\u4e32\uff0c\u7136\u540e\u4ea4\u7ed9\u89e3\u6790\u5668\u5904\u7406\u3002<\/p>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h2 class=\"wp-block-heading\">4. \u5b8c\u6574\u8bbe\u8ba1\u601d\u8def<\/h2>\n\n\n\n<h3 class=\"wp-block-heading\">\u7b2c\u4e00\u6b65\uff1a\u5bfc\u5165\u5de5\u5177<\/h3>\n\n\n\n<p>\u8fd9\u9053\u9898\u8981\u7528\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>from html.parser import HTMLParser\n<\/code><\/pre>\n\n\n\n<p><code>HTMLParser<\/code> \u662f Python \u5185\u7f6e\u7684 HTML \u89e3\u6790\u5de5\u5177\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\u4e8c\u6b65\uff1a\u5b9a\u4e49\u81ea\u5df1\u7684\u89e3\u6790\u5668\u7c7b<\/h3>\n\n\n\n<p>\u6211\u4eec\u53ef\u4ee5\u5199\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>class MyHTMLParser(HTMLParser):\n    ...\n<\/code><\/pre>\n\n\n\n<p>\u610f\u601d\u662f\uff1a<\/p>\n\n\n\n<p>\u6211\u521b\u5efa\u4e00\u4e2a\u81ea\u5df1\u7684 HTML \u89e3\u6790\u5668\uff0c\u5b83\u7ee7\u627f\u81ea Python \u5df2\u7ecf\u5199\u597d\u7684 <code>HTMLParser<\/code>\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\u5904\u7406\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;!-- comment --&gt;\n<\/code><\/pre>\n\n\n\n<p>\u5f53 <code>HTMLParser<\/code> \u8bfb\u5230\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>\u5176\u4e2d <code>data<\/code> \u5c31\u662f\u6ce8\u91ca\u91cc\u9762\u7684\u5185\u5bb9\u3002<\/p>\n\n\n\n<p>\u4f8b\u5982\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>&lt;!-- hello --&gt;\n<\/code><\/pre>\n\n\n\n<p>\u4f20\u8fdb\u6765\u7684 <code>data<\/code> \u662f\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>hello\n<\/code><\/pre>\n\n\n\n<p>\u5982\u679c\u6ce8\u91ca\u91cc\u9762\u6709\u6362\u884c\u7b26 <code>\\n<\/code>\uff0c\u8bf4\u660e\u662f\u591a\u884c\u6ce8\u91ca\u3002<\/p>\n\n\n\n<p>\u6240\u4ee5\u53ef\u4ee5\u8fd9\u6837\u5224\u65ad\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>if '\\n' in data:\n    print(\"&gt;&gt;&gt; Multi-line Comment\")\nelse:\n    print(\"&gt;&gt;&gt; Single-line Comment\")\n<\/code><\/pre>\n\n\n\n<p>\u7136\u540e\u518d\u6253\u5370\u6ce8\u91ca\u5185\u5bb9\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<h3 class=\"wp-block-heading\">\u7b2c\u56db\u6b65\uff1a\u5904\u7406\u666e\u901a\u6570\u636e<\/h3>\n\n\n\n<p>\u666e\u901a\u6570\u636e\u5c31\u662f\u6807\u7b7e\u4e4b\u95f4\u7684\u6587\u5b57\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>\u5176\u4e2d\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>Welcome to HackerRank\n<\/code><\/pre>\n\n\n\n<p>\u5c31\u662f data\u3002<\/p>\n\n\n\n<p>\u5f53 <code>HTMLParser<\/code> \u8bfb\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>\u4f46\u662f\u9898\u76ee\u8bf4\uff0c\u5982\u679c <code>data == '\\n'<\/code>\uff0c\u4e0d\u8981\u6253\u5370\u3002<\/p>\n\n\n\n<p>\u6240\u4ee5\u5199\u6210\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>if data != '\\n':\n    print(\"&gt;&gt;&gt; Data\")\n    print(data)\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\u4e94\u6b65\uff1a\u8bfb\u53d6\u8f93\u5165\u5e76\u62fc\u63a5 HTML<\/h3>\n\n\n\n<p>\u8f93\u5165\u7b2c\u4e00\u884c\u662f\u6574\u6570 <code>N<\/code>\u3002<\/p>\n\n\n\n<p>\u540e\u9762 <code>N<\/code> \u884c\u662f HTML \u4ee3\u7801\u3002<\/p>\n\n\n\n<p>\u6ce8\u610f\u8fd9\u91cc\u6709\u4e00\u4e2a\u5f88\u5bb9\u6613\u9519\u7684\u5730\u65b9\uff1a<\/p>\n\n\n\n<p>\u6211\u4eec\u4e0d\u80fd\u76f4\u63a5\u628a\u6bcf\u4e00\u884c\u8fde\u8d77\u6765\uff0c\u5426\u5219\u591a\u884c\u6ce8\u91ca\u4e2d\u7684\u6362\u884c\u4f1a\u4e22\u5931\u3002<\/p>\n\n\n\n<p>\u4f8b\u5982\u591a\u884c\u6ce8\u91ca\u539f\u672c\u662f\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>&lt;!-- line1\nline2 --&gt;\n<\/code><\/pre>\n\n\n\n<p>\u5982\u679c\u4e0d\u52a0 <code>'\\n'<\/code>\uff0c\u5c31\u4f1a\u53d8\u6210\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>&lt;!-- line1line2 --&gt;\n<\/code><\/pre>\n\n\n\n<p>\u8fd9\u6837\u7a0b\u5e8f\u5c31\u65e0\u6cd5\u5224\u65ad\u5b83\u662f\u591a\u884c\u6ce8\u91ca\u4e86\u3002<\/p>\n\n\n\n<p>\u6240\u4ee5\u6bcf\u8bfb\u53d6\u4e00\u884c\uff0c\u90fd\u8981\u52a0\u4e0a\u6362\u884c\u7b26\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>html += input() + '\\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\">5. \u4ee3\u7801\u5b9e\u73b0<\/h2>\n\n\n\n<pre class=\"wp-block-code\"><code>from html.parser import HTMLParser\n\n\nclass MyHTMLParser(HTMLParser):\n\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            print(\"&gt;&gt;&gt; Data\")\n            print(data)\n\n\nn = int(input())\n\nhtml = \"\"\nfor _ in range(n):\n    html += input() + '\\n'\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\">6. \u8fd0\u884c\u6f14\u793a<\/h2>\n\n\n\n<p>\u5047\u8bbe\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>\u7a0b\u5e8f\u5148\u628a\u8fd9 4 \u884c\u62fc\u6210\u4e00\u4e2a\u5b8c\u6574 HTML \u5b57\u7b26\u4e32\u3002<\/p>\n\n\n\n<p>\u9047\u5230\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>\u91cc\u9762\u6709\u6362\u884c\u7b26\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<p>\u9047\u5230\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>\u5176\u4e2d <code>Welcome to HackerRank<\/code> \u662f\u666e\u901a\u6570\u636e\uff0c\u6240\u4ee5\u8f93\u51fa\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>&gt;&gt;&gt; Data\nWelcome to HackerRank\n<\/code><\/pre>\n\n\n\n<p>\u9047\u5230\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>\u91cc\u9762\u6ca1\u6709\u6362\u884c\u7b26\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\">7. \u65b9\u6cd5\u603b\u7ed3<\/h2>\n\n\n\n<p>\u8fd9\u4e00\u7c7b\u9898\u7684\u5173\u952e\u4e0d\u662f\u81ea\u5df1\u4ece\u5934\u89e3\u6790\u5b57\u7b26\u4e32\uff0c\u800c\u662f\u8bc6\u522b\u9898\u76ee\u60f3\u8ba9\u4f60\u7528\u54ea\u4e2a\u5de5\u5177\u3002<\/p>\n\n\n\n<p>\u770b\u5230\u9898\u76ee\u8981\u6c42\u5904\u7406 HTML\uff0c\u5e76\u4e14\u8981\u5206\u522b\u5904\u7406 comment\u3001data\u3001tag \u8fd9\u4e9b\u5185\u5bb9\u65f6\uff0c\u5e94\u8be5\u9a6c\u4e0a\u60f3\u5230\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>HTMLParser\n<\/code><\/pre>\n\n\n\n<p>\u7136\u540e\u6839\u636e\u9898\u76ee\u9700\u8981\uff0c\u91cd\u5199\u5bf9\u5e94\u7684\u65b9\u6cd5\uff1a<\/p>\n\n\n\n<figure class=\"wp-block-table\"><table class=\"has-fixed-layout\"><thead><tr><th>\u9898\u76ee\u8981\u5904\u7406\u7684\u5185\u5bb9<\/th><th>\u5e94\u8be5\u91cd\u5199\u7684\u65b9\u6cd5<\/th><\/tr><\/thead><tbody><tr><td>\u5f00\u59cb\u6807\u7b7e<\/td><td><code>handle_starttag()<\/code><\/td><\/tr><tr><td>\u7ed3\u675f\u6807\u7b7e<\/td><td><code>handle_endtag()<\/code><\/td><\/tr><tr><td>\u7a7a\u6807\u7b7e<\/td><td><code>handle_startendtag()<\/code><\/td><\/tr><tr><td>\u6ce8\u91ca<\/td><td><code>handle_comment()<\/code><\/td><\/tr><tr><td>\u666e\u901a\u6570\u636e<\/td><td><code>handle_data()<\/code><\/td><\/tr><\/tbody><\/table><\/figure>\n\n\n\n<p>\u672c\u9898\u53ea\u9700\u8981\u5904\u7406\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>handle_comment()\nhandle_data()\n<\/code><\/pre>\n\n\n\n<p>\u6240\u4ee5\u4ee3\u7801\u5e76\u4e0d\u957f\uff0c\u96be\u70b9\u4e3b\u8981\u5728\u5ba1\u9898\u548c\u7406\u89e3 <code>HTMLParser<\/code> \u7684\u5de5\u4f5c\u65b9\u5f0f\u3002<\/p>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h2 class=\"wp-block-heading\">8. \u5c0f\u7ec3\u4e60<\/h2>\n\n\n\n<p>\u8bf7\u4f60\u5c1d\u8bd5\u5b8c\u6210\u4e00\u4e2a\u8f7b\u5fae\u53d8\u5f62\u9898\uff1a<\/p>\n\n\n\n<p>\u8f93\u5165\u82e5\u5e72\u884c HTML \u4ee3\u7801\uff0c\u8981\u6c42\u6253\u5370\u6240\u6709\u666e\u901a\u6570\u636e <code>Data<\/code>\uff0c\u4f46\u4e0d\u6253\u5370\u6ce8\u91ca\u3002<\/p>\n\n\n\n<p>\u793a\u4f8b\u8f93\u5165\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>3\n&lt;div&gt;Hello&lt;\/div&gt;\n&lt;!-- hidden comment --&gt;\n&lt;p&gt;Python&lt;\/p&gt;\n<\/code><\/pre>\n\n\n\n<p>\u671f\u671b\u8f93\u51fa\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>&gt;&gt;&gt; Data\nHello\n&gt;&gt;&gt; Data\nPython\n<\/code><\/pre>\n\n\n\n<p>\u63d0\u793a\uff1a<\/p>\n\n\n\n<p>\u53ea\u9700\u8981\u91cd\u5199 <code>handle_data()<\/code>\uff0c\u4e0d\u9700\u8981\u5199 <code>handle_comment()<\/code>\u3002<\/p>\n\n\n\n<h2 class=\"wp-block-heading\">\u6211\u4eec\u5f15\u5165\u4e86\u5230\u5e95\u54ea\u4e9b\u5de5\u5177\uff0c\u6211\u4eec\u662f\u600e\u4e48\u4f7f\u7528\u7684\uff1f\uff0c\u6211\u770b\u8fd9\u4e2a\u4ee3\u7801\uff0c\u4ed6\u597d\u50cf\u5e76\u6ca1\u6709\u4f7f\u7528\u5230\uff1f<\/h2>\n\n\n\n<p>\u8fd9\u4e2a\u7591\u95ee\u975e\u5e38\u5173\u952e\uff1a<strong>\u4ee3\u7801\u91cc\u786e\u5b9e\u6ca1\u6709\u76f4\u63a5\u5199\u201c\u63d0\u53d6\u6ce8\u91ca\u201d\u6216\u201c\u63d0\u53d6 data\u201d\u7684\u903b\u8f91<\/strong>\uff0c\u56e0\u4e3a\u8fd9\u4ef6\u4e8b\u4e0d\u662f\u6211\u4eec\u624b\u52a8\u505a\u7684\uff0c\u800c\u662f\u4ea4\u7ed9\u4e86 <code>HTMLParser<\/code> \u8fd9\u4e2a\u5de5\u5177\u53bb\u505a\u3002<\/p>\n\n\n\n<p>\u6211\u4eec\u5f15\u5165\u7684\u5de5\u5177\u53ea\u6709\u4e00\u4e2a\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>from html.parser import HTMLParser\n<\/code><\/pre>\n\n\n\n<p>\u8fd9\u91cc\u7684\u610f\u601d\u662f\uff1a<\/p>\n\n\n\n<p>\u4ece Python \u5185\u7f6e\u6a21\u5757 <code>html.parser<\/code> \u91cc\u9762\uff0c\u5bfc\u5165\u4e00\u4e2a\u53eb <code>HTMLParser<\/code> \u7684\u7c7b\u3002<\/p>\n\n\n\n<p>\u5b83\u7684\u4f5c\u7528\u662f\uff1a<strong>\u5e2e\u6211\u4eec\u89e3\u6790 HTML \u4ee3\u7801\uff0c\u5e76\u4e14\u5728\u9047\u5230\u4e0d\u540c\u5185\u5bb9\u65f6\uff0c\u81ea\u52a8\u8c03\u7528\u5bf9\u5e94\u7684\u65b9\u6cd5\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\">1. \u6211\u4eec\u5230\u5e95\u5f15\u5165\u4e86\u4ec0\u4e48\uff1f<\/h2>\n\n\n\n<p>\u8fd9\u53e5\u4ee3\u7801\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>from html.parser import HTMLParser\n<\/code><\/pre>\n\n\n\n<p>\u53ef\u4ee5\u62c6\u5f00\u7406\u89e3\uff1a<\/p>\n\n\n\n<figure class=\"wp-block-table\"><table class=\"has-fixed-layout\"><thead><tr><th>\u90e8\u5206<\/th><th>\u542b\u4e49<\/th><\/tr><\/thead><tbody><tr><td><code>html.parser<\/code><\/td><td>Python \u5185\u7f6e\u7684 HTML \u89e3\u6790\u6a21\u5757<\/td><\/tr><tr><td><code>HTMLParser<\/code><\/td><td>\u6a21\u5757\u91cc\u9762\u63d0\u4f9b\u7684 HTML \u89e3\u6790\u5668\u7c7b<\/td><\/tr><tr><td><code>from ... import ...<\/code><\/td><td>\u4ece\u67d0\u4e2a\u6a21\u5757\u4e2d\u5bfc\u5165\u67d0\u4e2a\u5de5\u5177<\/td><\/tr><\/tbody><\/table><\/figure>\n\n\n\n<p>\u6240\u4ee5\u6211\u4eec\u5f15\u5165\u7684\u662f\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>HTMLParser\n<\/code><\/pre>\n\n\n\n<p>\u5b83\u4e0d\u662f\u4e00\u4e2a\u666e\u901a\u51fd\u6570\uff0c\u800c\u662f\u4e00\u4e2a<strong>\u7c7b<\/strong>\u3002<\/p>\n\n\n\n<p>\u4f60\u53ef\u4ee5\u628a\u5b83\u7406\u89e3\u6210 Python \u5b98\u65b9\u5df2\u7ecf\u5199\u597d\u7684\u4e00\u4e2a\u201cHTML \u5206\u6790\u673a\u5668\u201d\u3002<\/p>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h2 class=\"wp-block-heading\">2. \u4e3a\u4ec0\u4e48\u770b\u8d77\u6765\u597d\u50cf\u6ca1\u6709\u7528\u5230\uff1f<\/h2>\n\n\n\n<p>\u5176\u5b9e\u7528\u5230\u4e86\uff0c\u5728\u8fd9\u91cc\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>class MyHTMLParser(HTMLParser):\n<\/code><\/pre>\n\n\n\n<p>\u8fd9\u4e00\u884c\u5c31\u662f\u5728\u4f7f\u7528 <code>HTMLParser<\/code>\u3002<\/p>\n\n\n\n<p>\u5b83\u7684\u610f\u601d\u662f\uff1a<\/p>\n\n\n\n<p>\u6211\u4eec\u81ea\u5df1\u5b9a\u4e49\u4e00\u4e2a\u7c7b <code>MyHTMLParser<\/code>\uff0c\u5b83\u7ee7\u627f Python \u5b98\u65b9\u63d0\u4f9b\u7684 <code>HTMLParser<\/code>\u3002<\/p>\n\n\n\n<p>\u6362\u53e5\u8bdd\u8bf4\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>class MyHTMLParser(HTMLParser):\n<\/code><\/pre>\n\n\n\n<p>\u53ef\u4ee5\u7406\u89e3\u6210\uff1a<\/p>\n\n\n\n<p>\u6211\u57fa\u4e8e\u5b98\u65b9\u7684 HTML \u89e3\u6790\u5668\uff0c\u505a\u4e00\u4e2a\u81ea\u5df1\u7684\u89e3\u6790\u5668\u3002<\/p>\n\n\n\n<p>\u5b98\u65b9\u7684 <code>HTMLParser<\/code> \u5df2\u7ecf\u6709\u201c\u8bfb\u53d6 HTML\u3001\u8bc6\u522b\u6807\u7b7e\u3001\u8bc6\u522b\u6ce8\u91ca\u3001\u8bc6\u522b\u6587\u672c\u201d\u7684\u80fd\u529b\u3002<\/p>\n\n\n\n<p>\u6211\u4eec\u81ea\u5df1\u5199\u7684 <code>MyHTMLParser<\/code> \u53ea\u8d1f\u8d23\u544a\u8bc9\u5b83\uff1a<\/p>\n\n\n\n<p>\u9047\u5230\u6ce8\u91ca\u65f6\uff0c\u6211\u8981\u600e\u4e48\u8f93\u51fa\uff1b<\/p>\n\n\n\n<p>\u9047\u5230\u666e\u901a\u6570\u636e\u65f6\uff0c\u6211\u8981\u600e\u4e48\u8f93\u51fa\u3002<\/p>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h2 class=\"wp-block-heading\">3. \u771f\u6b63\u542f\u52a8\u89e3\u6790\u7684\u662f\u54ea\u4e00\u884c\uff1f<\/h2>\n\n\n\n<p>\u771f\u6b63\u8ba9\u89e3\u6790\u5668\u5f00\u59cb\u5de5\u4f5c\u7684\uff0c\u662f\u6700\u540e\u8fd9\u4e00\u884c\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>parser.feed(html)\n<\/code><\/pre>\n\n\n\n<p>\u5b8c\u6574\u8fc7\u7a0b\u662f\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>parser = MyHTMLParser()\nparser.feed(html)\n<\/code><\/pre>\n\n\n\n<p>\u7b2c\u4e00\u884c\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>parser = MyHTMLParser()\n<\/code><\/pre>\n\n\n\n<p>\u610f\u601d\u662f\u521b\u5efa\u4e00\u4e2a\u6211\u4eec\u81ea\u5df1\u7684 HTML \u89e3\u6790\u5668\u5bf9\u8c61\u3002<\/p>\n\n\n\n<p>\u7b2c\u4e8c\u884c\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>parser.feed(html)\n<\/code><\/pre>\n\n\n\n<p>\u610f\u601d\u662f\u628a HTML \u5b57\u7b26\u4e32\u5582\u7ed9\u89e3\u6790\u5668\uff0c\u8ba9\u5b83\u5f00\u59cb\u5206\u6790\u3002<\/p>\n\n\n\n<p>\u8fd9\u91cc\u7684 <code>feed<\/code> \u53ef\u4ee5\u7406\u89e3\u4e3a\u201c\u5582\u5165\u6570\u636e\u201d\u3002<\/p>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h2 class=\"wp-block-heading\">4. \u4e3a\u4ec0\u4e48 <code>handle_comment()<\/code> \u548c <code>handle_data()<\/code> \u6ca1\u6709\u88ab\u6211\u4eec\u624b\u52a8\u8c03\u7528\uff1f<\/h2>\n\n\n\n<p>\u8fd9\u662f\u8fd9\u9053\u9898\u6700\u5bb9\u6613\u56f0\u60d1\u7684\u5730\u65b9\u3002<\/p>\n\n\n\n<p>\u4ee3\u7801\u91cc\u6ca1\u6709\u5199\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>parser.handle_comment(...)\nparser.handle_data(...)\n<\/code><\/pre>\n\n\n\n<p>\u56e0\u4e3a\u8fd9\u4e24\u4e2a\u65b9\u6cd5\u4e0d\u662f\u6211\u4eec\u4e3b\u52a8\u8c03\u7528\u7684\uff0c\u800c\u662f <code>HTMLParser<\/code> \u5728\u89e3\u6790\u8fc7\u7a0b\u4e2d\u81ea\u52a8\u8c03\u7528\u7684\u3002<\/p>\n\n\n\n<p>\u4f8b\u5982 HTML \u662f\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>&lt;div&gt;Hello&lt;\/div&gt;\n&lt;!-- test --&gt;\n<\/code><\/pre>\n\n\n\n<p>\u5f53\u6267\u884c\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>parser.feed(html)\n<\/code><\/pre>\n\n\n\n<p>\u65f6\uff0c<code>HTMLParser<\/code> \u4f1a\u81ea\u52a8\u5206\u6790\u8fd9\u6bb5\u5185\u5bb9\u3002<\/p>\n\n\n\n<p>\u5b83\u770b\u5230\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>&lt;div&gt;\n<\/code><\/pre>\n\n\n\n<p>\u77e5\u9053\u8fd9\u662f\u5f00\u59cb\u6807\u7b7e\u3002<\/p>\n\n\n\n<p>\u5b83\u770b\u5230\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>Hello\n<\/code><\/pre>\n\n\n\n<p>\u77e5\u9053\u8fd9\u662f\u666e\u901a\u6570\u636e\uff0c\u4e8e\u662f\u81ea\u52a8\u8c03\u7528\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>handle_data(\"Hello\")\n<\/code><\/pre>\n\n\n\n<p>\u5b83\u770b\u5230\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>&lt;!-- test --&gt;\n<\/code><\/pre>\n\n\n\n<p>\u77e5\u9053\u8fd9\u662f\u6ce8\u91ca\uff0c\u4e8e\u662f\u81ea\u52a8\u8c03\u7528\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>handle_comment(\"test\")\n<\/code><\/pre>\n\n\n\n<p>\u6240\u4ee5\u6211\u4eec\u5199\u7684\u8fd9\u4e24\u4e2a\u65b9\u6cd5\uff0c\u672c\u8d28\u4e0a\u662f\u201c\u56de\u8c03\u65b9\u6cd5\u201d\u3002<\/p>\n\n\n\n<p>\u4e5f\u5c31\u662f\u8bf4\uff1a<\/p>\n\n\n\n<blockquote class=\"wp-block-quote is-layout-flow wp-block-quote-is-layout-flow\">\n<p>\u6211\u4eec\u63d0\u524d\u5b9a\u4e49\u597d\u89c4\u5219\uff0c\u7b49 HTMLParser \u9047\u5230\u5bf9\u5e94\u5185\u5bb9\u65f6\uff0c\u5b83\u4f1a\u81ea\u52a8\u5e2e\u6211\u4eec\u8c03\u7528\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\">5. \u8fd9\u6bb5\u4ee3\u7801\u6bcf\u4e00\u90e8\u5206\u5230\u5e95\u5728\u5e72\u4ec0\u4e48\uff1f<\/h2>\n\n\n\n<p>\u6211\u4eec\u628a\u4ee3\u7801\u62c6\u5f00\u770b\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>from html.parser import HTMLParser\n<\/code><\/pre>\n\n\n\n<p>\u5bfc\u5165\u5b98\u65b9 HTML \u89e3\u6790\u5668\u3002<\/p>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<pre class=\"wp-block-code\"><code>class MyHTMLParser(HTMLParser):\n<\/code><\/pre>\n\n\n\n<p>\u5b9a\u4e49\u81ea\u5df1\u7684\u89e3\u6790\u5668\uff0c\u5e76\u7ee7\u627f\u5b98\u65b9\u89e3\u6790\u5668\u7684\u80fd\u529b\u3002<\/p>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<pre class=\"wp-block-code\"><code>def handle_comment(self, data):\n<\/code><\/pre>\n\n\n\n<p>\u544a\u8bc9\u89e3\u6790\u5668\uff1a<\/p>\n\n\n\n<p>\u5f53\u4f60\u9047\u5230 HTML \u6ce8\u91ca\u65f6\uff0c\u8bf7\u6267\u884c\u8fd9\u91cc\u7684\u4ee3\u7801\u3002<\/p>\n\n\n\n<p>\u6bd4\u5982\u9047\u5230\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>&lt;!-- hello --&gt;\n<\/code><\/pre>\n\n\n\n<p>\u8fd9\u91cc\u7684 <code>data<\/code> \u5c31\u662f\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>hello\n<\/code><\/pre>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<pre class=\"wp-block-code\"><code>if '\\n' in data:\n    print(\"&gt;&gt;&gt; Multi-line Comment\")\nelse:\n    print(\"&gt;&gt;&gt; Single-line Comment\")\n<\/code><\/pre>\n\n\n\n<p>\u5224\u65ad\u8fd9\u4e2a\u6ce8\u91ca\u91cc\u9762\u6709\u6ca1\u6709\u6362\u884c\u7b26\u3002<\/p>\n\n\n\n<p>\u6709\u6362\u884c\u7b26\uff0c\u5c31\u662f\u591a\u884c\u6ce8\u91ca\u3002<\/p>\n\n\n\n<p>\u6ca1\u6709\u6362\u884c\u7b26\uff0c\u5c31\u662f\u5355\u884c\u6ce8\u91ca\u3002<\/p>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<pre class=\"wp-block-code\"><code>def handle_data(self, data):\n<\/code><\/pre>\n\n\n\n<p>\u544a\u8bc9\u89e3\u6790\u5668\uff1a<\/p>\n\n\n\n<p>\u5f53\u4f60\u9047\u5230\u666e\u901a\u6587\u672c\u6570\u636e\u65f6\uff0c\u8bf7\u6267\u884c\u8fd9\u91cc\u7684\u4ee3\u7801\u3002<\/p>\n\n\n\n<p>\u6bd4\u5982\u9047\u5230\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>&lt;div&gt;Hello&lt;\/div&gt;\n<\/code><\/pre>\n\n\n\n<p>\u8fd9\u91cc\u7684 <code>data<\/code> \u5c31\u662f\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>Hello\n<\/code><\/pre>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<pre class=\"wp-block-code\"><code>if data != '\\n':\n<\/code><\/pre>\n\n\n\n<p>\u9898\u76ee\u8981\u6c42\u5982\u679c\u6570\u636e\u53ea\u662f\u6362\u884c\u7b26\uff0c\u5c31\u4e0d\u8981\u6253\u5370\u3002<\/p>\n\n\n\n<p>\u6240\u4ee5\u6211\u4eec\u8981\u8fc7\u6ee4\u6389\u5355\u72ec\u7684 <code>'\\n'<\/code>\u3002<\/p>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<pre class=\"wp-block-code\"><code>parser = MyHTMLParser()\nparser.feed(html)\n<\/code><\/pre>\n\n\n\n<p>\u521b\u5efa\u89e3\u6790\u5668\uff0c\u5e76\u628a HTML \u5185\u5bb9\u4ea4\u7ed9\u5b83\u5904\u7406\u3002<\/p>\n\n\n\n<p>\u4ece\u8fd9\u4e00\u523b\u5f00\u59cb\uff0c<code>HTMLParser<\/code> \u5c31\u4f1a\u81ea\u52a8\u626b\u63cf HTML\uff0c\u5e76\u81ea\u52a8\u8c03\u7528\u6211\u4eec\u5199\u597d\u7684\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\">6. \u7528\u4e00\u4e2a\u751f\u6d3b\u7c7b\u6bd4\u7406\u89e3<\/h2>\n\n\n\n<p>\u4f60\u53ef\u4ee5\u628a <code>HTMLParser<\/code> \u60f3\u8c61\u6210\u4e00\u4e2a\u5feb\u9012\u5206\u62e3\u673a\u5668\u3002<\/p>\n\n\n\n<p>HTML \u5185\u5bb9\u91cc\u9762\u6709\u5f88\u591a\u4e1c\u897f\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>\u6807\u7b7e\u3001\u6ce8\u91ca\u3001\u666e\u901a\u6587\u5b57\u3001\u6362\u884c\n<\/code><\/pre>\n\n\n\n<p><code>HTMLParser<\/code> \u8d1f\u8d23\u8bc6\u522b\u5b83\u4eec\u5c5e\u4e8e\u54ea\u4e00\u7c7b\u3002<\/p>\n\n\n\n<p>\u6211\u4eec\u5199\u7684\u4ee3\u7801\u76f8\u5f53\u4e8e\u63d0\u524d\u544a\u8bc9\u673a\u5668\uff1a<\/p>\n\n\n\n<p>\u5982\u679c\u4f60\u53d1\u73b0\u201c\u6ce8\u91ca\u201d\uff0c\u5c31\u6267\u884c <code>handle_comment()<\/code>\uff1b<\/p>\n\n\n\n<p>\u5982\u679c\u4f60\u53d1\u73b0\u201c\u666e\u901a\u6587\u5b57\u201d\uff0c\u5c31\u6267\u884c <code>handle_data()<\/code>\u3002<\/p>\n\n\n\n<p>\u6240\u4ee5\u6211\u4eec\u4e0d\u9700\u8981\u81ea\u5df1\u5199\u590d\u6742\u7684\u5b57\u7b26\u4e32\u67e5\u627e\u89c4\u5219\u3002<\/p>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h2 class=\"wp-block-heading\">7. \u6700\u6838\u5fc3\u7684\u4e00\u53e5\u8bdd<\/h2>\n\n\n\n<p>\u8fd9\u9053\u9898\u7684\u5173\u952e\u662f\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>HTMLParser \u8d1f\u8d23\u201c\u8bc6\u522b HTML \u7ed3\u6784\u201d\uff0c\u6211\u4eec\u8d1f\u8d23\u201c\u5b9a\u4e49\u9047\u5230\u6ce8\u91ca\u548c\u6570\u636e\u65f6\u600e\u4e48\u8f93\u51fa\u201d\u3002\n<\/code><\/pre>\n\n\n\n<p>\u6240\u4ee5\u5de5\u5177\u786e\u5b9e\u7528\u5230\u4e86\uff0c\u53ea\u662f\u5b83\u4e0d\u662f\u50cf\u666e\u901a\u51fd\u6570\u90a3\u6837\u76f4\u63a5\u8c03\u7528\uff0c\u800c\u662f\u901a\u8fc7\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>class MyHTMLParser(HTMLParser)\n<\/code><\/pre>\n\n\n\n<p>\u548c\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>parser.feed(html)\n<\/code><\/pre>\n\n\n\n<p>\u95f4\u63a5\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\">8. \u5c0f\u7ec3\u4e60<\/h2>\n\n\n\n<p>\u8bf7\u4f60\u5224\u65ad\u4e0b\u9762\u4ee3\u7801\u4e2d\uff0c\u54ea\u4e00\u884c\u771f\u6b63\u5f00\u59cb\u8ba9\u89e3\u6790\u5668\u5de5\u4f5c\uff1f<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>from html.parser import HTMLParser\n\nclass MyHTMLParser(HTMLParser):\n    def handle_data(self, data):\n        print(data)\n\nparser = MyHTMLParser()\nparser.feed(\"&lt;p&gt;Hello&lt;\/p&gt;\")\n<\/code><\/pre>\n\n\n\n<p>\u63d0\u793a\uff1a\u4e0d\u662f <code>class<\/code> \u90a3\u4e00\u884c\uff0c\u4e5f\u4e0d\u662f <code>def handle_data<\/code> \u90a3\u4e00\u884c\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"<p>1. \u9898\u76ee\u8003\u70b9 \u8fd9\u9053\u9898\u4e3b\u8981\u8003\uff1a \u8fd9\u9053\u9898\u4e0d\u662f\u8ba9\u6211\u4eec\u81ea\u5df1\u624b\u5199 HTML \u89e3\u6790\u5668\uff0c\u800c\u662f\u8ba9\u6211\u4eec\u4f7f\u7528 Python \u5df2\u7ecf [&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-2168","post","type-post","status-publish","format-standard","hentry","category-text"],"_links":{"self":[{"href":"http:\/\/www.preluna.xyz\/index.php\/wp-json\/wp\/v2\/posts\/2168","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=2168"}],"version-history":[{"count":2,"href":"http:\/\/www.preluna.xyz\/index.php\/wp-json\/wp\/v2\/posts\/2168\/revisions"}],"predecessor-version":[{"id":2172,"href":"http:\/\/www.preluna.xyz\/index.php\/wp-json\/wp\/v2\/posts\/2168\/revisions\/2172"}],"wp:attachment":[{"href":"http:\/\/www.preluna.xyz\/index.php\/wp-json\/wp\/v2\/media?parent=2168"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"http:\/\/www.preluna.xyz\/index.php\/wp-json\/wp\/v2\/categories?post=2168"},{"taxonomy":"post_tag","embeddable":true,"href":"http:\/\/www.preluna.xyz\/index.php\/wp-json\/wp\/v2\/tags?post=2168"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}