{"id":1262,"date":"2025-10-20T19:30:08","date_gmt":"2025-10-20T11:30:08","guid":{"rendered":"https:\/\/www.zhaozhao123.cn\/php\/my1js\/1262.html"},"modified":"2025-10-20T19:30:09","modified_gmt":"2025-10-20T11:30:09","slug":"symfony-domcrawler-%e4%b8%ad%e7%9a%84-text-%e4%b8%8e-innertext-%e7%9a%84%e7%94%a8%e6%b3%95%e5%af%b9%e6%af%94%e4%b8%8e%e5%8c%ba%e5%88%ab","status":"publish","type":"my1js","link":"https:\/\/www.zhaozhao123.cn\/php\/my1js\/1262.html","title":{"rendered":"Symfony DomCrawler \u4e2d\u7684\u00a0text() \u4e0e innerText() \u7684\u7528\u6cd5\u5bf9\u6bd4\u4e0e\u533a\u522b"},"content":{"rendered":"<p>\u5728\u7f51\u9875\u89e3\u6790\u548c DOM \u64cd\u4f5c\u4e2d\uff0c<code>innerText<\/code> \u548c <code>text()<\/code> \u662f\u4e24\u79cd\u5e38\u89c1\u7684\u6587\u672c\u63d0\u53d6\u65b9\u5f0f\uff0c\u4f46\u5b83\u4eec\u5728\u884c\u4e3a\u548c\u9002\u7528\u573a\u666f\u4e0a\u6709\u672c\u8d28\u533a\u522b\u3002\u4ee5\u4e0b\u662f\u9488\u5bf9 <strong>Symfony DomCrawler<\/strong> \u548c\u5176\u4ed6\u5e38\u89c1\u573a\u666f\u7684\u8be6\u7ec6\u5bf9\u6bd4\uff1a<\/p><hr class=\"wp-block-separator has-alpha-channel-opacity\"><h2 class=\"wp-block-heading\">\u4e00\u3001\u6838\u5fc3\u533a\u522b<\/h2><figure class=\"wp-block-table\"><table class=\"has-fixed-layout\"><thead><tr><th>\u7279\u6027<\/th><th><code>innerText<\/code> (\u6d4f\u89c8\u5668\u73af\u5883)<\/th><th><code>text()<\/code> (Symfony DomCrawler)<\/th><\/tr><\/thead><tbody><tr><td><strong>\u6765\u6e90<\/strong><\/td><td>JavaScript \u539f\u751f\u5c5e\u6027<\/td><td>Symfony DomCrawler \u7684\u65b9\u6cd5<\/td><\/tr><tr><td><strong>\u6267\u884c\u73af\u5883<\/strong><\/td><td>\u6d4f\u89c8\u5668\uff08\u4f9d\u8d56\u6e32\u67d3\u5f15\u64ce\uff09<\/td><td>\u670d\u52a1\u5668\u7aef\uff08\u7eaf\u6587\u672c\u89e3\u6790\uff09<\/td><\/tr><tr><td><strong>\u9690\u85cf\u5185\u5bb9\u5904\u7406<\/strong><\/td><td>\u5ffd\u7565\u88ab CSS \u9690\u85cf\u7684\u5143\u7d20\u7684\u6587\u672c<\/td><td>\u59cb\u7ec8\u8fd4\u56de\u6240\u6709\u8282\u70b9\u7684\u6587\u672c<\/td><\/tr><tr><td><strong>\u7a7a\u767d\u7b26\u5904\u7406<\/strong><\/td><td>\u5408\u5e76\u8fde\u7eed\u7a7a\u683c\uff0c\u4fdd\u7559\u6362\u884c\u903b\u8f91<\/td><td>\u4fdd\u7559\u539f\u59cb\u7a7a\u767d\u7b26\uff08\u5305\u62ec\u7f29\u8fdb\uff09<\/td><\/tr><tr><td><strong>\u6027\u80fd<\/strong><\/td><td>\u89e6\u53d1\u56de\u6d41\uff08\u6027\u80fd\u654f\u611f\u64cd\u4f5c\uff09<\/td><td>\u7eaf\u6587\u672c\u89e3\u6790\uff08\u65e0\u6e32\u67d3\u5f00\u9500\uff09<\/td><\/tr><\/tbody><\/table><\/figure><hr class=\"wp-block-separator has-alpha-channel-opacity\"><h2 class=\"wp-block-heading\">\u4e8c\u3001Symfony DomCrawler \u4e2d\u7684 <code>text()<\/code><\/h2><h3 class=\"wp-block-heading\">1. \u884c\u4e3a\u7279\u70b9<\/h3><ul class=\"wp-block-list\">\n<li><strong>\u9012\u5f52\u63d0\u53d6<\/strong>\uff1a\u8fd4\u56de\u5f53\u524d\u9009\u62e9\u7684\u7b2c\u4e00\u4e2a\u8282\u70b9\u53ca\u5176<strong>\u6240\u6709\u5b50\u8282\u70b9<\/strong>\u7684\u6587\u672c\u5185\u5bb9<\/li>\n\n\n\n<li><strong>\u539f\u59cb\u6587\u672c<\/strong>\uff1a\u4fdd\u7559 HTML \u4e2d\u7684\u7a7a\u767d\u7b26\uff08\u5305\u62ec\u6362\u884c\u548c\u7f29\u8fdb\uff09<\/li>\n\n\n\n<li><strong>\u4e0d\u5904\u7406\u6837\u5f0f<\/strong>\uff1a\u65e0\u8bba\u5143\u7d20\u662f\u5426\u88ab CSS \u9690\u85cf\uff0c\u90fd\u4f1a\u8fd4\u56de\u6587\u672c<\/li>\n\n\n\n<li><strong>\u7f16\u7801\u5b89\u5168<\/strong>\uff1a\u81ea\u52a8\u5904\u7406 HTML \u5b9e\u4f53\uff08\u5982 <code>&amp;amp;<\/code> \u2192 <code>&amp;<\/code>\uff09<\/li>\n<\/ul><h3 class=\"wp-block-heading\">2. \u793a\u4f8b<\/h3><pre class=\"wp-block-code\"><code>$html = &lt;&lt;&lt;HTML\n&lt;div class=\"content\"&gt;\n  Visible Text\n  &lt;span style=\"display:none\"&gt;Hidden Text&lt;\/span&gt;\n  &lt;p&gt;   Extra   Spaces   &lt;\/p&gt;\n&lt;\/div&gt;\nHTML;\n\n$crawler = new Crawler($html);\necho $crawler-&gt;filter('.content')-&gt;text();\n\n\/\/ \u8f93\u51fa\uff1a\n\"Visible Text Hidden Text    Extra   Spaces\"<\/code><\/pre><hr class=\"wp-block-separator has-alpha-channel-opacity\"><h2 class=\"wp-block-heading\">\u4e09\u3001\u6d4f\u89c8\u5668\u4e2d\u7684 <code>innerText<\/code><\/h2><h3 class=\"wp-block-heading\">1. \u884c\u4e3a\u7279\u70b9<\/h3><ul class=\"wp-block-list\">\n<li><strong>\u6e32\u67d3\u4f9d\u8d56<\/strong>\uff1a\u53ea\u8fd4\u56de<strong>\u5b9e\u9645\u6e32\u67d3\u53ef\u89c1<\/strong>\u7684\u6587\u672c<\/li>\n\n\n\n<li><strong>\u6837\u5f0f\u654f\u611f<\/strong>\uff1a\u81ea\u52a8\u8fc7\u6ee4\u88ab <code>display: none<\/code> \u6216 <code>visibility: hidden<\/code> \u9690\u85cf\u7684\u5185\u5bb9<\/li>\n\n\n\n<li><strong>\u7a7a\u767d\u4f18\u5316<\/strong>\uff1a\u5408\u5e76\u8fde\u7eed\u7a7a\u683c\uff0c\u6309\u6e32\u67d3\u7ed3\u679c\u6362\u884c<\/li>\n\n\n\n<li><strong>\u6027\u80fd\u5f71\u54cd<\/strong>\uff1a\u9700\u8981\u8ba1\u7b97\u5e03\u5c40\uff0c\u53ef\u80fd\u89e6\u53d1\u56de\u6d41<\/li>\n<\/ul><h3 class=\"wp-block-heading\">2. \u793a\u4f8b<\/h3><pre class=\"wp-block-code\"><code>&lt;div class=\"content\"&gt;\n  Visible Text\n  &lt;span style=\"display:none\"&gt;Hidden Text&lt;\/span&gt;\n  &lt;p&gt;   Extra   Spaces   &lt;\/p&gt;\n&lt;\/div&gt;<\/code><\/pre><pre class=\"wp-block-code\"><code>document.querySelector('.content').innerText;\n\n\/\/ \u8f93\u51fa\uff08\u6d4f\u89c8\u5668\u63a7\u5236\u53f0\uff09\uff1a\n\"Visible TextnExtra Spaces\"<\/code><\/pre><hr class=\"wp-block-separator has-alpha-channel-opacity\"><h2 class=\"wp-block-heading\">\u56db\u3001Symfony DomCrawler \u7684\u7279\u6b8a\u573a\u666f<\/h2><h3 class=\"wp-block-heading\">1. \u63d0\u53d6\u53ef\u89c1\u6587\u672c\uff08\u6a21\u62df <code>innerText<\/code>\uff09<\/h3><p>\u7531\u4e8e DomCrawler <strong>\u4e0d\u6267\u884c CSS<\/strong>\uff0c\u9700\u8981\u624b\u52a8\u8fc7\u6ee4\u9690\u85cf\u5143\u7d20\uff1a<\/p><pre class=\"wp-block-code\"><code>$crawler-&gt;filter('.content')\n  \/\/ \u8fc7\u6ee4\u9690\u85cf\u5143\u7d20\uff08\u5047\u8bbe\u901a\u8fc7\u7c7b\u540d\u6807\u8bb0\uff09\n  -&gt;reduce(function (Crawler $node) {\n      return !str_contains($node-&gt;attr('class'), 'hidden');\n  })\n  -&gt;text();<\/code><\/pre><h3 class=\"wp-block-heading\">2. \u89c4\u8303\u5316\u7a7a\u767d\u7b26<\/h3><p>\u5904\u7406 <code>text()<\/code> \u8fd4\u56de\u7684\u539f\u59cb\u7a7a\u767d\uff1a<\/p><pre class=\"wp-block-code\"><code>$text = $crawler-&gt;filter('p')-&gt;text();\n$normalizedText = trim(preg_replace('\/s+\/', ' ', $text));<\/code><\/pre><hr class=\"wp-block-separator has-alpha-channel-opacity\"><h2 class=\"wp-block-heading\">\u4e94\u3001\u9009\u62e9\u5efa\u8bae<\/h2><figure class=\"wp-block-table\"><table class=\"has-fixed-layout\"><thead><tr><th>\u573a\u666f<\/th><th>\u63a8\u8350\u65b9\u6cd5<\/th><\/tr><\/thead><tbody><tr><td>\u5feb\u901f\u63d0\u53d6\u6240\u6709\u6587\u672c<\/td><td><code>text()<\/code><\/td><\/tr><tr><td>\u9700\u8981\u4fdd\u7559\u539f\u59cb\u683c\u5f0f<\/td><td><code>text()<\/code><\/td><\/tr><tr><td>\u670d\u52a1\u5668\u7aef\u8fc7\u6ee4\u9690\u85cf\u5185\u5bb9<\/td><td>\u624b\u52a8\u9009\u62e9\u5668\u8fc7\u6ee4 + <code>text()<\/code><\/td><\/tr><tr><td>\u7cbe\u786e\u6a21\u62df\u6d4f\u89c8\u5668\u6e32\u67d3\u6587\u672c<\/td><td>\u7ed3\u5408 headless \u6d4f\u89c8\u5668<\/td><\/tr><\/tbody><\/table><\/figure><hr class=\"wp-block-separator has-alpha-channel-opacity\"><h2 class=\"wp-block-heading\">\u516d\u3001\u6027\u80fd\u5bf9\u6bd4\uff08PHP \u73af\u5883\uff09<\/h2><pre class=\"wp-block-code\"><code>\/\/ \u6d4b\u8bd5 1000 \u6b21 text() \u8c03\u7528\n$start = microtime(true);\nfor ($i = 0; $i &lt; 1000; $i++) {\n    $text = $crawler-&gt;filter('div')-&gt;text();\n}\necho 'text(): ' . (microtime(true) - $start) . 's';\n\n\/\/ \u5178\u578b\u7ed3\u679c\uff1atext(): 0.0021s \uff08\u65e0\u9700\u6e32\u67d3\uff0c\u6781\u5feb\uff09<\/code><\/pre><hr class=\"wp-block-separator has-alpha-channel-opacity\"><h2 class=\"wp-block-heading\">\u603b\u7ed3<\/h2><ul class=\"wp-block-list\">\n<li><strong><code>text()<\/code><\/strong> \u662f Symfony DomCrawler \u7684\u6838\u5fc3\u65b9\u6cd5\uff0c\u7528\u4e8e<strong>\u5feb\u901f\u83b7\u53d6\u539f\u59cb\u6587\u672c<\/strong><\/li>\n\n\n\n<li><strong><code>innerText<\/code><\/strong> \u662f\u6d4f\u89c8\u5668\u7279\u6709\u7684\u5c5e\u6027\uff0c<strong>\u4f9d\u8d56\u6e32\u67d3\u7ed3\u679c<\/strong><\/li>\n\n\n\n<li>\u5728\u670d\u52a1\u5668\u7aef\u89e3\u6790\u65f6\uff0c\u82e5\u9700\u8981\u6a21\u62df <code>innerText<\/code> \u884c\u4e3a\uff0c\u9700\u7ed3\u5408\u9009\u62e9\u5668\u8fc7\u6ee4\u548c\u6587\u672c\u540e\u5904\u7406<\/li>\n<\/ul>","protected":false},"excerpt":{"rendered":"<p>\u5728\u7f51\u9875\u89e3\u6790\u548c DOM \u64cd\u4f5c\u4e2d\uff0cinnerText \u548c text() \u662f\u4e24\u79cd\u5e38\u89c1\u7684\u6587\u672c\u63d0\u53d6\u65b9\u5f0f\uff0c\u4f46\u5b83\u4eec\u5728\u884c\u4e3a\u548c\u9002\u7528\u573a\u666f\u4e0a\u6709\u672c\u8d28\u533a\u522b\u3002\u4ee5\u4e0b\u662f\u9488\u5bf9 Symfony DomCrawler \u548c\u5176\u4ed6\u5e38\u89c1\u573a\u666f\u7684\u8be6\u7ec6\u5bf9\u6bd4\uff1a \u4e00\u3001\u6838\u5fc3\u533a\u522b \u7279\u6027 innerText (\u6d4f\u89c8\u5668\u73af\u5883) text() (Symfony DomCrawler) ..<\/p>\n","protected":false},"author":1,"featured_media":0,"menu_order":0,"template":"","meta":{"_acf_changed":false},"tags":[],"my1js2nav":[45],"tuisongtax":[],"class_list":["post-1262","my1js","type-my1js","status-publish","hentry","my1js2nav-symfony"],"acf":{"qian_art_seotitle":"","qian_art_seotitle_source":{"label":"SEO\u6807\u9898","type":"text","formatted_value":""},"qian_art_seokws":"","qian_art_seokws_source":{"label":"SEO\u5173\u952e\u8bcd","type":"text","formatted_value":""},"qian_art_stzhong":"","qian_art_stzhong_source":{"label":"\u4e2d | \u77ed\u6807\u9898","type":"text","formatted_value":""}},"_links":{"self":[{"href":"https:\/\/www.zhaozhao123.cn\/php\/wp-json\/wp\/v2\/my1js\/1262","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.zhaozhao123.cn\/php\/wp-json\/wp\/v2\/my1js"}],"about":[{"href":"https:\/\/www.zhaozhao123.cn\/php\/wp-json\/wp\/v2\/types\/my1js"}],"author":[{"embeddable":true,"href":"https:\/\/www.zhaozhao123.cn\/php\/wp-json\/wp\/v2\/users\/1"}],"wp:attachment":[{"href":"https:\/\/www.zhaozhao123.cn\/php\/wp-json\/wp\/v2\/media?parent=1262"}],"wp:term":[{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.zhaozhao123.cn\/php\/wp-json\/wp\/v2\/tags?post=1262"},{"taxonomy":"my1js2nav","embeddable":true,"href":"https:\/\/www.zhaozhao123.cn\/php\/wp-json\/wp\/v2\/my1js2nav?post=1262"},{"taxonomy":"tuisongtax","embeddable":true,"href":"https:\/\/www.zhaozhao123.cn\/php\/wp-json\/wp\/v2\/tuisongtax?post=1262"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}