{"id":1259,"date":"2025-10-20T19:26:54","date_gmt":"2025-10-20T11:26:54","guid":{"rendered":"https:\/\/www.zhaozhao123.cn\/php\/my1js\/1259.html"},"modified":"2025-10-20T19:29:16","modified_gmt":"2025-10-20T11:29:16","slug":"masterminds-html5%e4%b8%8esymfony-domcrawler%e7%bb%93%e5%90%88%e4%bd%bf%e7%94%a8%e6%95%99%e7%a8%8b%e4%b8%8e%e5%ae%9e%e6%88%98","status":"publish","type":"my1js","link":"https:\/\/www.zhaozhao123.cn\/php\/my1js\/1259.html","title":{"rendered":"masterminds\/html5\u4e0eSymfony DomCrawler\u7ed3\u5408\u4f7f\u7528\u6559\u7a0b\u4e0e\u5b9e\u6218"},"content":{"rendered":"

\u4ee5\u4e0b\u662f\u7ed3\u5408\u4f7f\u7528 masterminds\/html5<\/code>\uff08PHP \u7684 HTML5 \u89e3\u6790\u5e93\uff09\u4e0e Symfony DomCrawler \u7684\u6559\u7a0b\u548c\u5b9e\u6218\u6307\u5357\u3002\u901a\u8fc7\u4e8c\u8005\u7684\u7ed3\u5408\uff0c\u53ef\u4ee5\u66f4\u9ad8\u6548\u5730\u89e3\u6790\u73b0\u4ee3 HTML5 \u5185\u5bb9\uff0c\u5e76\u5229\u7528 DomCrawler \u5f3a\u5927\u7684\u6570\u636e\u63d0\u53d6\u80fd\u529b\u3002<\/p>

\u4e00\u3001\u80cc\u666f\u4ecb\u7ecd<\/h3>
    \n
  1. masterminds\/html5<\/strong>
    \u4e00\u4e2a\u7b26\u5408 HTML5 \u89c4\u8303\u7684 PHP \u89e3\u6790\u5e93\uff0c\u652f\u6301\u89e3\u6790\u590d\u6742\u7684 HTML5 \u6587\u6863\uff08\u5982\u672a\u95ed\u5408\u6807\u7b7e\u3001\u5d4c\u5957\u9519\u8bef\u7b49\uff09\uff0c\u9002\u7528\u4e8e\u5904\u7406\u73b0\u4ee3\u7f51\u9875\u3002<\/li>\n\n\n\n
  2. Symfony DomCrawler<\/strong>
    Symfony \u63d0\u4f9b\u7684 HTML\/XML \u89e3\u6790\u5de5\u5177\uff0c\u652f\u6301 XPath \u548c CSS \u9009\u62e9\u5668\uff0c\u9002\u5408\u4ece\u6587\u6863\u4e2d\u63d0\u53d6\u7ed3\u6784\u5316\u6570\u636e\u3002<\/li>\n<\/ol>

    \u4e8c\u8005\u7684\u7ed3\u5408\u80fd\u89e3\u51b3\u539f\u751f PHP DOM \u89e3\u6790\u5668\u5bf9 HTML5 \u652f\u6301\u4e0d\u8db3\u7684\u95ee\u9898\uff0c\u540c\u65f6\u4fdd\u7559 DomCrawler \u7684\u4fbf\u6377 API\u3002<\/p>

    \u4e8c\u3001\u73af\u5883\u51c6\u5907<\/h3>

    1. \u5b89\u88c5\u4f9d\u8d56<\/h4>

    \u901a\u8fc7 Composer \u5b89\u88c5\u4e24\u4e2a\u5e93\uff1a<\/p>

    composer require masterminds\/html5 symfony\/dom-crawler symfony\/css-selector<\/code><\/pre>
    2. \u5f15\u5165\u547d\u540d\u7a7a\u95f4<\/h4>
    use MastermindsHTML5;
    use SymfonyComponentDomCrawlerCrawler;<\/p>
    \u4e09\u3001\u57fa\u7840\u7528\u6cd5<\/h3>
    1. \u89e3\u6790 HTML5 \u5e76\u521b\u5efa Crawler \u5bf9\u8c61<\/h4>
    $html5 = new HTML5();\n$htmlContent = <<<'HTML'\n<!DOCTYPE html>\n<html>\n<head><title>Test<\/title><\/head>\n<body>\n  <article class=\"post\">\n    <h1>Hello HTML5!<\/h1>\n    <div data-content=\"main\">Content with <span>nested<\/span> elements.<\/div>\n  <\/article>\n<\/body>\n<\/html>\nHTML;\n\n\/\/ \u4f7f\u7528 html5 \u89e3\u6790\u5668\u751f\u6210 DOMDocument\n$dom = $html5->loadHTML($htmlContent);\n\n\/\/ \u5c06 DOMDocument \u4f20\u9012\u7ed9 DomCrawler\n$crawler = new Crawler($dom);<\/code><\/pre>
    2. \u4f7f\u7528 CSS \u9009\u62e9\u5668\u63d0\u53d6\u6570\u636e<\/h4>
    \/\/ \u63d0\u53d6\u6807\u9898\u6587\u672c\n$title = $crawler->filter('title')->text();\necho $title; \/\/ \u8f93\u51fa: Test\n\n\/\/ \u63d0\u53d6\u6587\u7ae0\u5185\u5bb9\n$crawler->filter('.post')->each(function (Crawler $node) {\n    $heading = $node->filter('h1')->text();\n    $content = $node->filter('[data-content=\"main\"]')->text();\n\n    echo \"Heading: $headingnContent: $contentn\";\n});<\/code><\/pre>
    \u56db\u3001\u5b9e\u6218\u573a\u666f\uff1a\u722c\u53d6\u52a8\u6001 HTML5 \u5185\u5bb9<\/h3>
    1. \u89e3\u6790\u8fdc\u7a0b\u7f51\u9875<\/h4>
    $url = 'https:\/\/example.com<\/a>';\n$htmlContent = file_get_contents($url);\n\n\/\/ \u4f7f\u7528 html5 \u89e3\u6790\u53ef\u80fd\u5305\u542b\u975e\u6807\u51c6\u6807\u7b7e\u7684\u9875\u9762\n$html5 = new HTML5();\n$dom = $html5->loadHTML($htmlContent);\n$crawler = new Crawler($dom);\n\n\/\/ \u63d0\u53d6\u6240\u6709\u94fe\u63a5\n$links = $crawler->filter('a')->extract(['href']);\nprint_r($links);<\/code><\/pre>
    2. \u5904\u7406 HTML5 \u7279\u6b8a\u6807\u7b7e<\/h4>
    \u82e5\u9875\u9762\u5305\u542b <template><\/code>\u3001<svg><\/code> \u6216\u81ea\u5b9a\u4e49\u6807\u7b7e\uff1a<\/p>
    $html = <<<'HTML'\n<div>\n  <template id=\"tpl\"><p>HTML5 Template<\/p><\/template>\n  <svg><circle cx=\"50\" cy=\"50\" r=\"40\"\/><\/svg>\n<\/div>\nHTML;\n$html5 = new HTML5();\n$dom = $html5->loadHTML($html);\n$crawler = new Crawler($dom);\n\n\/\/ \u63d0\u53d6 SVG \u4e2d\u7684 circle \u5c5e\u6027\n$circle = $crawler->filter('svg circle')->attr('cx');\necho \"Circle CX: $circle\"; \/\/ \u8f93\u51fa: 50<\/code><\/pre>
    \u4e94\u3001\u9ad8\u7ea7\u6280\u5de7<\/h3>
    1. \u9519\u8bef\u5904\u7406\u4e0e\u5bb9\u9519<\/h4>
    try {\n    $dom = $html5->loadHTML('<div><p>Broken HTML<\/div>');\n} catch (Exception $e) {\n    \/\/ \u5904\u7406\u89e3\u6790\u9519\u8bef\n    echo \"\u89e3\u6790\u5931\u8d25: \" . $e->getMessage();\n}\n\n\/\/ \u9759\u9ed8\u5ffd\u7565\u9519\u8bef\uff08\u9ed8\u8ba4\u884c\u4e3a\uff09\n$html5->setOption('ignore_parse_errors', true);\n$dom = $html5->loadHTML('<div><p>Broken HTML');<\/code><\/pre>
    2. \u7ed3\u5408 XPath \u590d\u6742\u67e5\u8be2<\/h4>
    \/\/ \u4f7f\u7528 XPath \u67e5\u627e\u5177\u6709 data-* \u5c5e\u6027\u7684\u5143\u7d20\n$result = $crawler->filterXPath('\/\/*[@data-content]')->each(function (Crawler $node) {\n    return $node->attr('data-content');\n});\nprint_r($result); \/\/ \u8f93\u51fa: ['main']<\/code><\/pre>
    \u516d\u3001\u6027\u80fd\u4f18\u5316<\/h3>