PHP DOM解析：高效获取HTML中的特定标题及其紧邻段落

<?php

$html = <<<TAG
<h1>This is my title</h1>

<p>This is a text right under my h1 title.</p>
<p>This is some more text under my h1 title</p>

<h2>This is my level 2 heading</h2>
<p>This is text right under my level 2 heading</p>

<h3>First h3</h3>
<p>First paragraph for the first h3</p>

<h3>Second h3</h3>
<p>First paragraph for the second h3</p>

<h3>Third h3</h3>
<p>First paragraph for the third h3</p>
<p>Second paragraph for the third h3</p>

<h2>This is my level 2 heading</h2>
<p>This is text right under my level 2 heading</p>
TAG;

$dom = new DOMDocument();
// 加载HTML，避免自动添加不必要的HTML/DOCTYPE声明，以便更精确地处理片段
$dom->loadHTML($html, LIBXML_HTML_NOIMPLIED | LIBXML_HTML_NODEFDTD);

$xpath = new DOMXPath($dom);

// 查询文档中所有的h3标签
$results = $xpath->query("//h3");

$extracted_data = []; // 用于存储提取到的数据

foreach ($results as $result) {
    $heading_text = $result->textContent;
    $paragraph_text = '';

    // 获取当前h3元素的下一个同级元素
    $next_element = $result->nextElementSibling;

    // 检查下一个元素是否存在，并且其标签名是否为'p'
    if ($next_element && 'p' === $next_element->nodeName) {
        $paragraph_text = $next_element->textContent;
    }

    $extracted_data[] = [
        'heading' => $heading_text,
        'paragraph' => $paragraph_text
    ];
}

<?php

$html = <<<TAG
<h1>This is my title</h1>

<p>This is a text right under my h1 title.</p>
<p>This is some more text under my h1 title</p>

<h2>This is my level 2 heading</h2>
<p>This is text right under my level 2 heading</p>

<h3>First h3</h3>
<p>First paragraph for the first h3</p>

<h3>Second h3</h3>
<p>First paragraph for the second h3</p>

<h3>Third h3</h3>
<p>First paragraph for the third h3</p>
<p>Second paragraph for the third h3</p>

<h2>This is my level 2 heading</h2>
<p>This is text right under my level 2 heading</p>
TAG;

$dom = new DOMDocument();
// 加载HTML，避免自动添加不必要的HTML/DOCTYPE声明
// LIBXML_HTML_NOIMPLIED: 防止libxml自动添加html/body标签
// LIBXML_HTML_NODEFDTD: 防止libxml自动添加默认的DOCTYPE
@$dom->loadHTML($html, LIBXML_HTML_NOIMPLIED | LIBXML_HTML_NODEFDTD); // 使用@抑制可能出现的警告

$xpath = new DOMXPath($dom);

// 查询文档中所有的h3标签
$h3_elements = $xpath->query("//h3");

$extracted_content = [];

foreach ($h3_elements as $h3_node) {
    $heading_text = $h3_node->textContent;
    $paragraph_text = '';

    // 获取当前h3元素的下一个同级元素
    $next_sibling = $h3_node->nextElementSibling;

    // 检查下一个同级元素是否存在且是<p>标签
    if ($next_sibling && 'p' === $next_sibling->nodeName) {
        $paragraph_text = $next_sibling->textContent;
    }

    $extracted_content[] = [
        'heading' => $heading_text,
        'paragraph' => $paragraph_text
    ];
}

// 打印结果
foreach ($extracted_content as $item) {
    echo "<h3>" . htmlspecialchars($item['heading']) . "</h3>";
    echo "<p>" . htmlspecialchars($item['paragraph']) . "</p>";
}

?>

<h3>First h3</h3><p>First paragraph for the first h3</p>
<h3>Second h3</h3><p>First paragraph for the second h3</p>
<h3>Third h3</h3><p>First paragraph for the third h3</p>