使用PHP DOM解析器高效提取HTML中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，使用选项避免对HTML片段自动添加缺失的标签
$dom->loadHTML($html, LIBXML_HTML_NOIMPLIED | LIBXML_HTML_NODEFDTD);

?>

<?php
// ... (接上文的HTML加载代码)

$xpath = new DOMXPath($dom);

// 使用XPath查询所有<h3>标签
// "//h3" 表示查找文档中所有h3元素，无论其在文档的哪个位置
$results = $xpath->query("//h3");

?>

<?php
// ... (接上文的HTML加载和XPath查询代码)

$extracted_data = [];

foreach ($results as $h3_element) {
    $h3_text = trim($h3_element->textContent); // 获取<h3>的文本内容
    $paragraph_text = '';

    // 获取下一个兄弟元素
    $next_element = $h3_element->nextElementSibling;

    // 检查下一个元素是否存在且是<p>标签
    if ($next_element && 'p' === $next_element->nodeName) {
        $paragraph_text = trim($next_element->textContent); // 获取<p>的文本内容
    }

    $extracted_data[] = [
        'heading' => $h3_text,
        'paragraph' => $paragraph_text
    ];
}

// 打印提取到的数据
foreach ($extracted_data as $item) {
    echo "<h3>" . htmlspecialchars($item['heading']) . "</h3>\n";
    echo "<p>" . htmlspecialchars($item['paragraph']) . "</p>\n";
}

?>

<?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;

// 1. 创建DOMDocument实例并加载HTML
$dom = new DomDocument();
// 使用LIBXML_HTML_NOIMPLIED | LIBXML_HTML_NODEFDTD选项处理HTML片段
$dom->loadHTML($html, LIBXML_HTML_NOIMPLIED | LIBXML_HTML_NODEFDTD);

// 2. 创建DOMXPath实例
$xpath = new DOMXPath($dom);

// 3. 查询所有<h3>标签
$h3_elements = $xpath->query("//h3");

$extracted_content = [];

// 4. 遍历所有<h3>标签，并提取其紧邻的第一个<p>标签
foreach ($h3_elements as $h3_node) {
    $heading_text = trim($h3_node->textContent);
    $paragraph_text = '';

    // 获取当前<h3>节点的下一个兄弟元素
    $next_sibling = $h3_node->nextElementSibling;

    // 检查下一个兄弟元素是否存在且其标签名为'p'
    if ($next_sibling instanceof DOMElement && $next_sibling->nodeName === 'p') {
        $paragraph_text = trim($next_sibling->textContent);
    }

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

// 5. 输出提取到的内容
echo "<h2>提取结果：</h2>\n";
foreach ($extracted_content as $item) {
    echo "<h3>" . htmlspecialchars($item['heading']) . "</h3>\n";
    echo "<p>" . htmlspecialchars($item['paragraph']) . "</p>\n";
}

?>

<h2>提取结果：</h2>
<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>