使用XPath将HTML无序列表转换为多维数组-php教程-PHP中文网

使用XPath将HTML无序列表转换为多维数组

花韻仙語

发布： 2025-08-12 17:50:14

原创

356人浏览过

使用xpath将html无序列表转换为多维数组

本文档详细介绍了如何使用PHP的DOMXPath解析HTML文档，并将特定的无序列表（<ul>）结构转换为多维数组。我们将通过示例代码，逐步讲解如何使用XPath查询和提取数据，并最终生成所需的JSON格式输出。该方法适用于从HTML中提取结构化数据，并进行进一步处理的场景。

解析HTML并使用XPath提取数据

首先，我们需要加载HTML字符串并创建一个DOMXPath对象。为了更有效地处理HTML，特别是包含大量空白的HTML，我们可以自定义一个函数 loadHTML_noemptywhitespace()，该函数会移除HTML中的多余空白节点，从而简化后续的XPath查询。

function loadHTML_noemptywhitespace(string $html, int $extra_flags = 0, int $exclude_flags = 0): \DOMDocument
{
    $flags = LIBXML_HTML_NODEFDTD | LIBXML_NOBLANKS | LIBXML_NONET;
    $flags = ($flags & ~ $exclude_flags) | $extra_flags;

    $domd = new \DOMDocument();
    $domd->preserveWhiteSpace = false;
    @$domd->loadHTML('<?xml encoding="UTF-8">' . $html, $flags);
    $removeAnnoyingWhitespaceTextNodes = function (\DOMNode $node) use (&$removeAnnoyingWhitespaceTextNodes): void {
        if ($node->hasChildNodes()) {
            for ($i = $node->childNodes->length - 1; $i >= 0; --$i) {
                $removeAnnoyingWhitespaceTextNodes($node->childNodes->item($i));
            }
        }
        if ($node->nodeType === XML_TEXT_NODE && !$node->hasChildNodes() && !$node->hasAttributes() && ! strlen(trim($node->textContent))) {
            $node->parentNode->removeChild($node);
        }
    };
    $removeAnnoyingWhitespaceTextNodes($domd);
    return $domd;
}

$html = <<<HTML
<div class="singlepost">

<ul class="linha_status" >
<li>Status: <b>Objeto em trânsito - por favor aguarde</b></li>
<li>Data  : 24/10/2021 | Hora: 12:04</li>           
<li>Origem: Unidade de Tratamento - Jaboatao Dos Guararapes / PE</li>
<li>Destino: Agência dos Correios - Cuitegi / PB</li>
</ul>

<ul class="linha_status" >
<li>Status: <b>Objeto em trânsito - por favor aguarde</b></li>
<li>Data  : 19/10/2021 | Hora: 00:03</li>           
<li>Origem: Unidade de Logística Integrada - Curitiba / PR</li>
<li>Destino: Unidade de Tratamento - Recife / PE</li>
</ul>

<ul class="linha_status" >
<li>Status: <b>Fiscalização aduaneira finalizada</b></li>
<li>Data  : 18/10/2021 | Hora: 23:35</li>
<li>Local: Unidade Operacional - Curitiba / PR</li>
</ul>

<ul class="linha_status" >
<li>Status: <b>Objeto recebido pelos Correios do Brasil</b></li>
<li>Data  : 16/10/2021 | Hora: 11:45</li>
<li>Local: Unidade de Logística Integrada - Curitiba / PR</li>
</ul>

<ul class="linha_status" >
<li>Status: <b>Objeto postado</b></li>
<li>Data  : 14/10/2021 | Hora: 20:30</li>
<li>Local: País -  / </li>
</ul>

</div>
HTML;

$domd = loadHTML_noemptywhitespace($html);
$xp = new DOMXPath($domd);

登录后复制

使用XPath查询并提取数据

接下来，我们使用XPath查询选择所有具有linha_status类的<ul>元素，并遍历每个<ul>元素中的<li>元素。对于每个<li>元素，我们使用explode()函数将其文本内容按冒号分隔，并将结果存储到一个关联数组中。

$extracted = [];
foreach($xp->query("//div[contains(@class,'singlepost')]/ul") as $ul){
    $ulData = [];
    foreach($xp->query("./li", $ul) as $li){
        $data = explode(":",$li->nodeValue, 2);
        $ulData[trim($data[0])] = trim($data[1]);
    }
    $extracted[] = $ulData;
}

登录后复制

生成JSON格式输出

最后，我们使用json_encode()函数将提取的数据转换为JSON格式。为了生成更易读的JSON，我们可以自定义一个 json_encode_pretty() 函数，该函数使用 JSON_PRETTY_PRINT 选项来格式化JSON输出。

序列猴子开放平台

具有长序列、多模态、单模型、大数据等特点的超大规模语言模型

查看详情

立即学习“前端免费学习笔记（深入）”；

function json_encode_pretty($data, int $extra_flags = 0, int $exclude_flags = 0): string
{
    $flags = JSON_PRETTY_PRINT | JSON_UNESCAPED_SLASHES | JSON_UNESCAPED_UNICODE | (defined("JSON_UNESCAPED_LINE_TERMINATORS") ? JSON_UNESCAPED_LINE_TERMINATORS : 0) | JSON_PRESERVE_ZERO_FRACTION | (defined("JSON_THROW_ON_ERROR") ? JSON_THROW_ON_ERROR : 0);
    $flags = ($flags | $extra_flags) & ~ $exclude_flags;
    return (json_encode($data, $flags));
}

echo json_encode_pretty($extracted);

登录后复制

完整代码示例

<?php

function json_encode_pretty($data, int $extra_flags = 0, int $exclude_flags = 0): string
{
    $flags = JSON_PRETTY_PRINT | JSON_UNESCAPED_SLASHES | JSON_UNESCAPED_UNICODE | (defined("JSON_UNESCAPED_LINE_TERMINATORS") ? JSON_UNESCAPED_LINE_TERMINATORS : 0) | JSON_PRESERVE_ZERO_FRACTION | (defined("JSON_THROW_ON_ERROR") ? JSON_THROW_ON_ERROR : 0);
    $flags = ($flags | $extra_flags) & ~ $exclude_flags;
    return (json_encode($data, $flags));
}


function loadHTML_noemptywhitespace(string $html, int $extra_flags = 0, int $exclude_flags = 0): \DOMDocument
{
    $flags = LIBXML_HTML_NODEFDTD | LIBXML_NOBLANKS | LIBXML_NONET;
    $flags = ($flags & ~ $exclude_flags) | $extra_flags;

    $domd = new \DOMDocument();
    $domd->preserveWhiteSpace = false;
    @$domd->loadHTML('<?xml encoding="UTF-8">' . $html, $flags);
    $removeAnnoyingWhitespaceTextNodes = function (\DOMNode $node) use (&$removeAnnoyingWhitespaceTextNodes): void {
        if ($node->hasChildNodes()) {
            for ($i = $node->childNodes->length - 1; $i >= 0; --$i) {
                $removeAnnoyingWhitespaceTextNodes($node->childNodes->item($i));
            }
        }
        if ($node->nodeType === XML_TEXT_NODE && !$node->hasChildNodes() && !$node->hasAttributes() && ! strlen(trim($node->textContent))) {
            $node->parentNode->removeChild($node);
        }
    };
    $removeAnnoyingWhitespaceTextNodes($domd);
    return $domd;
}

$html = <<<HTML
<div class="singlepost">

<ul class="linha_status" >
<li>Status: <b>Objeto em trânsito - por favor aguarde</b></li>
<li>Data  : 24/10/2021 | Hora: 12:04</li>           
<li>Origem: Unidade de Tratamento - Jaboatao Dos Guararapes / PE</li>
<li>Destino: Agência dos Correios - Cuitegi / PB</li>
</ul>

<ul class="linha_status" >
<li>Status: <b>Objeto em trânsito - por favor aguarde</b></li>
<li>Data  : 19/10/2021 | Hora: 00:03</li>           
<li>Origem: Unidade de Logística Integrada - Curitiba / PR</li>
<li>Destino: Unidade de Tratamento - Recife / PE</li>
</ul>

<ul class="linha_status" >
<li>Status: <b>Fiscalização aduaneira finalizada</b></li>
<li>Data  : 18/10/2021 | Hora: 23:35</li>
<li>Local: Unidade Operacional - Curitiba / PR</li>
</ul>

<ul class="linha_status" >
<li>Status: <b>Objeto recebido pelos Correios do Brasil</b></li>
<li>Data  : 16/10/2021 | Hora: 11:45</li>
<li>Local: Unidade de Logística Integrada - Curitiba / PR</li>
</ul>

<ul class="linha_status" >
<li>Status: <b>Objeto postado</b></li>
<li>Data  : 14/10/2021 | Hora: 20:30</li>
<li>Local: País -  / </li>
</ul>

</div>
HTML;

$domd = loadHTML_noemptywhitespace($html);
$xp = new DOMXPath($domd);
$extracted = [];
foreach($xp->query("//div[contains(@class,'singlepost')]/ul") as $ul){
    $ulData = [];
    foreach($xp->query("./li", $ul) as $li){
        $data = explode(":",$li->nodeValue, 2);
        $ulData[trim($data[0])] = trim($data[1]);
    }
    $extracted[] = $ulData;
}
echo json_encode_pretty($extracted);

?>

登录后复制