本文介绍了如何使用PHP的DOMDocument和DOMXPath类，结合XPath表达式，将包含状态信息的HTML无序列表转换为结构化的多维数组，并最终输出为JSON格式。重点在于使用XPath准确提取所需数据，并处理HTML中的空白字符，确保数据的准确性和可读性。
在Web开发中，经常需要从HTML文档中提取数据。当数据以特定结构（例如无序列表）呈现时，使用XPath可以方便地定位和提取所需的信息。本教程将演示如何使用PHP的DOMDocument和DOMXPath类，将HTML无序列表转换为多维数组，并最终输出为JSON格式。
1. 加载HTML并创建DOMXPath对象
首先，需要将HTML字符串加载到DOMDocument对象中，并创建一个DOMXPath对象，以便使用XPath表达式查询DOM树。为了去除HTML中可能存在的空白字符，提高数据提取的准确性，可以使用自定义的loadHTML_noemptywhitespace函数。
立即学习“前端免费学习笔记（深入）”；
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 ($node->hasChildNodes()) {
// 递归处理子节点
for ($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))) {
// 移除空白文本节点
$node->parentNode->removeChild($node);
}
};
$removeAnnoyingWhitespaceTextNodes($domd);
return $domd;
}
$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>';
$domd=loadHTML_noemptywhitespace($html);
$xp=new DOMXPath($domd);2. 使用XPath查询UL元素
使用XPath表达式//div[contains(@class,'singlepost')]/ul选择所有包含singlepost类的div元素下的ul元素。
$extracted=[];
foreach($xp->query("//div[contains(@class,'singlepost')]/ul") as $ul){
$ulData=[];
// ...
}3. 提取LI元素中的数据
在每个ul元素中，使用XPath表达式./li选择所有的li元素。然后，使用explode函数将每个li元素的文本内容按冒号分隔，提取键值对，并将其存储到$ulData数组中。
foreach($xp->query("./li", $ul) as $li){
$data = explode(":",$li->nodeValue, 2);
$uldata[trim($data[0])] = trim($data[1]);
}
$extracted[]=$uldata;4. 将结果转换为JSON格式
最后，使用json_encode_pretty函数将提取的数据转换为JSON格式，并输出。json_encode_pretty函数可以格式化JSON输出，使其更易于阅读。
function json_encode_pretty($data, int $extra_flags = 0, int $exclude_flags = 0): string
{
// prettiest flags for: 7.3.9
$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);完整代码示例
<?php
function json_encode_pretty($data, int $extra_flags = 0, int $exclude_flags = 0): string
{
// prettiest flags for: 7.3.9
$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 ($node->hasChildNodes()) {
// Warning: it's important to do it backwards; if you do it forwards, the index for DOMNodeList might become invalidated;
// that's why i don't use foreach() - don't change it (unless you know what you're doing, ofc)
for ($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($node->textContent))) {
//echo "Removing annoying POS";
// var_dump($node);
$node->parentNode->removeChild($node);
} //elseif ($node instanceof DOMText) { echo "not removed"; var_dump($node, $node->hasChildNodes(), $node->hasAttributes(), trim($node->textContent)); }
};
$removeAnnoyingWhitespaceTextNodes($domd);
return $domd;
}
$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>';
$domd=loadHTML_noemptywhitespace($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);
?>注意事项
总结
本教程演示了如何使用PHP的DOMDocument和DOMXPath类，结合XPath表达式，将HTML无序列表转换为结构化的多维数组，并最终输出为JSON格式。通过使用XPath准确提取所需数据，并处理HTML中的空白字符，可以有效地从HTML文档中提取数据，并将其转换为易于处理的格式。
以上就是使用XPath将无序列表HTML标记转换为多维数组的详细内容，更多请关注php中文网其它相关文章！
HTML怎么学习？HTML怎么入门？HTML在哪学？HTML怎么学才快？不用担心，这里为大家提供了HTML速学教程(入门课程)，有需要的小伙伴保存下载就能学习啦！
Copyright 2014-2025 https://www.php.cn/ All Rights Reserved | php.cn | 湘ICP备2023035733号
117
收藏
