Php DomDocument parse新行适用于span，但不适用于img

请看这里：

为什么换行符正确显示为

span

s，而不是

img

s

<?php
    outputImages();
    outputSpans();




    function outputImages(){
        $html = "<div class='test'>
                    <pre>
                    <img src='http://d...content-available-to-author-only...e.com/5x5/000/fff'>
                    <img src='http://d...content-available-to-author-only...e.com/5x5/000/fff'>
                    <img src='http://d...content-available-to-author-only...e.com/5x5/000/fff'>
                    </pre>
                </div>";
        getHtml($html);
    }


    function outputSpans(){
        $html = "<div class='test'>
                    <pre>
                    <span>a</span>
                    <span>b</span>
                    <span>c</span>
                    </pre>
                </div>";
        getHtml($html);
    }


    function getHtml($html){
        $doc = new DOMDocument;
        $doc->loadhtml($html);
        $xpath = new DOMXPath($doc);
        $tags = $xpath->query('//div[@class="test"]');
        print(get_inner_html($tags[0]));
    }


    function get_inner_html( $node ) {
        $innerHTML= '';
        $children = $node->childNodes;
        foreach ($children as $child) {
            $innerHTML .= $child->ownerDocument->saveXML( $child );
        }

        return $innerHTML;
    }

---

DOMDocument:：loadHTML

函数还有第二个

选项

参数。看起来，

LIBXML_NOBLANKS

是（至少一个）默认值

你可以用

outputImages();
outputSpans();

function outputImages() {
    $html = "<div class='test'>
                <pre>
                <img src='http://d...content-available-to-author-only...e.com/5x5/000/fff'>
                <img src='http://d...content-available-to-author-only...e.com/5x5/000/fff'>
                <img src='http://d...content-available-to-author-only...e.com/5x5/000/fff'>
                </pre>
            </div>";
    getHtml($html);
}

function outputSpans() {
    $html = "<div class='test'>
                <pre>
                <span>a</span>
                <span>b</span>
                <span>c</span>
                </pre>
            </div>";
    getHtml($html);
}

function getHtml($html) {
    $doc = new DOMDocument;
    $doc->loadHTML($html, LIBXML_NOEMPTYTAG);
    $xpath = new DOMXPath($doc);
    $tags = $xpath->query('//div[@class="test"]');
    print(get_inner_html($tags->item(0)));
}

function get_inner_html( $node ) {
    $innerHTML= '';
    $children = $node->childNodes;
    foreach ($children as $child) {
        $innerHTML .= $child->ownerDocument->saveXML( $child );
    }
    return $innerHTML;
}

若要覆盖该默认值，您的代码将对这两个示例起相同的作用

p、 s.
不知道你为什么用

$tags

变量是一个

DOMNodeList

，因此您应该使用

$tags->item（0）

来获取第一个标记

您的完整代码应如下所示：

outputImages（）；
outputSpans（）；
函数outputImages（）{
$html=”
";
getHtml（$html）；
}
函数outputSpans（）{
$html=”
A.
B
C
";
getHtml（$html）；
}
函数getHtml（$html）{
$doc=新文档；
$doc->loadHTML（$html，LIBXML\u NOEMPTYTAG）；
$xpath=新的DOMXPath（$doc）；
$tags=$xpath->query（'//div[@class=“test”]'）；
打印（获取内部html（$tags->item（0））；
}
函数get\u internal\u html（$node）{
$innerHTML=''；
$children=$node->childNodes；
foreach（$childrenas$child）{
$innerHTML.=$child->ownerDocument->saveXML（$child）；
}
返回$innerHTML；
}

print(get_inner_html($tags[0]));

outputImages();
outputSpans();

function outputImages() {
    $html = "<div class='test'>
                <pre>
                <img src='http://d...content-available-to-author-only...e.com/5x5/000/fff'>
                <img src='http://d...content-available-to-author-only...e.com/5x5/000/fff'>
                <img src='http://d...content-available-to-author-only...e.com/5x5/000/fff'>
                </pre>
            </div>";
    getHtml($html);
}

function outputSpans() {
    $html = "<div class='test'>
                <pre>
                <span>a</span>
                <span>b</span>
                <span>c</span>
                </pre>
            </div>";
    getHtml($html);
}

function getHtml($html) {
    $doc = new DOMDocument;
    $doc->loadHTML($html, LIBXML_NOEMPTYTAG);
    $xpath = new DOMXPath($doc);
    $tags = $xpath->query('//div[@class="test"]');
    print(get_inner_html($tags->item(0)));
}

function get_inner_html( $node ) {
    $innerHTML= '';
    $children = $node->childNodes;
    foreach ($children as $child) {
        $innerHTML .= $child->ownerDocument->saveXML( $child );
    }
    return $innerHTML;
}