- mb_convert_encoding: documentation ( source)
<?php
$html = <<< HTML
<article id="p73" class="p-quote">
Albert Einstein’s Quotes Collection
<blockquote><p>Life is like riding a bicycle. To keep your balance, you must keep moving.</p></blockquote>
<blockquote><p>Pure mathematics is, in its way, the poetry of logical ideas.</p></blockquote>
<blockquote><p>Education is what remains after one has forgotten what one has learned in school.</p></blockquote>
<blockquote><p>Learn from yesterday, live for today, hope for tomorrow. The important thing is not to stop questioning.</p></blockquote>
<blockquote><p>Logic will get you from A to B. Imagination will take you everywhere.</p></blockquote>
<blockquote><p>If you can’t explain it simply, you don’t understand it well enough.</p></blockquote>
<blockquote><p>The difference between stupidity and genius is that genius has its limits.</p></blockquote>
</article>
HTML;
class ExtractTag {
private $doc = null;
public function __construct($html) {
$this->doc = new DomDocument();
$content = mb_convert_encoding(
$html,
'HTML-ENTITIES',
'UTF-8'
);
@$this->doc->loadHTML($content);
}
private function getFirstTag($tag) {
$elements = $this->doc->getElementsByTagName($tag);
if (!$elements->count()) {
throw new Exception('no elements found');
}
return $elements->item(0);
}
private function printFirstTag($tag) {
$firstTag = $this->getFirstTag($tag);
echo $this->doc->saveHTML($firstTag);
}
public function print_image() {
$this->printFirstTag('img');
}
public function print_quote() {
$this->printFirstTag('blockquote');
}
}
$dom = new ExtractTag($html);
echo $dom->print_quote(); #Expect to see a <blockquote>
echo $dom->print_image(); #Expect to see nothing since there is no <img> tag in the html!