邻居,我刚刚在下面制作了这个片段,它使用了您的逻辑,并进行了一些调整以在 get_contents 函数中显示网页中的指定类。也许您可以插入您的价值观并尝试一下?
(注意:我将错误检查放在那里以查看一些错误。在您调整时使用它会有所帮助。)
<?php
error_reporting(E_ALL);
ini_set('display_errors', '1');
$url = "http://www.tizag.com/cssT/cssid.php";
$class_to_scrape="display";
$html = file_get_contents($url);
$document = new DOMDocument();
$document->loadHTML($html);
$selector = new DOMXPath($document);
$anchors = $selector->query("/html/body//div[@class='". $class_to_scrape ."']");
echo "ok, no php syntax errors. <br>Lets see what we scraped.<br>";
foreach ($anchors as $node) {
$full_content = innerHTML($node);
echo "<br>".$full_content."<br>" ;
}
/* this function preserves the inner content of the scraped element.
** http://stackoverflow.com/questions/5349310/how-to-scrape-web-page-data-without-losing-tags
** So be sure to go and give that post an uptick too:)
**/
function innerHTML(DOMNode $node)
{
$doc = new DOMDocument();
foreach ($node->childNodes as $child) {
$doc->appendChild($doc->importNode($child, true));
}
return $doc->saveHTML();
}
?>