PHP通过DOMDocument对象来抓取网页中的指定class的内容

Posted 2020-12-21 bird-eat-vegetable

 

<?php

function getTagClassContent($url, $tagName, $className) //要抓取的网页, 要抓取的Tag名, 要抓取的Class名
{
    $doc = new DOMDocument();
    @$doc->loadhtml(file_get_contents($url)); 
    $nodes = $doc->getElementsByTagName($tagName); 
    
    $res = array();
    foreach($nodes as $n) {
        if($attrItemClass = $n->attributes->getNamedItem(‘class‘)) {
            if($classes = explode(‘ ‘, $attrItemClass->textContent)) {
                if(in_array($className, $classes)) {
                    
                    $res[] = $n->textContent;
                }
            }
        }
    }
    
    return $res;
}

$res = getTagClassContent(‘http://www.dyhjw.com/meiyuanzhishu‘, ‘span‘, ‘nom‘);

var_dump($res);

/*
输出：
array(1) {
  [0]=>
  string(7) "92.7375"
}
*/