php采集curl与XPath

curl与XPath

curl的function函数代码在:https://www.cnblogs.com/zqblog1314/p/13322999.html

<?php
//推荐使用curl
//引入curl的自定义函数
include __DIR__.'/function.php';

$url = '********************';

$html = http_request($url);


// 申明一个dom对象
$dom = new DOMDocument();
// 忽略html不严格的格式
libxml_use_internal_errors(1);
$dom->loadHTML($html);
// 转为xpath对象
$xpath = new DOMXPath($dom);

// 查询路径
/*$query = '/html/head/title';

$nodeList = $xpath->query($query);

foreach ($nodeList as $item){
    echo $item->nodeValue;
}*/

//查询所有的图片
//$query = '//img/@data-original';
$query = '/html/body/div[3]/div[2]/div/div[2]/div[2]//img/@data-original';
$nodeList = $xpath->query($query);

foreach ($nodeList as $item){
    echo $item->nodeValue."\n";
}

 

posted @ 2020-07-16 15:47  养猪至富  阅读(259)  评论(0)    收藏  举报