PHP 之simple_html_dom实现网页数据采集

<?php
    set_time_limit(0);
    include './simple_html_dom.php';
    $url = 'https://price.pcauto.com.cn/price/rank/nb1-lb0-o1/';
    $html = file_get_html($url);
    $list = $html->find("#JlistTb .j-list");
    $id = array();
    $title = array();
    $price = array();
    $dealer_price = array();
    $pic = array();
    for ($i=0; $i < count($list); $i++) {
        $idText = $html->find("#JlistTb .j-list dd[name=dealer_price]", $i)->id;
        $id[] = explode("_", $idText)[2];
        $title[] = $html->find("#JlistTb .j-list .sname", $i)->innertext;
        $price[] = $html->find("#JlistTb .j-list .pri", $i)->innertext;
        $dealer_price[] = $html->find("#JlistTb .j-list .emphs", $i)->innertext;
        $pic[] = "https:".$html->find("#JlistTb .j-list .pic img", $i)->getAttribute("#src");
    }
    $list = array();
    for ($i=0; $i < count($title); $i++) {
        $list[$i] = array(
            'id' => $id[$i],
            'title' => $title[$i],
            'price' => $price[$i],
            'dealer_price' => $dealer_price[$i],
            'pic' => $pic[$i],
            'area_id' => 1
        );
    }
    var_dump($list);
?>

数组打印结果为

参考文档：https://github.com/yangsphp/simple_html_dom-master