PHP verwendet QueryList, um auf einfache Weise dynamisch gerenderte JavaScript-Seiten zu sammeln

composer require jaeger/querylist
GitHub: https://github.com/jae-jae/QueryList

composer require jaeger/querylist-phantomjs
GitHub: https://github.com/jae-jae/QueryList-PhantomJS

use QL\QueryList;
use QL\Ext\PhantomJs;
$ql = QueryList::getInstance();
// 安装时需要设置PhantomJS二进制文件路径
$ql->use(PhantomJs::class,'/usr/local/bin/phantomjs');
//or Custom function name
$ql->use(PhantomJs::class,'/usr/local/bin/phantomjs','browser');

$html = $ql->browser('https://m.toutiao.com')->getHtml();
print_r($html);

$data = $ql->browser('https://m.toutiao.com')->find('p')->texts();
print_r($data->all());

Array
(
    [0] => 自拍模式开启！国庆假期我和国旗合个影
    [1] => 你旅途已开始 他们仍在自己的岗位上为你的假期保驾护航
    [2] => 喜极而泣，都教授终于回到地球了！
    //....
)

// 更多选项可以查看文档: http://phantomjs.org/api/command-line.html
$ql->browser('https://m.toutiao.com',true,[
    // 使用http代理
    '--proxy' => '192.168.1.42:8080',
    '--proxy-type' => 'http'
])

$data = $ql->browser(function (\JonnyW\PhantomJs\Http\RequestInterface $r){
    $r->setMethod('GET');
    $r->setUrl('https://m.toutiao.com');
    $r->setTimeout(10000); // 10 seconds
    $r->setDelay(3); // 3 seconds
    return $r;
})->find('p')->texts();
print_r($data->all());

$data = $ql->browser(function (\JonnyW\PhantomJs\Http\RequestInterface $r){
    $r->setMethod('GET');
    $r->setUrl('https://m.toutiao.com');
    $r->setTimeout(10000); // 10 seconds
    $r->setDelay(3); // 3 seconds
    return $r;
},true,[
    '--cookies-file' => '/path/to/cookies.txt'
])->rules([
    'title' => ['p','text'],
    'link' => ['a','href']
])->query()->getData();
print_r($data->all());