[PHP知识库]PHP 抓取静态页面，解决文件编码问题 UTF-8GBK

    public function test()
    {

//        $url = 'http://finance.people.com.cn/n1/2021/0824/c1004-32204729.html'; //gpk
//        $url = 'https://sz.oeeee.com/html/202109/07/1133661.html';
//        $url = 'http://opinion.people.com.cn/GB/8213/420650/index.html';
        $url = 'https://www.baidu.com/?tn=02003390_8_hao_pg'; //utf-8
        $lines_array = file($url);
        $lines_string = implode('', $lines_array);
        file_put_contents("uploads/curlHtml/test.txt", $lines_string);
        $encodings = $this->get_encoding($lines_string);
        if ($encodings == 'GBK') {
            $html = preg_replace('/charset=gb2312/', 'charset=UTF8', $lines_string);
            $html = iconv('gbk', 'utf-8', $html);
        } else {
            $html = $lines_string;
        }
        echo $html;
    }
        //获取文件编码
    function get_encoding($str = "")
    {
        $encodings = array(
            'ASCII',
            'UTF-8',
            'GBK'
        );
        foreach ($encodings as $encoding) {
            if ($str === mb_convert_encoding(mb_convert_encoding($str, "UTF-32", $encoding), $encoding, "UTF-32")) {
                return $encoding;
            }
        }
        return false;
    }