在日常PHP开发中, 经常需要抓取远程数据, 常用的方式为: file_get_contents 和 curl, 本文结合实际经验进行分析比较, 希望对大家有所帮助

{基本用法}

> file_get_contents

$content = file_get_contents("http://yiilib.com"); //Html content

> curl

// 1. init
$ch = curl_init();

// 2. config
curl_setopt($ch, CURLOPT_URL, "http://yiilib.com");
curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);
curl_setopt($ch, CURLOPT_HEADER, 0);

// 3. load html
$output = curl_exec($ch);

// 4. close curl
curl_close($ch);

{对比/区别}

> 用时

20次抓取yiilib.com平均值 

> 稳定性

curl的稳定性明显优于file_get_contents

{建议}

建议在项目中优先使用curl作为抓取工具

{Demo Code}

public static function load($url, $header=null, $https = false){
    if (empty($url)) {
    	return '';
    }//do nothing for empty
    
    //init
    $ch = curl_init();
    
    //set options
    curl_setopt($ch, CURLOPT_URL, $url);
    curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1); //return result
    curl_setopt($ch, CURLOPT_FOLLOWLOCATION,1); //follow 301

    //user agent
    $userAgent = 'Mozilla/5.0 (compatible; MSIE 5.01; Windows NT 5.0)';
    curl_setopt($ch, CURLOPT_USERAGENT, $userAgent);   //set User-Agent
    
    
    //outtime
    curl_setopt ($ch, CURLOPT_CONNECTTIMEOUT, 6); //connection timeout
    curl_setopt ($ch, CURLOPT_TIMEOUT, 20); //timeout
    
    //set more header
    if (!empty($header)) {
        curl_setopt($ch, CURLOPT_HTTPHEADER , $header );
    }
    
    curl_setopt($ch, CURLOPT_HEADER, 0); //no need response header, faster
    
    
    //for https, skip verify paper and host
    if ($https) {
        curl_setopt($ch, CURLOPT_SSL_VERIFYPEER, FALSE);
        curl_setopt($ch, CURLOPT_SSL_VERIFYHOST, FALSE);
    }
    
    //get result
    $output = curl_exec($ch);
    
    //close
    curl_close($ch);
    
    //return 
    return $output;
}