1
我们有一个任务来过滤来自机器人的真实卷曲请求。我向该网站发送了一个curl请求,但是它向我返回了一个无效的图像文件(我知道,因为当我用我的浏览器查看它时,它工作)。它以某种方式知道我的请求不是真实的。我在这里忽略了一个字段,我试图完全模仿浏览器请求。用于卷曲请求的浏览器标头
$header_arr = array(
'0' =>'Host: www.myittest.com',
'1' =>'User-Agent: Mozilla/5.0 (Windows NT 6.1; WOW64; rv:33.0) Gecko/20100101 Firefox/33.0',
'2' =>'Accept: text/html,application/xhtml+xml,application/xml;q=0.9,*\/*;q=0.8',
'3' =>'Accept-Language: en-US,en;q=0.5',
'4' =>'Accept-Encoding: gzip, deflate',
'5' =>'Connection: keep-alive',
);
$ch = curl_init($url);
curl_setopt($ch, CURLOPT_HTTPHEADER, $header_arr);
curl_setopt($ch, CURLOPT_TIMEOUT, 30);
curl_setopt($ch, CURLOPT_BINARYTRANSFER, TRUE);
curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);
curl_setopt($ch, CURLOPT_FOLLOWLOCATION, 1);
curl_setopt($ch, CURLOPT_MAXREDIRS, 6);
$raw=curl_exec($ch);
尝试'$ ch = curl_init(); curl_setopt($ ch,CURLOPT_URL,$ url);'而不是'$ ch = curl_init($ url);' – 2014-11-04 05:43:47