, я делаю простое приложение, которое считывает данные json с 15 разных URL-адресов. У меня есть особая потребность делать это на сервере. Я использую file_get_contents ($ url)
.
Поскольку я использую file_get_contents ($ url). Я написал простой сценарий, он:
$websites = array(
$url1,
$url2,
$url3,
...
$url15
);
foreach ($websites as $website) {
$data[] = file_get_contents($website);
}
, и оказалось, что он очень медленный, потому что он ждет первого запроса, а затем выполняет следующий.
Я хотел бы обеспечить более полный пример, не поражая ЦП в 100% и отказывая, когда существует небольшая ошибка или что-то неожиданное.
Это также показывает Вам, как выбрать заголовки, тело, информацию о запросе и ручное перенаправление после.
Правовая оговорка, этот код предназначается, чтобы быть расширенным и реализованным в библиотеку или как точка быстрого запуска, и как таковой, функции в нем сведены к минимуму.
function mtime(){
return microtime(true);
}
function ptime($prev){
$t = microtime(true) - $prev;
$t = $t * 1000;
return str_pad($t, 20, 0, STR_PAD_RIGHT);
}
function curl_multi_exec_full($mh, &$still_running) {
// In theory curl_multi_exec should never return CURLM_CALL_MULTI_PERFORM (-1) because it has been deprecated
// In practice it sometimes does
// So imagine that this just runs curl_multi_exec once and returns it's value
do {
$state = curl_multi_exec($mh, $still_running);
// curl_multi_select($mh, $timeout) simply blocks for $timeout seconds while curl_multi_exec() returns CURLM_CALL_MULTI_PERFORM
// We add it to prevent CPU 100% usage in case this thing misbehaves
} while ($still_running > 0 && $state === CURLM_CALL_MULTI_PERFORM && curl_multi_select($mh, 0.1));
return $state;
}
function curl_multi_wait($mh, $minTime = 0.001, $maxTime = 1){
$umin = $minTime*1000000;
$start_time = microtime(true);
// it sleeps until there is some activity on any of the descriptors (curl files)
// it returns the number of descriptors (curl files that can have activity)
$num_descriptors = curl_multi_select($mh, $maxTime);
// if the system returns -1, it means that the wait time is unknown, and we have to decide the minimum time to wait
// but our `$timespan` check below catches this edge case, so this `if` isn't really necessary
if($num_descriptors === -1){
usleep($umin);
}
$timespan = (microtime(true) - $start_time);
// This thing runs very fast, up to 1000 times for 2 urls, which wastes a lot of CPU
// This will reduce the runs so that each interval is separated by at least minTime
if($timespan < $umin){
usleep($umin - $timespan);
//print "sleep for ".($umin - $timeDiff).PHP_EOL;
}
}
$handles = [
[
CURLOPT_URL=>"http://example.com/",
CURLOPT_HEADER=>false,
CURLOPT_RETURNTRANSFER=>true,
CURLOPT_FOLLOWLOCATION=>false,
],
[
CURLOPT_URL=>"http://www.php.net",
CURLOPT_HEADER=>false,
CURLOPT_RETURNTRANSFER=>true,
CURLOPT_FOLLOWLOCATION=>false,
// this function is called by curl for each header received
// This complies with RFC822 and RFC2616, please do not suggest edits to make use of the mb_ string functions, it is incorrect!
// https://stackoverflow.com/a/41135574
CURLOPT_HEADERFUNCTION=>function($ch, $header)
{
print "header from http://www.php.net: ".$header;
//$header = explode(':', $header, 2);
//if (count($header) < 2){ // ignore invalid headers
// return $len;
//}
//$headers[strtolower(trim($header[0]))][] = trim($header[1]);
return strlen($header);
}
]
];
//create the multiple cURL handle
$mh = curl_multi_init();
$chandles = [];
foreach($handles as $opts) {
// create cURL resources
$ch = curl_init();
// set URL and other appropriate options
curl_setopt_array($ch, $opts);
// add the handle
curl_multi_add_handle($mh, $ch);
$chandles[] = $ch;
}
//execute the multi handle
$prevRunning = null;
$count = 0;
do {
$time = mtime();
// $running contains the number of currently running requests
$status = curl_multi_exec_full($mh, $running);
$count++;
print ptime($time).": curl_multi_exec status=$status running $running".PHP_EOL;
// One less is running, meaning one has finished
if($running < $prevRunning){
print ptime($time).": curl_multi_info_read".PHP_EOL;
// msg: The CURLMSG_DONE constant. Other return values are currently not available.
// result: One of the CURLE_* constants. If everything is OK, the CURLE_OK will be the result.
// handle: Resource of type curl indicates the handle which it concerns.
while ($read = curl_multi_info_read($mh, $msgs_in_queue)) {
$info = curl_getinfo($read['handle']);
if($read['result'] !== CURLE_OK){
// handle the error somehow
print "Error: ".$info['url'].PHP_EOL;
}
if($read['result'] === CURLE_OK){
/*
// This will automatically follow the redirect and still give you control over the previous page
// TODO: max redirect checks and redirect timeouts
if(isset($info['redirect_url']) && trim($info['redirect_url'])!==''){
print "running redirect: ".$info['redirect_url'].PHP_EOL;
$ch3 = curl_init();
curl_setopt($ch3, CURLOPT_URL, $info['redirect_url']);
curl_setopt($ch3, CURLOPT_HEADER, 0);
curl_setopt($ch3, CURLOPT_RETURNTRANSFER, 1);
curl_setopt($ch3, CURLOPT_FOLLOWLOCATION, 0);
curl_multi_add_handle($mh,$ch3);
}
*/
print_r($info);
$body = curl_multi_getcontent($read['handle']);
print $body;
}
}
}
// Still running? keep waiting...
if ($running > 0) {
curl_multi_wait($mh);
}
$prevRunning = $running;
} while ($running > 0 && $status == CURLM_OK);
//close the handles
foreach($chandles as $ch){
curl_multi_remove_handle($mh, $ch);
}
curl_multi_close($mh);
print $count.PHP_EOL;