Created
October 2, 2022 08:12
-
-
Save thistehneisen/dbc818e0a93e39a8624d70597aeeb993 to your computer and use it in GitHub Desktop.
Downloads everything from a host
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
<?php | |
$baseUrl = 'https://[domain.tld]/?item=[item]&id=[id]'; | |
$maxItems = 1000; | |
$maxId = 2000; | |
function getUrl($url, $headersOnly = TRUE) { | |
$userAgent = 'Mozilla/5.0 (Windows NT 6.1; rv:8.0) Gecko/20100101 Firefox/8.0'; | |
$options = [ | |
CURLOPT_CUSTOMREQUEST => 'GET', | |
CURLOPT_POST => FALSE, | |
CURLOPT_USERAGENT => $userAgent, | |
CURLOPT_RETURNTRANSFER => TRUE, | |
CURLOPT_HEADER => $headersOnly, | |
CURLOPT_NOBODY => $headersOnly, | |
CURLOPT_FOLLOWLOCATION => TRUE, | |
CURLOPT_ENCODING => '', | |
CURLOPT_AUTOREFERER => TRUE, | |
CURLOPT_CONNECTTIMEOUT => 3, | |
CURLOPT_TIMEOUT => 3, | |
CURLOPT_MAXREDIRS => 2, | |
]; | |
$ch = curl_init($url); | |
curl_setopt_array($ch, $options); | |
$response = curl_exec($ch); | |
curl_close($ch); | |
if ($headersOnly) { | |
$data = []; | |
$headers = explode(PHP_EOL, $response); | |
foreach ($headers as $row) { | |
$parts = explode(':', $row); | |
if (count($parts) === 2) { | |
$data[trim($parts[0])] = trim($parts[1]); | |
} | |
} | |
return $data; | |
} | |
return $response; | |
} | |
for ($currentId = 1; $currentId < $maxId; $currentId++) { | |
for ($currentItem = 1; $currentItem <= $maxItems; $currentItem++) { | |
$targetUrl = str_replace(['[item]', '[id]'], [$currentItem, $currentId], $baseUrl); | |
$response = getUrl($targetUrl); | |
if (isset($response['Content-Description']) && $response['Content-Description'] === 'File Transfer') { | |
$fileName = preg_match('/attachment; filename="(.*)"/', $response['Content-Disposition'], $matches); | |
$fileName = $matches[1]; | |
print('Downloading: ' . $fileName).PHP_EOL; | |
file_put_contents('data/' . $currentItem . '-' . $currentId . '-' . $fileName, getUrl($targetUrl, FALSE)); | |
break; | |
} else print('Processed: ' . $targetUrl).PHP_EOL; | |
} | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment