Last active
January 2, 2024 23:24
-
-
Save adactio/3d6983bea9b30c993a65b12537ce930c to your computer and use it in GitHub Desktop.
A proxy that tries to redirect bad links to the internet archive.
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 | |
| // Check that the request is coming from my site. | |
| if (!isset($_SERVER['HTTP_REFERER']) || !stristr(strtolower($_SERVER['HTTP_REFERER']), strtolower($_SERVER['SERVER_NAME']))) { | |
| http_response_code(403); | |
| exit; | |
| } | |
| // There has to be a URL provided in the query string. | |
| if (!isset($_GET['url'])) { | |
| http_response_code(400); | |
| exit; | |
| } | |
| // Make a very quick curl request to get the response headers from the URL. | |
| // The time limit is set to 1 second. | |
| $options = array( | |
| CURLOPT_URL => $_GET['url'], | |
| CURLOPT_USERAGENT => $_SERVER['SERVER_NAME'], | |
| CURLOPT_RETURNTRANSFER => TRUE, | |
| CURLOPT_HEADER => TRUE, | |
| CURLOPT_NOBODY => TRUE, | |
| CURLOPT_TIMEOUT_MS => 1000 | |
| ); | |
| $curl = curl_init(); | |
| curl_setopt_array($curl, $options); | |
| $curl_errno = curl_errno($curl); | |
| $response = curl_exec($curl); | |
| curl_close($curl); | |
| // If there was any error (like a time out), give up and go to the URL. | |
| if ($curl_errno > 0 || empty($response)) { | |
| header('Location: '.$_GET['url']); | |
| exit; | |
| } | |
| // Pick the response headers apart to get the HTTP status code. | |
| $data = preg_split("/[\r\n]+/", $response); | |
| $status = $data[0]; | |
| // If the response is OK, go to the URL. | |
| if (stristr($status, '200') || stristr($status, '304')) { | |
| header('Location: '.$_GET['url']); | |
| exit; | |
| } | |
| // If the response is a redirect, go around again but this time use the redirect URL. | |
| if (stristr($status, '30')) { | |
| $headers = array(); | |
| foreach($data as $line) { | |
| if (stristr($line, ': ')) { | |
| $pieces = explode(': ', $line); | |
| $name = trim($pieces[0]); | |
| $value = trim($pieces[1]); | |
| $headers[$name] = $value; | |
| } | |
| } | |
| if (isset($headers['Location'])) { | |
| $redirect = '/redirect?url='.urlencode($headers['Location']); | |
| if (isset($_GET['date'])) { | |
| $redirect.= '&date='.urlencode($_GET['date']); | |
| } | |
| header('Location: '.$redirect); | |
| exit; | |
| } | |
| } | |
| // Construct the archive.org search endpoint. | |
| $wayback = 'https://web.archive.org/cdx/search/cdx?output=json&filter=statuscode:200&url='.urlencode($_GET['url']); | |
| // If we have a date, provide it. Otherwise ask for the latest snapshot. | |
| if (isset($_GET['date'])) { | |
| $wayback.= '&from='.urlencode($_GET['date']).'&limit=1'; | |
| } else { | |
| $wayback.= '&limit=-1'; | |
| } | |
| // Ping that archive.org URL. | |
| // This time there's no time limit; this might take a while. | |
| $options = array( | |
| CURLOPT_URL => $wayback, | |
| CURLOPT_USERAGENT => $_SERVER['SERVER_NAME'], | |
| CURLOPT_RETURNTRANSFER => TRUE, | |
| CURLOPT_HEADER => FALSE | |
| ); | |
| $curl = curl_init(); | |
| curl_setopt_array($curl, $options); | |
| $result = curl_exec($curl); | |
| curl_close($curl); | |
| $response = json_decode($result,true); | |
| // If there's an archived copy, redirect to that. | |
| if (isset($response[1]) && $response[1][4] == '200') { | |
| header('Location: https://web.archive.org/web/'.$response[1][1].'/'.$response[1][2]); | |
| exit; | |
| } | |
| // There's no archived copy. Give up and go the URL anyway. | |
| header('Location: '.$_GET['url']); | |
| ?> |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Here's the corresponding client-side JavaScript code that passes links to this script:
https://gist.github.com/adactio/8be51468ff8c9591f9c98e0612bfae16