Last active
August 12, 2023 00:44
-
-
Save ipkpjersi/3ce754391ab8390f23d9b9f80fca3994 to your computer and use it in GitHub Desktop.
Lemmy User Comment Scraper
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 | |
function fetchContent($url) { | |
$production = false; //Change as needed | |
$ch = curl_init($url); | |
curl_setopt($ch, CURLOPT_RETURNTRANSFER, true); | |
if (empty($production)) { | |
curl_setopt($ch, CURLOPT_SSL_VERIFYHOST, 0); | |
curl_setopt($ch, CURLOPT_SSL_VERIFYPEER, 0); | |
} | |
curl_setopt($ch, CURLOPT_FOLLOWLOCATION, true); | |
curl_setopt($ch, CURLOPT_MAXREDIRS, 10); | |
curl_setopt($ch, CURLOPT_USERAGENT, 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36'); | |
$content = curl_exec($ch); | |
if (curl_errno($ch)) { | |
die('Curl error: ' . curl_error($ch)); | |
} | |
curl_close($ch); | |
return $content; | |
} | |
$instance = isset($_POST['instance']) ? $_POST['instance'] : (isset($_GET['instance']) ? $_GET['instance'] : null); | |
$username = isset($_POST['username']) ? $_POST['username'] : (isset($_GET['username']) ? $_GET['username'] : null); | |
if (!$instance || !$username) { | |
die(json_encode(['error' => 'Both "instance" and "username" parameters are required.'])); | |
} | |
//Sanitize the user input | |
$instance = filter_var($instance, FILTER_SANITIZE_URL); | |
$username = preg_replace("/[^a-zA-Z0-9_\-]/", '', $username); | |
if (!$instance || !$username) { | |
die(json_encode(['error' => 'Invalid "instance" or "username" provided.'])); | |
} | |
$url = "$instance/api/v3/user/?username=$username&limit=50"; | |
//Initial fetch to get the comment_count | |
$content = fetchContent($url); | |
$data = json_decode($content, true); | |
$all_comments = []; | |
$total_pages = ceil($data['person_view']['counts']['comment_count'] / 50); | |
$date = date("m-d-Y_H-i-s"); | |
//Fetch all comments | |
for ($i = 1; $i <= $total_pages; $i++) { | |
$page_url = "$url&page=$i"; | |
$page_content = fetchContent($page_url); | |
$page_data = json_decode($page_content, true); | |
$all_comments = array_merge($all_comments, $page_data['comments']); | |
} | |
//Replace the 'comments' section in the last page_data with our merged comments | |
$page_data['comments'] = $all_comments; | |
//Append additional data | |
$page_data['website'] = $instance; | |
$page_data['username'] = $username; | |
$page_data['date'] = $date; | |
$filename = str_replace(["https://", "https://www."], "", $instance) . "-$username-" . $date . ".json"; | |
header('Content-Disposition: attachment; filename=' . $filename); | |
header('Content-Type: application/json'); | |
echo json_encode($page_data); |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment