Compare commits

...

3 commits

Author SHA1 Message Date
1b81034873 Stop tracking vendor folder 2025-05-21 00:45:45 +00:00
f2a56ee43c first 2025-05-21 00:45:13 +00:00
8581adf302 first 2025-05-21 00:44:19 +00:00
7 changed files with 1714 additions and 9 deletions

13
.gitignore vendored
View file

@ -1,9 +1,8 @@
# ---> ThinkPHP
# gitignore template for ThinkPHP v3.2.3
# website: http://www.thinkphp.cn/
/already_sent/*
!/already_sent/.gitkeep
/_credentials/*
!/_credentials/.gitkeep
/_vendor/*
/vendor/
# Logs and Cache files
/Application/Runtime/
# Common configure file
/Application/Common/Conf/config.php

View file

@ -1,3 +1,34 @@
# fedi_slurp
A bunch of scripts to fetch your Mastodon / snac bookmarks (using Mastodon API) and save them in your Readeck account for reading later or Youtube account for watching later.
# Fedi Link Fetcher
A pair of PHP scripts that extract links from your Mastodon / snac bookmarks and add them to:
- YouTube Playlist (Google oAUTH API)
- Readeck (simple API token)
## TODO instructions readeck API
how to get tokeb in web ui
## TODO isntructions Youtube PlayList
1. Go to the Google Cloud Console:
• Project > APIs & Services > Credentials
create oauth client ID
for TV and limited INPUT
• Download the OAuth 2.0 Client ID JSON file
save as /home/snac/youtube_list/client_secret.json
Option 1: Add your Google account as a test user
1. Go to Google Cloud Console > OAuth consent screen
~> Audience
2. Scroll to “Test users”
3. Add your Google email (e.g. jacques.lema@gmail.com)
composer require google/apiclient:^2.0

93
add_to_fedilist.php Normal file
View file

@ -0,0 +1,93 @@
<?php
// === Example use ===
#addVideoToFediList('https://www.youtube.com/watch?v=dQw4w9WgXcQ');
function isYouTubeLink($url) {
return preg_match('#^(https?://)?(www\.)?(youtube\.com/watch\?v=|youtu\.be/)[a-zA-Z0-9_-]{11}#', $url);
}
function addVideoToFediList($videoUrl) {
$playlistId = @file_get_contents(__DIR__ .'/_credentials/fedilist_id.txt');
if (!$playlistId) {
echo "‼️ Error: FediList ID not found. Make sure fedilist_id.txt exists.\n";
return false;
}
$token = @json_decode(file_get_contents(__DIR__ .'/_credentials/token.json'), true);
if (!$token || !isset($token['access_token'])) {
echo "‼️ Error: token.json missing or invalid. Authenticate first.\n";
return false;
}
// Extract video ID from URL
if (!preg_match('/(?:v=|\/)([a-zA-Z0-9_-]{11})/', $videoUrl, $matches)) {
echo "⁉️ Invalid YouTube URL: $videoUrl\n";
return false;
}
$videoId = $matches[1];
// === Step 1: Check if video is already in playlist ===
$checkUrl = "https://www.googleapis.com/youtube/v3/playlistItems?part=snippet&playlistId={$playlistId}&maxResults=50";
$found = false;
do {
$ch = curl_init($checkUrl);
curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);
curl_setopt($ch, CURLOPT_HTTPHEADER, [
'Authorization: Bearer ' . $token['access_token'],
'User-Agent: curl/7.64.1'
]);
$response = curl_exec($ch);
curl_close($ch);
$data = json_decode($response, true);
foreach ($data['items'] ?? [] as $item) {
if (($item['snippet']['resourceId']['videoId'] ?? '') === $videoId) {
echo " Video already in FediList: $videoId\n";
return false;
}
}
$checkUrl = $data['nextPageToken'] ?? false
? $checkUrl . '&pageToken=' . $data['nextPageToken']
: false;
} while ($checkUrl);
// === Step 2: Add the video ===
$postData = [
'snippet' => [
'playlistId' => $playlistId,
'resourceId' => [
'kind' => 'youtube#video',
'videoId' => $videoId
]
]
];
$ch = curl_init('https://www.googleapis.com/youtube/v3/playlistItems?part=snippet');
curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);
curl_setopt($ch, CURLOPT_HTTPHEADER, [
'Authorization: Bearer ' . $token['access_token'],
'Content-Type: application/json',
'User-Agent: curl/7.64.1'
]);
curl_setopt($ch, CURLOPT_POSTFIELDS, json_encode($postData));
$response = curl_exec($ch);
curl_close($ch);
$result = json_decode($response, true);
if (isset($result['id'])) {
echo "✅ Added video to FediList: $videoId\n";
return true;
} else {
echo "‼️ Failed to add video:\n$response\n";
return false;
}
}
?>

5
composer.json Normal file
View file

@ -0,0 +1,5 @@
{
"require": {
"google/apiclient": "^2.0"
}
}

1281
composer.lock generated Normal file

File diff suppressed because it is too large Load diff

118
create_fedilist.php Executable file
View file

@ -0,0 +1,118 @@
#!/usr/bin/php
<?php
// === Load client credentials ===
$secrets = json_decode(file_get_contents(__DIR__ . '/_credentials/client_secret.json'), true);
$client = $secrets['installed'] ?? $secrets['web'] ?? null;
if (!$client || !isset($client['client_id'], $client['client_secret'])) {
die("Error: Invalid client_secret.json format.\n");
}
$clientId = $client['client_id'];
$clientSecret = $client['client_secret'];
// === cURL helper function ===
function curlPost($url, $data, $headers = []) {
$ch = curl_init($url);
curl_setopt($ch, CURLOPT_POST, true);
curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);
curl_setopt($ch, CURLOPT_HTTPHEADER, array_merge([
'Content-Type: application/x-www-form-urlencoded',
'User-Agent: curl/7.64.1'
], $headers));
curl_setopt($ch, CURLOPT_POSTFIELDS, http_build_query($data));
$response = curl_exec($ch);
if (curl_errno($ch)) {
die("cURL error: " . curl_error($ch) . "\n");
}
curl_close($ch);
return json_decode($response, true);
}
// === Create playlist helper ===
function createPlaylist($accessToken) {
$data = [
'snippet' => [
'title' => 'FediList',
'description' => 'A custom playlist for federated videos'
],
'status' => [
'privacyStatus' => 'private'
]
];
$ch = curl_init('https://www.googleapis.com/youtube/v3/playlists?part=snippet,status');
curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);
curl_setopt($ch, CURLOPT_HTTPHEADER, [
"Authorization: Bearer $accessToken",
"Content-Type: application/json",
"User-Agent: curl/7.64.1"
]);
curl_setopt($ch, CURLOPT_POSTFIELDS, json_encode($data));
$response = curl_exec($ch);
if (curl_errno($ch)) {
die("cURL error: " . curl_error($ch) . "\n");
}
curl_close($ch);
$result = json_decode($response, true);
$result = json_decode($response, true);
if (isset($result['id'])) {
echo "FediList created!\nPlaylist ID: " . $result['id'] . "\n";
file_put_contents(__DIR__ . '/_credentials/fedilist_id.txt', $result['id']);
} else {
echo "Failed to create playlist:\n$response\n";
}
}
// === Step 1: Get device code ===
$deviceData = curlPost('https://oauth2.googleapis.com/device/code', [
'client_id' => $clientId,
'scope' => 'https://www.googleapis.com/auth/youtube'
]);
if (!isset($deviceData['user_code'])) {
die("Failed to get device code.\n");
}
echo "==== DEVICE AUTHORIZATION ====\n";
echo "Visit: " . $deviceData['verification_url'] . "\n";
echo "Enter code: " . $deviceData['user_code'] . "\n\n";
// === Step 2: Poll for token ===
$token = null;
$startTime = time();
while (true) {
sleep($deviceData['interval']);
$tokenResponse = curlPost('https://oauth2.googleapis.com/token', [
'client_id' => $clientId,
'client_secret' => $clientSecret,
'device_code' => $deviceData['device_code'],
'grant_type' => 'urn:ietf:params:oauth:grant-type:device_code'
]);
if (isset($tokenResponse['access_token'])) {
$token = $tokenResponse;
file_put_contents(__DIR__ . '/_credentials/token.json', json_encode($token));
break;
}
if (isset($tokenResponse['error']) && $tokenResponse['error'] !== 'authorization_pending') {
die("Auth error: " . $tokenResponse['error'] . "\n");
}
if (time() - $startTime > $deviceData['expires_in']) {
die("Authorization timed out.\n");
}
}
// === Step 3: Create FediList Playlist ===
createPlaylist($token['access_token']);
?>

178
fedi_slurp.php Executable file
View file

@ -0,0 +1,178 @@
#!/usr/bin/php
<?php
//-----------------------------
// CREDENTIALS
//-----------------------------
$MASTODON_TOKEN = '8beea62e32b336e5d934d06a21b0b996';
$MASTODON_HOST = 'go.lema.org';
$READECK_TOKEN = 'LDJb4YbGKe6Fp8cSygpuw5LjmwkgGTAbFbP77TQtYwe1hFZ4';
$READECK_HOST = 'read.lema.org';
$MINIMUM_TEXT_SIZE = 500; // article with less characters of content will be ignored
//-----------------------------
// FETCH MASTODON BOOKMARKS
//-----------------------------
echo "# Fetching mastodon / snac bookmarks...\n";
date_default_timezone_set('America/Sao_Paulo');
echo date('Y-m-d H:i:s')."\n";
$ch = curl_init("https://$MASTODON_HOST/api/v1/bookmarks");
curl_setopt_array($ch, [
CURLOPT_RETURNTRANSFER => true,
CURLOPT_HTTPHEADER => [
"Authorization: Bearer $MASTODON_TOKEN",
"Accept: application/json"
]
]);
$bookmarksJson = curl_exec($ch);
$bookmarks = json_decode($bookmarksJson, true);
if (!is_array($bookmarks)) {
die("❌ Failed to parse Mastodon bookmarks.\n");
}
echo "Found bookmarks:".count($bookmarks)."\n";
//-----------------------------
// FIND VALID URLs in posts
//-----------------------------
foreach ($bookmarks as $status) {
if (!isset($status['content'])) {
continue;
}
$content = strip_tags($status['content']);
preg_match_all('/https?:\/\/[^\s"<]+/', $content, $matches);
if (!empty($matches[0])) {
$oneLink = $matches[0][0];
if (filter_var($oneLink, FILTER_VALIDATE_URL)) {
$links[] = $oneLink;
} else {
// This happens for example if URL has an emoji at the end
echo "INVALID URL: $oneLink\n";
}
}
}
echo "Valid URLS:".count($links)."\n";
print_r($links);
//-----------------------------
// SEND LINKS TO READECK
//-----------------------------
$apiUrl = "https://$READECK_HOST/api/bookmarks";
$ch = curl_init();
curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);
curl_setopt($ch, CURLOPT_POST, true);
curl_setopt($ch, CURLOPT_USERAGENT, 'Mozilla/5.0');
$headers = [
"Authorization: Bearer $READECK_TOKEN",
'Accept: application/json',
'Content-Type: application/json'
];
$alreadySentDir = __DIR__ . "/already_sent";
if (!is_dir($alreadySentDir)) {
mkdir($alreadySentDir, 0755, true); // recursive mkdir
}
require("add_to_fedilist.php");
foreach ($links as $link) {
if (isYouTubeLink($link)) {
addVideoToFediList($link);
continue;
}
// READECK will accept several times the same URL !
// Make sure we don't send it several times by keeping an archive here
$hash = md5($link);
$filePath = __DIR__ . "/already_sent/{$hash}.txt";
if (file_exists($filePath)) {
echo " Already sent: $link\n";
continue;
}
$options = [
'http' => [
'method' => 'GET',
'header' => "User-Agent: Mozilla/5.0\r\n"
]
];
// First check if page has content
//$ch = curl_init($link);;
curl_setopt($ch, CURLOPT_URL, $link);
curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);
$content = curl_exec($ch);
if ($content === false) {
echo "❌ Failed to fetch $link\n";
continue;
}
$plainText = strip_tags($content);
if (strlen($plainText) < $MINIMUM_TEXT_SIZE) {
echo "⚠️ Skipping $link\ncontent too small (".strlen($plainText)." chars < $MINIMUM_TEXT_SIZE )\n";
continue;
}
echo "🟢 Will add to Readeck $link\nLength: " . strlen($plainText)."\n";
//not passing title here, since we don't have it
$payload = json_encode([
"labels" => ["automasto"],
"url" => $link
]);
curl_setopt($ch, CURLOPT_URL, $apiUrl);
curl_setopt($ch, CURLOPT_POSTFIELDS, $payload);
curl_setopt($ch, CURLOPT_HTTPHEADER, $headers);
$response = curl_exec($ch);
$httpCode = curl_getinfo($ch, CURLINFO_HTTP_CODE);
if (curl_errno($ch)) {
echo "❌ Error adding $link: " . curl_error($ch) . "\n";
} else {
// Store already sent file only if connection worked
file_put_contents($filePath, $link);
$json = json_decode($response, true);
if (json_last_error() === JSON_ERROR_NONE) {
if ($httpCode >= 200 && $httpCode < 300) {
echo "✅ [$httpCode] Successfully added: $link\n";
} else {
echo "⚠️ Server returned status $httpCode for $link\n";
}
} else {
echo "⚠️ Response is not valid JSON for $link: $response\n";
}
}
}
curl_close($ch);