// Wikipedia Archive Checker - Add to your common.js
// Adds an archive checking form to Special:Preferences
(function() {
'use strict';
//don't run on mobile
if (mw.config.get('skin') === 'minerva' ) {
return;
}
// Only run on watchlist page
if (mw.config.get('wgCanonicalSpecialPageName') !== 'Watchlist') {
return;
}
// Flag to prevent double initialization
let initialized = false;
// Create the archive checker section
function createArchiveChecker() {
const section = document.createElement('div');
section.id = 'archive-checker-section';
section.style.cssText = `
margin: 20px 0;
padding: 20px;
border: 1px solid #a2a9b1;
border-radius: 4px;
background-color: #f8f9fa;
`;
section.innerHTML = `
<h3 style="margin-top: 0; color: #0645ad;">Archive Checker</h3>
<p>Check if a URL exists in various web archives:</p>
<div style="margin-bottom: 15px;">
<input type="text" id="url-input" placeholder="Enter URL (e.g., example.com)"
style="width: 300px; padding: 8px; border: 1px solid #a2a9b1; border-radius: 2px;">
<button id="check-btn" style="margin-left: 10px; padding: 8px 15px; background: #0645ad; color: white; border: none; border-radius: 2px; cursor: pointer;">Check</button>
</div>
<div id="results-container" style="margin-top: 15px;"></div>
`;
return section;
}
// Normalize URL (add protocol if missing)
function normalizeUrl(url) {
url = url.trim();
if (!url) return '';
// Remove protocol if present, we'll add it back consistently
url = url.replace(/^https?:\/\//, '');
url = url.replace(/^www\./, '');
return url;
}
// Archive services configuration
const archiveServices = [
{
name: 'Archive.today',
checkUrl: (url) => `https://archive.ph/${encodeURIComponent(url)}`,
searchUrl: (url) => `https://archive.ph/${encodeURIComponent(url)}`,
apiCheck: true,
notFoundStrings: ['No results']
},
{
name: 'Ghost Archive',
checkUrl: (url) => `https://ghostarchive.org/search?term=${encodeURIComponent(url)}`,
searchUrl: (url) => `https://ghostarchive.org/search?term=${encodeURIComponent(url)}`,
apiCheck: false
},
{
name: 'Wayback Machine',
checkUrl: (url) => `https://web.archive.org/web/20250000000000*/${encodeURIComponent(url)}`,
searchUrl: (url) => `https://web.archive.org/web/*/${encodeURIComponent(url)}`,
apiUrl: (url) => `https://archive.org/wayback/available?url=${encodeURIComponent(url)}`,
apiCheck: true,
notFoundStrings: ['Wayback Machine has not archived that URL.']
}
];
// Check archives
async function checkArchives(url) {
const resultsContainer = document.getElementById('results-container');
resultsContainer.innerHTML = '<p>Checking archives...</p>';
const normalizedUrl = normalizeUrl(url);
if (!normalizedUrl) {
resultsContainer.innerHTML = '<p style="color: red;">Please enter a valid URL.</p>';
return;
}
console.log(`[Archive Checker] Starting check for URL: ${normalizedUrl}`);
const results = [];
for (const service of archiveServices) {
console.log(`[Archive Checker] Checking ${service.name}...`);
const result = {
name: service.name,
url: service.searchUrl(normalizedUrl),
available: null,
error: null
};
if (service.apiCheck) {
try {
let checkUrl;
if (service.name === 'Wayback Machine' && service.apiUrl) {
// Use the dedicated API for Wayback Machine
checkUrl = service.apiUrl(normalizedUrl);
console.log(`[Archive Checker] ${service.name} API URL: ${checkUrl}`);
const response = await fetch(checkUrl);
console.log(`[Archive Checker] ${service.name} API Response status: ${response.status}`);
const data = await response.json();
console.log(`[Archive Checker] ${service.name} API Response data:`, data);
// Check if archived_snapshots has any properties (indicating archives exist)
const hasArchives = data.archived_snapshots &&
Object.keys(data.archived_snapshots).length > 0 &&
data.archived_snapshots.closest;
result.available = !!hasArchives; // Ensure it's a boolean
if (hasArchives) {
result.url = data.archived_snapshots.closest.url;
console.log(`[Archive Checker] ${service.name} - Archive found: ${result.url}`);
} else {
console.log(`[Archive Checker] ${service.name} - No archive found (empty archived_snapshots)`);
}
} else {
// For other services, fetch the page content and check for "not found" strings
checkUrl = service.checkUrl(normalizedUrl);
console.log(`[Archive Checker] ${service.name} Check URL: ${checkUrl}`);
const response = await fetch(checkUrl, {
mode: 'cors',
credentials: 'omit'
});
console.log(`[Archive Checker] ${service.name} Response status: ${response.status}`);
if (response.ok) {
const text = await response.text();
console.log(`[Archive Checker] ${service.name} Response length: ${text.length} characters`);
// Check if any "not found" strings are present
const notFound = service.notFoundStrings &&
service.notFoundStrings.some(str => text.includes(str));
if (notFound) {
result.available = false;
console.log(`[Archive Checker] ${service.name} - Not found (detected: "${service.notFoundStrings.find(str => text.includes(str))}")`);
} else {
result.available = true;
console.log(`[Archive Checker] ${service.name} - Archive appears to be available`);
}
} else {
result.available = null;
result.error = `HTTP ${response.status}`;
console.log(`[Archive Checker] ${service.name} - HTTP error: ${response.status}`);
}
}
} catch (error) {
console.error(`[Archive Checker] ${service.name} - Error:`, error);
result.error = error.message;
result.available = null;
}
} else {
console.log(`[Archive Checker] ${service.name} - API check disabled, will show manual link`);
}
results.push(result);
}
console.log(`[Archive Checker] Check completed. Results:`, results);
displayResults(results, normalizedUrl);
}
// Display results
function displayResults(results, originalUrl) {
const resultsContainer = document.getElementById('results-container');
console.log(`[Archive Checker] Displaying results for ${originalUrl}:`, results);
let html = `<h4>Results for: ${originalUrl}</h4>`;
html += '<div style="display: grid; gap: 10px;">';
results.forEach(result => {
console.log(`[Archive Checker] Processing result for ${result.name}:`, {
available: result.available,
availableType: typeof result.available,
error: result.error
});
const statusText = result.available === true ? '✓ Available' :
result.available === false ? '✗ Not found' :
result.error ? `⚠ ${result.error}` : '? Check manually';
const statusColor = result.available === true ? '#006400' :
result.available === false ? '#8b0000' : '#666';
console.log(`[Archive Checker] ${result.name} - Status: ${statusText}, Color: ${statusColor}`);
html += `
<div style="padding: 10px; border: 1px solid #ddd; border-radius: 4px; background: white;">
<div style="display: flex; justify-content: space-between; align-items: center;">
<span><strong>${result.name}</strong></span>
<span style="color: ${statusColor};">${statusText}</span>
</div>
<div style="margin-top: 8px;">
<a href="${result.url}" target="_blank" rel="noopener"
style="color: #0645ad; text-decoration: none;">
Visit ${result.name} →
</a>
</div>
</div>
`;
});
html += '</div>';
html += `<p style="margin-top: 15px; font-size: 0.9em; color: #666;">
<strong>Note:</strong> Some archives may require manual verification.
Click the links above to check each archive service.
</p>`;
resultsContainer.innerHTML = html;
}
// Add the archive checker section and set up event listeners
function addArchiveChecker() {
// Prevent multiple initialization
if (initialized || document.getElementById('archive-checker-section')) {
return;
}
const watchlistContent = document.querySelector('.mw-changeslist, #mw-content-text');
if (!watchlistContent) {
return;
}
initialized = true;
// Add our section to the top of the watchlist page
const archiveChecker = createArchiveChecker();
watchlistContent.parentNode.insertBefore(archiveChecker, watchlistContent);
// Add event listeners
const checkBtn = document.getElementById('check-btn');
const urlInput = document.getElementById('url-input');
checkBtn.addEventListener('click', () => {
const url = urlInput.value;
checkArchives(url);
});
urlInput.addEventListener('keypress', (e) => {
if (e.key === 'Enter') {
checkBtn.click();
}
});
}
// Initialize the checker
function init() {
// Try to add immediately if page is already loaded
addArchiveChecker();
// If not added yet, wait for the page to be fully loaded
if (!initialized) {
const observer = new MutationObserver(function(mutations, obs) {
if (!initialized) {
addArchiveChecker();
if (initialized) {
obs.disconnect();
}
}
});
observer.observe(document.body, {
childList: true,
subtree: true
});
// Cleanup observer after reasonable time
setTimeout(() => {
observer.disconnect();
}, 5000);
}
}
// Start when DOM is ready
if (document.readyState === 'loading') {
document.addEventListener('DOMContentLoaded', init);
} else {
init();
}
})();
