Superclean URLs
Pricing
Pay per usage
Clean messy URLs from lead exports. Remove 60+ tracking parameters (utm_*, fbclid, gclid), normalize format, extract domains, and optionally verify URLs are reachable. Perfect for cold email personalization and CRM data hygiene.
Pricing
Pay per usage
Rating
0.0
(0)
Developer
Superlative
Maintained by CommunityActor stats
2
Bookmarked
8
Total users
1
Monthly active users
8 days ago
Last modified
Categories
Share
# This file tells Git which files shouldn't be added to source control.DS_Store.idea.vscode.zednode_modulesstorage
# Added by Apify CLI.venv{ "name": "superclean-urls", "version": "0.1.0", "type": "module", "description": "Clean messy URLs from lead exports. Remove tracking parameters, normalize format, extract domains.", "main": "src/main.js", "scripts": { "start": "node src/main.js", "test": "node --test" }, "author": "Superlative <hello@superlative.tech>", "license": "ISC", "dependencies": { "apify": "^3.3.2" }}
tests/node_modules/.claude/storage/apify_storage/.envtests/test/node_modules/.claude/storage/apify_storage/.envscripts/1/**2 * Tracking parameters to remove from URLs.3 * Includes UTM, social media, advertising, and email marketing params.4 */5export const TRACKING_PARAMS = [6 // UTM parameters (Google Analytics standard)7 'utm_source',8 'utm_medium',9 'utm_campaign',10 'utm_term',11 'utm_content',12 'utm_id',13 'utm_source_platform',14 'utm_creative_format',15 'utm_marketing_tactic',16
17 // Facebook / Meta18 'fbclid',19 'fb_action_ids',20 'fb_action_types',21 'fb_source',22 'fb_ref',23
24 // Google Ads25 'gclid',26 'gclsrc',27 'dclid',28 'gbraid',29 'wbraid',30
31 // Microsoft / Bing32 'msclkid',33
34 // Twitter / X35 'twclid',36
37 // LinkedIn38 'li_fat_id',39 'li_tc',40
41 // TikTok42 'ttclid',43
44 // Email marketing45 'mc_eid',46 'mc_cid',47 '_hsenc',48 '_hsmi',49 'mkt_tok',50 'oly_enc_id',51 'oly_anon_id',52 'vero_id',53 'vero_conv',54
55 // Analytics & tracking56 'ref',57 '_ga',58 '_gl',59 'spm',60 'scid',61 'clickid',62 'click_id',63 'trk',64 'tracking',65
66 // Affiliate67 'aff',68 'affiliate',69 'affiliate_id',70 'partner',71 'partner_id',72
73 // Other common tracking74 'source',75 'campaign',76 'medium',77 '_ke',78 'igshid',79 's_kwcid',80 'ef_id'81];82
83/**84 * Parameters that start with these prefixes should also be removed.85 */86export const TRACKING_PREFIXES = [87 'utm_',88 'hsa_',89 'fb_',90 'mc_',91 '_hs',92 'pk_',93 'mtm_'94];1import { TRACKING_PARAMS, TRACKING_PREFIXES } from './constants.js';2
3/**4 * Clean a URL according to the specified options.5 * @param {string} urlString - The URL to clean6 * @param {Object} options - Cleaning options7 * @returns {Object} - Cleaned URL result with confidence score8 */9export function cleanUrl(urlString, options = {}) {10 const {11 style = 'full',12 forceHttps = true,13 removeTracking = true14 } = options;15
16 const result = {17 input: urlString,18 output: '',19 domain: '',20 protocol: '',21 path: '',22 query: '',23 hash: '',24 valid: false,25 confidence: 026 };27
28 // Handle empty or whitespace-only input29 const trimmed = (urlString || '').trim();30 if (!trimmed) {31 result.output = '';32 result.confidence = 0;33 return result;34 }35
36 // Track modifications for confidence scoring37 let modifications = 0;38 let majorFixes = 0;39
40 // Step 1: Add protocol if missing41 let urlWithProtocol = trimmed;42 if (!/^https?:\/\//i.test(urlWithProtocol)) {43 // Check for other protocols we don't handle44 if (/^[a-z][a-z0-9+.-]*:/i.test(urlWithProtocol)) {45 // Has a protocol but not http/https (e.g., ftp://, mailto:)46 result.output = trimmed;47 result.confidence = 0.3;48 return result;49 }50 urlWithProtocol = 'https://' + urlWithProtocol;51 majorFixes++;52 }53
54 // Step 2: Parse the URL55 let parsed;56 try {57 parsed = new URL(urlWithProtocol);58 } catch (e) {59 // Invalid URL - try to extract domain anyway60 const domainMatch = trimmed.match(/^(?:https?:\/\/)?(?:www\.)?([a-z0-9][-a-z0-9]*(?:\.[a-z0-9][-a-z0-9]*)+)/i);61 if (domainMatch) {62 result.domain = domainMatch[1].toLowerCase();63 result.output = style === 'domain' ? result.domain : trimmed;64 result.confidence = 0.3;65 } else {66 result.output = trimmed;67 result.confidence = 0;68 }69 return result;70 }71
72 result.valid = true;73
74 // Step 3: Normalize hostname75 let hostname = parsed.hostname.toLowerCase();76
77 // Step 4: Force HTTPS78 let protocol = parsed.protocol;79 if (forceHttps && protocol === 'http:') {80 protocol = 'https:';81 modifications++;82 }83
84 // Step 5: Remove tracking parameters85 if (removeTracking) {86 const params = new URLSearchParams(parsed.search);87 const originalParamCount = Array.from(params.keys()).length;88
89 for (const param of Array.from(params.keys())) {90 const lowerParam = param.toLowerCase();91
92 // Check exact matches93 if (TRACKING_PARAMS.includes(lowerParam)) {94 params.delete(param);95 continue;96 }97
98 // Check prefix matches99 for (const prefix of TRACKING_PREFIXES) {100 if (lowerParam.startsWith(prefix)) {101 params.delete(param);102 break;103 }104 }105 }106
107 const newParamCount = Array.from(params.keys()).length;108 if (newParamCount < originalParamCount) {109 modifications += (originalParamCount - newParamCount);110 }111
112 parsed.search = params.toString() ? '?' + params.toString() : '';113 }114
115 // Step 6: Clean path (remove trailing slash except for root)116 let path = parsed.pathname;117 if (path.length > 1 && path.endsWith('/')) {118 path = path.slice(0, -1);119 modifications++;120 }121
122 // Step 7: Extract domain and components123 result.domain = hostname.replace(/^www\./, '');124 result.protocol = protocol.replace(':', '');125 result.path = path === '/' ? '' : path;126 result.query = parsed.search ? parsed.search.slice(1) : '';127 result.hash = parsed.hash ? parsed.hash.slice(1) : '';128
129 // Step 8: Build output based on style130 if (style === 'domain') {131 result.output = result.domain;132 } else {133 // style === 'full'134 const port = parsed.port ? ':' + parsed.port : '';135 const search = parsed.search || '';136 const hashPart = parsed.hash || '';137 const cleanPath = path === '/' ? '' : path;138 result.output = `${protocol}//${hostname}${port}${cleanPath}${search}${hashPart}`;139 }140
141 // Step 9: Calculate confidence142 if (majorFixes > 0) {143 result.confidence = 0.7;144 } else if (modifications > 0) {145 result.confidence = 0.9;146 } else {147 result.confidence = 1.0;148 }149
150 return result;151}152
153/**154 * Process an array of URLs.155 * @param {string[]} urls - Array of URLs to clean156 * @param {Object} options - Cleaning options157 * @returns {Object[]} - Array of results158 */159export function cleanUrls(urls, options = {}) {160 return urls.map((url, index) => {161 const cleaned = cleanUrl(url, options);162 return {163 id: index + 1,164 input: cleaned.input,165 output: cleaned.output,166 domain: cleaned.domain,167 protocol: cleaned.protocol,168 path: cleaned.path,169 query: cleaned.query,170 hash: cleaned.hash,171 valid: cleaned.valid,172 confidence: Math.round(cleaned.confidence * 100) / 100173 };174 });175}1import http from 'node:http';2import { Actor } from 'apify';3import { cleanUrl, cleanUrls } from './cleaner.js';4
5const PPE_EVENT = 'url-clean';6
7/**8 * Normalize flexible input formats for Clay/API compatibility.9 * Accepts: ["string"] or [{input: "string"}]10 * Returns: ["string"]11 */12function normalizeItems(items) {13 return items.map((item) => {14 if (typeof item === 'string') {15 return item;16 }17 if (item && typeof item === 'object' && 'input' in item) {18 return String(item.input ?? '');19 }20 return String(item ?? '');21 });22}23
24await Actor.init();25
26if (Actor.config.get('metaOrigin') === 'STANDBY') {27 startStandbyServer();28} else {29 await runBatchMode();30 await Actor.exit();31}32
33// ---------------------------------------------------------------------------34// Standby mode — HTTP server for instant single-URL cleaning35// ---------------------------------------------------------------------------36
37function startStandbyServer() {38 const port = Actor.config.get('containerPort');39
40 const server = http.createServer(async (req, res) => {41 // Readiness probe42 if (req.headers['x-apify-container-server-readiness-probe']) {43 res.writeHead(200, { 'Content-Type': 'application/json' });44 res.end(JSON.stringify({ status: 'ready' }));45 return;46 }47
48 // GET only49 if (req.method !== 'GET') {50 res.writeHead(405, { 'Content-Type': 'application/json' });51 res.end(JSON.stringify({ error: 'Method not allowed. Use GET.' }));52 return;53 }54
55 // No input param → serve landing page56 const reqUrl = new URL(req.url, `http://${req.headers.host}`);57 if (!reqUrl.searchParams.get('input')) {58 res.writeHead(200, { 'Content-Type': 'text/html' });59 res.end(getLandingPageHtml());60 return;61 }62
63 try {64 const result = handleStandbyRequest(reqUrl);65 await Actor.pushData(result);66
67 // Charge PPE68 try {69 await Actor.charge({ eventName: PPE_EVENT, count: 1 });70 } catch (chargeErr) {71 console.warn(`PPE charge failed: ${chargeErr.message}`);72 }73
74 res.writeHead(200, { 'Content-Type': 'application/json' });75 res.end(JSON.stringify(result));76 } catch (err) {77 const statusCode = err.statusCode || 500;78 res.writeHead(statusCode, { 'Content-Type': 'application/json' });79 res.end(JSON.stringify({ error: err.message }));80 }81 });82
83 server.listen(port, () => {84 console.log(`Superclean URLs Standby server listening on port ${port}`);85 });86}87
88function handleStandbyRequest(reqUrl) {89 const input = reqUrl.searchParams.get('input');90
91 if (!input) {92 const err = new Error("Provide an 'input' query parameter with the URL to clean.");93 err.statusCode = 400;94 throw err;95 }96
97 const style = reqUrl.searchParams.get('style') || 'full';98 const forceHttps = reqUrl.searchParams.get('forceHttps') !== 'false';99 const removeTracking = reqUrl.searchParams.get('removeTracking') !== 'false';100
101 const validStyles = ['full', 'domain'];102 if (!validStyles.includes(style)) {103 const err = new Error(`Invalid style "${style}". Must be one of: ${validStyles.join(', ')}`);104 err.statusCode = 400;105 throw err;106 }107
108 const cleaned = cleanUrl(input, { style, forceHttps, removeTracking });109
110 return {111 id: 1,112 input: cleaned.input,113 output: cleaned.output,114 domain: cleaned.domain,115 protocol: cleaned.protocol,116 path: cleaned.path,117 query: cleaned.query,118 hash: cleaned.hash,119 valid: cleaned.valid,120 confidence: Math.round(cleaned.confidence * 100) / 100,121 };122}123
124// ---------------------------------------------------------------------------125// Batch mode — existing pipeline for standard Actor runs126// ---------------------------------------------------------------------------127
128async function runBatchMode() {129 const input = await Actor.getInput();130
131 let {132 items: rawItems = [],133 item,134 style = 'full',135 forceHttps = true,136 removeTracking = true137 } = input || {};138
139 // Support single "item" string field for API/integration callers140 if (typeof item === 'string' && item.trim()) {141 if (!Array.isArray(rawItems)) rawItems = [];142 rawItems = [item.trim(), ...rawItems];143 }144
145 // Coerce bare string to array146 if (typeof rawItems === 'string') rawItems = [rawItems];147
148 // Validate input149 if (!Array.isArray(rawItems) || rawItems.length === 0) {150 await Actor.fail('Input required: provide "items" (array of URLs) or "item" (single URL string). Example: {"items": ["https://example.com"]}');151 return;152 }153
154 // Normalize input format (supports both ["string"] and [{input: "string"}])155 const items = normalizeItems(rawItems);156
157 console.log(`Processing ${items.length} URL(s) with style: ${style}`);158 console.log(`Options: forceHttps=${forceHttps}, removeTracking=${removeTracking}`);159
160 // Clean the URLs161 const results = cleanUrls(items, {162 style,163 forceHttps,164 removeTracking165 });166
167 // Charge PPE per item, then push to dataset168 let chargedCount = 0;169 let chargeLimitReached = false;170 for (const result of results) {171 if (!chargeLimitReached) {172 try {173 const chargeResult = await Actor.charge({ eventName: PPE_EVENT, count: 1 });174 chargedCount++;175 if (chargeResult?.eventChargeLimitReached) {176 chargeLimitReached = true;177 console.log(`User spending limit reached after charging ${chargedCount}/${results.length} items`);178 }179 } catch (chargeErr) {180 console.warn(`PPE charge failed: ${chargeErr.message}`);181 }182 }183 }184
185 await Actor.pushData(results);186
187 // Log summary188 const validCount = results.filter(r => r.valid).length;189 const avgConfidence = results.length > 0190 ? (results.reduce((sum, r) => sum + r.confidence, 0) / results.length).toFixed(2)191 : 0;192
193 console.log(`Processed ${results.length} URLs`);194 console.log(`Valid format: ${validCount}, Invalid format: ${results.length - validCount}`);195 console.log(`Average confidence: ${avgConfidence}`);196}197
198// ---------------------------------------------------------------------------199// Landing page HTML for Standby mode200// ---------------------------------------------------------------------------201
202function getLandingPageHtml() {203 return `<!DOCTYPE html>204<html lang="en">205<head>206<meta charset="utf-8">207<meta name="viewport" content="width=device-width, initial-scale=1">208<title>Superclean URLs — Superlative</title>209<link rel="preconnect" href="https://fonts.googleapis.com">210<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin>211<link href="https://fonts.googleapis.com/css2?family=DM+Sans:wght@400;500;700&family=Space+Mono:wght@400;700&display=swap" rel="stylesheet">212<style>213:root{--color-bg:#0a0e14;--color-surface:#12171f;--color-border:#1e2632;--color-text:#e8eaed;--color-text-muted:#8b95a5;--color-accent:#4ade80;--color-accent-dim:rgba(74,222,128,0.15);--font-display:'Space Mono',monospace;--font-body:'DM Sans',sans-serif}214*{margin:0;padding:0;box-sizing:border-box}215body{font-family:var(--font-body);background:var(--color-bg);color:var(--color-text);line-height:1.6;min-height:100vh;overflow-x:hidden}216a{color:var(--color-accent);text-decoration:none;transition:color .2s ease}217a:hover{color:#6ee7a0}218.grid-bg{position:fixed;top:0;left:0;width:100%;height:100%;background-image:linear-gradient(var(--color-border) 1px,transparent 1px),linear-gradient(90deg,var(--color-border) 1px,transparent 1px);background-size:60px 60px;opacity:.3;pointer-events:none;z-index:0}219.accent-line{position:fixed;top:0;left:0;width:100%;height:2px;background:linear-gradient(90deg,transparent 0%,var(--color-accent) 50%,transparent 100%);animation:shimmer 3s ease-in-out infinite;z-index:10}220@keyframes shimmer{0%,100%{transform:translateX(-100%)}50%{transform:translateX(100%)}}221@keyframes fadeUp{from{opacity:0;transform:translateY(20px)}to{opacity:1;transform:translateY(0)}}222.container{position:relative;z-index:1;max-width:900px;margin:0 auto;padding:0 24px}223header{padding:32px 0}224.logo{font-family:var(--font-display);font-size:14px;font-weight:700;letter-spacing:.1em;text-transform:uppercase;color:var(--color-text);display:flex;align-items:center;gap:10px;text-decoration:none}225.logo:hover{color:var(--color-text)}226.logo-mark{width:28px;height:28px;background:var(--color-accent);display:flex;align-items:center;justify-content:center}227.logo-mark svg{width:16px;height:16px}228.hero{padding:80px 0 60px;animation:fadeUp .8s ease-out}229.hero-label{font-family:var(--font-display);font-size:12px;font-weight:400;letter-spacing:.15em;text-transform:uppercase;color:var(--color-accent);margin-bottom:24px;display:flex;align-items:center;gap:12px}230.hero-label::before{content:'';width:24px;height:1px;background:var(--color-accent)}231h1{font-family:var(--font-display);font-size:clamp(28px,5vw,44px);font-weight:700;line-height:1.15;margin-bottom:20px;letter-spacing:-.02em}232h1 .highlight{color:var(--color-accent)}233.hero-desc{font-size:18px;color:var(--color-text-muted);max-width:540px;margin-bottom:28px;line-height:1.7}234.hero-link{font-family:var(--font-display);font-size:13px;letter-spacing:.05em;color:var(--color-accent);display:inline-flex;align-items:center;gap:6px}235.section{padding:60px 0;border-top:1px solid var(--color-border);animation:fadeUp .8s ease-out .2s backwards}236.section-label{font-family:var(--font-display);font-size:11px;font-weight:400;letter-spacing:.2em;text-transform:uppercase;color:var(--color-text-muted);margin-bottom:24px}237h2{font-family:var(--font-display);font-size:20px;font-weight:700;margin-bottom:16px;letter-spacing:-.01em}238p,li{font-size:15px;color:var(--color-text-muted);line-height:1.7}239li{margin-bottom:6px}240ul{margin:.5rem 0 1rem 1.25rem}241strong{color:var(--color-text);font-weight:600}242pre{background:var(--color-surface);color:var(--color-text);padding:16px 20px;overflow-x:auto;margin:12px 0 16px;font-family:var(--font-display);font-size:13px;line-height:1.6;border:1px solid var(--color-border)}243code{font-family:var(--font-display);font-size:13px}244p code,li code,td code{background:var(--color-accent-dim);color:var(--color-accent);padding:2px 6px}245table{width:100%;border-collapse:collapse;margin:12px 0 16px;font-size:14px}246th,td{border:1px solid var(--color-border);padding:10px 14px;text-align:left}247th{background:var(--color-surface);color:var(--color-text-muted);font-family:var(--font-display);font-size:12px;font-weight:400;letter-spacing:.05em;text-transform:uppercase}248td{color:var(--color-text-muted)}249.badge{display:inline-block;background:var(--color-accent-dim);color:var(--color-accent);padding:3px 8px;font-family:var(--font-display);font-size:11px;font-weight:400;letter-spacing:.05em}250.note{font-size:13px;color:var(--color-text-muted);margin-top:8px}251.product-grid{display:grid;grid-template-columns:repeat(auto-fit,minmax(240px,1fr));gap:16px;margin-top:24px}252.product-card{background:var(--color-surface);border:1px solid var(--color-border);padding:24px;transition:all .3s ease;text-decoration:none;color:inherit;display:block}253.product-card:hover{border-color:var(--color-accent);transform:translateY(-2px)}254.product-name{font-family:var(--font-display);font-size:14px;font-weight:700;margin-bottom:8px;color:var(--color-text);display:flex;align-items:center;gap:8px}255.product-name .status{font-size:9px;font-weight:400;padding:3px 6px;background:var(--color-accent-dim);color:var(--color-accent);letter-spacing:.1em}256.product-desc{font-size:14px;color:var(--color-text-muted);line-height:1.5}257footer{padding:48px 0;border-top:1px solid var(--color-border)}258.footer-content{display:flex;justify-content:space-between;align-items:center;flex-wrap:wrap;gap:24px}259.footer-text{font-size:13px;color:var(--color-text-muted)}260.footer-links{display:flex;gap:24px}261.footer-links a{font-family:var(--font-display);font-size:12px;color:var(--color-text-muted);letter-spacing:.05em}262.footer-links a:hover{color:var(--color-accent)}263@media(max-width:600px){.hero{padding:60px 0 40px}.section{padding:40px 0}.footer-content{flex-direction:column;align-items:flex-start}pre{font-size:12px;padding:12px 14px}}264</style>265</head>266<body>267<div class="grid-bg"></div>268<div class="accent-line"></div>269
270<div class="container">271 <header>272 <a href="https://apify.com/superlativetech?fpr=8e9l1" class="logo">273 <div class="logo-mark">274 <svg viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2.5">275 <polyline points="4 17 10 11 4 5"></polyline>276 <line x1="12" y1="19" x2="20" y2="19"></line>277 </svg>278 </div>279 Superlative280 </a>281 </header>282
283 <section class="hero">284 <div class="hero-label">Superclean</div>285 <h1>Superclean <span class="highlight">URLs</span></h1>286 <p class="hero-desc">Instant URL cleaning and normalization. Remove tracking params, fix protocols, extract domains. Sub-second responses via Standby API.</p>287 <a href="https://apify.com/superlativetech/superclean-urls?fpr=8e9l1" class="hero-link">View on Apify Store →</a>288 </section>289
290 <section class="section">291 <div class="section-label">Features</div>292 <h2>What this does</h2>293 <ul>294 <li><strong>Removes tracking</strong> — Strip UTM, fbclid, gclid, and 50+ other tracking params</li>295 <li><strong>Normalizes format</strong> — Consistent protocol, lowercase domains, clean paths</li>296 <li><strong>Extracts domains</strong> — Pull clean domain names from full URLs</li>297 <li><strong>Validates URLs</strong> — Identify and flag invalid URL formats</li>298 <li><strong>Batch mode</strong> — Process hundreds of URLs via the standard Actor run</li>299 </ul>300 </section>301
302 <section class="section">303 <div class="section-label">Getting Started</div>304 <h2>Quick start</h2>305 <p>Replace <code>YOUR_TOKEN</code> with your Apify API token.</p>306
307 <p style="margin-top:16px"><strong>Clean a URL (full output):</strong></p>308 <pre>curl "https://superlativetech--superclean-urls.apify.actor?token=YOUR_TOKEN&input=https://example.com/%3Futm_source%3Dlinkedin%26fbclid%3Dabc123"</pre>309
310 <p><strong>Extract domain only:</strong></p>311 <pre>curl "https://superlativetech--superclean-urls.apify.actor?token=YOUR_TOKEN&input=https://www.example.com/about&style=domain"</pre>312
313 <p><strong>Keep tracking params:</strong></p>314 <pre>curl "https://superlativetech--superclean-urls.apify.actor?token=YOUR_TOKEN&input=https://example.com/%3Futm_source%3Dx&removeTracking=false"</pre>315 </section>316
317 <section class="section">318 <div class="section-label">Reference</div>319 <h2>Query parameters</h2>320 <table>321 <tr><th>Parameter</th><th>Required</th><th>Description</th></tr>322 <tr><td><code>input</code></td><td>Yes</td><td>URL to clean</td></tr>323 <tr><td><code>style</code></td><td>No</td><td>Output format: <code>full</code> (default) or <code>domain</code></td></tr>324 <tr><td><code>forceHttps</code></td><td>No</td><td>Convert http to https (default: <code>true</code>)</td></tr>325 <tr><td><code>removeTracking</code></td><td>No</td><td>Remove tracking parameters (default: <code>true</code>)</td></tr>326 <tr><td><code>token</code></td><td>Yes</td><td>Your Apify API token</td></tr>327 </table>328 </section>329
330 <section class="section">331 <div class="section-label">Response</div>332 <h2>Response format</h2>333 <pre>{334 "id": 1,335 "input": "https://example.com/?utm_source=linkedin",336 "output": "https://example.com",337 "domain": "example.com",338 "protocol": "https",339 "path": "",340 "query": "",341 "hash": "",342 "valid": true,343 "confidence": 0.9344}</pre>345 </section>346
347 <section class="section">348 <div class="section-label">Cost</div>349 <h2>Pricing</h2>350 <p>Pay-per-event pricing on the Apify platform:</p>351 <table>352 <tr><th>Tier</th><th>URLs</th><th>Per 1,000</th></tr>353 <tr><td>Base</td><td>Any</td><td>$0.50</td></tr>354 <tr><td><span class="badge">Bronze</span></td><td>100+</td><td>$0.45</td></tr>355 <tr><td><span class="badge">Silver</span></td><td>1,000+</td><td>$0.40</td></tr>356 <tr><td><span class="badge">Gold</span></td><td>10,000+</td><td>$0.35</td></tr>357 </table>358 </section>359
360 <section class="section">361 <div class="section-label">Auth</div>362 <h2>Authentication</h2>363 <p>Authenticate using either method:</p>364 <ul>365 <li>Query parameter: <code>?token=YOUR_APIFY_TOKEN</code></li>366 <li>Header: <code>Authorization: Bearer YOUR_APIFY_TOKEN</code></li>367 </ul>368 <p style="margin-top:8px">Get your token from <a href="https://console.apify.com/settings/integrations">Apify Console → Settings → Integrations</a>.</p>369 </section>370
371 <section class="section">372 <div class="section-label">Superlative</div>373 <h2>More from Superlative</h2>374 <div class="product-grid">375 <a href="https://apify.com/superlativetech/superclean-company-names?fpr=8e9l1" class="product-card">376 <div class="product-name">Company Names <span class="status">Live</span></div>377 <p class="product-desc">Normalize company names for CRM and cold email outreach.</p>378 </a>379 <a href="https://apify.com/superlativetech/superclean-job-titles?fpr=8e9l1" class="product-card">380 <div class="product-name">Job Titles <span class="status">Live</span></div>381 <p class="product-desc">Standardize job titles for outreach sequences.</p>382 </a>383 <a href="https://apify.com/superlativetech/superclean-person-names?fpr=8e9l1" class="product-card">384 <div class="product-name">Person Names <span class="status">Live</span></div>385 <p class="product-desc">Clean and format person names for personalization.</p>386 </a>387 <a href="https://apify.com/superlativetech/superclean-product-names?fpr=8e9l1" class="product-card">388 <div class="product-name">Product Names <span class="status">Live</span></div>389 <p class="product-desc">Normalize product and brand names from exports.</p>390 </a>391 <a href="https://apify.com/superlativetech/superclean-places?fpr=8e9l1" class="product-card">392 <div class="product-name">Places <span class="status">Live</span></div>393 <p class="product-desc">Parse and standardize location strings.</p>394 </a>395 <a href="https://apify.com/superlativetech/superclean-phone-numbers?fpr=8e9l1" class="product-card">396 <div class="product-name">Phone Numbers <span class="status">Live</span></div>397 <p class="product-desc">Format and validate phone numbers.</p>398 </a>399 <a href="https://apify.com/superlativetech/dns-lookup?fpr=8e9l1" class="product-card">400 <div class="product-name">Supernet DNS Lookup <span class="status">Live</span></div>401 <p class="product-desc">Look up DNS records for any domain.</p>402 </a>403 <a href="https://apify.com/superlativetech/http-api?fpr=8e9l1" class="product-card">404 <div class="product-name">HTTP API <span class="status">Live</span></div>405 <p class="product-desc">General-purpose HTTP request utility.</p>406 </a>407 </div>408 </section>409
410 <footer>411 <div class="footer-content">412 <p class="footer-text">© 2026 Superlative</p>413 <div class="footer-links">414 <a href="https://apify.com/superlativetech?fpr=8e9l1">Apify Store</a>415 </div>416 </div>417 </footer>418</div>419
420</body>421</html>`;422}{ "actorOutputSchemaVersion": 1, "properties": { "allResults": { "type": "string", "template": "{{links.apiDefaultDatasetUrl}}/items", "title": "All Results" } }}{ "openapi": "3.0.3", "info": { "title": "Superclean URLs — Standby API", "description": "Instant URL cleaning and normalization via HTTP GET. Remove tracking parameters, normalize format, extract domains. Returns the same fields as batch mode.", "version": "0.2.0" }, "paths": { "/": { "get": { "summary": "Clean a URL", "description": "Clean and normalize a single URL. Removes tracking parameters, normalizes protocol and format, extracts domain components.", "operationId": "cleanUrl", "parameters": [ { "name": "input", "in": "query", "description": "URL to clean (e.g. `https://example.com/?utm_source=linkedin`).", "required": true, "schema": { "type": "string", "example": "https://example.com/?utm_source=linkedin&fbclid=abc123" } }, { "name": "style", "in": "query", "description": "Output format. `full` returns cleaned URL, `domain` returns domain only.", "required": false, "schema": { "type": "string", "enum": ["full", "domain"], "default": "full" } }, { "name": "forceHttps", "in": "query", "description": "Convert http:// to https://. Set to `false` to keep original protocol.", "required": false, "schema": { "type": "string", "enum": ["true", "false"], "default": "true" } }, { "name": "removeTracking", "in": "query", "description": "Remove tracking parameters (utm_*, fbclid, gclid, etc.). Set to `false` to keep them.", "required": false, "schema": { "type": "string", "enum": ["true", "false"], "default": "true" } } ], "responses": { "200": { "description": "Cleaned URL result with domain components and confidence score.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/CleanedUrl" }, "examples": { "trackingRemoved": { "summary": "Tracking params removed", "value": { "id": 1, "input": "https://example.com/?utm_source=linkedin&fbclid=abc123", "output": "https://example.com", "domain": "example.com", "protocol": "https", "path": "", "query": "", "hash": "", "valid": true, "confidence": 0.9 } }, "domainOnly": { "summary": "Domain extraction", "value": { "id": 1, "input": "https://www.example.com/about", "output": "example.com", "domain": "example.com", "protocol": "https", "path": "/about", "query": "", "hash": "", "valid": true, "confidence": 1 } } } } } }, "400": { "description": "Invalid request — missing input or invalid style.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/Error" }, "example": { "error": "Provide an 'input' query parameter with the URL to clean." } } } }, "405": { "description": "Method not allowed — only GET is supported.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/Error" }, "example": { "error": "Method not allowed. Use GET." } } } } } } } }, "components": { "schemas": { "CleanedUrl": { "type": "object", "required": ["id", "input", "output", "valid", "confidence"], "properties": { "id": { "type": "integer", "description": "Row number (always 1 for single-item Standby requests)." }, "input": { "type": "string", "description": "Original URL before cleaning." }, "output": { "type": "string", "description": "Cleaned URL (or domain if style=domain)." }, "domain": { "type": "string", "description": "Extracted registrable domain." }, "protocol": { "type": "string", "description": "Protocol (http or https)." }, "path": { "type": "string", "description": "URL path." }, "query": { "type": "string", "description": "Query string without leading ?." }, "hash": { "type": "string", "description": "Fragment/anchor without leading #." }, "valid": { "type": "boolean", "description": "Whether the URL format is valid." }, "confidence": { "type": "number", "description": "Confidence score from 0 to 1." } } }, "Error": { "type": "object", "required": ["error"], "properties": { "error": { "type": "string", "description": "Human-readable error message." } } } } }}{ "title": "Superclean URLs Input", "type": "object", "schemaVersion": 1, "properties": { "items": { "title": "URLs to clean", "type": "array", "description": "List of URLs to clean. Can include full URLs, domains, or messy lead data.", "editor": "stringList", "prefill": ["https://www.example.com/?utm_source=linkedin&fbclid=abc123"] }, "style": { "title": "Output style", "type": "string", "description": "How to format the output field. Components (protocol, path, query, hash) are always included as separate fields.", "enum": ["full", "domain"], "enumTitles": ["Full URL", "Domain only"], "default": "full" }, "forceHttps": { "title": "Force HTTPS", "type": "boolean", "description": "Convert http:// to https://.", "default": true }, "removeTracking": { "title": "Remove tracking parameters", "type": "boolean", "description": "Strip UTM, fbclid, gclid, and other tracking parameters.", "default": true }, "item": { "title": "Item (single)", "type": "string", "description": "Single URL to clean — shorthand for API/integration callers. If both 'item' and 'items' are provided, 'item' is prepended to the list.", "editor": "textfield", "sectionCaption": "API shorthand", "sectionDescription": "For API and integration callers (Clay, Make, n8n) who want to pass a single item without wrapping it in an array." } }, "required": []}{ "actorSpecification": 1, "name": "superclean-urls", "title": "Superclean URLs", "description": "Clean and normalize URLs. Remove tracking params, validate format. Rule-based. Input: URL strings. Output: {input, output, confidence}. Batch or instant API.", "version": "0.2", "dockerfile": "../Dockerfile", "usesStandbyMode": true, "buildTag": "latest", "webServerSchema": "./web_server_openapi.json", "input": "./input_schema.json", "output": "./output_schema.json", "storages": { "dataset": { "actorSpecification": 1, "title": "Cleaned URLs", "views": { "results": { "title": "Results", "transformation": { "fields": ["id", "input", "output", "domain", "protocol", "path", "query", "valid", "confidence"] }, "display": { "component": "table", "properties": { "id": { "label": "ID", "format": "number" }, "input": { "label": "Input", "format": "text" }, "output": { "label": "Output", "format": "text" }, "domain": { "label": "Domain", "format": "text" }, "protocol": { "label": "Protocol", "format": "text" }, "path": { "label": "Path", "format": "text" }, "query": { "label": "Query", "format": "text" }, "valid": { "label": "Valid", "format": "boolean" }, "confidence": { "label": "Confidence", "format": "number" } } } } } } }, "defaultRunOptions": { "build": "latest", "memoryMbytes": 128, "timeoutSecs": 360 }, "minMemoryMbytes": 128, "maxMemoryMbytes": 512}