Form Label Auditor
Pricing
Pay per usage
"Enrich public GitHub repository URLs with stars, forks, topics, license, activity, owner metadata, release data, and lead-scoring signals. Built for B2B lead generation, devtools research, and competitive intelligence."
Pricing
Pay per usage
Rating
0.0
(0)
Developer
Sanskar Jaiswal
Maintained by CommunityActor stats
0
Bookmarked
2
Total users
1
Monthly active users
8 hours ago
Last modified
Categories
Share
FROM apify/actor-node:22
WORKDIR /usr/src/appCOPY package*.json ./RUN npm install --omit=devCOPY . ./CMD ["npm", "start"]{ "name": "form-label-auditor", "version": "0.1.0", "description": "Apify Actor that audits public pages for accessible form labels.", "type": "module", "private": true, "main": "src/main.js", "scripts": { "start": "node src/main.js", "test": "node --test test/*.test.js", "lint": "node --check src/main.js" }, "dependencies": { "apify": "^3.4.5" }, "devDependencies": {}}{ "actorSpecification": 1, "name": "form-label-auditor", "title": "Form Label Auditor", "description": "Audit one public page for accessible labels on input, select, and textarea controls for accessibility and SEO QA.", "version": "0.1", "buildTag": "latest", "meta": { "templateId": "js-start" }, "input": "./input_schema.json", "output": "./output_schema.json", "storages": { "dataset": "./dataset_schema.json" }, "dockerfile": "./Dockerfile", "defaultRunOptions": { "build": "latest", "timeoutSecs": 60, "memoryMbytes": 512 }}{ "actorSpecification": 1, "fields": { "inputUrl": { "type": "string" }, "finalUrl": { "type": "string" }, "status": { "type": ["integer", "null"] }, "ok": { "type": "boolean" }, "controlCount": { "type": "integer" }, "labeledCount": { "type": "integer" }, "missingLabelCount": { "type": "integer" }, "labelCoveragePercent": { "type": "integer" }, "score": { "type": "integer" }, "grade": { "type": "string" }, "issues": { "type": "array" }, "recommendations": { "type": "array" }, "error": { "type": ["string", "null"] } }, "views": { "overview": { "title": "Form label audit", "transformation": { "fields": ["inputUrl", "finalUrl", "status", "ok", "controlCount", "missingLabelCount", "labelCoveragePercent", "score", "grade", "issues"] }, "display": { "component": "table" } } }}{ "title": "Form Label Auditor Input", "description": "Enter one public HTTP or HTTPS page URL to audit form controls for accessible labels.", "type": "object", "schemaVersion": 1, "properties": { "startUrl": { "title": "Page URL", "type": "string", "description": "Public HTTP or HTTPS page URL to audit. Credentials and private network targets are rejected.", "editor": "textfield", "prefill": "https://example.com" }, "timeoutSeconds": { "title": "Timeout seconds", "type": "integer", "description": "Request timeout for the page fetch.", "editor": "number", "default": 10, "minimum": 3, "maximum": 30 }, "maxControls": { "title": "Max controls in output", "type": "integer", "description": "Maximum form controls and missing controls to include in the dataset item.", "editor": "number", "default": 50, "minimum": 1, "maximum": 200 } }, "required": ["startUrl"]}{ "actorOutputSchemaVersion": 1, "title": "Form Label Audit Output", "properties": { "results": { "type": "string", "title": "Audit results", "template": "{{links.apiDefaultDatasetUrl}}/items" } }}1import { Actor } from 'apify';2import dns from 'node:dns/promises';3import net from 'node:net';4import { fileURLToPath } from 'node:url';5
6const USER_AGENT = 'FormLabelAuditor/0.1 (+https://apify.com)';7const MAX_BODY_BYTES = 2_000_000;8
9function isPrivateIPv4(ip) {10 const parts = ip.split('.').map(Number);11 if (parts.length !== 4 || parts.some((n) => Number.isNaN(n))) return false;12 const [a, b] = parts;13 return a === 10 || (a === 172 && b >= 16 && b <= 31) || (a === 192 && b === 168) || a === 127 || a === 0 || (a === 169 && b === 254);14}15
16function isPrivateIPv6(ip) {17 const normalized = ip.toLowerCase();18 return normalized === '::1' || normalized.startsWith('fc') || normalized.startsWith('fd') || normalized.startsWith('fe80:');19}20
21export async function normalizeAndValidateUrl(rawUrl) {22 if (!rawUrl || typeof rawUrl !== 'string') throw new Error('startUrl is required');23 if (/^[a-z][a-z0-9+.-]*:/i.test(rawUrl) && !/^https?:\/\//i.test(rawUrl)) throw new Error('Only HTTP and HTTPS URLs are supported');24
25 const withScheme = /^https?:\/\//i.test(rawUrl) ? rawUrl : `https://${rawUrl}`;26 const url = new URL(withScheme);27 if (!['http:', 'https:'].includes(url.protocol)) throw new Error('Only HTTP and HTTPS URLs are supported');28 if (!url.hostname || url.username || url.password) throw new Error('URL must be public and must not include credentials');29
30 const literalType = net.isIP(url.hostname);31 if (literalType === 4 && isPrivateIPv4(url.hostname)) throw new Error('Private IPv4 targets are blocked');32 if (literalType === 6 && isPrivateIPv6(url.hostname)) throw new Error('Private IPv6 targets are blocked');33
34 const records = literalType ? [{ address: url.hostname, family: literalType }] : await dns.lookup(url.hostname, { all: true });35 for (const record of records) {36 if (record.family === 4 && isPrivateIPv4(record.address)) throw new Error('DNS resolves to a private IPv4 address; blocked for SSRF safety');37 if (record.family === 6 && isPrivateIPv6(record.address)) throw new Error('DNS resolves to a private IPv6 address; blocked for SSRF safety');38 }39 return url;40}41
42function clampInteger(value, fallback, min, max) {43 const parsed = Number(value);44 if (!Number.isFinite(parsed)) return fallback;45 return Math.min(Math.max(Math.trunc(parsed), min), max);46}47
48function getAttr(tag, name) {49 const match = tag.match(new RegExp(`\\s${name}\\s*=\\s*("([^"]*)"|'([^']*)'|([^\\s>]+))`, 'i'));50 return match ? (match[2] ?? match[3] ?? match[4] ?? '').trim() : null;51}52
53function textFromHtml(raw) {54 return raw.replace(/<[^>]*>/g, ' ').replace(/\s+/g, ' ').trim();55}56
57export function parseFormLabels(html, maxControls = 50) {58 const labelForIds = new Map();59 const nestedLabels = [];60 for (const match of html.matchAll(/<label\b[^>]*>[\s\S]*?<\/label>/gi)) {61 const tag = match[0].match(/<label\b[^>]*>/i)?.[0] || '';62 const text = textFromHtml(match[0]);63 const forId = getAttr(tag, 'for');64 if (forId) labelForIds.set(forId, text);65 for (const control of match[0].matchAll(/<(input|select|textarea)\b[^>]*>/gi)) nestedLabels.push({ tag: control[0], text });66 }67
68 const controls = [];69 for (const match of html.matchAll(/<(input|select|textarea)\b[^>]*>/gi)) {70 const tag = match[0];71 const type = (getAttr(tag, 'type') || match[1]).toLowerCase();72 if (match[1].toLowerCase() === 'input' && ['hidden', 'submit', 'button', 'reset', 'image'].includes(type)) continue;73 const id = getAttr(tag, 'id');74 const ariaLabel = getAttr(tag, 'aria-label');75 const ariaLabelledBy = getAttr(tag, 'aria-labelledby');76 const title = getAttr(tag, 'title');77 const placeholder = getAttr(tag, 'placeholder');78 const labelText = (id && labelForIds.get(id)) || nestedLabels.find((item) => item.tag === tag)?.text || null;79 const accessibleName = labelText || ariaLabel || ariaLabelledBy || title || null;80 controls.push({81 tag: match[1].toLowerCase(),82 type,83 id: id || null,84 name: getAttr(tag, 'name') || null,85 hasLabel: Boolean(labelText),86 hasAriaLabel: Boolean(ariaLabel || ariaLabelledBy),87 hasTitle: Boolean(title),88 placeholder: placeholder || null,89 accessibleName,90 ok: Boolean(accessibleName),91 });92 }93
94 const missing = controls.filter((control) => !control.ok);95 return {96 controlCount: controls.length,97 labeledCount: controls.length - missing.length,98 missingLabelCount: missing.length,99 labelCoveragePercent: controls.length ? Math.round(((controls.length - missing.length) / controls.length) * 100) : 100,100 controls: controls.slice(0, maxControls),101 missingControls: missing.slice(0, maxControls),102 };103}104
105function scoreLabels({ parsed, status, error }) {106 const issues = [];107 const recommendations = [];108 let score = 100;109
110 if (error) return { score: 0, grade: 'F', issues: [error], recommendations: ['Verify the URL is public, reachable, and returns HTML.'] };111 if (!status || status >= 400) {112 score -= 40;113 issues.push(`HTTP status is ${status || 'unknown'}`);114 recommendations.push('Audit a live 2xx HTML page.');115 }116 if (parsed.controlCount === 0) {117 issues.push('No form controls found');118 recommendations.push('No action needed if the page has no forms.');119 }120 if (parsed.missingLabelCount > 0) {121 score -= Math.min(80, parsed.missingLabelCount * 20);122 issues.push(`${parsed.missingLabelCount} form control(s) lack an accessible name`);123 recommendations.push('Add visible label elements linked with for/id, or use aria-label for compact controls.');124 }125
126 const bounded = Math.max(0, score);127 const grade = bounded >= 90 ? 'A' : bounded >= 75 ? 'B' : bounded >= 60 ? 'C' : bounded >= 45 ? 'D' : 'F';128 return { score: bounded, grade, issues: [...new Set(issues)], recommendations: [...new Set(recommendations)] };129}130
131async function fetchHtml(url, timeoutSeconds) {132 await normalizeAndValidateUrl(url.href);133 const controller = new AbortController();134 const timeout = setTimeout(() => controller.abort(), timeoutSeconds * 1000);135 try {136 const response = await fetch(url, { redirect: 'manual', signal: controller.signal, headers: { 'user-agent': USER_AGENT, accept: 'text/html,*/*;q=0.1' } });137 const location = response.headers.get('location');138 if (location && response.status >= 300 && response.status < 400) {139 const next = new URL(location, url.href);140 await normalizeAndValidateUrl(next.href);141 return fetchHtml(next, timeoutSeconds);142 }143 return { status: response.status, finalUrl: url.href, contentType: response.headers.get('content-type') || '', body: (await response.text()).slice(0, MAX_BODY_BYTES) };144 } finally {145 clearTimeout(timeout);146 }147}148
149export async function auditFormLabels(input) {150 const startUrl = await normalizeAndValidateUrl(input.startUrl);151 const timeoutSeconds = clampInteger(input.timeoutSeconds, 10, 3, 30);152 const maxControls = clampInteger(input.maxControls, 50, 1, 200);153 const checkedAt = new Date().toISOString();154 let fetched = null;155 let error = null;156
157 try { fetched = await fetchHtml(startUrl, timeoutSeconds); } catch (caught) { error = caught.message; }158
159 const parsed = parseFormLabels(fetched?.body || '', maxControls);160 const scored = scoreLabels({ parsed, status: fetched?.status, error });161 return {162 inputUrl: input.startUrl,163 normalizedInputUrl: startUrl.href,164 finalUrl: fetched?.finalUrl || startUrl.href,165 status: fetched?.status || null,166 ok: !error && fetched?.status >= 200 && fetched?.status < 400 && parsed.missingLabelCount === 0,167 checkedAt,168 ...parsed,169 score: scored.score,170 grade: scored.grade,171 issues: scored.issues,172 recommendations: scored.recommendations,173 error,174 };175}176
177const isExecutedDirectly = process.argv[1] && fileURLToPath(import.meta.url) === process.argv[1];178
179if (process.env.NODE_ENV !== 'test' && isExecutedDirectly) {180 await Actor.init();181 try {182 const input = await Actor.getInput();183 const result = await auditFormLabels(input || {});184 await Actor.pushData(result);185 await Actor.setValue('OUTPUT', result);186 Actor.log.info('Form label audit complete', { finalUrl: result.finalUrl, score: result.score, grade: result.grade });187 } finally {188 await Actor.exit();189 }190}1import assert from 'node:assert/strict';2import { test } from 'node:test';3import { auditFormLabels, normalizeAndValidateUrl, parseFormLabels } from '../src/main.js';4
5test('blocks non-public and credentialed targets', async () => {6 await assert.rejects(() => normalizeAndValidateUrl('ftp://example.com'), /Only HTTP/);7 await assert.rejects(() => normalizeAndValidateUrl('https://user:pass@example.com'), /credentials/);8 await assert.rejects(() => normalizeAndValidateUrl('http://127.0.0.1'), /Private IPv4/);9});10
11test('parses visible, nested, and aria labels', () => {12 const parsed = parseFormLabels(`13 <form>14 <label for="email">Email address</label><input id="email" name="email">15 <label>Search <input name="q"></label>16 <select aria-label="Country"><option>US</option></select>17 <textarea name="message"></textarea>18 <input type="hidden" name="token">19 </form>20 `);21 assert.equal(parsed.controlCount, 4);22 assert.equal(parsed.labeledCount, 3);23 assert.equal(parsed.missingLabelCount, 1);24 assert.equal(parsed.labelCoveragePercent, 75);25 assert.equal(parsed.missingControls[0].tag, 'textarea');26});27
28test('audits missing labels', async () => {29 const originalFetch = globalThis.fetch;30 globalThis.fetch = async () => new Response('<form><input id="email"><button>Go</button></form>', { status: 200, headers: { 'content-type': 'text/html' } });31
32 try {33 const result = await auditFormLabels({ startUrl: 'https://example.com/contact' });34 assert.equal(result.controlCount, 1);35 assert.equal(result.missingLabelCount, 1);36 assert.equal(result.ok, false);37 assert.match(result.issues.join(' '), /lack an accessible name/);38 assert.equal(result.grade, 'B');39 } finally {40 globalThis.fetch = originalFetch;41 }42});