Link Attribute Auditor
Pricing
Pay per usage
Audit one public page for anchor rel attributes, sponsored/nofollow/ugc usage, unsafe target blank links, and empty anchor text. Built for SEO, affiliate disclosure, and frontend QA workflows.
Pricing
Pay per usage
Rating
0.0
(0)
Developer
Sanskar Jaiswal
Maintained by CommunityActor stats
0
Bookmarked
2
Total users
1
Monthly active users
4 days ago
Last modified
Categories
Share
FROM apify/actor-node:22
COPY package*.json ./RUN npm --quiet set progress=false && npm install --omit=dev
COPY . ./
CMD ["npm", "start"]{ "name": "link-attribute-auditor", "version": "0.1.0", "description": "Apify Actor that audits public pages for link rel attributes, sponsored/nofollow usage, and unsafe target blank links.", "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": "link-attribute-auditor", "title": "Link Attribute Auditor", "description": "Audit one public page for link rel attributes, sponsored/nofollow usage, empty anchor text, and unsafe target blank links.", "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, "views": { "overview": { "title": "Link attribute audits", "transformation": { "fields": ["inputUrl", "normalizedInputUrl", "status", "ok", "linkCount", "externalLinkCount", "targetBlankCount", "unsafeTargetBlankCount", "nofollowCount", "sponsoredCount", "ugcCount", "score", "grade", "issues", "recommendations", "checkedAt"] }, "display": { "component": "table", "properties": { "inputUrl": { "label": "Input URL", "format": "link" }, "normalizedInputUrl": { "label": "Normalized URL", "format": "link" }, "status": { "label": "HTTP status" }, "ok": { "label": "OK" }, "linkCount": { "label": "Links" }, "externalLinkCount": { "label": "External links" }, "targetBlankCount": { "label": "Target blank" }, "unsafeTargetBlankCount": { "label": "Unsafe target blank" }, "nofollowCount": { "label": "Nofollow" }, "sponsoredCount": { "label": "Sponsored" }, "ugcCount": { "label": "UGC" }, "score": { "label": "Score" }, "grade": { "label": "Grade" }, "issues": { "label": "Issues" }, "recommendations": { "label": "Recommendations" }, "checkedAt": { "label": "Checked at", "format": "date" } } } } }, "fields": { "inputUrl": { "type": "string" }, "normalizedInputUrl": { "type": "string" }, "status": { "type": ["integer", "null"] }, "ok": { "type": "boolean" }, "linkCount": { "type": "integer" }, "externalLinkCount": { "type": "integer" }, "targetBlankCount": { "type": "integer" }, "unsafeTargetBlankCount": { "type": "integer" }, "nofollowCount": { "type": "integer" }, "sponsoredCount": { "type": "integer" }, "ugcCount": { "type": "integer" }, "score": { "type": "integer" }, "grade": { "type": "string" }, "issues": { "type": "array", "items": { "type": "string" } }, "recommendations": { "type": "array", "items": { "type": "string" } }, "checkedAt": { "type": "string" } }}{ "title": "Link Attribute Auditor Input", "description": "Enter one public HTTP or HTTPS page URL to audit anchor rel attributes for SEO, affiliate disclosure, and target blank safety.", "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" }, "maxLinks": { "title": "Maximum links", "type": "integer", "description": "Maximum number of HTTP/HTTPS links to parse from the page.", "editor": "number", "default": 200, "minimum": 1, "maximum": 1000 }, "timeoutSeconds": { "title": "Timeout seconds", "type": "integer", "description": "Request timeout for the page fetch.", "editor": "number", "default": 10, "minimum": 3, "maximum": 30 } }, "required": ["startUrl"]}{ "actorOutputSchemaVersion": 1, "title": "Link attribute audit output", "properties": { "results": { "type": "string", "title": "Link attribute audits", "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 = 'LinkAttributeAuditor/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 decodeEntities(text) {49 return String(text || '')50 .replace(/ /gi, ' ')51 .replace(/&/gi, '&')52 .replace(/</gi, '<')53 .replace(/>/gi, '>')54 .replace(/"/gi, '"')55 .replace(/'/g, "'")56 .replace(/\s+/g, ' ')57 .trim();58}59
60function stripTags(html) {61 return html.replace(/<script\b[\s\S]*?<\/script>/gi, ' ')62 .replace(/<style\b[\s\S]*?<\/style>/gi, ' ')63 .replace(/<[^>]+>/g, ' ')64 .replace(/\s+/g, ' ')65 .trim();66}67
68function attrsFromTag(tag) {69 const attrs = {};70 for (const match of tag.matchAll(/([a-zA-Z_:][-a-zA-Z0-9_:.]*)\s*=\s*("([^"]*)"|'([^']*)'|([^\s"'>]+))/g)) {71 attrs[match[1].toLowerCase()] = decodeEntities(match[3] ?? match[4] ?? match[5] ?? '');72 }73 return attrs;74}75
76export function parseAnchors(html, baseUrl, maxLinks = 200) {77 const anchors = [];78 const base = new URL(baseUrl);79 for (const match of html.matchAll(/<a\b[^>]*>[\s\S]*?<\/a>/gi)) {80 if (anchors.length >= maxLinks) break;81 const tag = match[0].match(/^<a\b[^>]*>/i)?.[0] || '';82 const attrs = attrsFromTag(tag);83 if (!attrs.href || attrs.href.startsWith('#') || /^javascript:/i.test(attrs.href) || /^mailto:/i.test(attrs.href) || /^tel:/i.test(attrs.href)) continue;84
85 let absoluteUrl = null;86 let host = null;87 try {88 const parsed = new URL(attrs.href, base.href);89 if (!['http:', 'https:'].includes(parsed.protocol)) continue;90 absoluteUrl = parsed.href;91 host = parsed.hostname;92 } catch {93 continue;94 }95
96 const relTokens = (attrs.rel || '').toLowerCase().split(/\s+/).filter(Boolean);97 const targetBlank = (attrs.target || '').toLowerCase() === '_blank';98 const external = host !== base.hostname;99 const text = decodeEntities(stripTags(match[0]));100 anchors.push({101 url: absoluteUrl,102 text: text.slice(0, 120),103 external,104 targetBlank,105 rel: relTokens,106 nofollow: relTokens.includes('nofollow'),107 sponsored: relTokens.includes('sponsored'),108 ugc: relTokens.includes('ugc'),109 noopener: relTokens.includes('noopener'),110 noreferrer: relTokens.includes('noreferrer'),111 issues: [],112 });113 }114 return anchors;115}116
117function scoreLinks({ links, status, error }) {118 const issues = [];119 const recommendations = [];120 let score = 100;121 if (error) return { score: 0, grade: 'F', issues: [error], recommendations: ['Verify the URL is public, reachable, and returns HTML.'] };122 if (!status || status >= 400) {123 score -= 40;124 issues.push(`HTTP status is ${status || 'unknown'}`);125 recommendations.push('Audit a live 2xx HTML page.');126 }127
128 const externalLinks = links.filter((l) => l.external);129 const blankLinks = links.filter((l) => l.targetBlank);130 const unsafeBlankLinks = blankLinks.filter((l) => !l.noopener && !l.noreferrer);131 const externalFollowLinks = externalLinks.filter((l) => !l.nofollow && !l.sponsored && !l.ugc);132 const sponsoredWithoutRel = externalLinks.filter((l) => /\b(sponsor|affiliate|partner|paid|ref=|utm_medium=affiliate)\b/i.test(`${l.text} ${l.url}`) && !l.sponsored);133 const emptyTextLinks = links.filter((l) => !l.text);134
135 for (const link of unsafeBlankLinks) link.issues.push('target_blank_without_noopener');136 for (const link of sponsoredWithoutRel) link.issues.push('likely_sponsored_without_rel_sponsored');137 for (const link of emptyTextLinks) link.issues.push('empty_anchor_text');138
139 if (unsafeBlankLinks.length) {140 score -= Math.min(30, unsafeBlankLinks.length * 8);141 issues.push(`target="_blank" links missing rel="noopener" or rel="noreferrer": ${unsafeBlankLinks.length}`);142 recommendations.push('Add rel="noopener" to links that open in a new tab.');143 }144 if (sponsoredWithoutRel.length) {145 score -= Math.min(25, sponsoredWithoutRel.length * 10);146 issues.push(`Likely sponsored or affiliate links missing rel="sponsored": ${sponsoredWithoutRel.length}`);147 recommendations.push('Mark paid, affiliate, or partner links with rel="sponsored".');148 }149 if (emptyTextLinks.length) {150 score -= Math.min(20, emptyTextLinks.length * 5);151 issues.push(`Links with empty anchor text: ${emptyTextLinks.length}`);152 recommendations.push('Use descriptive link text or an accessible label for image/icon links.');153 }154 if (externalLinks.length && externalFollowLinks.length === externalLinks.length) {155 score -= 10;156 issues.push('All external links are followed links');157 recommendations.push('Review external links and add nofollow, sponsored, or ugc where appropriate.');158 }159
160 const bounded = Math.max(0, score);161 const grade = bounded >= 90 ? 'A' : bounded >= 75 ? 'B' : bounded >= 60 ? 'C' : bounded >= 45 ? 'D' : 'F';162 return { score: bounded, grade, issues: [...new Set(issues)], recommendations: [...new Set(recommendations)] };163}164
165async function fetchHtml(url, timeoutSeconds) {166 await normalizeAndValidateUrl(url.href);167 const controller = new AbortController();168 const timeout = setTimeout(() => controller.abort(), timeoutSeconds * 1000);169 try {170 const response = await fetch(url, { redirect: 'manual', signal: controller.signal, headers: { 'user-agent': USER_AGENT, accept: 'text/html,*/*;q=0.1' } });171 const location = response.headers.get('location');172 if (location && response.status >= 300 && response.status < 400) {173 const next = new URL(location, url.href);174 await normalizeAndValidateUrl(next.href);175 return fetchHtml(next, timeoutSeconds);176 }177 return { status: response.status, finalUrl: url.href, contentType: response.headers.get('content-type') || '', body: (await response.text()).slice(0, MAX_BODY_BYTES) };178 } finally {179 clearTimeout(timeout);180 }181}182
183export async function auditLinkAttributes(input) {184 const startUrl = await normalizeAndValidateUrl(input.startUrl);185 const timeoutSeconds = clampInteger(input.timeoutSeconds, 10, 3, 30);186 const maxLinks = clampInteger(input.maxLinks, 200, 1, 1000);187 const checkedAt = new Date().toISOString();188 let fetched = null;189 let error = null;190
191 try { fetched = await fetchHtml(startUrl, timeoutSeconds); } catch (caught) { error = caught.message; }192
193 const finalUrl = fetched?.finalUrl || startUrl.href;194 const links = parseAnchors(fetched?.body || '', finalUrl, maxLinks);195 const scored = scoreLinks({ links, status: fetched?.status, error });196 const externalLinks = links.filter((l) => l.external);197 const targetBlankLinks = links.filter((l) => l.targetBlank);198 const unsafeTargetBlankLinks = targetBlankLinks.filter((l) => !l.noopener && !l.noreferrer);199 const sponsoredLinks = links.filter((l) => l.sponsored);200 const nofollowLinks = links.filter((l) => l.nofollow);201 const ugcLinks = links.filter((l) => l.ugc);202 const linkSamples = links.filter((l) => l.issues.length).slice(0, 50);203
204 return {205 inputUrl: input.startUrl,206 normalizedInputUrl: startUrl.href,207 finalUrl,208 status: fetched?.status || null,209 ok: !error && fetched?.status >= 200 && fetched?.status < 400,210 checkedAt,211 linkCount: links.length,212 externalLinkCount: externalLinks.length,213 targetBlankCount: targetBlankLinks.length,214 unsafeTargetBlankCount: unsafeTargetBlankLinks.length,215 nofollowCount: nofollowLinks.length,216 sponsoredCount: sponsoredLinks.length,217 ugcCount: ugcLinks.length,218 linkSamples,219 score: scored.score,220 grade: scored.grade,221 issues: scored.issues,222 recommendations: scored.recommendations,223 error,224 };225}226
227const isExecutedDirectly = process.argv[1] && fileURLToPath(import.meta.url) === process.argv[1];228
229if (process.env.NODE_ENV !== 'test' && isExecutedDirectly) {230 await Actor.init();231 try {232 const input = await Actor.getInput();233 const result = await auditLinkAttributes(input || {});234 await Actor.pushData(result);235 await Actor.setValue('OUTPUT', result);236 Actor.log.info('Link attribute audit complete', { finalUrl: result.finalUrl, score: result.score, grade: result.grade });237 } finally {238 await Actor.exit();239 }240}1import assert from 'node:assert/strict';2import { test } from 'node:test';3import { auditLinkAttributes, normalizeAndValidateUrl, parseAnchors } 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 link attributes and filters non-http links', () => {12 const links = parseAnchors(`13 <a href="/docs" target="_blank">Docs</a>14 <a href="https://partner.example/deal?utm_medium=affiliate" rel="nofollow">Partner</a>15 <a href="mailto:test@example.com">Email</a>16 `, 'https://example.com/page', 10);17
18 assert.equal(links.length, 2);19 assert.equal(links[0].url, 'https://example.com/docs');20 assert.equal(links[0].targetBlank, true);21 assert.equal(links[0].external, false);22 assert.equal(links[1].external, true);23 assert.equal(links[1].nofollow, true);24});25
26test('audits unsafe target blank and likely sponsored links', async () => {27 const originalFetch = globalThis.fetch;28 globalThis.fetch = async () => new Response(`29 <html><body>30 <a href="https://example.org" target="_blank">External</a>31 <a href="https://shop.example/deal?utm_medium=affiliate">Affiliate deal</a>32 <a href="/empty"><span></span></a>33 <a href="/safe" target="_blank" rel="noopener">Safe</a>34 </body></html>35 `, { status: 200, headers: { 'content-type': 'text/html' } });36
37 try {38 const result = await auditLinkAttributes({ startUrl: 'https://example.com/page' });39 assert.equal(result.linkCount, 4);40 assert.equal(result.externalLinkCount, 2);41 assert.equal(result.unsafeTargetBlankCount, 1);42 assert.equal(result.targetBlankCount, 2);43 assert.match(result.issues.join(' '), /target="_blank"/);44 assert.match(result.issues.join(' '), /sponsored/);45 assert.match(result.issues.join(' '), /empty anchor text/);46 assert.equal(result.linkSamples.length, 3);47 } finally {48 globalThis.fetch = originalFetch;49 }50});