ncklrs/claude-chrome-user-testing/link-checker

// Links to extract
const linkSelectors = [
  'a[href]',           // Standard links
  'area[href]',        // Image map links
  'link[href]',        // Stylesheet/resource links (optional)
];

async (page) => {
  const links = await page.evaluate(() => {
    const anchors = document.querySelectorAll('a[href]');
    return Array.from(anchors).map(a => ({
      href: a.href,
      text: a.textContent.trim().slice(0, 50),
      location: a.closest('[id]')?.id || 'page'
    }));
  });
  return links;
}

async (page) => {
  const response = await page.request.head(url, {
    timeout: 10000,
    ignoreHTTPSErrors: false
  });
  return {
    status: response.status(),
    headers: response.headers()
  };
}

const checkLink = async (url) => {
  const redirects = [];
  let currentUrl = url;
  let maxRedirects = 5;
  while (maxRedirects > 0) {
    const response = await fetch(currentUrl, {
      method: 'HEAD',
      redirect: 'manual'
    });
    if (response.status >= 300 && response.status < 400) {
      const location = response.headers.get('location');
      redirects.push({ from: currentUrl, to: location, status: response.status });
      currentUrl = new URL(location, currentUrl).href;
      maxRedirects--;
    } else {
      return { finalStatus: response.status, redirects };
    }
  }
  return { error: 'Too many redirects', redirects };
};

function crawl(startUrl, maxDepth):
  visited = Set()
  toVisit = [(startUrl, 0)]  // (url, depth)
  results = []
 
  while toVisit not empty:
    (url, depth) = toVisit.pop()
 
    if url in visited or depth > maxDepth:
      continue
 
    visited.add(url)
    pageLinks = extractLinks(url)
    results.extend(validateLinks(pageLinks))
 
    if depth < maxDepth:
      for link in pageLinks:
        if isInternal(link) and link not in visited:
          toVisit.append((link, depth + 1))
 
  return results

const linkReport = {
  url: 'https://example.com',
  checkedAt: '2025-01-06T14:30:00Z',
  summary: {
    total: 47,
    working: 44,
    broken: 2,
    redirects: 3,
    skipped: 1
  },
  broken: [
    { url: '/old-page', foundOn: '/', status: 404 },
  ],
  redirects: [
    { url: '/blog', redirectsTo: '/news', status: 301 },
  ],
  warnings: [
    { type: 'javascript-link', url: 'javascript:void(0)', foundOn: '/nav' },
  ],
  byPage: {
    '/': { checked: 15, broken: 1 },
    '/about': { checked: 8, broken: 1 },
  }
};

## Link Health
 
### Summary
-**Links Encountered**: 32
-**Working**: 30 (94%)
-**Broken**: 2 (6%)
 
### Broken Links Found During Testing
 
| Link | Encountered During | Status |
|------|-------------------|--------|
| /products/sale | Browsing products | 404 |
| /help/faq | Looking for help | 404 |
 
### Impact on User Experience
The persona encountered 2 broken links during their journey,
which could cause confusion and frustration.