Collect improperly formatted person page URLs in Grove

scrape-staff-urls.js

const staffLinks = []

// Navigate across the site and expand "Read More" buttons on the site.
// This script will collect any improper author links it finds while you go along.
setInterval(() => {
  const bylines = document.querySelectorAll('[class*="Promo"][class*="-authorName"] .Link')

  for (let byline of bylines) {
    let href = byline.href
	
	if (href.endsWith('-1')                      // 1. Look for duplicate permalinks
      || href.split('-').length > 3              // 2. Look for partner organizations
	) {
	  staffLinks.push(href)
	  continue
	}

    if ( !href                                   // 3. Skip invalid links
      || href.startsWith('https://www.stlpr.org/people/')  // a. Skip links that already match our desired format
      || !href.startsWith('https://www.stlpr.org/')        // b. Skip partner station links
      || staffLinks.includes(href)                         // 4. Skip links we've already noted
    ) continue

    staffLinks.push(href)                        // 4. Catch all links that remain
  }
}, 1000)