Wiki Table Scraper

wiki-table-scraper.js

(function() {
  const table = document.querySelector('.wikitable'); // Adjust the selector if needed
  if (!table) {
    console.log('Table not found.');
    return;
  }

  const rows = table.querySelectorAll('tr');
  const data = Array.from(rows).slice(1).map(row => {
    const cells = row.querySelectorAll('td');
    if (cells.length < 4) {
      return null; // Skip malformed rows
    }

    let title = cells[0].innerText.trim();
    title = title.replace(/\[.*?\]/g, ''); // Remove text in square brackets

    const artist = cells[1].innerText.trim();
    const year = parseInt(cells[2].innerText.trim(), 10);
    let progression = cells[3].innerText.trim();
    progression = progression.replace(/\(.*?\)/g, '').trim(); // Remove text in brackets  
    const recordedKey = cells[4].innerText.trim();

    const wikiUrl = cells[0].querySelector('a') ? `https://en.wikipedia.org${cells[0].querySelector('a').getAttribute('href')}` : '';
    let ultimateGuitarUrl = '';
    const refLink = cells[0].querySelector('a[rel="nofollow"]');

    if (refLink && refLink.href.includes('ultimate-guitar.com')) {
      ultimateGuitarUrl = refLink.href;
    }

    return {
      title,
      artist,
      year,
      progression,
      recordedKey,
      wikiUrl,
      ultimateGuitarUrl
    };
  }).filter(Boolean); // Remove nulls for any skipped rows

  console.log(JSON.stringify(data, null, 2));
})();

This can be run directly in the browser console and will generate a JSON string. I used it to quickly get the data from this page for a project I was working on. The script was mainly written by ChatGPT.