scrapes spotify's top 10k song as csv from this page https://annas-archive.li/blog/spotify/spotify-top-10k-songs-table.html

song_scrape.js

(() => {
  // 1) Find the biggest table on the page (handles cases with multiple tables)
  const tables = [...document.querySelectorAll("table")];
  if (!tables.length) throw new Error("No <table> elements found.");

  const table = tables
    .map(t => ({ t, rows: t.querySelectorAll("tbody tr").length }))
    .sort((a, b) => b.rows - a.rows)[0].t;

  // 2) Extract header
  const headerCells =
    [...table.querySelectorAll("thead tr th")].map(th => th.innerText.trim()) ||
    [];

  // Fallback if <thead> is missing
  const firstRowCells = [...(table.querySelector("tbody tr")?.children ?? [])].map(
    td => td.innerText.trim()
  );
  const headers = headerCells.length ? headerCells : firstRowCells.map((_, i) => `col_${i+1}`);

  // 3) Extract body rows
  const rows = [...table.querySelectorAll("tbody tr")].map(tr =>
    [...tr.children].map(td => td.innerText.replace(/\s+/g, " ").trim())
  );

  // 4) CSV encode
  const esc = (v) => {
    const s = (v ?? "").toString();
    return /[",\n]/.test(s) ? `"${s.replace(/"/g, '""')}"` : s;
  };

  const csv = [
    headers.map(esc).join(","),
    ...rows.map(r => r.map(esc).join(",")),
  ].join("\n");

  // 5) Download
  const blob = new Blob([csv], { type: "text/csv;charset=utf-8" });
  const a = document.createElement("a");
  a.href = URL.createObjectURL(blob);
  a.download = "spotify-top-10k-songs-table.csv";
  document.body.appendChild(a);
  a.click();
  a.remove();

  return `Exported ${rows.length} rows to spotify-top-10k-songs-table.csv`;
})();