Remove duplicate movies

remove-movie-dupes.js

// This is messy as all heck. Sorry! But it works.
// Warning: if you have the same movie from different years (e.g. The Italian Job from 1969 and 2003), one will be deleted
// incorrectly. This mainly catches movies that have different filenames but are still duplicates.
const glob = require("glob");
const fs = require("fs");

const getDirectories = function (src, callback) {
  glob(src + "/**/*", callback);
};

function removeDupe(a, b) {
  let rem = a.size > b.size ? b : a;
  // let save = a.size > b.size ? a : b;
  // console.log("Would delete", rem.path, rem.size, "OVER", save.path, save.size);
  try {
    return fs.unlinkSync(rem.path);
  } catch (e) {
    console.error("Could not delete", rem, e);
  }
}

let paths = [];
if (require.main === module) {
  getDirectories("/data/Movies", async function (err, files) {
    if (err) {
      console.log("Error", err);
      return;
    }
    for (let file of files) {
      if (file.slice(-4) === ".mp4" || file.slice(-4) === ".mkv") {
        let filename = file.split("/").slice(-1)[0];
        if (filename) {
          filename = filename
            .slice(0, -4)
            .replace(" ", "")
            .replace("(", "")
            .replace(")", "")
            .replace("'", "")
            .replace("_", "")
            .replace("-", "")
            .replace(/\d{4}/g, "")
            .replace(/\./g, "")
            .trim()
            .toLowerCase();
          const stats = fs.statSync(file);
          paths.push({ filename, path: file, size: stats.size });
        }
      }
    }
    const sorted = paths.sort();
    for (let i = 0; i < sorted.length - 1; i++) {
      if (sorted[i].filename === sorted[i + 1].filename) {
        await removeDupe(sorted[i], sorted[i + 1]);
      }
    }
  });
}

Might also think about the approach of using 'md5sum', 'sha256' or other CRC checksum tools to compare files.
(md5sum works best upto 2G, sha256/sha512 works best with bigger files)