Borrowed from a chrome web extension at https://github.com/mikan/ec-url-cleaner

sanitize_url.mjs

#!/usr/bin/env node

`use strict`;

import {argv} from "node:process";
import {URL} from "node:url";
//const url = require('node:url');

// [SOURCE](https://github.com/mikan/ec-url-cleaner)

/* node:coverage disable */
/*
if (this.chrome) {
  chrome.runtime.onMessage.addListener(() => {
    const result = clean(window.location.href);
    document.getElementsByTagName("body")[0].focus();
    navigator.clipboard.writeText(result).then(() => {
      console.log("ec-url-cleaner: " + result);
    });
  });
}
*/
/* node:coverage enable */

/**
 * Remove noisy params from given URL.
 *
 * @param url {string} URL as string
 * @return string
 */
function clean(url) {
  const parser = new URL(url);
  let path = parser.pathname;
  const tokens = path.split("/");

  // only query params are deleted for non-amazon sites
  if (!parser.host.startsWith("www.amazon.")) {
    return parser.origin + path;
  }

  // delete ref
  if (tokens[tokens.length - 1].startsWith("ref=")) {
    tokens.splice(tokens.length - 1, 1);
    path = tokens.join("/");
  }

  // category
  if (tokens.indexOf("b") > 0) {
    return parser.origin + "/b/?node=" + parser.searchParams.get("node");
  } else if (tokens.indexOf("s") > 0) {
    return (
      parser.origin +
      "/s/?bbn=" +
      parser.searchParams.get("bbn") +
      "&rh=" +
      parser.searchParams.get("rh")
    );
  } else if (path.startsWith("/gp/browse.html")) {
    return parser.origin + "/gp/browse.html?node=" + parser.searchParams.get("node");
  }

  // products
  if (tokens.indexOf("dp") > 1 && tokens[2] === "dp") {
    path = "/dp/" + tokens[3] + "/";
  } else if (path.startsWith("/gp/product/")) {
    path = "/dp/" + tokens[3] + "/";
  } else if (path.startsWith("/gp/video/detail/")) {
    path = "/dp/" + tokens[4] + "/";
  }
  return parser.origin + path;
}

try {
  module.exports = { clean };
} catch (e) {
  // module used by unit testing
}

/*
  usage

./clean.mjs <INPUT_URL>
...where INPUT_URL must be shell escaped when passing said URL string inside a shell context

input -> "https://www.amazon.com/Document-Portable-Auto-Feed-Rechargeable-PDSDK-ST470PU-VP/dp/B00J2FB9EA/ref=sr_1_4?dib=eyJ2IjoiMSJ9.KCG4iplZNLIw3RqLj-0-VsxZfQWVkJBqH2B1EgdNDXG7j4d8GCXD4PhKZsFYsLgP-kayvBzWgfjoxPKNNeofS6-ILUxTIr7R1cpu-yvY4Jcms1fbs9IrIoHiSpebqM1eTNbblvN1AUKnfI98ThTrPDu9G3WqHLI5uEjOKBupanv7y3Iwo8Qx_umNJNsHDxHIfdmKVZe7TQIBFDvNgu8jSUZ95wyAm19kHwnKkvCSrJ8.L3sDYuaadVvssV5ZfpUScO5MEgSBkiXQSmCHsd6FOPM&dib_tag=se&keywords=vupoint+magic+scanner&qid=1744304364&sr=8-4"
output -> https://www.amazon.com/dp/B00J2FB9EA/

input -> 'https://www.amazon.com/Document-Portable-Auto-Feed-Rechargeable-PDSDK-ST470PU-VP/dp/B00J2FB9EA/ref=sr_1_4?dib=eyJ2IjoiMSJ9.KCG4iplZNLIw3RqLj-0-VsxZfQWVkJBqH2B1EgdNDXG7j4d8GCXD4PhKZsFYsLgP-kayvBzWgfjoxPKNNeofS6-ILUxTIr7R1cpu-yvY4Jcms1fbs9IrIoHiSpebqM1eTNbblvN1AUKnfI98ThTrPDu9G3WqHLI5uEjOKBupanv7y3Iwo8Qx_umNJNsHDxHIfdmKVZe7TQIBFDvNgu8jSUZ95wyAm19kHwnKkvCSrJ8.L3sDYuaadVvssV5ZfpUScO5MEgSBkiXQSmCHsd6FOPM&dib_tag=se&keywords=vupoint+magic+scanner&qid=1744304364&sr=8-4'
output -> https://www.amazon.com/dp/B00J2FB9EA/

*/

import { strict as assert } from 'node:assert';
{
  const testUrl = "https://www.amazon.com/";
  const expectedUrl = "https://www.amazon.com/";

  const res = clean(testUrl);
  assert.deepEqual(res, expectedUrl);
}

let res;
// print process.argv
argv.forEach((arg, idx) => {
  // console.log(`${idx}: ${arg}`);
  if(arg && arg != null && arg != "") {
    const url = arg;
    let sanitizedUrl = url.replaceAll(`'`, ``).replaceAll(`"`, ``);
    // FIXME(JEFF): failure case   
    // sanitizedUrl = new URL(url);

    // ok
    sanitizedUrl = URL.parse(url);
    res = sanitizedUrl;
    console.log(res);
  }
});

// print process.argv
argv.forEach((arg, idx) => {
  // console.log(`${idx}: ${arg}`);
  if(arg && arg != null && arg != "") {
    const url = arg;
    let sanitizedUrl = url.replaceAll(`'`, ``).replaceAll(`"`, ``);
    // FIXME(JEFF): failure case    
    // sanitizedUrl = new URL(url);
    sanitizedUrl = URL.parse(url);
    // error
    res = clean(sanitizedUrl);
    console.log(res);
  }
});