How to grab Amazon ASIN number using regex in Javascript?

Question

www.amazon.in/gp/slredirect/picassoRedirect.html/ref=pa_sp_atf_next_aps_sr_pg2_1?ie=UTF8&adId=A00689312QGP01ZB3KM3N&url=%2FLifebuoy-Alcohol-Based-Protection-Sanitizer%2Fdp%2FB0866JTZXN%2Fref%3Dsr_1_49_sspa%3Fdchild%3D1%26keywords%3DHand%2Bsanitizer%26qid%3D1622721840%26smid%3DAT95IG9ONZD7S%26sr%3D8-49-spons%26psc%3D1&qualifier=1622721840&id=1588289180417395&widgetName=sp_atf_next

ASIN = B0866JTZXN

How do i get the asin number?

please make an attempt yourself before asking for others to do the work — depperm, Jun 03 '21 at 13:16
@AdmirMisini You need `%2F([A-Z0-9]+)%2Fref` to narrow it down better since there are more than two `%2F` — MonkeyZeus, Jun 03 '21 at 13:43
@DivyanshuSah https://stackoverflow.com/questions/432493/how-do-you-access-the-matched-groups-in-a-javascript-regular-expression — Admir Misini, Jun 03 '21 at 13:44

VLAZ · Answer 1 · 2021-06-03T14:14:20.230

What you have is structured data in the form of a URL. You can use plain JavaScript without regex to parse and traverse it:

Parse as search parameters.
Get the parameter url.
Split the result into parts.
Get the part after /dp/.

function extractASIN(url) {
  const searchParams = new URLSearchParams(url);
  const queryURL = searchParams.get("url");
  const parts = queryURL.split("/");
  const precedingIndex = parts.indexOf("dp");

  return parts[precedingIndex+1];
}

test("www.amazon.in/gp/slredirect/picassoRedirect.html/ref=pa_sp_atf_next_aps_sr_pg2_1?ie=UTF8&adId=A00689312QGP01ZB3KM3N&url=%2FLifebuoy-Alcohol-Based-Protection-Sanitizer%2Fdp%2FB0866JTZXN%2Fref%3Dsr_1_49_sspa%3Fdchild%3D1%26keywords%3DHand%2Bsanitizer%26qid%3D1622721840%26smid%3DAT95IG9ONZD7S%26sr%3D8-49-spons%26psc%3D1&qualifier=1622721840&id=1588289180417395&widgetName=sp_atf_next");

test("www.amazon.in/gp/slredirect/picassoRedirect.html/ref=pa_sp_atf_aps_sr_pg1_1?ie=UTF8&adId=A027625218II94KXW8EWJ&url=%2FDettol-Sanitizer-Regular-200-Pack%2Fdp%2FB076ZH5ZJL%2Fref%3Dsr_1_2_sspa%3Fdchild%3D1%26keywords%3DHand%2Bsanitizer%26qid%3D1622720663%26sr%3D8-2-spons%26psc%3D1&qualifier=1622720663&id=6679001242725581&widgetName=sp_atf");

function test(str) {
  const result = extractASIN(str);
  console.log(`ASIN = ${result}`);
}

Alternatively, you can use basic string manipulation

Get where dp%2F is.
Where the next %2F is.
Extract the string between the two.

function extractASIN(url) {
  const startToken = "dp%2F";
  const endToken = "%2F";
  
  const start = url.indexOf(startToken) + startToken.length;
  const end = url.indexOf(endToken, start);
  
  return url.slice(start, end);
}

test("www.amazon.in/gp/slredirect/picassoRedirect.html/ref=pa_sp_atf_next_aps_sr_pg2_1?ie=UTF8&adId=A00689312QGP01ZB3KM3N&url=%2FLifebuoy-Alcohol-Based-Protection-Sanitizer%2Fdp%2FB0866JTZXN%2Fref%3Dsr_1_49_sspa%3Fdchild%3D1%26keywords%3DHand%2Bsanitizer%26qid%3D1622721840%26smid%3DAT95IG9ONZD7S%26sr%3D8-49-spons%26psc%3D1&qualifier=1622721840&id=1588289180417395&widgetName=sp_atf_next");

test("www.amazon.in/gp/slredirect/picassoRedirect.html/ref=pa_sp_atf_aps_sr_pg1_1?ie=UTF8&adId=A027625218II94KXW8EWJ&url=%2FDettol-Sanitizer-Regular-200-Pack%2Fdp%2FB076ZH5ZJL%2Fref%3Dsr_1_2_sspa%3Fdchild%3D1%26keywords%3DHand%2Bsanitizer%26qid%3D1622720663%26sr%3D8-2-spons%26psc%3D1&qualifier=1622720663&id=6679001242725581&widgetName=sp_atf");

function test(str) {
  const result = extractASIN(str);
  console.log(`ASIN = ${result}`);
}

If you really want a regex, you can use /dp%2F(\w*)%2F/ to capture the value between dp%2F and %2F then return it:

function extractASIN(url) {
  return url.match(/dp%2F(\w*)%2F/)[1];
}

test("www.amazon.in/gp/slredirect/picassoRedirect.html/ref=pa_sp_atf_next_aps_sr_pg2_1?ie=UTF8&adId=A00689312QGP01ZB3KM3N&url=%2FLifebuoy-Alcohol-Based-Protection-Sanitizer%2Fdp%2FB0866JTZXN%2Fref%3Dsr_1_49_sspa%3Fdchild%3D1%26keywords%3DHand%2Bsanitizer%26qid%3D1622721840%26smid%3DAT95IG9ONZD7S%26sr%3D8-49-spons%26psc%3D1&qualifier=1622721840&id=1588289180417395&widgetName=sp_atf_next");

test("www.amazon.in/gp/slredirect/picassoRedirect.html/ref=pa_sp_atf_aps_sr_pg1_1?ie=UTF8&adId=A027625218II94KXW8EWJ&url=%2FDettol-Sanitizer-Regular-200-Pack%2Fdp%2FB076ZH5ZJL%2Fref%3Dsr_1_2_sspa%3Fdchild%3D1%26keywords%3DHand%2Bsanitizer%26qid%3D1622720663%26sr%3D8-2-spons%26psc%3D1&qualifier=1622720663&id=6679001242725581&widgetName=sp_atf");

function test(str) {
  const result = extractASIN(str);
  console.log(`ASIN = ${result}`);
}

How to grab Amazon ASIN number using regex in Javascript?

1 Answers1