Last active
September 10, 2024 14:52
-
-
Save stephanieleary/b6753e1b7ac4eb3294cd16b0bb1fef72 to your computer and use it in GitHub Desktop.
regular expression to find ISBNs in text, URLs or microdata
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| function matchISBNs(html) { | |
| // flatten string and find ISBN-looking things | |
| let isbns = html.replaceAll("\n", ' ').match("/(?=([0-9]|X|-){10,20})(97(8|9))?-?(0|1|8)([0-9]|-){8,14}([0-9]|X)/gi"); | |
| if (!isbns || !isbns.length) | |
| return; | |
| // remove dashes | |
| isbns = isbns.map((value) => value.replaceAll('-', '')); | |
| // throw out anything that isn't 10 or 13 characters | |
| isbns = isbns.filter((value, index, array) => (value.length == 10 || value.length == 13)); | |
| // de-dupe | |
| isbns = isbns.filter((value, index, array) => array.indexOf(value) === index); | |
| return isbns; | |
| } | |
| let text = document.body.innerText; | |
| let html = document.body.innerHTML; | |
| //let html = document.getElementById('isbns').value; | |
| // look in URLs | |
| let hrefs = html.match(/href=(["'])(.*?)\1/gi); | |
| // also in microdata | |
| let itemids = html.match(/itemid=(["'])(.*?)\1/gi); | |
| // combine URLs, microdata, and visible content | |
| text += ' ' + hrefs + ' ' + itemids; | |
| let isbns = matchISBNs(text); | |
| // result: array of ISBNs without dashes | |
| // demo: https://codepen.io/stephanieleary/full/XWLPWww | |
| // bookmarklet: https://codepen.io/stephanieleary/full/bGPxGrW |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment