You cannot use a regex to extract JSON from an arbitrary text. Since regexes are usually not powerful enough to validate JSON (unless you can use PCRE) they also cannot match it - if they could, they could also validate JSON.

However, if you know that the top-level element of your JSON is always an object or array, you can go by the following approach:

• Find the first opening ({ or [) and last closing (} or ]) brace in your string.


• Try to parse that block of text (including the braces) using JSON.parse(). If it succeeded, finish and return the parsed result.


• Take the previous closing brace and try parsing that string. If it succeeds, you are done again.


• Repeat this until you got no brace or one that comes before the current opening brace.


• Find the first opening brace after the one from step 1. If you did not find any, the string did not contain a JSON object/array and you can stop.


• Go to step 2.

Here is a function that extracts a JSON object and returns the object and its position. If you really need top-level arrays, too, it should be to extend:

function extractJSON(str) {

    var firstOpen, firstClose, candidate;

    firstOpen = str.indexOf('{', firstOpen + 1);

    do {

        firstClose = str.lastIndexOf('}');

        console.log('firstOpen: ' + firstOpen, 'firstClose: ' + firstClose);

        if(firstClose <= firstOpen) {

            return null;

        }

        do {

            candidate = str.substring(firstOpen, firstClose + 1);

            console.log('candidate: ' + candidate);

            try {

                var res = JSON.parse(candidate);

                console.log('...found');

                return [res, firstOpen, firstClose + 1];

            }

            catch(e) {

                console.log('...failed');

            }

            firstClose = str.substr(0, firstClose).lastIndexOf('}');

        } while(firstClose > firstOpen);

        firstOpen = str.indexOf('{', firstOpen + 1);

    } while(firstOpen != -1);

}



var obj = {'foo': 'bar', xxx: '} me[ow]'};

var str = 'blah blah { not {json but here is json: ' + JSON.stringify(obj) + ' and here we have stuff that is } really } not ] json }} at all';

var result = extractJSON(str);

console.log('extracted object:', result[0]);

console.log('expected object :', obj);

console.log('did it work     ?', JSON.stringify(result[0]) == JSON.stringify(obj) ? 'yes!' : 'no');

console.log('surrounding str :', str.substr(0, result[1]) + '<JSON>' + str.substr(result[2]));

Demo (executed in the nodejs environment, but should work in a browser, too): https://paste.aeum.net/show/81/