Htykuut

I'm trying to get some images from an Amazon product page, I was able to extract all the images from the page in a single string but my knowledge of regular expressions is not that good for being able to separate it different URL's.

My goal is to get an array/list that contains all of the images that have "hiRes", for example, this one.

https://images-na.ssl-images-amazon.com/images/I/715ljjcwtbL.SL1500.jpg

Here is the complete string

All the images are under the 'colorImage' subdivision.

P.when('A').register("ImageBlockATF", function(A){



    var data = {



                'colorImages': { 'initial': [{"hiRes":"https://images-na.ssl-images-amazon.com/images/I/715ljjcwtbL._SL1500_.jpg","thumb":"https://images-na.ssl-images-amazon.com/images/I/41vopqQJxiL._SS40_.jpg","large":"https://images-na.ssl-images-amazon.com/images/I/41vopqQJxiL.jpg","main":{"https://images-na.ssl-images-amazon.com/images/I/715ljjcwtbL._SX355_.jpg":[219,355],"https://images-na.ssl-images-amazon.com/images/I/715ljjcwtbL._SX450_.jpg":[278,450],"https://images-na.ssl-images-amazon.com/images/I/715ljjcwtbL._SX425_.jpg":[263,425],"https://images-na.ssl-images-amazon.com/images/I/715ljjcwtbL._SX466_.jpg":[288,466],"https://images-na.ssl-images-amazon.com/images/I/715ljjcwtbL._SX522_.jpg":[323,522],"https://images-na.ssl-images-amazon.com/images/I/715ljjcwtbL._SX569_.jpg":[352,569],"https://images-na.ssl-images-amazon.com/images/I/715ljjcwtbL._SX679_.jpg":[420,679]},"variant":"MAIN","lowRes":null},{"hiRes":"https://images-na.ssl-images-amazon.com/images/I/71wL0h3T8ZL._SL1500_.jpg","thumb":"https://images-na.ssl-images-amazon.com/images/I/41gksdhlW%2BL._SS40_.jpg","large":"https://images-na.ssl-images-amazon.com/images/I/41gksdhlW%2BL.jpg","main":{"https://images-na.ssl-images-amazon.com/images/I/71wL0h3T8ZL._SX355_.jpg":[215,355],"https://images-na.ssl-images-amazon.com/images/I/71wL0h3T8ZL._SX450_.jpg":[272,450],"https://images-na.ssl-images-amazon.com/images/I/71wL0h3T8ZL._SX425_.jpg":[257,425],"https://images-na.ssl-images-amazon.com/images/I/71wL0h3T8ZL._SX466_.jpg":[282,466],"https://images-na.ssl-images-amazon.com/images/I/71wL0h3T8ZL._SX522_.jpg":[315,522],"https://images-na.ssl-images-amazon.com/images/I/71wL0h3T8ZL._SX569_.jpg":[344,569],"https://images-na.ssl-images-amazon.com/images/I/71wL0h3T8ZL._SX679_.jpg":[410,679]},"variant":"PT01","lowRes":null},{"hiRes":"https://images-na.ssl-images-amazon.com/images/I/71R48178vZL._SL1500_.jpg","thumb":"https://images-na.ssl-images-amazon.com/images/I/41LaWXfiG5L._SS40_.jpg","large":"https://images-na.ssl-images-amazon.com/images/I/41LaWXfiG5L.jpg","main":{"https://images-na.ssl-images-amazon.com/images/I/71R48178vZL._SX355_.jpg":[217,355],"https://images-na.ssl-images-amazon.com/images/I/71R48178vZL._SX450_.jpg":[275,450],"https://images-na.ssl-images-amazon.com/images/I/71R48178vZL._SX425_.jpg":[260,425],"https://images-na.ssl-images-amazon.com/images/I/71R48178vZL._SX466_.jpg":[285,466],"https://images-na.ssl-images-amazon.com/images/I/71R48178vZL._SX522_.jpg":[319,522],"https://images-na.ssl-images-amazon.com/images/I/71R48178vZL._SX569_.jpg":[348,569],"https://images-na.ssl-images-amazon.com/images/I/71R48178vZL._SX679_.jpg":[415,679]},"variant":"PT02","lowRes":null},{"hiRes":"https://images-na.ssl-images-amazon.com/images/I/81BZF8-hNpL._SL1500_.jpg","thumb":"https://images-na.ssl-images-amazon.com/images/I/41f4nUmawdL._SS40_.jpg","large":"https://images-na.ssl-images-amazon.com/images/I/41f4nUmawdL.jpg","main":{"https://images-na.ssl-images-amazon.com/images/I/81BZF8-hNpL._SX355_.jpg":[250,355],"https://images-na.ssl-images-amazon.com/images/I/81BZF8-hNpL._SX450_.jpg":[316,450],"https://images-na.ssl-images-amazon.com/images/I/81BZF8-hNpL._SX425_.jpg":[299,425],"https://images-na.ssl-images-amazon.com/images/I/81BZF8-hNpL._SX466_.jpg":[328,466],"https://images-na.ssl-images-amazon.com/images/I/81BZF8-hNpL._SX522_.jpg":[367,522],"https://images-na.ssl-images-amazon.com/images/I/81BZF8-hNpL._SX569_.jpg":[400,569],"https://images-na.ssl-images-amazon.com/images/I/81BZF8-hNpL._SX679_.jpg":[478,679]},"variant":"PT03","lowRes":null},{"hiRes":"https://images-na.ssl-images-amazon.com/images/I/A1YDIIAWSWL._SL1500_.jpg","thumb":"https://images-na.ssl-images-amazon.com/images/I/51dH0wiIHjL._SS40_.jpg","large":"https://images-na.ssl-images-amazon.com/images/I/51dH0wiIHjL.jpg","main":{"https://images-na.ssl-images-amazon.com/images/I/A1YDIIAWSWL._SX355_.jpg":[266,355],"https://images-na.ssl-images-amazon.com/images/I/A1YDIIAWSWL._SX450_.jpg":[338,450],"https://images-na.ssl-images-amazon.com/images/I/A1YDIIAWSWL._SX425_.jpg":[319,425],"https://images-na.ssl-images-amazon.com/images/I/A1YDIIAWSWL._SX466_.jpg":[350,466],"https://images-na.ssl-images-amazon.com/images/I/A1YDIIAWSWL._SX522_.jpg":[392,522],"https://images-na.ssl-images-amazon.com/images/I/A1YDIIAWSWL._SX569_.jpg":[427,569],"https://images-na.ssl-images-amazon.com/images/I/A1YDIIAWSWL._SX679_.jpg":[509,679]},"variant":"PT04","lowRes":null},{"hiRes":"https://images-na.ssl-images-amazon.com/images/I/61qFqipGhCL._SL1500_.jpg","thumb":"https://images-na.ssl-images-amazon.com/images/I/31RVniM5g2L._SS40_.jpg","large":"https://images-na.ssl-images-amazon.com/images/I/31RVniM5g2L.jpg","main":{"https://images-na.ssl-images-amazon.com/images/I/61qFqipGhCL._SY355_.jpg":[355,355],"https://images-na.ssl-images-amazon.com/images/I/61qFqipGhCL._SY450_.jpg":[450,450],"https://images-na.ssl-images-amazon.com/images/I/61qFqipGhCL._SX425_.jpg":[425,425],"https://images-na.ssl-images-amazon.com/images/I/61qFqipGhCL._SX466_.jpg":[466,466],"https://images-na.ssl-images-amazon.com/images/I/61qFqipGhCL._SX522_.jpg":[522,522],"https://images-na.ssl-images-amazon.com/images/I/61qFqipGhCL._SX569_.jpg":[569,569],"https://images-na.ssl-images-amazon.com/images/I/61qFqipGhCL._SX679_.jpg":[679,679]},"variant":"PT05","lowRes":null},{"hiRes":"https://images-na.ssl-images-amazon.com/images/I/61C1UIQU7YL._SL1500_.jpg","thumb":"https://images-na.ssl-images-amazon.com/images/I/31593M2oY0L._SS40_.jpg","large":"https://images-na.ssl-images-amazon.com/images/I/31593M2oY0L.jpg","main":{"https://images-na.ssl-images-amazon.com/images/I/61C1UIQU7YL._SY355_.jpg":[355,355],"https://images-na.ssl-images-amazon.com/images/I/61C1UIQU7YL._SY450_.jpg":[450,450],"https://images-na.ssl-images-amazon.com/images/I/61C1UIQU7YL._SX425_.jpg":[425,425],"https://images-na.ssl-images-amazon.com/images/I/61C1UIQU7YL._SX466_.jpg":[466,466],"https://images-na.ssl-images-amazon.com/images/I/61C1UIQU7YL._SX522_.jpg":[522,522],"https://images-na.ssl-images-amazon.com/images/I/61C1UIQU7YL._SX569_.jpg":[569,569],"https://images-na.ssl-images-amazon.com/images/I/61C1UIQU7YL._SX679_.jpg":[679,679]},"variant":"PT06","lowRes":null},{"hiRes":"https://images-na.ssl-images-amazon.com/images/I/71QthPBNgLL._SL1500_.jpg","thumb":"https://images-na.ssl-images-amazon.com/images/I/41EChsg2DAL._SS40_.jpg","large":"https://images-na.ssl-images-amazon.com/images/I/41EChsg2DAL.jpg","main":{"https://images-na.ssl-images-amazon.com/images/I/71QthPBNgLL._SX355_.jpg":[251,355],"https://images-na.ssl-images-amazon.com/images/I/71QthPBNgLL._SX450_.jpg":[318,450],"https://images-na.ssl-images-amazon.com/images/I/71QthPBNgLL._SX425_.jpg":[301,425],"https://images-na.ssl-images-amazon.com/images/I/71QthPBNgLL._SX466_.jpg":[330,466],"https://images-na.ssl-images-amazon.com/images/I/71QthPBNgLL._SX522_.jpg":[369,522],"https://images-na.ssl-images-amazon.com/images/I/71QthPBNgLL._SX569_.jpg":[402,569],"https://images-na.ssl-images-amazon.com/images/I/71QthPBNgLL._SX679_.jpg":[480,679]},"variant":"PT07","lowRes":null},{"hiRes":"https://images-na.ssl-images-amazon.com/images/I/71xAVDnbRzL._SL1500_.jpg","thumb":"https://images-na.ssl-images-amazon.com/images/I/41LXguq9kAL._SS40_.jpg","large":"https://images-na.ssl-images-amazon.com/images/I/41LXguq9kAL.jpg","main":{"https://images-na.ssl-images-amazon.com/images/I/71xAVDnbRzL._SX355_.jpg":[250,355],"https://images-na.ssl-images-amazon.com/images/I/71xAVDnbRzL._SX450_.jpg":[316,450],"https://images-na.ssl-images-amazon.com/images/I/71xAVDnbRzL._SX425_.jpg":[299,425],"https://images-na.ssl-images-amazon.com/images/I/71xAVDnbRzL._SX466_.jpg":[328,466],"https://images-na.ssl-images-amazon.com/images/I/71xAVDnbRzL._SX522_.jpg":[367,522],"https://images-na.ssl-images-amazon.com/images/I/71xAVDnbRzL._SX569_.jpg":[400,569],"https://images-na.ssl-images-amazon.com/images/I/71xAVDnbRzL._SX679_.jpg":[477,679]},"variant":"PT08","lowRes":null}]},



                'colorToAsin': {'initial': {}},



                'holderRatio': 1.0,



                'holderMaxHeight': 700,



                'heroImage': {'initial': },



                'heroVideo': {'initial': },



                'spin360ColorData': {'initial': {}},



                'spin360ColorEnabled': {'initial': 0},



                'spin360ConfigEnabled': false,



                'spin360LazyLoadEnabled': false,



                'playVideoInImmersiveView':'false',



                'tabbedImmersiveViewTreatment':'T2',



                'totalVideoCount':'0',



                'videoIngressATFSlateThumbURL':'',



                'mediaTypeCount':'0',



                'atfEnhancedHoverOverlay' : true,



                'winningAsin': 'B07HGMDY4T',



                'weblabs' : {},



                'aibExp3Layout' : 1,



                'aibRuleName' : 'R17',



                'acEnabled' : false



                };



    A.trigger('P.AboveTheFold'); // trigger ATF event.



    return data;



});

If you want to stick with a regex solution, you could try a match like this: r'"hiRes":"(https.*?.jpg)"'

A quick explanation:

• Match any string that starts with "hiRes":"https and finishes with .jpg"
  


• Use a capturing group to get the actual URL (this assumes all URLs will start with https and end with .jpg
  

You could use the above regex with re.match or re.search to hopefully get what you are looking for. You should be able to extract you match groups out from here. See https://docs.python.org/3/library/re.html#match-objects id you need more details on this.