I'm extracting certain keys in several JSON files and then converting it to a CSV in Python. I'm able to define a key list when I run my code and get the information I need.
However, there are certain sub-keys that I want to ignore from the JSON file. For example, if we look at the following snippet:
[
{
"callId": "abc123",
"errorCode": 0,
"apiVersion": 2,
"statusCode": 200,
"statusReason": "OK",
"time": "2020-12-14T12:00:32.744Z",
"registeredTimestamp": 1417731582000,
"UID": "_guid_abc123==",
"created": "2014-12-04T22:19:42.894Z",
"createdTimestamp": 1417731582000,
"data": {},
"preferences": {},
"emails": {
"verified": [],
"unverified": []
},
"identities": [
{
"provider": "facebook",
"providerUID": "123",
"allowsLogin": true,
"isLoginIdentity": true,
"isExpiredSession": true,
"lastUpdated": "2014-12-04T22:26:37.002Z",
"lastUpdatedTimestamp": 1417731997002,
"oldestDataUpdated": "2014-12-04T22:26:37.002Z",
"oldestDataUpdatedTimestamp": 1417731997002,
"firstName": "John",
"lastName": "Doe",
"nickname": "John Doe",
"profileURL": "https://www.facebook.com/John.Doe",
"age": 50,
"birthDay": 31,
"birthMonth": 12,
"birthYear": 1969,
"city": "City, State",
"education": [
{
"school": "High School Name",
"schoolType": "High School",
"degree": null,
"startYear": 0,
"fieldOfStudy": null,
"endYear": 0
}
],
"educationLevel": "High School",
"favorites": {
"music": [
{
"name": "Music 1",
"id": "123",
"category": "Musician/band"
},
{
"name": "Music 2",
"id": "123",
"category": "Musician/band"
}
],
"movies": [
{
"name": "Movie 1",
"id": "123",
"category": "Movie"
},
{
"name": "Movie 2",
"id": "123",
"category": "Movie"
}
],
"television": [
{
"name": "TV 1",
"id": "123",
"category": "Tv show"
}
]
},
"followersCount": 0,
"gender": "m",
"hometown": "City, State",
"languages": "English",
"likes": [
{
"name": "Like 1",
"id": "123",
"time": "2014-10-31T23:52:53.0000000Z",
"category": "TV",
"timestamp": "1414799573"
},
{
"name": "Like 2",
"id": "123",
"time": "2014-09-16T08:11:35.0000000Z",
"category": "Music",
"timestamp": "1410855095"
}
],
"locale": "en_US",
"name": "John Doe",
"photoURL": "https://graph.facebook.com/123/picture?type=large",
"timezone": "-8",
"thumbnailURL": "https://graph.facebook.com/123/picture?type=square",
"username": "john.doe",
"verified": "true",
"work": [
{
"companyID": null,
"isCurrent": null,
"endDate": null,
"company": "Company Name",
"industry": null,
"title": "Company Title",
"companySize": null,
"startDate": "2010-12-31T00:00:00"
}
]
}
],
"isActive": true,
"isLockedOut": false,
"isRegistered": true,
"isVerified": false,
"lastLogin": "2014-12-04T22:26:33.002Z",
"lastLoginTimestamp": 1417731993000,
"lastUpdated": "2014-12-04T22:19:42.769Z",
"lastUpdatedTimestamp": 1417731582769,
"loginProvider": "facebook",
"loginIDs": {
"emails": [],
"unverifiedEmails": []
},
"rbaPolicy": {
"riskPolicyLocked": false
},
"oldestDataUpdated": "2014-12-04T22:19:42.894Z",
"oldestDataUpdatedTimestamp": 1417731582894,
"registered": "2014-12-04T22:19:42.956Z",
"regSource": "",
"socialProviders": "facebook"
}
]
I want to extract data from created and identities but ignore identities.favorites and identities.likes as well as their data underneath it.
This is what I have so far, below. I defined the JSON keys that I want to extract in the key_list variable:
import json, pandas
from flatten_json import flatten
# Enter the path to the JSON and the filename without appending '.json'
file_path = r'C:\Path\To\file_name'
# Open and load the JSON file
json_list = json.load(open(file_path + '.json', 'r', encoding='utf-8', errors='ignore'))
# Extract data from the defined key names
key_list = ['created', 'identities']
json_list = [{k:d[k] for k in key_list} for d in json_list]
# Flatten and convert to a data frame
json_list_flattened = (flatten(d, '.') for d in json_list)
df = pandas.DataFrame(json_list_flattened)
# Export to CSV in the same directory with the original file name
export_csv = df.to_csv (file_path + r'.csv', sep=',', encoding='utf-8', index=None, header=True)
Similar to the key_list, I suspect that I would make an ignore list and factor that in the json_list for loop that I have? Something like:
key_ignore = ['identities.favorites', 'identities.likes']`
Then utilize the dict.pop() which looks like it will remove the unwanted sub-keys if it matches? Just not sure how to implement that correctly.
As a result, the code should extract data from the defined keys in key_list and ignore the sub keys defined in key_ignore, which is identities.favorites and identities.likes. Then the rest of the code will continue to convert it into a CSV:
| created | identities.0.provider | identities.0.providerUID | identities... |
|---|---|---|---|
| 2014-12-04T19:23:05.191Z | site | cb8168b0cf734b70ad541f0132763761 | ... |
If the keys are always there, you can use
del d[0]['identities'][0]['likes']
del d[0]['identities'][0]['favorites']
or if you want to remove the columns from the dataframe after reading all the json data in you can use
df.drop(df.filter(regex='identities.0.favorites|identities.0.likes').columns, axis=1, inplace=True)