We Keep Coding

python parse data from nested json

I have the following (excerpt) json data structure:
{
"apiToken": {
"createdAt": "2022-03-04T12:18:29.000956Z",
"expiresAt": "2022-09-04T12:18:29.000956Z"
},
"canGenerateApiToken": true,
"dateJoined": "2021-01-29T10:07:04.395172Z",
"email": "john#doe.com",
"emailReadOnly": true,
"emailVerified": true,
"firstLogin": "2021-01-29T13:01:33.294216Z",
"fullName": "John Doe",
"fullNameReadOnly": true,
"groupsReadOnly": false,
"id": "32168415841",
"isSystem": false,
"lastLogin": "2022-09-12T08:51:00.159750Z",
"lowestRole": "Admin",
"primaryTwoFaMethod": "application",
"scope": "account",
"scopeRoles": [
{
"id": "68418945648943589",
"name": "AT || ACME Inc.",
"roleId": "9848949354653168",
"roleName": "Admin",
"roles": [
"Admin"
]
}
],
"siteRoles": [],
"source": "sso_saml",
"tenantRoles": [],
"twoFaEnabled": true
}
I'm trying to write certain data into an excel file with:
df = pd.json_normalize(result)
df.head()
df[['scope', 'fullName', 'email', 'lowestRole', 'scope',
'scopeRoles.name']].to_excel(completename)
But I struggle with 'scopeRoles.name' as it's nested.
with the code above I get
raise KeyError(f"None of [{key}] are in the [{axis_name}]")
KeyError: "None of [Index(['scope', 'fullName', 'email', 'lowestRole', 'scope', 'scopeRoles.name'], dtype='object')] are in the [columns]"
I also tried different versions, but always failed.
I basically need to understand how I can specify the fields to write into excel when the field itself is nested. If I just use "non-nested" entries it works perfectly fine
thanks

You need to flatten your JSON data file.
You could use the flatten_json package.
pip install flatten_json
from flatten_json import flatten
unflat_json = {'user':
{'Rachel':
{'UserID': 1717171717,
'Email': 'rachel1999#gmail.com',
'friends': ['John', 'Jeremy', 'Emily']
}
}
}
flat_json = flatten(unflat_json)
print(flat_json)
Output:
{‘user_Rachel_UserID’: 1717171717, ‘user_Rachel_Email’: ‘rachel1999#gmail.com’, ‘user_Rachel_friends_0’: ‘John’, ‘user_Rachel_friends_1’: ‘Jeremy’, ‘user_Rachel_friends_2’: ‘Emily’}

To deal with a list of dictionaries, you can use df.from_records(). But, you need to process it separately to combine each dataframe together. I assumed the data used is exactly the same, considering the df['scopeRoles'] only consisted of one element. Please try something like this:
import pandas as pd
result = {
"apiToken": {
"createdAt": "2022-03-04T12:18:29.000956Z",
"expiresAt": "2022-09-04T12:18:29.000956Z"
},
"canGenerateApiToken": True,
"dateJoined": "2021-01-29T10:07:04.395172Z",
"email": "john#doe.com",
"emailReadOnly": True,
"emailVerified": True,
"firstLogin": "2021-01-29T13:01:33.294216Z",
"fullName": "John Doe",
"fullNameReadOnly": True,
"groupsReadOnly": False,
"id": "32168415841",
"isSystem": False,
"lastLogin": "2022-09-12T08:51:00.159750Z",
"lowestRole": "Admin",
"primaryTwoFaMethod": "application",
"scope": "account",
"scopeRoles": [
{
"id": "68418945648943589",
"name": "AT || ACME Inc.",
"roleId": "9848949354653168",
"roleName": "Admin",
"roles": [
"Admin"
]
}
],
"siteRoles": [],
"source": "sso_saml",
"tenantRoles": [],
"twoFaEnabled": True
}
df = pd.json_normalize(result)
df2 = df[['scope', 'fullName', 'email', 'lowestRole', 'scope']]
# from_records() returns a dataframe from a list of dict df['scopeRoles'].
df3 = df.from_records(df["scopeRoles"][0])
# join df2 and df3
res = df2.join(df3)
print(res)
I hope this code helps!
EDIT
To get the name column only, you just have to subscript like so:
df3 = df.from_records(df["scopeRoles"][0])['name']

create dataframe in pandas using multilevel dict dynamic

I am fetching api and trying that response into csv but on catch is there this is multilevel dict or json when i am converting into csv most of the look like list of dict or dicts
I am trying using this
def expand(data):
d = pd.Series(data)
t = d.index
for i in t:
if type(d[i]) in (list,dict):
expend_s = pd.Series(d[i])
t.append(expend_s.index)
d = d.append(expend_s)
d = d.drop([i])
return d
df['person'].apply(expand)
but this solution is not working. if we see person col there is multiple dict or list of dict like
"birthDate": "0000-00-00",
"genderCode": {
"codeValue": "M",
"shortName": "Male",
"longName": "Male"
},
"maritalStatusCode": {
"codeValue": "M",
"shortName": "Married"
},
"disabledIndicator": False,
"preferredName": {},
"ethnicityCode": {
"codeValue": "4",
"shortName": "4",
"longName": "Not Hispanic or Latino"
},
"raceCode": {
"identificationMethodCode": {},
"codeValue": "1",
"shortName": "White",
"longName": "White"
},
"militaryClassificationCodes": [],
"governmentIDs": [
{
"itemID": "9200037107708_4385",
"idValue": "XXX-XX-XXXX",
"nameCode": {
"codeValue": "SSN",
"longName": "Social Security Number"
},
"countryCode": "US"
}
],
"legalName": {
"givenName": "Jack",
"middleName": "C",
"familyName1": "Abele",
"formattedName": "Abele, Jack C"
},
"legalAddress": {
"nameCode": {
"codeValue": "Personal Address 1",
"shortName": "Personal Address 1",
"longName": "Personal Address 1"
},
"lineOne": "1932 Keswick Lane",
"cityName": "Concord",
"countrySubdivisionLevel1": {
"subdivisionType": "StateTerritory",
"codeValue": "CA",
"shortName": "California"
},
"countryCode": "US",
"postalCode": "94518"
},
"communication": {
"mobiles": [
{
"itemID": "9200037107708_4389",
"nameCode": {
"codeValue": "Personal Cell",
"shortName": "Personal Cell"
},
"countryDialing": "1",
"areaDialing": "925",
"dialNumber": "6860589",
"access": "1",
"formattedNumber": "(925) 686-0589"
}
]
}
}
your suggestion and advice would be so helpful

I think we can solve multiple dict using read as pd.josn_normalise and list of dict using the below functions first we get those columns which have list
def df_list_and_dict_col(explode_df: pd.DataFrame, primary_key: str,
col_name: str, folder: str) -> pd.DataFrame:
""" convert list of dict or list of into clean dataframe
Keyword arguments:
-----------------
dict: explode_df -- dataframe where we have to expand column
dict: col_name -- main_file name where most of data is present
Return: pd.DataFrame
return clean or expand dataframe
"""
explode_df[col_name] = explode_df[col_name].replace('', '[]', regex=True)
explode_df[col_name] = explode_df[col_name].fillna('[]')
explode_df[col_name] = explode_df[col_name].astype(
'string') # to make sure that entire column is string
explode_df[col_name] = explode_df[col_name].apply(ast.literal_eval)
explode_df = explode_df.explode(col_name)
explode_df = explode_df.reset_index(drop=True)
normalized_df = pd.json_normalize(explode_df[col_name])
explode_df = explode_df.join(
other=normalized_df,
lsuffix="_left",
rsuffix="_right"
)
explode_df = explode_df.drop(columns=col_name)
type_df = explode_df.applymap(type)
col_list = []
for col in type_df.columns:
if (type_df[col]==type([])).any():
col_list.append(col)
# print(col_list,explode_df.columns)
if len(col_list) != 0:
for col in col_list:
df_list_and_dict_col(explode_df[[primary_key,col]], primary_key,
col, folder)
explode_df.drop(columns=col, inplace =True)
print(f'{col}.csv is done')
explode_df.to_csv(f'{folder}/{col_name}.csv')
first we get list col and pass col to function one by one and then check is there any list inside col and then go on and save into csv
type_df = df.applymap(type)
col_list =[]
for col in type_df.columns:
if (type_df[col]==type([])).any():
col_list.append(col)
for col in col_list:
# print(col, df[['associateOID',col]])
df_list_and_dict_col(df[['primary_key',col]].copy(), 'primary_key', col,folder='worker')
df.drop(columns=col, inplace=True)
now you have multiple csv in normalise format

How to convert a list of OrderedDict to nested json with grouped keys in python

I'm working on a project where I need to convert a set of data rows from database into list of OrderedDict for other purpose and use this list of OrderedDict to convert into a nested JSON format in python. I'm starting to learn python. I was able convert the query response from database which is a list of lists to list of OrderedDict.
I have the list of OrderedDict as below:
{
'OUTBOUND': [
OrderedDict([('Leg', 1), ('SessionID', 'W12231fwfegwcaa2'),('FeeCode', 'ATO'),('SeatGroup', '2'),
('Currency', 'MXN'),('Modality', 'VB'),('BookingClass', 'A'),('Price', 145.0),('Num_Pax', 1),('Channel', 'Web')]),
OrderedDict([('Leg', 1),('SessionID', 'W12231fwfegwcaa2'),('FeeCode', 'ATO'),('SeatGroup', '4'),
('Currency', 'MXN'),('Modality', 'VB'),('BookingClass', 'A'),('Price', 111.0),('Num_Pax', 1),('Channel', 'Web')]),
OrderedDict([('Leg', 1),('SessionID', 'W12231fwfegwcaa2'),('FeeCode', 'BDM'),('SeatGroup', 'null'),
('Currency', 'MXN'),('Modality', 'VB'),('BookingClass', 'A'),('Price', 111.0),('Num_Pax', 1),('Channel', 'Web')]),
OrderedDict([('Leg', 2),('SessionID', 'W12231fwfegwcaa2'),('FeeCode', 'ATO'),('SeatGroup', '1'),
('Currency', 'MXN'),('Modality', 'VB'),('BookingClass', 'U'),('Price', 180.0),('Num_Pax', 1),('Channel', 'Web'))]),
OrderedDict([('Leg', 2),('SessionID', 'W12231fwfegwcaa2'),('FeeCode', 'ATO'),('SeatGroup', '4'),
('Currency', 'MXN'),('Modality', 'VB'),('BookingClass', 'U'),('Price', 97.0),('Num_Pax', 1),('Channel', 'Web')]),
OrderedDict([('Leg', 2),('SessionID', 'W12231fwfegwcaa2'),('FeeCode', 'BDM'),('SeatGroup', 'null'),
('Currency', 'MXN'),('Modality', 'VB'),('BookingClass', 'U'),('Price', 97.0),('Num_Pax', 1),('Channel', 'Web')])
]
}
And I needed the nested format like below:
{
"OUTBOUND": [
{
"Leg": 1,
"SessionID": "W12231fwfegwcaa2",
"Modality": "VB",
"BookingClass": "A",
"FeeCodes":[
{
"FeeCode": "ATO",
"Prices":
[
{
"SeatGroup": "2",
"Price": 145.0,
"Currency": "MXN"
},
{
"SeatGroup": "4",
"Price": 111.0,
"Currency": "MXN"
}
]
},
{
"FeeCode": "VBABDM",
"Prices":
[
{
"SeatGroup": "null",
"Price": 111.0,
"Currency": "MXN"
}
]
}
],
"Num_Pax": 1,
"Channel": "Web"
},
{
"Leg": 2,
"SessionID": "W12231fwfegwcaa2",
"Modality": "VB",
"BookingClass": "U",
"FeeCodes":[
{
"FeeCode": "ATO",
"Prices":
[
{
"SeatGroup": "1",
"Price": 180.0,
"Currency": "MXN"
},
{
"SeatGroup": "4",
"price": 97.0,
"Currency": "MXN"
}
]
},
{
"FeeCode": "VBABDM",
"Prices":
[
{
"SeatGroup": "null",
"price": 97.0,
"Currency": "MXN"
}
]
}
],
"Num_Pax": 1,
"Channel": "Web"
}
]
}
If I'm not wrong, I need to group by Leg, SessionID, Modality, BookingClass, NumPax and Channel and group the FeeCode, SeatGroup, Price and Currency into nested format as above but unable to move ahead with how to loop and group for nesting.
It would be great if I could get some help. Thanks

I was able to write a python code to get the format as I needed using simple looping with a couple of changes in the output like the fields SessionID, Num_Pax and Channel is taken outside then the OUTBOUND field and fields within are generated.
Instead of OrderedDict, I used a list of lists as input which I convert into Pandas DataFrame and work with the DataFrame to get the nested format.
Below is the code I used:
outbound_df = pd.DataFrame(response_outbound,columns=All_columns)
Common_columns = ['Leg', 'Modality', 'BookingClass']
### Taking SessionID, AirlineCode,Num_Pax and Channel outside OUTBOUND part as they are common for all the leg level data
response_data['SessionID'] = outbound_df['SessionID'].unique()[0]
response_data['Num_Pax'] = int(outbound_df['Num_Pax'].unique()[0])
response_data['Channel'] = outbound_df['Channel'].unique()[0]
temp_data = []
Legs = outbound_df['Leg'].unique()
for i in Legs:
subdata = outbound_df[outbound_df['Leg']==i]
### Initializing leg_data dict
leg_data = collections.OrderedDict()
### Populating common fields of the leg (Leg, Modality,BookingClass)
for j in Common_columns:
if(j=='Leg'):
leg_data[j] = int(subdata[j].unique()[0])
else:
leg_data[j] = subdata[j].unique()[0]
leg_data['FeeCodes'] = []
FeeCodes = subdata['FeeCode'].unique()
for fc in FeeCodes:
subdata_fees = subdata[subdata['FeeCode']==fc]
Prices = {'FeeCode':fc, "Prices":[]}
for _,rows in subdata_fees.iterrows():
data = {}
data['SeatGroup'] = rows['SeatGroup']
data['Price'] = float(rows['Price'])
data['Currency'] = rows['Currency']
Prices["Prices"].append(data)
leg_data["FeeCodes"].append(Prices)
temp_data.append(leg_data)
response_data["OUTBOUND"] = temp_data
I can just do json.dumps on response_data to get json format which will be sent to the next steps.
Below is the output format I get:
{
"SessionID":"W12231fwfegwcaa2",
"Num_Pax":1,
"Channel":"Web",
"OUTBOUND":[
{
"Leg":1,
"Modality":"VB",
"BookingClass":"A",
"FeeCodes":[
{
"FeeCode":"ATO",
"Prices":[
{
"SeatGroup":"2",
"Price":145.0,
"Currency":"MXN"
},
{
"SeatGroup":"4",
"Price":111.0,
"Currency":"MXN"
}
]
},
{
"FeeCode":"VBABDM",
"Prices":[
{
"SeatGroup":"null",
"Price":111.0,
"Currency":"MXN"
}
]
}
]
},
{
"Leg":2,
"Modality":"VB",
"BookingClass":"U",
"FeeCodes":[
{
"FeeCode":"ATO",
"Prices":[
{
"SeatGroup":"1",
"Price":180.0,
"Currency":"MXN"
},
{
"SeatGroup":"4",
"price":97.0,
"Currency":"MXN"
}
]
},
{
"FeeCode":"VBABDM",
"Prices":[
{
"SeatGroup":"null",
"price":97.0,
"Currency":"MXN"
}
]
}
]
}
]
}
Please let me know if we can shorten the code in terms of lengthy iterations or any other changes. Thanks.
PS: Sorry for my editing mistakes

Assuming that you stored the dictionary to some variable foo, you can do:
import json
json.dumps(foo)
And be careful, you added extra bracket in the 4th element OUTBOUND list

Issue parsing JSON file-Python

Have this section in one large JSON file
"UserDetailList": [
{
"UserName": "citrix-xendesktop-ec2-provisioning",
"GroupList": [],
"CreateDate": "2017-11-07T14:20:14Z",
"UserId": "AIDAI2YJINPRUEM3XHKXO",
"Path": "/",
"AttachedManagedPolicies": [
{
"PolicyName": "AmazonEC2FullAccess",
"PolicyArn": "arn:aws:iam::aws:policy/AmazonEC2FullAccess"
},
{
"PolicyName": "AmazonS3FullAccess",
"PolicyArn": "arn:aws:iam::aws:policy/AmazonS3FullAccess"
}
],
"Arn": "arn:aws:iam::279052847476:user/citrix-xendesktop-ec2-provisioning"
},
Need to extract AttachedManagedPolicy.Policy name for user
Desired output:
"citrix-xendesktop-ec2-provisioning","AmazonEC2FullAccess"
"citrix-xendesktop-ec2-provisioning","AmazonS3FullAccess"
Some users don't have any policy at all so need some checking mechanism to avoid errors
with open('1.json') as file:
data = json.load(file)
for element in data['UserDetailList']:
s = element['UserName'], element['AttachedManagedPolicies']
print s
And getting
(u'citrix-xendesktop-ec2-provisioning', [{u'PolicyName': u'AmazonEC2FullAccess', u'PolicyArn': u'arn:aws:iam::aws:policy/AmazonEC2FullAccess'}, {u'PolicyName': u'AmazonS3FullAccess', u'PolicyArn': u'arn:aws:iam::aws:policy/AmazonS3FullAccess'}])
When added element['AttachedManagedPolicies']['PolicyName']
got: TypeError: list indices must be integers, not str

You are getting error because element['AttachedManagedPolicies'] is list not dictionary you need to iterate over element['AttachedManagedPolicies'] and then access key as below:
[i['PolicyName'] for i in element['AttachedManagedPolicies']]
this will construct list of values for key PolicyName
As you said you have very large JSON structure you might have empty values or not values and for that you can proceed as below:
d = {
"UserDetailList": [
{
"UserName": "citrix-xendesktop-ec2-provisioning",
"GroupList": [],
"CreateDate": "2017-11-07T14:20:14Z",
"UserId": "AIDAI2YJINPRUEM3XHKXO",
"Path": "/",
"AttachedManagedPolicies": [
{
"PolicyName": "AmazonEC2FullAccess",
"PolicyArn": "arn:aws:iam::aws:policy/AmazonEC2FullAccess"
},
{
"PolicyName": "AmazonS3FullAccess",
"PolicyArn": "arn:aws:iam::aws:policy/AmazonS3FullAccess"
}
],
"Arn": "arn:aws:iam::279052847476:user/citrix-xendesktop-ec2-provisioning"
}
]
}
user_list = d.get("UserDetailList", None) # if unable to fetch key then it will return None
if user_list:
for user_detail in user_list:
username = user_detail.get("UserName", None)
policies = [i.get('PolicyName') for i in user_detail.get('AttachedManagedPolicies', []) if i.get('PolicyName', None)] # empty list constructed if no policy exist
print(username, policies)

How to add title row to using writer and unicodecsv

I have the following JSON file - test.json (names, keys and addresses changed for security reasons)
[
{
"accountMode":"Live",
"acquirer":"TEST",
"acquirerConstraints":{
"cardTypes":[
"MASTERCARD",
"MAESTRO",
"VISA"
],
"cvcRegexp":"^[0-9]{3}$",
"cvcRequired":true,
"maxAmount":500000,
"minAmount":50
},
"acquirerDetails":{
"TEST":"Studio",
"ERROR_LIST":[
],
"MERCHANT_CODE":"218331",
"VALID":true,
"_mId":"T712484",
"_status":"INPROCESS",
"email":"test7#gmail.com",
"name":"Studio",
"valid":true
},
"acquirerValidations":null,
"allowedCurrencies":[
"EUR",
"USD",
"GBP"
],
"apiKeyPairs":[
{
"accountMode":"Live",
"label":"Virtual Terminal",
"publishableKey":"niunibiubniunijknkjknj",
"source":"VIRTUAL_TERMINAL"
},
{
"accountMode":"Live",
"label":"Default",
"publishableKey":"iiuhiuhiu",
"source":"ECOMMERCE"
}
],
"appLogoUrl":null,
"applicationId":"541d75e0-7db8b343a31f",
"authorizationCode":"",
"closedDate":null,
"closureReason":null,
"declineAvsAddressFailure":false,
"declineAvsZipFailure":false,
"declineCvcFailure":false,
"defaultCurrency":"EUR",
"descriptor":null,
"email":"test1#gmail.com",
"id":"ddddeff",
"invitationCode":null,
"locale":"en_IE",
"merchantApplication":{
"accountNumber":null,
"acquirer":"TEST",
"annualAmount":null,
"annualVolume":null,
"applicationType":"APPROVAL",
"bankName":"UNKNOWN",
"brand":null,
"businessAddress":"54 My St, 1",
"businessAddress2":null,
"businessCity":"Abbey",
"businessCountry":"IRL",
"businessPhone":null,
"businessState":"DUBLIN",
"businessZip":null,
"data":null,
"email":"test#gmail.com",
"escalationPhone":null,
"fax":null,
"legalName":"UAB \"Studio\"",
"maxTransactionAmount":null,
"mccCode":"5712",
"merchantPromotionCode":null,
"mobile":null,
"monthlyAmount":null,
"monthlyVolume":null,
"ownerFirstName":"tlana",
"ownerLastName":"nava",
"phone":"37647",
"GuideAccepted":null,
"privacyAccepted":true,
"privacyVersion":"1a",
"referenceId":"9104d65i08d071",
"routingNumber":null,
"singleTransactionAmount":null,
"statementName":"UAB \"Studio\"",
"taxId":null,
"termsAccepted":true,
"termsVersion":"1a",
"url":"http://www.design.lt"
},
"merchantId":"12484",
"merchantPromotionCode":null,
"mposEnabled":true,
"name":"Studio",
"netonfiguration":null,
"onboardedDate":1505513232485,
"onboardingMethod":null,
"onboardingStatus":"INPROCESS",
"partner":null,
"saqCompliant":false,
"saqExpires":null,
"settings":[
{
"key":"MERCHANT_DETAILS",
"value":"{\"zip\":\"Wicklow\",\"phone\":\"342647\",\"email\":\"suppoor#outlook.com\",\"address\":\"Bck 6\",\"state\":\"Ireland\",\"addressLine2\":\"Unit 8, Bl Par\",\"city\":\"Wicklow\"}"
},
{
"key":"VAT_NUMBER",
"value":"/evzaqen/"
}
],
"timezone":"Europe/Dublin",
"tinStatus":null
},
{
"accountMode":"Live",
"acquirer":"TEST",
"acquirerConstraints":{
"cardTypes":[
"MASTERCARD",
"MAESTRO",
"VISA"
],
"cvcRegexp":"^[0-9]{3}$",
"cvcRequired":true,
"maxAmount":500000,
"minAmount":50
},
"acquirerDetails":{
"TEST":"test",
"ERROR_LIST":[
],
"MERCHANT_CODE":"594920",
"MID_ASSIGNED":true,
"VALID":true,
"_mId":"103558",
"_status":"APPROVED",
"acquiringMid":"1036598",
"descriptor":"test 8885551212",
"email":"test#gmail.com",
"gatewayMid":"SIMP337",
"id":"SIMP337",
"level4Mid":"76576576",
"name":"test",
"status":"APPROVED",
"transactionCurrency":"USD;EUR;GBP",
"valid":true,
"paymentGatewayKey":"ytfytfytfyt"
},
"acquirerValidations":null,
"allowedCurrencies":[
"EUR",
"USD",
"GBP"
],
"apiKeyPairs":[
],
"appLogoUrl":null,
"applicationId":"949bdde5-07-d8d58f4c3d01",
"authorizationCode":"",
"closedDate":null,
"closureReason":null,
"declineAvsAddressFailure":false,
"declineAvsZipFailure":false,
"declineCvcFailure":false,
"defaultCurrency":"EUR",
"descriptor":"test85551212",
"email":"test#gmail.com",
"id":"9f3a7d7",
"invitationCode":null,
"locale":"en_US",
"merchantApplication":{
"accountNumber":null,
"acquirer":"TEST",
"annualAmount":null,
"annualVolume":null,
"applicationType":"APPROVAL",
"bankName":"UNKNOWN",
"brand":null,
"businessAddress":"123 test",
"businessAddress2":null,
"businessCity":"Atlanta",
"businessCountry":"IRL",
"businessPhone":null,
"businessState":"CARLOW",
"businessZip":null,
"data":null,
"email":"test#gmail.com",
"escalationPhone":null,
"fax":null,
"legalName":"stest",
"maxTransactionAmount":null,
"mccCode":"521",
"merchantPromotionCode":null,
"mobile":null,
"monthlyAmount":null,
"monthlyVolume":null,
"ownerFirstName":"moto",
"ownerLastName":"test",
"phone":"3141212",
"GuideAccepted":null,
"privacyAccepted":true,
"privacyVersion":"1a",
"referenceId":"2920",
"routingNumber":null,
"singleTransactionAmount":null,
"statementName":"test",
"taxId":null,
"termsAccepted":true,
"termsVersion":"1a",
"url":null
},
"merchantId":"1036558",
"merchantPromotionCode":null,
"mposEnabled":true,
"name":"test",
"netonfiguration":null,
"onboardedDate":1456846054925,
"onboardingMethod":null,
"onboardingStatus":"CLOSED",
"partner":null,
"saqCompliant":false,
"saqExpires":null,
"settings":[
],
"timezone":"Europe/Dublin",
"tinStatus":"InCompliance"
}
]
I want to process this file and take some of the information and populate a CSV file with it. To do this I am using the following:
import unicodecsv
import json
json_data = open("test.json")
data = json.load(json_data)
f = unicodecsv.writer(open("results.csv","wb+"))
for entry in data:
if "merchantApplication" in entry:
ma = entry["merchantApplication"]
if "email" in ma:
f.writerow([ma["ownerFirstName"],ma["ownerLastName"],ma["email"],ma["legalName"],ma["businessAddress"],ma["businessAddress2"],ma["businessCity"],ma["businessCountry"],ma["businessState"],ma["businessZip"],ma["phone"],ma["mobile"]])
json_data.close()
This Works fine but does not print the headers above the columns. How do I add in the headers? I am using Python 2.7.10

How do I add in the headers?
Well quite simply by calling f.writerow((<your>,<headers>,<here>)) before your for loop.