We Keep Coding

Python: Convert json with extra data error into CSV

I have a JSON in below format which I receive from a different team and not allowed to make any changes to it:
{
"content": [
{
"id": "5603bbaae412390b73f0c7f",
"name": "ABC",
"description": "Test",
"rsid": "pwcs",
"type": "project",
"owner": {
"id": 529932
},
"created": "2015-09-24T09:00:26Z"
},
{
"id": "56094673e4b0a7e17e310b83",
"name": "secores",
"description": "Panel",
"rsid": "pwce",
"type": "project",
"owner": {
"id": 520902
},
"created": "2015-09-28T13:53:55Z"
}
],
"totalPages": 9,
"totalElements": 8592,
"number": 0,
"numberOfElements": 1000,
"firstPage": true,
"lastPage": false,
"sort": null,
"size": 1000
}
{
"content": [
{
"id": "5bf2cc64d977553780706050",
"name": "Services Report",
"description": "",
"rsid": "pcie",
"type": "project",
"owner": {
"id": 518013
},
"created": "2018-11-19T14:44:52Z"
},
{
"id": "5bf2d56e40b39312e3e167d0",
"name": "Standard form",
"description": "",
"rsid": "wcu",
"type": "project",
"owner": {
"id": 521114
},
"created": "2018-11-19T15:23:26Z"
}
],
"totalPages": 9,
"totalElements": 8592,
"number": 1,
"numberOfElements": 1000,
"firstPage": false,
"lastPage": false,
"sort": null,
"size": 1000
}
{
"content": [
{
"id": "5d95e7d6187c6d6376fd1bad",
"name": "New Project",
"description": "",
"rsid": "pcinforrod",
"type": "project",
"owner": {
"id": 200904228
},
"created": "2019-10-03T12:21:42Z"
},
{
"id": "5d95fc6e56d2e82519629b96",
"name": "Demo - 10/03",
"description": "",
"rsid": "sitedev",
"type": "project",
"owner": {
"id": 20001494
},
"created": "2019-10-03T13:49:34Z"
}
],
"totalPages": 9,
"totalElements": 8592,
"number": 2,
"numberOfElements": 1000,
"firstPage": false,
"lastPage": false,
"sort": null,
"size": 1000
}
I am trying to convert it into CSV using below code:
import csv
import json
with open("C:\python\SampleJSON.json",'rb') as file:
data = json.load(file)
fname = "workspaceExcelDemo.csv"
with open(fname,"w", encoding="utf-8", newline='') as file:
csv_file = csv.writer(file)
csv_file.writerow(["id","name","rsid"])
for item in data["content"]:
csv_file.writerow([item['id'],item['name'],item['rsid']])
However I am getting below error message while executing the above piece of code:
raise JSONDecodeError("Extra data", s, end)
json.decoder.JSONDecodeError: Extra data: line 35 column 1 (char 937)
How do I convert the above JSON into CSV without making any changes to the JSON file?

If I understand your question and the comments well you could use the json.dumps method:
import csv
import json
with open("C:\python\SampleJSON.json",'rb') as file:
data = [json.loads(line) for line in file]
"""
The json.dumps method converts a Python object to a JSON formatted string.
The json.loads method parses a JSON string into a native Python object.
Replacing the "=" character with an empty string.
"""
data = json.loads(json.dumps(data).replace("=", ""))
fname = "workspaceExcelDemo.csv"
with open(fname, "w", encoding="utf-8", newline='') as file:
csv_file = csv.writer(file)
csv_file.writerow(["id", "name", "rsid"])
for item in data[0]["content"]:
csv_file.writerow([item['id'], item['name'], item['rsid']])

Ignore specific JSON keys when extracting data in Python

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:
JSON Sample
[
{
"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:
Current Code
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.
Expected Output
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)

How to read fields without numeric index in JSON

I have a json file where I need to read it in a structured way to insert in a database each value in its respective column, but in the tag "customFields" the fields change index, example: "Tribe / Customer" can be index 0 (row['customFields'][0]) in a json block, and in the other one be index 3 (row['customFields'][3]), so I tried to read the data using the name of the row field ['customFields'] ['Tribe / Customer'], but I got the error below:
TypeError: list indices must be integers or slices, not str
Script:
def getCustomField(ModelData):
for row in ModelData["data"]["squads"][0]["cards"]:
print(row['identifier'],
row['customFields']['Tribe / Customer'],
row['customFields']['Stopped with'],
row['customFields']['Sub-Activity'],
row['customFields']['Activity'],
row['customFields']['Complexity'],
row['customFields']['Effort'])
if __name__ == "__main__":
f = open('test.json')
json_file = json.load(f)
getCustomField(json_file)
JSON:
{
"data": {
"squads": [
{
"name": "TESTE",
"cards": [
{
"identifier": "0102",
"title": "TESTE",
"description": " TESTE ",
"status": "on_track",
"priority": null,
"assignees": [
{
"fullname": "TESTE",
"email": "TESTE"
}
],
"createdAt": "2020-04-16T15:00:31-03:00",
"secondaryLabel": null,
"primaryLabels": [
"TESTE",
"TESTE"
],
"swimlane": "TESTE",
"workstate": "Active",
"customFields": [
{
"name": "Tribe / Customer",
"value": "TESTE 1"
},
{
"name": "Checkpoint",
"value": "GNN"
},
{
"name": "Stopped with",
"value": null
},
{
"name": "Sub-Activity",
"value": "DEPLOY"
},
{
"name": "Activity",
"value": "TOOL"
},
{
"name": "Complexity",
"value": "HIGH"
},
{
"name": "Effort",
"value": "20"
}
]
},
{
"identifier": "0103",
"title": "TESTE",
"description": " TESTE ",
"status": "on_track",
"priority": null,
"assignees": [
{
"fullname": "TESTE",
"email": "TESTE"
}
],
"createdAt": "2020-04-16T15:00:31-03:00",
"secondaryLabel": null,
"primaryLabels": [
"TESTE",
"TESTE"
],
"swimlane": "TESTE",
"workstate": "Active",
"customFields": [
{
"name": "Tribe / Customer",
"value": "TESTE 1"
},
{
"name": "Stopped with",
"value": null
},
{
"name": "Checkpoint",
"value": "GNN"
},
{
"name": "Sub-Activity",
"value": "DEPLOY"
},
{
"name": "Activity",
"value": "TOOL"
},
{
"name": "Complexity",
"value": "HIGH"
},
{
"name": "Effort",
"value": "20"
}
]
}
]
}
]
}
}

You'll have to parse the list of custom fields into something you can access by name. Since you're accessing multiple entries from the same list, a dictionary is the most appropriate choice.
for row in ModelData["data"]["squads"][0]["cards"]:
custom_fields_dict = {field['name']: field['value'] for field in row['customFields']}
print(row['identifier'],
custom_fields_dict['Tribe / Customer'],
...
)
If you only wanted a single field you could traverse the list looking for a match, but it would be less efficient to do that repeatedly.
I'm skipping over dealing with missing fields - you'd probably want to use get('Tribe / Customer', some_reasonable_default) if there's any possibility of the field not being present in the json list.

Accessing nested value in loop in json using python

I want to fetch the value of each api3 in this json object where each array has api3 value.
{
"count": 10,
"result": [
{
"type": "year",
"year": {
"month": {
"api1": {
"href": "https://Ap1.com"
},
"api2": {
"href": "FETCH-CONTENT"
},
"api3": {
"href": "https://Ap3.com"
},
"api4": {
"href": "https://Ap4.com"
}
},
"id": "sdvnkjsnvj",
"summary": "summeryc",
"type": "REST",
"apiId": "mlksmfmksdfs",
"idProvider": {
"id": "sfsmkfmskf",
"name": "Apikey"
},
"tags": []
}
},
{
"type": "year1",
"year": {
"month": {
"api1": {
"href": "https://Ap11.com"
},
"api2": {
"href": "FETCH-CONTENT-1"
},
"api3": {
"href": "https://Ap13.com"
},
"api4": {
"href": "https://Ap14.com"
}
},
"id": "sdvnkjsnvj",
"summary": "summeryc",
"type": "REST",
"apiId": "mlksmfmksdfs",
"idProvider": {
"id": "sfsmkfmskf",
"name": "Apikey"
},
"tags": []
}
},
I am able to get the whole json object and first value inside it.
with open('C:\python\examplee.json','r+') as fr:
data = json.load(fr)
print(data["result"])
Thank you in advance for helping me figuring this.

For each element in list of result key, get the value for the nested dictionary within item
print([item['year']['month']['api3'] for item in data['result']])
The output will be [{'href': 'https://Ap3.com'}, {'href': 'https://Ap13.com'}]
Or if you want to get the href value as well
print([item['year']['month']['api3']['href'] for item in data['result']])
The output will be
['https://Ap3.com', 'https://Ap13.com']
So your whole code will look like
data = {}
with open('C:\python\examplee.json','r+') as fr:
data = json.load(fr)
print([item['year']['month']['api3']['href'] for item in dct['result']])

Looks like your JSON schema is static so you can just use this:
print([x['year']['month']['api3']['href'] for x in data['result']])
will return you:
['https://Ap3.com', 'https://Ap13.com']

Flatten nested json to csv with nested column names

I have rather very weird requirement now. I have below json and somehow I have to convert it into flat csv.
[
{
"authorizationQualifier": "SDA",
"authorizationInformation": " ",
"securityQualifier": "ASD",
"securityInformation": " ",
"senderQualifier": "ASDAD",
"senderId": "FADA ",
"receiverQualifier": "ADSAS",
"receiverId": "ADAD ",
"date": "140101",
"time": "0730",
"standardsId": null,
"version": "00501",
"interchangeControlNumber": "123456789",
"acknowledgmentRequested": "0",
"testIndicator": "T",
"functionalGroups": [
{
"functionalIdentifierCode": "ADSAD",
"applicationSenderCode": "ASDAD",
"applicationReceiverCode": "ADSADS",
"date": "20140101",
"time": "07294900",
"groupControlNumber": "123456789",
"responsibleAgencyCode": "X",
"version": "005010X221A1",
"transactions": [
{
"name": "ASDADAD",
"transactionSetIdentifierCode": "adADS",
"transactionSetControlNumber": "123456789",
"implementationConventionReference": null,
"segments": [
{
"BPR03": "ad",
"BPR14": "QWQWDQ",
"BPR02": "1.57",
"BPR13": "23223",
"BPR01": "sad",
"BPR12": "56",
"BPR10": "32424",
"BPR09": "12313",
"BPR08": "DA",
"BPR07": "123456789",
"BPR06": "12313",
"BPR05": "ASDADSAD",
"BPR16": "21313",
"BPR04": "SDADSAS",
"BPR15": "11212",
"id": "aDSASD"
},
{
"TRN02": "2424",
"TRN03": "35435345",
"TRN01": "3435345",
"id": "FSDF"
},
{
"REF02": "fdsffs",
"REF01": "sfsfs",
"id": "fsfdsfd"
},
{
"DTM02": "2432424",
"id": "sfsfd",
"DTM01": "234243"
}
],
"loops": [
{
"id": "24324234234",
"segments": [
{
"N101": "sfsfsdf",
"N102": "sfsf",
"id": "dgfdgf"
},
{
"N301": "sfdssfdsfsf",
"N302": "effdssf",
"id": "fdssf"
},
{
"N401": "sdffssf",
"id": "sfds",
"N402": "sfdsf",
"N403": "23424"
},
{
"PER06": "Wsfsfdsfsf",
"PER05": "sfsf",
"PER04": "23424",
"PER03": "fdfbvcb",
"PER02": "Pedsdsf",
"PER01": "sfsfsf",
"id": "fdsdf"
}
]
},
{
"id": "2342",
"segments": [
{
"N101": "sdfsfds",
"N102": "vcbvcb",
"N103": "dsfsdfs",
"N104": "343443",
"id": "fdgfdg"
},
{
"N401": "dfsgdfg",
"id": "dfgdgdf",
"N402": "dgdgdg",
"N403": "234244"
},
{
"REF02": "23423342",
"REF01": "fsdfs",
"id": "sfdsfds"
}
]
}
]
}
]
}
]
}
]
The column header name corresponding to deeper key-value make take nested form, like functionalGroups[0].transactions[0].segments[0].BPR15.
I am able to do this in java using this github project (here you can find the output format I desire in the explanation) in one line:
flatJson = JSONFlattener.parseJson(new File("files/simple.json"), "UTF-8");
The output was:
date,securityQualifier,testIndicator,functionalGroups[1].functionalIdentifierCode,functionalGroups[1].date,functionalGroups[1].applicationReceiverCode, ...
140101,00,T,HP,20140101,ETIN,...
But I want to do this in python. I tried as suggested in this answer:
with open('data.json') as data_file:
data = json.load(data_file)
df = json_normalize(data, record_prefix=True)
with open('temp2.csv', "w", newline='\n') as csv_file:
csv_file.write(df.to_csv())
However, for column functionalGroups, it dumps json as a cell value.
I also tried as suggested in this answer:
with open('data.json') as f: # this ensures opening and closing file
a = json.loads(f.read())
df = pandas.DataFrame(a)
print(df.transpose())
But this also seem to do the same:
0
acknowledgmentRequested 0
authorizationInformation
authorizationQualifier SDA
date 140101
functionalGroups [{'functionalIdentifierCode': 'ADSAD', 'applic...
interchangeControlNumber 123456789
receiverId ADAD
receiverQualifier ADSAS
securityInformation
securityQualifier ASD
senderId FADA
senderQualifier ASDAD
standardsId None
testIndicator T
time 0730
version 00501
Is it possible to do what I desire in python?