Extract specific JSON keys and convert to CSV in Python - python

I'm converting several JSON files into a CSV using the following code below, it works as intended, but it converts all of the data in the JSON file. Instead, I want it to do the following:
Load JSON file [done]
Extract certain nested data in the JSON file [wip]
Convert to CSV [done]
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
dic = json.load(open(file_path + '.json', 'r', encoding='utf-8', errors='ignore'))
# Flatten and convert to a data frame
dic_flattened = (flatten(d, '.') for d in dic)
df = pandas.DataFrame(dic_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)
In the example at the bottom, I only want everything under the following keys: created, emails, and identities. The rest is useless information (such as statusCode) or it's duplicated under a different key name (such as profile and userInfo).
I know it requires a for loop and if statement to specify the key names later on, but not sure the best way to implement it. This is what I have so far when I want to test it:
Attempted 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_file = open(file_path + '.json', 'r', encoding='utf-8', errors='ignore')
dic = json.load(json_file)
# List keys to extract
key_list = ['created', 'emails', 'identities']
for d in dic:
#print(d['identities']) #Print all 'identities'
#if 'identities' in d: #Check if 'identities' exists
if key_list in d:
# Flatten and convert to a data frame
#dic_flattened = (flatten(d, '.') for d in dic)
#df = pandas.DataFrame(dic_flattened)
else:
# Skip
# 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)
Is this the right logic?
file_name.json Example
[
{
"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": 30,
"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",
"followersCount": 0,
"gender": "m",
"hometown": "City, State",
"languages": "English",
"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"
}
]

As mentioned by juanpa.arrivillaga, I simply need to add the following line after the key_list:
json_list = [{k:d[k] for k in key_list} for d in json_list]
This is the full working 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', 'emails', '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)

Related

Converting text file to json

I have text file and I want to convert it to JSON:
red|2022-09-29|03:15:00|info 1
blue|2022-09-29|10:50:00|
yellow|2022-09-29|07:15:00|info 2
so i type a script to convert this file into JSON:
import json
filename = 'input_file.txt'
dict1 = {}
fields =['name', 'date', 'time', 'info']
with open(filename) as fh:
l = 1
for line in fh:
description = list( line.strip().split("|", 4))
print(description)
sno ='name'+str(l)
i = 0
dict2 = {}
while i<len(fields):
dict2[fields[i]]= description[i]
i = i + 1
dict1[sno]= dict2
l = l + 1
out_file = open("json_file.json", "w")
json.dump(dict1, out_file, indent = 4)
out_file.close()
and output looks like this:
{
"name1": {
"name": "red",
"date": "2022-09-29",
"time": "03:15:00",
"info": "info 1"
},
"name2": {
"name": "blue",
"date": "2022-09-29",
"time": "10:50:00",
"info": ""
},
"name3": {
"name": "yellow",
"date": "2022-09-29",
"time": "07:15:00",
"info": "info 2"
}
}
As you can see I do so, but now I want to change looks of this JSON file. How can I change it to make my output looks like this:
to look like this:
[
{"name":"red", "date": "2022-09-29", "time": "03:15:00", "info":"info 1"},
{"name":"blue", "date": "2022-09-29", "time": "10:50:00", "info":""},
{"name":"yellow", "date": "2022-09-29", "time": "07:15:00", "info":"info 2"}
]
If you see your required json output, it is a list and not a dict like you have right now. So using a list(data) instead of dict(dict1) should give the correct output.
Following updated code should generate the json data in required format -
import json
filename = 'input_file.txt'
data = []
fields =['name', 'date', 'time', 'info']
with open(filename) as fh:
l = 1
for line in fh:
description = list( line.strip().split("|", 4))
print(description)
sno ='name'+str(l)
i = 0
dict2 = {}
while i<len(fields):
dict2[fields[i]]= description[i]
i = i + 1
data.append(dict2)
l = l + 1
out_file = open("json_file.json", "w")
json.dump(data, out_file, indent = 4)
out_file.close()
I would use pandas, it allows you to solve your problem in one statement and avoid reinventing a wheel:
import pandas as pd
pd.read_table("input_file.txt", sep="|", header=None,
names=["name", "date" , "time", "info"]).fillna("")\
.to_json("json_file.json", orient="records")

How to convert nested JSON files to CSV in python

I am completely new to python and trying to covert nested json files to csv. The current code I am trying to use is:
import json
def read_json(filename: str) -> dict:
try:
with open(filename, "r") as f:
data = json.loads(f.read())
except:
raise Exception(f"Reading {filename} file encountered an error")
return data
def normalize_json(data: dict) -> dict:
new_data = dict()
for key, value in data.items():
if not isinstance(value, dict):
new_data[key] = value
else:
for k, v in value.items():
new_data[key + "_" + k] = v
return new_data
def generate_csv_data(data: dict) -> str:
# Defining CSV columns in a list to maintain
# the order
csv_columns = data.keys()
# Generate the first row of CSV
csv_data = ",".join(csv_columns) + "\n"
# Generate the single record present
new_row = list()
for col in csv_columns:
new_row.append(str(data[col]))
# Concatenate the record with the column information
# in CSV format
csv_data += ",".join(new_row) + "\n"
return csv_data
def write_to_file(data: str, filepath: str) -> bool:
try:
with open(filepath, "w+") as f:
f.write(data)
except:
raise Exception(f"Saving data to {filepath} encountered an error")
def main():
# Read the JSON file as python dictionary
data = read_json(filename="test2.json")
# Normalize the nested python dict
new_data = normalize_json(data=data)
# Pretty print the new dict object
print("New dict:", new_data)
# Generate the desired CSV data
csv_data = generate_csv_data(data=new_data)
# Save the generated CSV data to a CSV file
write_to_file(data=csv_data, filepath=data2.csv")
if __name__ == '__main__':
main()
It works partly: I get a CSV file that contains all values. However, for the nested key fields it only gives me the "highest" level (e.g. I get "currentEmployments" but not "currentEmployments_firmId").
Could someone help me with this?
Sample json file:
{
"basicInformation": {
"individualId": 10000,
"firstName": "Name",
"middleName": "middleName.",
"lastName": "lastName",
"bcScope": "Active",
"iaScope": "NotInScope",
"daysInIndustryCalculatedDate": "1/1/2000"
},
"currentEmployments": [
{
"firmId": 001,
"firmName": "firm1",
"iaOnly": "N",
"registrationBeginDate": "1/1/2005",
"firmBCScope": "ACTIVE",
"firmIAScope": "ACTIVE",
"iaSECNumber": "10000",
"iaSECNumberType": "100",
"bdSECNumber": "1000",
"branchOfficeLocations": [
{
"locatedAtFlag": "Y",
"supervisedFromFlag": "N",
"privateResidenceFlag": "N",
"branchOfficeId": "10000",
"street1": "street1",
"city": "city",
"state": "MD",
"country": "United States",
"zipCode": "10000"
}
]
}
],
"currentIAEmployments": [],
"previousEmployments": [
{
"iaOnly": "N",
"bdSECNumber": "20000",
"firmId": 200,
"firmName": "firm2",
"street1": "street",
"city": "city",
"state": "MD",
"country": "UNITED STATES",
"zipCode": "10000",
}
],
"examsCount": {
"stateExamCount": 0,
"principalExamCount": 0,
"productExamCount": 1
},
}

Excel to JSON format with python

I have an excel sheet which is in the below format
I want to convert this excel sheet into JSON format using Python. each JSON object is a diagonal value and column headings in the below format.
{
"Records": [
{
"RecordId": "F1",
"Assets": [
{
"AssetId": "A1",
"Support": "S11"
},
{
"AssetId": "A2",
"Support": "S12"
},
{
"AssetId": "A3",
"Support": "S13"
}
]
},
{
"RecordId": "F2",
"Assets": [
{
"AssetId": "A1",
"Support": "S21"
},
{
"AssetId": "A2",
"Support": "S22"
},
{
"AssetId": "A3",
"Support": "S23"
}
]
}
]
}
I have written some code it seems not working as I expected.
import json
import pandas as pd
df = pd.read_excel (r'test.xlsx', sheet_name='Sheet2')
#initialize data
data=[0 for i in range(len(df))]
datac=[0 for c in range(len(df.columns))]
newset=dict()
for i in range(len(df)):
# data[i] = r'{"'+str(df.columns.values[0])+'": "' +str(df.loc[i][0])+'", '+str(df.columns.values[1])+'": "' +str(df.loc[i][1])+'", '+str(df.columns.values[2])+'": "' +str(df.loc[i][2])+'"}'
#data[i] = {str(df.columns.values[1]) : str(df.loc[i][0]), str(df.columns.values[1]): str(df.loc[i][1]), str(df.columns.values[2]): str(df.loc[i][2])}
for c in range(1,len(df.columns)):
#data[i] = {str('RecordId') : str(df.loc[i][0]),str('Assets'):[{"AssetId": str(df.columns.values[c]),"Support": str(df.loc[i][c])}]}
datac[c] = {"AssetId": str(df.columns.values[c]),"Support": str(df.loc[i][c])}
data[i]={str('RecordId') : str(df.loc[i][0]),str('Assets'):datac[c]}
print(data[i])
output_lines = [json.dumps(line)+",\n" for line in data]
output_lines[-1] = output_lines[-1][:-2] # remove ",\n" from last line
with open(r'Savedwork.json', 'w') as json_file:
json_file.writelines(output_lines)
What you need is the iterrows() method, it will iterate over the
dataframe's rows as (index, series) pairs. The columns() method will give you
the list of column names, so you'll be able to iterate over the columns in the
series, and access them by name.
import json
import pandas as pd
df = pd.read_excel('test.xlsx')
recs = []
for i, row in df.iterrows():
rec = {
'RecordId': row[0],
'Assets': [{'AssetId': c, 'Support': row[c]} for c in df.columns[1:]]
}
recs.append(rec)
out = {'Records': recs}
(yes, it could all be done in a single list comprehension, but abusing those hinders readability)
Also, you don't need to do json.dumps on lines, and then assemble them with
newlines (don't work at the text level): build a dictionary with the entire
data, and then json.dump that:
print(json.dumps(out, indent=4))
You can create the dicts directly in pandas.
First set the first column with F1, F2 as index:
df.set_index(0, inplace = True)
df.index.name = None
Then create the dicts in pandas with dict keys as column names, export it to a dict and save it to json:
import json
df = df.apply(lambda x: [{"AssetId": x.name, "Support": i} for i in x], axis =1).reset_index().rename(columns={'index': 'RecordId', 0: 'Assets'})
json_data = {"Records": df.to_dict('records')}
with open('r'Savedwork.json', 'w') as fp:
json.dump(json_data, fp)
another solution is to take a snapshot of the entire workbook in json format and reorganize it out of the box. Using the collect function of XLtoy is possible to do that via command line, this approach allows you more degrees of freedom.
[i'm the main developer of XLtoy]

how to extract specific data from json and put in to csv using python

I have a JSON which is in nested form. I would like to extract specific data from json and put into csv using pandas python.
data = {
"class":"hudson.model.Hudson",
"jobs":[
{
"_class":"hudson.model.FreeStyleProject",
"name":"git_checkout",
"url":"http://localhost:8080/job/git_checkout/",
"builds":[
{
"_class":"hudson.model.FreeStyleBuild",
"duration":1201,
"number":6,
"result":"FAILURE",
"url":"http://localhost:8080/job/git_checkout/6/"
}
]
},
{
"_class":"hudson.model.FreeStyleProject",
"name":"output",
"url":"http://localhost:8080/job/output/",
"builds":[
]
},
{
"_class":"org.jenkinsci.plugins.workflow.job.WorkflowJob",
"name":"pipeline_test",
"url":"http://localhost:8080/job/pipeline_test/",
"builds":[
{
"_class":"org.jenkinsci.plugins.workflow.job.WorkflowRun",
"duration":9274,
"number":85,
"result":"SUCCESS",
"url":"http://localhost:8080/job/pipeline_test/85/"
},
{
"_class":"org.jenkinsci.plugins.workflow.job.WorkflowRun",
"duration":4251,
"number":84,
"result":"SUCCESS",
"url":"http://localhost:8080/job/pipeline_test/84/"
}
]
}
]
}
From the above JSON i want to fetch jobs name value and builds result value . I am new to python any help will be appreciated .
Till now i have tried
main_data = data['jobs]
json_normalize(main_data,['builds'],
record_prefix='jobs_', errors='ignore')
which gives information only build key values and not the name of job .
Can anyone help ?
Expected Output:
Considering only first build result value you can need to be in csv column you can achieve this using pandas.
data = {
"class": "hudson.model.Hudson",
"jobs": [
{
"_class": "hudson.model.FreeStyleProject",
"name": "git_checkout",
"url": "http://localhost:8080/job/git_checkout/",
"builds": [
{
"_class": "hudson.model.FreeStyleBuild",
"duration": 1201,
"number": 6,
"result": "FAILURE",
"url": "http://localhost:8080/job/git_checkout/6/"
}
]
},
{
"_class": "hudson.model.FreeStyleProject",
"name": "output",
"url": "http://localhost:8080/job/output/",
"builds": []
},
{
"_class": "org.jenkinsci.plugins.workflow.job.WorkflowJob",
"name": "pipeline_test",
"url": "http://localhost:8080/job/pipeline_test/",
"builds": [
{
"_class": "org.jenkinsci.plugins.workflow.job.WorkflowRun",
"duration": 9274,
"number": 85,
"result": "SUCCESS",
"url": "http://localhost:8080/job/pipeline_test/85/"
},
{
"_class": "org.jenkinsci.plugins.workflow.job.WorkflowRun",
"duration": 4251,
"number": 84,
"result": "SUCCESS",
"url": "http://localhost:8080/job/pipeline_test/84/"
}
]
}
]
}
main_data = data.get('jobs')
res = {'name':[], 'result':[]}
for name_dict in main_data:
res['name'].append(name_dict.get('name','NA'))
resultval = name_dict['builds'][0].get('result') if len(name_dict['builds'])>0 else 'NA'
res['result'].append(resultval)
print(res)
import pandas as pd
df = pd.DataFrame(res)
df.to_csv("/home/file_timer/jobs.csv", index=False)
Check the csv file output
name,result
git_checkout,FAILURE
output,NA
pipeline_test,SUCCESS
If 'NA' result want to skip then
main_data = data.get('jobs')
res = {'name':[], 'result':[]}
for name_dict in main_data:
if len(name_dict['builds'])==0:
continue
res['name'].append(name_dict.get('name', 'NA'))
resultval = name_dict['builds'][0].get('result')
res['result'].append(resultval)
print(res)
import pandas as pd
df = pd.DataFrame(res)
df.to_csv("/home/akash.pagar/shell_learning/file_timer/jobs.csv", index=False)
Output will bw like
name,result
git_checkout,FAILURE
pipeline_test,SUCCESS
Simply with build number,
for job in data.get('jobs'):
for build in job.get('builds'):
print(job.get('name'), build.get('number'), build.get('result'))
gives the result
git_checkout 6 FAILURE
pipeline_test 85 SUCCESS
pipeline_test 84 SUCCESS
If you want to get the result of latest build, and pretty sure about the build number always in decending order,
for job in data.get('jobs'):
if job.get('builds'):
print(job.get('name'), job.get('builds')[0].get('result'))
and if you are not sure the order,
for job in data.get('jobs'):
if job.get('builds'):
print(job.get('name'), sorted(job.get('builds'), key=lambda k: k.get('number'))[-1].get('result'))
then the result will be:
git_checkout FAILURE
pipeline_test SUCCESS
Assuming last build is the last element of its list and you don't care about jobs with no builds, this does:
import pandas as pd
#data = ... #same format as in the question
z = [(job["name"], job["builds"][-1]["result"]) for job in data["jobs"] if len(job["builds"])]
df = pd.DataFrame(data=z, columns=["name", "result"])
#df.to_csv #TODO
Also we don't necessarily need pandas to create the csv file.
You could do:
import csv
#z = ... #see previous code block
with open("f.csv", 'w') as fp:
csv.writer(fp).writerows([("name", "result")] + z)

convert csv file to multiple nested json format

I have written a code to convert csv file to nested json format. I have multiple columns to be nested hence assigning separately for each column. The problem is I'm getting 2 fields for the same column in the json output.
import csv
import json
from collections import OrderedDict
csv_file = 'data.csv'
json_file = csv_file + '.json'
def main(input_file):
csv_rows = []
with open(input_file, 'r') as csvfile:
reader = csv.DictReader(csvfile, delimiter='|')
for row in reader:
row['TYPE'] = 'REVIEW', # adding new key, value
row['RAWID'] = 1,
row['CUSTOMER'] = {
"ID": row['CUSTOMER_ID'],
"NAME": row['CUSTOMER_NAME']
}
row['CATEGORY'] = {
"ID": row['CATEGORY_ID'],
"NAME": row['CATEGORY']
}
del (row["CUSTOMER_NAME"], row["CATEGORY_ID"],
row["CATEGORY"], row["CUSTOMER_ID"]) # deleting since fields coccuring twice
csv_rows.append(row)
with open(json_file, 'w') as f:
json.dump(csv_rows, f, sort_keys=True, indent=4, ensure_ascii=False)
f.write('\n')
The output is as below:
[
{
"CATEGORY": {
"ID": "1",
"NAME": "Consumers"
},
"CATEGORY_ID": "1",
"CUSTOMER_ID": "41",
"CUSTOMER": {
"ID": "41",
"NAME": "SA Port"
},
"CUSTOMER_NAME": "SA Port",
"RAWID": [
1
]
}
]
I'm getting 2 entries for the fields I have assigned using row[''].
Is there any other way to get rid of this? I want only one entry for a particular field in each record.
Also how can I convert the keys to lower case after reading from csv.DictReader(). In my csv file all the columns are in upper case and hence I'm using the same to assign. But I want to convert all of them to lower case.
In order to convert the keys to lower case, it would be simpler to generate a new dict per row. BTW, it should be enough to get rid of the duplicate fields:
for row in reader:
orow = collection.OrderedDict()
orow['type'] = 'REVIEW', # adding new key, value
orow['rawid'] = 1,
orow['customer'] = {
"id": row['CUSTOMER_ID'],
"name": row['CUSTOMER_NAME']
}
orow['category'] = {
"id": row['CATEGORY_ID'],
"name": row['CATEGORY']
}
csv_rows.append(orow)

Categories

Resources