We Keep Coding

How to search through multiple (thousands) of JSON files to find files with a specific value and then append those specific values to a new list

I recently generated 10,000 images with a corresponding .json file. I generated 10 before I did the bigger collection and so I am trying to filter out or search through the 10,000 json files, for a specific key value. here is one of the JSON files for example:
{
"name": "GrapeGrannys #1",
"description": "Grannys with grapes etc.",
"image": "ipfs://NewUriToReplace/1.png",
"dna": "93596679f006e3a9226700e0e7539179b532bf29",
"edition": 1,
"date": 1667406230920,
"attributes": [
{
"trait_type": "Backgrounds",
"value": "sunrise_beach"
},
{
"trait_type": "main",
"value": "GrapeGranny"
},
{
"trait_type": "eyeColor",
"value": "gray"
},
{
"trait_type": "skirtAndTieColor",
"value": "green"
},
{
"trait_type": "Headwear",
"value": "hat1"
},
{
"trait_type": "specialItems",
"value": "ThugLife"
}
],
"compiler": "HashLips Art Engine"
}
In "attributes", I want to I want to target the first object and its value and check to see if that value is equal to "GrapeCity".
Then after all files have been read and searched through, Id like the files with that specific value "GrapeCity" to be stored in a new list or array that I can print and see which specific files contain that keyword. Here is what I have tried in Python:
import json
import glob
# from datetime import datetime
src = "./Assets/json"
# date = datetime.now()
data = []
files = glob.glob('$./Assets/json/*', recursive=True)
for single_file in files:
with open(single_file, 'r') as f:
try:
json_file = json.load(f)
data.append([
json_file["attributes"]["values"]["GrapeCity"]
])
except KeyError:
print(f'Skipping {single_file}')
data.sort()
print(data)
# csv_filename = f'{str(date)}.csv'
# with open(csv_filename, "w", newline="") as f:
# writer = csv.writer(f)
# writer.writerows(data)
# print("Updated CSV")
At one point I was getting a typeError but now it is just outputing an empty array. Any help is appreciated!

json_file["attributes"] is a list so you can't access it like a dictionary.
Try this:
for single_file in files:
with open(single_file, 'r') as f:
try:
json_file = json.load(f)
attrs = json_file["attributes"]
has_grape_city = any(attr["value"] == "GrapeCity" for attr in attrs)
if has_grape_city:
data.append(single_file)
except KeyError:
print(f'Skipping {single_file}')

Convert a JSON string to multiple CSV's based on its structure and name it to a certain value

I currently have A JSON file saved containing some data I want to convert to CSV. Here is the data sample below, please note, I have censored the actual value in there for security and privacy reasons.
{
"ID value1": {
"Id": "ID value1",
"TechnischContactpersoon": {
"Naam": "Value",
"Telefoon": "Value",
"Email": "Value"
},
"Disclaimer": [
"Value"
],
"Voorzorgsmaatregelen": [
{
"Attributes": {},
"FileId": "value",
"FileName": "value",
"FilePackageLocation": "value"
},
{
"Attributes": {},
"FileId": "value",
"FileName": "value",
"FilePackageLocation": "value"
},
]
},
"ID value2": {
"Id": "id value2",
"TechnischContactpersoon": {
"Naam": "Value",
"Telefoon": "Value",
"Email": "Value"
},
"Disclaimer": [
"Placeholder"
],
"Voorzorgsmaatregelen": [
{
"Attributes": {},
"FileId": "value",
"FileName": "value",
"FilePackageLocation": "value"
}
]
},
Though I know how to do this (because I already have a function to handle a JSON to CSV convertion) with a simple JSON string without issues. I do not know to this with this kind of JSON file that this kind of a structure layer. Aka a second layer beneath the first. Also you may have noticed that there is an ID value above
Because as may have noticed from structure is actually another layer inside the JSON file. So in total I need to have two kinds of CSV files:
The main CSV file just containing the ID, Disclaimer. This CSV file
is called utility networks and contains all possible ID value's and
the value
A file containing the "Voorzorgsmaatregelen" value's. Because there are multiple values in this section, one CSV file per unique
ID file is needed and needs to be named after the Unique value id.
Deleted this part because it was irrelevant.
Data_folder = "Data"
Unazones_file_name = "UnaZones"
Utilitynetworks_file_name = "utilityNetworks"
folder_path_JSON_BS_JSON = folder_path_creation(Data_folder)
pkml_file_path = os.path.join(folder_path_JSON_BS_JSON,"pmkl.json")
print(pkml_file_path)
json_object = json_open(pkml_file_path)
json_content_unazones = json_object.get("mapRequest").get("UnaZones")
json_content_utility_Networks = json_object.get("utilityNetworks")
Unazones_json_location = json_to_save(json_content_unazones,folder_path_JSON_BS_JSON,Unazones_file_name)
csv_file_location_unazones = os.path.join(folder_path_CSV_file_path(Data_folder),(Unazones_file_name+".csv"))
csv_file_location_Utilitynetwork = os.path.join(folder_path_CSV_file_path(Data_folder),(Unazones_file_name+".csv"))
json_content_utility_Networks = json_object.get("utilityNetworks")
Utility_networks_json_location = json_to_save(json_content_utility_Networks,folder_path_JSON_BS_JSON,Utilitynetworks_file_name)
def json_to_csv_convertion(json_file_path: str, csv_file_location: str):
loaded_json_data = json_open(json_file_path)
# now we will open a file for writing
data_file = open(csv_file_location, 'w', newline='')
# # create the csv writer object
csv_writer = csv.writer(data_file,delimiter = ";")
# Counter variable used for writing
# headers to the CSV file
count = 0
for row in loaded_json_data:
if count == 0:
# Writing headers of CSV file
header = row.keys()
csv_writer.writerow(header)
count += 1
# Writing data of CSV file
csv_writer.writerow(row.values())
data_file.close()
def folder_path_creation(path: str):
if not os.path.exists(path):
os.makedirs(path)
return path
def json_open(complete_folder_path):
with open(complete_folder_path) as f:
json_to_load = json.load(f) # Modified "objectids" to "object_ids" for readability -sg
return json_to_load
def json_to_save(input_json, folder_path: str, file_name: str):
json_save_location = save_file(input_json, folder_path, file_name, "json")
return json_save_location
So how do I this starting from this?
for obj in json_content_utility_Networks:
Go from there?
Keep in mind that is JSON value has already one layer above every object for every object I need to start one layer below it.
So how do I this?

How to append data to JSON list that doesn't contains any key for that list?

[
{
"name": "name one",
"id": 1
},
{
"name": "name two",
"id": 2
}
]
I want to append object to the list in .json file. how do i do?

You could read the existing json content update it and rewrite the updated list.
import json
with open("myfile.json", "r+") as f:
my_file = f.read() # read the current content
my_list = json.loads(my_file) # convert from json object to dictionary type
dict_obj = {
"name": "name three",
"id": 3
}
my_list.append(dict_obj)
f.seek(0) # sets point at the beginning of the file
f.truncate() # Clear previous content
print(f" going to rewrite {my_list}")
f.write(json.dumps(my_list)) # Write updated version file

I'm not entirely sure of what you are asking but perhaps the code below will help:
const myList = [
{
"name": "name one",
"id": 1
},
{
"name": "name two",
"id": 2
}
]
const myNewItem = {
"name": "name three",
"id": 3
}
const addItemIfDifferentId = (list, newItem) => [...list, !list.map(({id}) =>id).includes(newItem.id) ? {...newItem} : {} ]
const newList = addItemIfDifferentId(myList, myNewItem)
newList

Maybe this will help you:
import json
# When loading a .json files it will be a string:
with open('data.json') as json_file:
x = json.load(json_file) //{"key1":"123", "key2":"456", "key3":"789"}
# python object to be appended
y = {"key4": "101112"}
# Load the json string to be an object type:
z = json.loads(x)
# appending the data
z.update(y)
# the result is a JSON string:
print(json.dumps(z))
with open('data.json', 'w') as outfile:
json.dump(z, outfile)

Handling keys inside a key from .json file

I am trying to print an specific key from a JSON file without success.
.json file is:
{
"testing": [
{
"_name": "teste",
"_profile_telphone": "212331233",
"_age": "21"
}
]
}
the function I'm using is:
def load(self):
filename = self.profile_entry.get()
if filename == "":
msg = "Insert a profile name"
messagebox.showinfo("Profile name is empty", msg)
self.profile_entry.focus()
else:
with open('profile_'+filename+'.json', 'r') as outfile:
data = json.load(outfile)
print(data[filename])
outfile.close()
with print(data[filename]) I can print entire
{
"_name": "teste",
"_profile_telphone": "212331233",
"_age": "21"
}
But how can I print only name or age for example?

data is a list of JSONs - you have a json array there, in order to parse it you can do it with a for statement
for element in data[filename]:
print(element[‘_name’])
print(element[‘_profile_telphone’])
print(element[‘_age’])

Python & Multilevel JSON File read and add

I am attempting to read the following JSON file and update it, specifically:
I can get the latest data analysis (var: lastAnalysisCompleted) was completed using get_json()
I get the following error code "list indices must be integers or slices, not str" when attempting to set baselineDictionaryFilename variable
I want to create a new grouping under the 'analysis' using the write_json() module. But running into errors.
How can I proceed?
New grouping:
"01-02-2020":{
"dictionaryFileName": "Dictionary_01-02-2020.json",
"analysisFileName": "Analysis_Output_01-02-2020.xlsx",
"netNewLabelledEntries": "10",
"range90": "1",
"range80": "3",
"range75":"1",
"rangeLessThan75":"5"
}
def get_json():
with open(jFile, 'r') as myfile:
data=myfile.read()
# parse file
obj = json.loads(data)
#secret = parsed_input['secret']
lastAnalysisCompleted = obj['lastAnalysisCompleted']
baselineDictionaryFileName = obj['analysis'][lastAnalysisCompleted]['dictionaryFileName']
Here is the module I wrote to update JSON but it doesn't work
def write_json(filename=jFile):
with open(filename, 'w') as f:
json.dump(data, f, indent=3)
with open(jFile) as json_file:
data = json.load(json_file)
temp = data['analysis']
y = {
"01-02-2020":{
"dictionaryFileName": "Dictionary_01-02-2020.json",
"analysisFileName": "Analysis_Output_01-02-2020.xlsx",
"netNewLabelledEntries": "10",
"range90": "1",
"range80": "3",
"range75":"1",
"rangeLessThan75":"5"
}
}
temp.append(y)
write_json(data)
Here is my JSON file.
{
"lastAnalysisCompleted": "01-01-2020",
"analysis":[
{
"12-31-2019":{
"dictionaryFileName": "Dictionary_12-31-2019.json",
"analysisFileName": "Analysis_Output_12-31-2019.xlsx",
"netNewLabelledEntries": "10",
"range90": "1",
"range80": "3",
"range75":"1",
"rangeLessThan75":"5"
},
"01-01-2020":{
"dictionaryFileName": "Dictionary_01-01-2020.json",
"analysisFileName": "Analysis_Output_01-01-2020.xlsx",
"netNewLabelledEntries": "10",
"range90": "1",
"range80": "3",
"range75":"1",
"rangeLessThan75":"5"
}
}
]
}

The problem in your code for getting the file name it is array of dicts you need to use index to access specific dictionary.
def get_json():
with open('test.json', 'r') as myfile:
data=myfile.read()
# parse file
obj = json.loads(data)
#secret = parsed_input['secret']
lastAnalysisCompleted = obj['lastAnalysisCompleted']
baselineDictionaryFileName = ''.join([d[lastAnalysisCompleted]['dictionaryFileName'] for d in obj['analysis'] if lastAnalysisCompleted in d])
And for writing to json file you are passing data to write_json() function and in function you are not defined argument for data
def write_json(data, filename=jFile):
with open(filename, 'w') as f:
json.dump(data, f, indent=3)