I have the below Json file which I need to query to get the values of the keys inside 'validations' in a list
for example the column_values_not_null output will need to be this:
['lu_name', 'transaction_amount']
"validation_file_name": "ctm",
"connection_type": "s3",
"low_threshold": 500000,
"high_threshold": 1000000,
"frequency": "weekly",
"validations": [
{
"columns_to_match_ordered_list" :[
"lu_name",
"site_name",
"transaction_date_time",
"margin",
"transaction_currency_code",
"reversal_indicator_description",
"reversal_amount",
"original_amount"
]
},
{
"column_values_not_null":[
"lu_name",
"transaction_amount"
]
},
{
"column_values_not_duplicate": [
"lu_name",
"response_code_description"
]
}
]
I am able to do the below but I need to do this without using the index value
f = open('test.json')
json_content = json.load(f)
print(json_content['validations'][1]['column_values_not_null'])
Get a list by querying the validations key. The sum( ,[]) are used to flat the list (as required by the condition "without using the index value" if got it right), for details about it with pros and cons see doc.
data = #
def validations(data: dict, key_query: str) -> list:
for k, v in data.items():
if k == 'validations':
return sum(sum([list(d.values()) for d in v if key_query in d], []), [])
print(validations(data, query='column_values_not_null'))
# ['lu_name', 'transaction_amount']
Related
Want to convert Sample JSON data into CSV file using python. I am retrieving JSON data from API.
As my JSON has nested objects, so it normally cannot be directly converted to CSV.I don't want to do any hard coding and I want to make a python code fully dynamic.
So, I have written a function that flatten my JSON Data but I am not able to work out how to iterate all records, finding relevant column names and then output those data into CSV.
In the Sample JSON file I have mentioned only 2 records but in actual there are 100 records.
Sample JSON Look like this:
[
{
"id":"Random_Company_57",
"unid":"75",
"fieldsToValues":{
"Email":"None",
"occupation":"SO1 Change",
"manager":"None",
"First Name":"Bells",
"employeeID":"21011.0",
"loginRequired":"true",
"superUser":"false",
"ldapSuperUser":"false",
"archived":"true",
"password":"None",
"externalUser":"false",
"Username":"Random_Company_57",
"affiliation":"",
"Phone":"+16 22 22 222",
"unidDominoKey":"",
"externalUserActive":"false",
"secondaryOccupation":"SO1 Change",
"retypePassword":"None",
"Last Name":"Christmas"
},
"hierarchyFieldAccess":[
],
"userHierarchies":[
{
"hierarchyField":"Company",
"value":"ABC Company"
},
{
"hierarchyField":"Department",
"value":"gfds"
},
{
"hierarchyField":"Project",
"value":"JKL-SDFGHJW"
},
{
"hierarchyField":"Division",
"value":"Silver RC"
},
{
"hierarchyField":"Site",
"value":"SQ06"
}
],
"locale":{
"id":1,
"dateFormat":"dd/MM/yyyy",
"languageTag":"en-UA"
},
"roles":[
"User"
],
"readAccessRoles":[
],
"preferredLanguage":"en-AU",
"prefName":"Christmas Bells",
"startDate":"None",
"firstName":"Bells",
"lastName":"Christmas",
"fullName":"Christmas Bells",
"lastModified":"2022-02-22T03:47:41.632Z",
"email":"None",
"docNo":"None",
"virtualSuperUser":false
},
{
"id":"xyz.abc#safe.net",
"unid":"98",
"fieldsToValues":{
"Email":"xyz.abc#safe.net",
"occupation":"SO1 Change",
"manager":"None",
"First Name":"Bells",
"employeeID":"21011.0",
"loginRequired":"false",
"superUser":"false",
"ldapSuperUser":"false",
"archived":"false",
"password":"None",
"externalUser":"false",
"Username":"xyz.abc#safe.net",
"affiliation":"",
"Phone":"+16 2222 222 222",
"unidDominoKey":"",
"externalUserActive":"false",
"secondaryOccupation":"SO1 Change",
"retypePassword":"None",
"Last Name":"Christmas"
},
"hierarchyFieldAccess":[
],
"userHierarchies":[
{
"hierarchyField":"Company",
"value":"ABC Company"
},
{
"hierarchyField":"Department",
"value":"PUHJ"
},
{
"hierarchyField":"Project",
"value":"RPOJ-SDFGHJW"
},
{
"hierarchyField":"Division",
"value":"Silver RC"
},
{
"hierarchyField":"Site",
"value":"SQ06"
}
],
"locale":{
"id":1,
"dateFormat":"dd/MM/yyyy",
"languageTag":"en-UA"
},
"roles":[
"User"
],
"readAccessRoles":[
],
"preferredLanguage":"en-AU",
"prefName":"Christmas Bells",
"startDate":"None",
"firstName":"Bells",
"lastName":"Christmas",
"fullName":"Christmas Bells",
"lastModified":"2022-03-16T05:04:13.085Z",
"email":"xyz.abc#safe.net",
"docNo":"None",
"virtualSuperUser":false
}
]
What I have tried.
def flattenjson(b, delim):
val = {}
for i in b.keys():
if isinstance(b[i], dict):
get = flattenjson(b[i], delim)
for j in get.keys():
val[i + delim + j] = get[j]
else:
val[i] = b[i]
print(val)
return val
json=[{Sample JSON String that mentioned above}]
flattenjson(json,"__")
I don't know it is a right way to deal this problem or not?
My final aim is that all the above json data will output in a csv file.
Based on this answer, you could loop through your list of json data and flatten each json with the given function (they always have the same structure?), then build a DataFrame and write the data to csv. That's the easiest way I can think of,
try this:
import pandas as pd
import json
import collections
def flatten(dictionary, parent_key=False, separator='__'):
items = []
for key, value in dictionary.items():
new_key = str(parent_key) + separator + key if parent_key else key
if isinstance(value, collections.MutableMapping):
items.extend(flatten(value, new_key, separator).items())
elif isinstance(value, list):
for k, v in enumerate(value):
items.extend(flatten({str(k): v}, new_key).items())
else:
items.append((new_key, value))
return dict(items)
with open('your_json.json') as f:
data = json.load(f) # data is a the example you provided (list of dicts)
all_records=[]
for jsn in data:
tmp = flatten(jsn)
all_records.append(tmp)
df = pd.DataFrame(all_records)
out = df.to_csv('json_to_csv.csv')
I want to extract all the lists and modify them from a nested dictionary which has multiple levels and the list can be a value in any of the levels.
For example:
test = {
'Type 1': {
'Type1_mainkey1': {
'Type1_key2': {
'Type1_key2_key1': [
'Type1_list1'
],
'Type1_key2_key2': [
'Type1_list2'
],
'Type1_key2_key2': [
'Type1_list3',
'Type1_list4'
]
}
}
},
'Type 2': {
'Type2_mainkey1': {
'Type2_key2': [
'Type2_list1',
'Type2_list2'
]},
'Type2_key3': {
'Type2_key3_key1': [
'Type2_list3',
'Type2_list4'
]
}
}
}
This is the kind of dictionary that might be present. I was wondering if there is a way of extracting the lists and updating the dictionary.
My function so far:
def find_list(data):
if not any([isinstance(data.get(k), dict) for k in data]):
return data
else:
for dkey in data:
if isinstance(data.get(dkey), dict):
return find_list(data.get(dkey))
else:
continue
And on running this:
out = find_list(test)
My output is:
{'Type1_key2_key1': ['Type1_list1'],
'Type1_key2_key2': ['Type1_list3', 'Type1_list4']}
Whereas, the expected output is all the list items and their keys (so that I can modify the list and update)
In my example below the only thing I am doing differently is collecting the results during each recursive step and adding to previous returns. I added some inline comments to hopefully better explain.
def find_list(data):
d = {} # initialize collection object to hold results
if not any([isinstance(data.get(k), dict) for k in data]):
return data
else:
for dkey in data:
if isinstance(data.get(dkey), dict):
# add results of each recursive call to the collection
d.update(find_list(data.get(dkey)))
return d # return the collection of results
Using your test dictionary with this example gives this output:
{
'Type1_key2_key1': ['Type1_list1'],
'Type1_key2_key2': ['Type1_list3', 'Type1_list4'],
'Type2_key2': ['Type2_list1', 'Type2_list2'],
'Type2_key3_key1': ['Type2_list3', 'Type2_list4']
}
I am trying to get a nested dict from a list of phrases.
My phrases for example are:
show version
show module
show module 0 det
show running-config
I am expecting a structure like this:
"show":{
"version":None,
"module":{
"0": {
"det"
}
},
"running-config":None
}
What I am trying is: split the phrases, from each array I am converting it to Dict.
for line in commandsOrdered:
value = line[-1]
line.pop(-1)
for key in list(reversed(line[:])):
value = {key: value}
sL.append(value)
And once I have a list of dicts, I am merging the dictionaries.
super_dict = {}
for d in sL:
for k, v in d.items():
super_dict.setdefault(k, []).append(v)
But I am getting this:
{
"show": [
"module",
{
"module": {
"0": "det"
}
},
"running-config",
"version"
],
"0": [
"det"
],
"module": [
{
"0": "det"
}
]
}
The max depth I have is 9 words in a phrase.
Any idea how to solve this?
Thanks
Something like this is fairly straightforward:
commandsOrdered = [
'show version',
'show module',
'show module 0 det',
'show running-config'
]
result = {}
for command in commandsOrdered:
parts = command.split()
d = result
for key in parts[:-1]:
if key not in d or not d[key]:
d[key] = {}
d = d[key]
d[parts[-1]] = None
print(result)
Output:
{'show': {'version': None, 'module': {'0': {'det': None}}, 'running-config': None}}
Not using defaultdict to meet the None requirement. You could easily write this recursively as well though, given the limited depth. That would make for simpler code, but not a faster solution per se.
I have a json object and I'm trying to extract a couple of values from a nested list. Then print them in markup. I'm getting and error - AttributeError: 'list' object has no attribute 'get'
I understand that it's a list and I can't preform a get. I've been searching for the proper method for a few hours now and I'm running out of steam. I'm able to get the Event, but not Value1 and Value2.
This is the json object
{
"resource": {
"data": {
"event": "qwertyuiop",
"eventVersion": "1.05",
"parameters": {
"name": "sometext",
"othername": [
""
],
"thing": {
"something": {
"blah": "whatever"
},
"abc": "123",
"def": {
"xzy": "value"
}
},
"something": [
"else"
]
},
"whatineed": [{
"value1": "text.i.need",
"value2": "text.i.need.also"
}]
}
}
}
And this is my function
def parse_json(json_data: dict) -> Info:
some_data = json_data.get('resource', {})
specific_data = some_data.get('data', {})
whatineed_data = specific_data.get('whatineed', {})
formatted_json = json.dumps(json_data, indent=2)
description = f'''
h3. Details
*Event:* {some_data.get('event')}
*Value1:* {whatineed_data('value1')}
*Value2:* {whatineed_data('value2')}
'''
From the data structure, whatineed is a list with a single item, which in turn is a dictionary. So, one way to access it would be:
whatineed_list = specific_data.get('whatineed', [])
whatineed_dict = whatineed_list[0]
At this point you can do:
value1 = whatineed_dict.get('value1')
value2 = whatineed_dict.get('value2')
You can change your function to the following:
def parse_json(json_data: dict) -> Info:
some_data = json_data.get('resource')
specific_data = some_data.get('data', {})
whatineed_data = specific_data.get('whatineed', {})
formatted_json = json.dumps(json_data, indent=2)
description = '''
h3. Details
*Event:* {}
*Value1:* {}
*Value2:* {}
'''.format(some_data.get('data').get('event'),whatineed_data[0]['value1'], whatineed_data[0]['value2'])
Since whatineed_data is a list, you need to index the element first
Python handles json as strings unless they are coming directly from a file. This could be the source for some of your problems. Also this article might help.
Assuming that "whatineed" attribute is really a list, and it's elements are dicts, you can't call whatineed.get asking for Value1 or Value2 as if they are attributes, because it is a list and it don't have attributes.
So, you have two options:
If whatineed list has a single element ever, you can access this element directly and than access the element attributes:
element = whatineed[0]
v1 = element.get('value1', {})
v2 = element.get('value2', {})
Or, if whatineed list can have more items, so, you will need to iterate over this list and access those elements:
for element in whatineed:
v1 = element.get('value1', {})
v2 = element.get('value2', {})
## Do something with values
With given script I am able to get output as I showed in a screenshot,
but there is a column named as cve.description.description_data which is again in json format. I want to extract that data as well.
import json
import pandas as pd
from pandas.io.json import json_normalize
#load json object
with open('nvdcve-1.0-modified.json') as f:
d = json.load(f)
#tells us parent node is 'programs'
nycphil = json_normalize(d['CVE_Items'])
nycphil.head(3)
works_data = json_normalize(data=d['CVE_Items'], record_path='cve')
works_data.head(3)
nycphil.to_csv("test4.csv")
If I change works_data = json_normalize(data=d['CVE_Items'], record_path='cve.descr') it gives this error:
"result = result[spec] KeyError: 'cve.description'"
JSON format as follows:
{
"CVE_data_type":"CVE",
"CVE_data_format":"MITRE",
"CVE_data_version":"4.0",
"CVE_data_numberOfCVEs":"1000",
"CVE_data_timestamp":"2018-04-04T00:00Z",
"CVE_Items":[
{
"cve":{
"data_type":"CVE",
"data_format":"MITRE",
"data_version":"4.0",
"CVE_data_meta":{
"ID":"CVE-2001-1594",
"ASSIGNER":"cve#mitre.org"
},
"affects":{
"vendor":{
"vendor_data":[
{
"vendor_name":"gehealthcare",
"product":{
"product_data":[
{
"product_name":"entegra_p&r",
"version":{
"version_data":[
{
"version_value":"*"
}
]
}
}
]
}
}
]
}
},
"problemtype":{
"problemtype_data":[
{
"description":[
{
"lang":"en",
"value":"CWE-255"
}
]
}
]
},
"references":{
"reference_data":[
{
"url":"http://apps.gehealthcare.com/servlet/ClientServlet/2263784.pdf?DOCCLASS=A&REQ=RAC&DIRECTION=2263784-100&FILENAME=2263784.pdf&FILEREV=5&DOCREV_ORG=5&SUBMIT=+ ACCEPT+"
},
{
"url":"http://www.forbes.com/sites/thomasbrewster/2015/07/10/vulnerable- "
},
{
"url":"https://ics-cert.us-cert.gov/advisories/ICSMA-18-037-02"
},
{
"url":"https://twitter.com/digitalbond/status/619250429751222277"
}
]
},
"description":{
"description_data":[
{
"lang":"en",
"value":"GE Healthcare eNTEGRA P&R has a password of (1) value."
}
]
}
},
"configurations":{
"CVE_data_version":"4.0",
"nodes":[
{
"operator":"OR",
"cpe":[
{
"vulnerable":true,
"cpe22Uri":"cpe:/a:gehealthcare:entegra_p%26r",
"cpe23Uri":"cpe:2.3:a:gehealthcare:entegra_p\\&r:*:*:*:*:*:*:*:*"
}
]
}
]
},
"impact":{
"baseMetricV2":{
"cvssV2":{
"version":"2.0",
"vectorString":"(AV:N/AC:L/Au:N/C:C/I:C/A:C)",
"accessVector":"NETWORK",
"accessComplexity":"LOW",
"authentication":"NONE",
"confidentialityImpact":"COMPLETE",
"integrityImpact":"COMPLETE",
"availabilityImpact":"COMPLETE",
"baseScore":10.0
},
"severity":"HIGH",
"exploitabilityScore":10.0,
"impactScore":10.0,
"obtainAllPrivilege":false,
"obtainUserPrivilege":false,
"obtainOtherPrivilege":false,
"userInteractionRequired":false
}
},
"publishedDate":"2015-08-04T14:59Z",
"lastModifiedDate":"2018-03-28T01:29Z"
}
]
}
I want to flatten all data.
Assuming the multiple URLs delineate between rows and all else meta data repeats, consider a recursive function call to extract every key-value pair in nested json object, d.
The recursive function will call global to update the needed global objects to be binded into a list of dictionaries for pd.DataFrame() call. Last loop at end updates the recursive function's dictionary, inner, to integrate the different urls (stored in multi)
import json
import pandas as pd
# load json object
with open('nvdcve-1.0-modified.json') as f:
d = json.load(f)
multi = []; inner = {}
def recursive_extract(i):
global multi, inner
if type(i) is list:
if len(i) == 1:
for k,v in i[0].items():
if type(v) in [list, dict]:
recursive_extract(v)
else:
inner[k] = v
else:
multi = i
if type(i) is dict:
for k,v in i.items():
if type(v) in [list, dict]:
recursive_extract(v)
else:
inner[k] = v
recursive_extract(d['CVE_Items'])
data_dict = []
for i in multi:
tmp = inner.copy()
tmp.update(i)
data_dict.append(tmp)
df = pd.DataFrame(data_dict)
df.to_csv('Output.csv')
Output (all columns the same except for URL, widened for emphasis)