How to recursively find specific key in nested JSON?
Question:
I’m trying to pull nested values from a json file. I want to print out each of the values for every “id” key. I think I’m close but can’t figure out why the obj type changes from a dict to a list, and then why I’m unable to parse that list.
Here is a link to the json I’m working with: http://hastebin.com/ratevimixa.tex
and here is my current code:
#!/usr/bin/env python
#-*- coding: utf-8 -*-
import json
json_data = open('JubJubProductions.json', 'r+')
jdata = json.loads(json_data.read().decode("utf-8"))
def recursion(dict):
for key, value in dict.items():
if type(value) == type(dict):
if key != "paging":
for key, value in value.items():
if isinstance (value,list):
print key
# place where I need to enter list comprehension?
if type(value) == type(dict):
if key == "id":
print " id found " + value
if key != "id":
print key + " 1st level"
if key == "id":
print key
else:
if key == "id":
print "id found " + value
if __name__ == '__main__':
recursion(jdata)
——————————————————————————————-update
This is now what I’m working with and it’ll return a single id value, but not all of them:
#!/usr/bin/env python
#-*- coding: utf-8 -*-
import json
json_data = open('jubjubProductions', 'r+')
jdata = json.loads(json_data.read().decode("utf-8"))
def id_generator(d):
for k, v in d.items():
if k == "id":
yield v
elif isinstance(v, dict):
for id_val in id_generator(v):
yield id_val
if __name__ == '__main__':
for _ in id_generator(jdata):
print (_)
Answers:
def id_generator(dict_var):
for k, v in dict_var.items():
if k == "id":
yield v
elif isinstance(v, dict):
for id_val in id_generator(v):
yield id_val
This will create an iterator which will yield every value on any level under key “id”. Example usage (printing all of those values):
for _ in id_generator(some_json_dict):
print(_)
The JSON might contain a list of objects, which needs to be searched:
Python 2.7 version:
def item_generator(json_input, lookup_key):
if isinstance(json_input, dict):
for k, v in json_input.iteritems():
if k == lookup_key:
yield v
else:
for child_val in item_generator(v, lookup_key):
yield child_val
elif isinstance(json_input, list):
for item in json_input:
for item_val in item_generator(item, lookup_key):
yield item_val
Python 3.x version:
def item_generator(json_input, lookup_key):
if isinstance(json_input, dict):
for k, v in json_input.items():
if k == lookup_key:
yield v
else:
yield from item_generator(v, lookup_key)
elif isinstance(json_input, list):
for item in json_input:
yield from item_generator(item, lookup_key)
A little bit cleaner code (in python 3.x).
def parse_json_recursively(json_object, target_key):
if type(json_object) is dict and json_object:
for key in json_object:
if key == target_key:
print("{}: {}".format(target_key, json_object[key]))
parse_json_recursively(json_object[key], target_key)
elif type(json_object) is list and json_object:
for item in json_object:
parse_json_recursively(item, target_key)
json_object = {"key1": "val1", "key2": [{"key3":"val3", "key4": "val4"}, 123, "abc"]}
target_key = "key3"
parse_json_recursively(json_object, target_key) # Ouput key3: val3
def get_val(j, s, v=None):
for k in j:
if v == None and k == s:
return j[k]
elif v != None and k == s and v == j[k]:
return True
elif v != None and k == s and v != j[k]:
return False
elif isinstance(j[k], dict):
return get_val(j[k], s, v)
You can use with for a json list l below,
for l in j:
r = get_val(l, 'key')
print(r)
for l in j:
r = get_val(l, 'mac', '00-60-2F-5A-04-51')
print(r)
Extension to python 3.x answer:
If nested json has similar keys under different list or dictionaries and you want to take first value of it..
below is the generic way:
def get_value_from_generator(json_input, lookup_key):
value = list(item_generator(json_input, lookup_key))
val = value[0] if value else None
print(f'lookup_key -> value : {val}')
return val
def item_generator(json_input, lookup_key):
if isinstance(json_input, dict):
for k, v in json_input.items():
print(f'{k} -- {v}')
if k == lookup_key:
yield v
else:
yield from item_generator(v, lookup_key)
elif isinstance(json_input, list):
for item in json_input:
yield from item_generator(item, lookup_key)
Here is a simple recursive function to collect all values from a json document for a given key. Values can be json documents as well. The corresponding values appended to search_result.
def json_full_search(lookup_key, json_dict, search_result = []):
if type(json_dict) == dict:
for key, value in json_dict.items():
if key == lookup_key:
search_result.append(value)
json_full_search(lookup_key, value, search_result)
elif type(json_dict) == list:
for element in json_dict:
json_full_search(lookup_key, element, search_result)
return search_result
I’m trying to pull nested values from a json file. I want to print out each of the values for every “id” key. I think I’m close but can’t figure out why the obj type changes from a dict to a list, and then why I’m unable to parse that list.
Here is a link to the json I’m working with: http://hastebin.com/ratevimixa.tex
and here is my current code:
#!/usr/bin/env python
#-*- coding: utf-8 -*-
import json
json_data = open('JubJubProductions.json', 'r+')
jdata = json.loads(json_data.read().decode("utf-8"))
def recursion(dict):
for key, value in dict.items():
if type(value) == type(dict):
if key != "paging":
for key, value in value.items():
if isinstance (value,list):
print key
# place where I need to enter list comprehension?
if type(value) == type(dict):
if key == "id":
print " id found " + value
if key != "id":
print key + " 1st level"
if key == "id":
print key
else:
if key == "id":
print "id found " + value
if __name__ == '__main__':
recursion(jdata)
——————————————————————————————-update
This is now what I’m working with and it’ll return a single id value, but not all of them:
#!/usr/bin/env python
#-*- coding: utf-8 -*-
import json
json_data = open('jubjubProductions', 'r+')
jdata = json.loads(json_data.read().decode("utf-8"))
def id_generator(d):
for k, v in d.items():
if k == "id":
yield v
elif isinstance(v, dict):
for id_val in id_generator(v):
yield id_val
if __name__ == '__main__':
for _ in id_generator(jdata):
print (_)
def id_generator(dict_var):
for k, v in dict_var.items():
if k == "id":
yield v
elif isinstance(v, dict):
for id_val in id_generator(v):
yield id_val
This will create an iterator which will yield every value on any level under key “id”. Example usage (printing all of those values):
for _ in id_generator(some_json_dict):
print(_)
The JSON might contain a list of objects, which needs to be searched:
Python 2.7 version:
def item_generator(json_input, lookup_key):
if isinstance(json_input, dict):
for k, v in json_input.iteritems():
if k == lookup_key:
yield v
else:
for child_val in item_generator(v, lookup_key):
yield child_val
elif isinstance(json_input, list):
for item in json_input:
for item_val in item_generator(item, lookup_key):
yield item_val
Python 3.x version:
def item_generator(json_input, lookup_key):
if isinstance(json_input, dict):
for k, v in json_input.items():
if k == lookup_key:
yield v
else:
yield from item_generator(v, lookup_key)
elif isinstance(json_input, list):
for item in json_input:
yield from item_generator(item, lookup_key)
A little bit cleaner code (in python 3.x).
def parse_json_recursively(json_object, target_key):
if type(json_object) is dict and json_object:
for key in json_object:
if key == target_key:
print("{}: {}".format(target_key, json_object[key]))
parse_json_recursively(json_object[key], target_key)
elif type(json_object) is list and json_object:
for item in json_object:
parse_json_recursively(item, target_key)
json_object = {"key1": "val1", "key2": [{"key3":"val3", "key4": "val4"}, 123, "abc"]}
target_key = "key3"
parse_json_recursively(json_object, target_key) # Ouput key3: val3
def get_val(j, s, v=None):
for k in j:
if v == None and k == s:
return j[k]
elif v != None and k == s and v == j[k]:
return True
elif v != None and k == s and v != j[k]:
return False
elif isinstance(j[k], dict):
return get_val(j[k], s, v)
You can use with for a json list l below,
for l in j:
r = get_val(l, 'key')
print(r)
for l in j:
r = get_val(l, 'mac', '00-60-2F-5A-04-51')
print(r)
Extension to python 3.x answer:
If nested json has similar keys under different list or dictionaries and you want to take first value of it..
below is the generic way:
def get_value_from_generator(json_input, lookup_key):
value = list(item_generator(json_input, lookup_key))
val = value[0] if value else None
print(f'lookup_key -> value : {val}')
return val
def item_generator(json_input, lookup_key):
if isinstance(json_input, dict):
for k, v in json_input.items():
print(f'{k} -- {v}')
if k == lookup_key:
yield v
else:
yield from item_generator(v, lookup_key)
elif isinstance(json_input, list):
for item in json_input:
yield from item_generator(item, lookup_key)
Here is a simple recursive function to collect all values from a json document for a given key. Values can be json documents as well. The corresponding values appended to search_result.
def json_full_search(lookup_key, json_dict, search_result = []):
if type(json_dict) == dict:
for key, value in json_dict.items():
if key == lookup_key:
search_result.append(value)
json_full_search(lookup_key, value, search_result)
elif type(json_dict) == list:
for element in json_dict:
json_full_search(lookup_key, element, search_result)
return search_result