How to remove whitespaces and newlines from every value in a JSON file?

Question

I have a JSON file that has the following structure:

{
    \"name\":[
        {
            \"someKey\": \"\\n\\n   some Value   \"
        },
          


        

Answer 1

Now I want to strip off all he whitespaces and newlines for every value in the JSON file

Using pkgutil.simplegeneric() to create a helper function get_items():

import json
import sys
from pkgutil import simplegeneric

@simplegeneric
def get_items(obj):
    while False: # no items, a scalar object
        yield None

@get_items.register(dict)
def _(obj):
    return obj.items() # json object. Edit: iteritems() was removed in Python 3

@get_items.register(list)
def _(obj):
    return enumerate(obj) # json array

def strip_whitespace(json_data):
    for key, value in get_items(json_data):
        if hasattr(value, 'strip'): # json string
            json_data[key] = value.strip()
        else:
            strip_whitespace(value) # recursive call


data = json.load(sys.stdin) # read json data from standard input
strip_whitespace(data)
json.dump(data, sys.stdout, indent=2)

Note: functools.singledispatch() function (Python 3.4+) would allow to use collections' MutableMapping/MutableSequence instead of dict/list here.

Output

{
  "anotherName": [
    {
      "anArray": [
        {
          "anotherKey": "value", 
          "key": "value"
        }, 
        {
          "anotherKey": "value", 
          "key": "value"
        }
      ]
    }
  ], 
  "name": [
    {
      "someKey": "some Value"
    }, 
    {
      "someKey": "another value"
    }
  ]
}

Answer 2

Parse the file using JSON:

import json
file = file.replace('\n', '')    # do your cleanup here
data = json.loads(file)

then walk through the resulting data structure.

Answer 3

This may not be the most efficient process, but it works. I copied that sample into a file named json.txt, then read it, deserialized it with json.loads(), and used a pair of functions to recursively clean it and everything inside it.

import json

def clean_dict(d):
    for key, value in d.iteritems():
        if isinstance(value, list):
            clean_list(value)
        elif isinstance(value, dict):
            clean_dict(value)
        else:
            newvalue = value.strip()
            d[key] = newvalue

def clean_list(l):
    for index, item in enumerate(l):
        if isinstance(item, dict):
            clean_dict(item)
        elif isinstance(item, list):
            clean_list(item)
        else:
            l[index] = item.strip()

# Read the file and send it to the dict cleaner
with open("json.txt") as f:
    data = json.load(f)

print "before..."
print data, "\n"

clean_dict(data)

print "after..."
print data

The result...

before...
{u'anotherName': [{u'anArray': [{u'anotherKey': u'  value', u'key': u'    value\n\n'}, {u'anotherKey': u'value', u'key': u'    value\n'}]}], u'name': [{u'someKey': u'\n\n   some Value   '}, {u'someKey': u'another value    '}]} 

after...
{u'anotherName': [{u'anArray': [{u'anotherKey': u'value', u'key': u'value'}, {u'anotherKey': u'value', u'key': u'value'}]}], u'name': [{u'someKey': u'some Value'}, {u'someKey': u'another value'}]}