Retrieving JSON objects from a text file (using Python)

This decodes your “list” of JSON Objects from a string:

from json import JSONDecoder

def loads_invalid_obj_list(s):
    decoder = JSONDecoder()
    s_len = len(s)

    objs = []
    end = 0
    while end != s_len:
        obj, end = decoder.raw_decode(s, idx=end)
        objs.append(obj)

    return objs

The bonus here is that you play nice with the parser. Hence it keeps telling you exactly where it found an error.

Examples

>>> loads_invalid_obj_list('{}{}')
[{}, {}]

>>> loads_invalid_obj_list('{}{\n}{')
Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
  File "decode.py", line 9, in loads_invalid_obj_list
    obj, end = decoder.raw_decode(s, idx=end)
  File     "/System/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/json/decoder.py", line 376, in raw_decode
    obj, end = self.scan_once(s, idx)
ValueError: Expecting object: line 2 column 2 (char 5)

Clean Solution (added later)

import json
import re

#shameless copy paste from json/decoder.py
FLAGS = re.VERBOSE | re.MULTILINE | re.DOTALL
WHITESPACE = re.compile(r'[ \t\n\r]*', FLAGS)

class ConcatJSONDecoder(json.JSONDecoder):
    def decode(self, s, _w=WHITESPACE.match):
        s_len = len(s)

        objs = []
        end = 0
        while end != s_len:
            obj, end = self.raw_decode(s, idx=_w(s, end).end())
            end = _w(s, end).end()
            objs.append(obj)
        return objs

Examples

>>> print json.loads('{}', cls=ConcatJSONDecoder)
[{}]

>>> print json.load(open('file'), cls=ConcatJSONDecoder)
[{}]

>>> print json.loads('{}{} {', cls=ConcatJSONDecoder)
Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
  File "/System/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/json/__init__.py", line 339, in loads
    return cls(encoding=encoding, **kw).decode(s)
  File "decode.py", line 15, in decode
    obj, end = self.raw_decode(s, idx=_w(s, end).end())
  File "/System/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/json/decoder.py", line 376, in raw_decode
    obj, end = self.scan_once(s, idx)
ValueError: Expecting object: line 1 column 5 (char 5)