Unable to read json data using python

Question

unable to load read json data

Code:

import json
import pymysql
import os

with open("C:/feed/datafile2021-02-23_15.json", "r") as myfile:
   

 data=myfile.read()

obj = json.loads(data)
ac_obj=obj["data"]
print(ac_obj)

json Data:

{
  "query_status": "ok",
  "data": [
    {
      "sha256_hash": "8291db6ed7f2be2e014d6ad586a2fa2021c6f59334416e1042ed88edea137d0b",
      "sha3_384_hash": "d684410f118253b96c5799aa44e3e2ef1d9ef9728ee6ee13cd6c076368f5a9de8189779a0214e26398f4e48915284013",
      "sha1_hash": "20590d6000caf00092b80e3bfc740c492e2f7e50",
      "md5_hash": "ff26664f179c0a189471183aa87e3c4a",
      "first_seen": "2021-02-23 08:46:04",
      "last_seen": null,
      "file_name": "SecuriteInfo.com.Variant.Zusy.368685.25618.6070",
      "file_size": 2684128,
      "file_type_mime": "application/x-dosexec",
      "file_type": "exe",
      "reporter": "SecuriteInfoCom",
      "origin_country": "FR",
      "anonymous": 0,
      "signature": null,
      "imphash": "4328f7206db519cd4e82283211d98e83",
      "tlsh": "34C533817B3D457AE4E3C93293F3F61E4FB4920C956869FB5B79C1203DA9F0250A924B",
      "ssdeep": "49152:z+cw5wkXuOdHLP+0ZSq5DhWNA0ZriICJEz3eUdWot2K0pHcAZaRMEZpk:KcWwG1dH60tj0ZWIyEz3tWotZ2HcA7Ek",
      "tags": null,
      "code_sign": [],
      "intelligence": {
        "clamav": null,
        "downloads": "20",
        "uploads": "1",
        "mail": null
      }
    },
    {
      "sha256_hash": "3d3112ce7c1a80e0378b15c7084b1b49a9805a5e47a85a97acdd7841d0a9b40b",
      "sha3_384_hash": "1ff30f891e4b6eb421a5181373943bf23cc8633f66cc20265450ffc255047aae308344a71a74d1794b14323c41c4276b",
      "sha1_hash": "b24be163878f851e0b9bc5da8967879d5ff3d846",
      "md5_hash": "e48ba1147b75508b7f58cace584373cb",
      "first_seen": "2021-02-23 08:45:59",
      "last_seen": null,
      "file_name": "SecuriteInfo.com.Trojan.GenericKDZ.73123.31244.15546",
      "file_size": 555008,
      "file_type_mime": "application/x-dosexec",
      "file_type": "exe",
      "reporter": "SecuriteInfoCom",
      "origin_country": "US",
      "anonymous": 0,
      "signature": null,
      "imphash": "71b77d57e8aec8db116eba9e387ce755",
      "tlsh": "79C4D010BBF1D035F6B266F4497992A5A93ABD717B3480CF53C626DA1A386E09C31723",
      "ssdeep": "12288:it0DzYl40RFrFMFf7CphShPDd+ByKZz+RfCJP079dwkkV46D25sT6fVU:imDItRFZMIphShZzsyCJP0pcV46DusT7",
      "tags": null,
      "code_sign": [],
      "intelligence": {
        "clamav": null,
        "downloads": "15",
        "uploads": "1",
        "mail": null
      }
    }
  ]
}

Error log:

Traceback (most recent call last):
  File ".\sampletest.py", line 10, in <module>
    obj = json.loads(data)
  File "C:\Program Files\Python38\lib\json\__init__.py", line 357, in loads    
    return _default_decoder.decode(s)
  File "C:\Program Files\Python38\lib\json\decoder.py", line 337, in decode    
    obj, end = self.raw_decode(s, idx=_w(s, 0).end())
  File "C:\Program Files\Python38\lib\json\decoder.py", line 355, in raw_decode
    raise JSONDecodeError("Expecting value", s, err.value) from None
json.decoder.JSONDecodeError: Expecting value: line 1 column 1 (char 0)

Check your file contents. Print out data to make sure it's what you expect it to be — rdas
– rdas, Commented Feb 23, 2021 at 10:32
@rdas when i print the data geeting like this ÿþ{ "query_status": "ok", "data": [ { "sha256_hash": "8291db6ed7f2be2e014d6ad586a2fa2021c6f59334416e1042ed88edea137d0b", "md5_hash": "ff26664f179c0a189471183aa87e3c4a", "first_seen": "2021-02-23 08:46:04", "last_seen": null, "file_name": "SecuriteInfo.com.Variant.Zusy.368685.25618.6070", "file_size": 2684128, "mail": null } } after passing data to loads function not getting data obj = json.loads(data) — yugandarA
– yugandarA, Commented Feb 23, 2021 at 10:39

bherbruck · Accepted Answer · 2021-02-23 13:20:47Z

1

You don't need to read the file then json.loads(), you can just use json.load() and that data works fine for me:

import json

def read_json(path):
    with open(path, 'r') as file:
        return json.load(file)

data = read_json('data.json')

# pretty print the output
from pprint import pprint
pprint(data)

Output:

{'data': [{'anonymous': 0,
           'code_sign': [],
           'file_name': 'SecuriteInfo.com.Variant.Zusy.368685.25618.6070',      
           'file_size': 2684128,
           'file_type': 'exe',
           'file_type_mime': 'application/x-dosexec',
           'first_seen': '2021-02-23 08:46:04',
           'imphash': '4328f7206db519cd4e82283211d98e83',
           'intelligence': {'clamav': None,
                            'downloads': '20',
                            'mail': None,
                            'uploads': '1'},
           'last_seen': None,
           'md5_hash': 'ff26664f179c0a189471183aa87e3c4a',
           'origin_country': 'FR',
           'reporter': 'SecuriteInfoCom',
           'sha1_hash': '20590d6000caf00092b80e3bfc740c492e2f7e50',
           'sha256_hash': '8291db6ed7f2be2e014d6ad586a2fa2021c6f59334416e1042ed88edea137d0b',
           'sha3_384_hash': 'd684410f118253b96c5799aa44e3e2ef1d9ef9728ee6ee13cd6c076368f5a9de8189779a0214e26398f4e48915284013',
           'signature': None,
           'ssdeep': '49152:z+cw5wkXuOdHLP+0ZSq5DhWNA0ZriICJEz3eUdWot2K0pHcAZaRMEZpk:KcWwG1dH60tj0ZWIyEz3tWotZ2HcA7Ek',
           'tags': None,
           'tlsh': '34C533817B3D457AE4E3C93293F3F61E4FB4920C956869FB5B79C1203DA9F0250A924B'},
          {'anonymous': 0,
           'code_sign': [],
           'file_name': 'SecuriteInfo.com.Trojan.GenericKDZ.73123.31244.15546', 
           'file_size': 555008,
           'file_type': 'exe',
           'file_type_mime': 'application/x-dosexec',
           'first_seen': '2021-02-23 08:45:59',
           'imphash': '71b77d57e8aec8db116eba9e387ce755',
           'intelligence': {'clamav': None,
                            'downloads': '15',
                            'mail': None,
                            'uploads': '1'},
           'last_seen': None,
           'md5_hash': 'e48ba1147b75508b7f58cace584373cb',
           'origin_country': 'US',
           'reporter': 'SecuriteInfoCom',
           'sha1_hash': 'b24be163878f851e0b9bc5da8967879d5ff3d846',
           'sha256_hash': '3d3112ce7c1a80e0378b15c7084b1b49a9805a5e47a85a97acdd7841d0a9b40b',
           'sha3_384_hash': '1ff30f891e4b6eb421a5181373943bf23cc8633f66cc20265450ffc255047aae308344a71a74d1794b14323c41c4276b',
           'signature': None,
           'ssdeep': '12288:it0DzYl40RFrFMFf7CphShPDd+ByKZz+RfCJP079dwkkV46D25sT6fVU:imDItRFZMIphShZzsyCJP0pcV46DusT7',
           'tags': None,
           'tlsh': '79C4D010BBF1D035F6B266F4497992A5A93ABD717B3480CF53C626DA1A386E09C31723'}],
 'query_status': 'ok'}

answered Feb 23, 2021 at 13:20

bherbruck

2,2161 gold badge8 silver badges18 bronze badges

Sign up to request clarification or add additional context in comments.

4 Comments

bherbruck Over a year ago

@GoldenLion that's what is done here, just in a reusable function as not to introduce spaghetti into the code.

ListenSoftware Louise Ai Agent Over a year ago

the json string can be assigned directly to a dataframe. pd.DataFrame(myjson). If the json is hierarchial than use json_normalize to flatten out the data then move it to a dataframe.

bherbruck Over a year ago

the question didn't mention pandas, it is an extra package to install and IMO pandas can be a bit overkill in many applications and too many people rely on it for all their ETL nowadays

ListenSoftware Louise Ai Agent Over a year ago

pandas has some overhead but most of the visualization can be done with it. Pandas is a desired end goal.

Collectives™ on Stack Overflow

Unable to read json data using python

1 Answer 1

4 Comments

Your Answer

Hot Network Questions

Collectives™ on Stack Overflow

1 Answer 1

4 Comments

Your Answer

Sign up or log in

Post as a guest

Related