Develop Reference

How to pick up data from json objects in python?

I am trying to pick Instances in the json objects data which looks like this
[{'Groups': [], 'Instances': [{'AmiLaunchIndex': 0, 'ImageId': 'ami-0ceecbb0f30a902a6', 'InstanceId': 'i-xxxxx', 'InstanceType': 't2.micro', 'KeyName': 'xxxx', 'LaunchTime': {'$date': '2022-12-17T13:07:54Z'}, 'Monitoring': {'State': 'disabled'}, 'Placement': {'AvailabilityZone': 'us-west-2b', 'GroupName': '', 'Tenancy': 'default'}, 'PrivateDnsName': 'ip-zxxxxx.us-west-2.compute.internal', 'PrivateIpAddress': 'xxxxx', 'ProductCodes': [], 'PublicDnsName': 'ec2-xx-xxx-xxx.us-west-2.compute.amazonaws.com', 'PublicIpAddress': 'xxxxxx', 'State': {'Code': 16, 'Name': 'running'}, 'StateTransitionReason': '', 'SubnetId': 'subnet-xxxxx', 'VpcId': 'vpc-xxxxx', 'Architecture': 'x86_64', 'BlockDeviceMappings': [{'DeviceName': '/dev/xvda', 'Ebs': {'AttachTime': {'$date': '2022-12-17T13:07:55Z'}, 'DeleteOnTermination': True, 'Status': 'attached', 'VolumeId': 'vol-xxxx'}}], 'ClientToken': '529fc1ac-bf64-4804-b0b8-7c7778ace68c', 'EbsOptimized': False, 'EnaSupport': True, 'Hypervisor': 'xen', 'NetworkInterfaces': [{'Association': {'IpOwnerId': 'amazon', 'PublicDnsName': 'ec2-35-86-111-31.us-west-2.compute.amazonaws.com', 'PublicIp': 'xxxxx'}, 'Attachment': {'AttachTime': {'$date': '2022-12-17T13:07:54Z'}, 'AttachmentId': 'eni-attach-0cac7d4af20664b23', 'DeleteOnTermination': True, 'DeviceIndex': 0, 'Status': 'attached', 'NetworkCardIndex': 0}, 'Description': '', 'Groups': [{'GroupName': 'launch-wizard-5', 'GroupId': 'sg-xxxxx'}], 'Ipv6Addresses': [], 'MacAddress': 'xxxxx', 'NetworkInterfaceId': 'eni-xxxxx', 'OwnerId': 'xxxx', 'PrivateDnsName': 'ip-xxxxx.us-west-2.compute.internal', 'PrivateIpAddress': 'xxx.xxx.xxx', 'PrivateIpAddresses': [{'Association': {'IpOwnerId': 'amazon', 'PublicDnsName': 'ec2-xx-xx-xx-xxx.us-west-2.compute.amazonaws.com', 'PublicIp': 'xxx.xxx.xxx'}, 'Primary': True, 'PrivateDnsName': 'ip-172-31-20-187.us-west-2.compute.internal', 'PrivateIpAddress': 'xxx.xxx.xxx'}], 'SourceDestCheck': True, 'Status': 'in-use', 'SubnetId': 'subnet-xxxxxxx', 'VpcId': 'vpc-0b09cd4sedxxx', 'InterfaceType': 'interface'}], 'RootDeviceName': '/dev/xvda', 'RootDeviceType': 'ebs', 'SecurityGroups': [{'GroupName': 'launch-wizard-5', 'GroupId': 'sg-0a0d1c79d8076660e'}], 'SourceDestCheck': True, 'Tags': [{'Key': 'Name', 'Value': 'MainServers'}], 'VirtualizationType': 'hvm', 'CpuOptions': {'CoreCount': 1, 'ThreadsPerCore': 1}, 'CapacityReservationSpecification': {'CapacityReservationPreference': 'open'}, 'HibernationOptions': {'Configured': False}, 'MetadataOptions': {'State': 'applied', 'HttpTokens': 'optional', 'HttpPutResponseHopLimit': 1, 'HttpEndpoint': 'enabled', 'HttpProtocolIpv6': 'disabled', 'InstanceMetadataTags': 'disabled'}, 'EnclaveOptions': {'Enabled': False}, 'PlatformDetails': 'Linux/UNIX', 'UsageOperation': 'RunInstances', 'UsageOperationUpdateTime': {'$date': '2022-12-17T13:07:54Z'}, 'PrivateDnsNameOptions': {'HostnameType': 'ip-name', 'EnableResourceNameDnsARecord': True, 'EnableResourceNameDnsAAAARecord': False}, 'MaintenanceOptions': {'AutoRecovery': 'default'}}], 'OwnerId': '76979cfxdsss11', 'ReservationId': 'r-xxxxx'}]
I tired loading data and doing
resp = json.loads(jsonfile)
reqData= resp['Instances']
But getting error
TypeError: list indices must be integers or slices, not str
Is there any way I can fix this and get the data? Help will be extremely appriciated.

It's wrapped inside a list. So simply do:
print(lst[0]["Instances"])

To select only the instances from the data, you can use the json.loads function to parse the JSON data and extract the Instances field as a list.
import json
# Parse the JSON data
data = json.loads(json_data)
# Extract the instances
instances = data['Instances']
You can then iterate over the data with something like this
for instance in instances:
instance_id = instance['InstanceId']
instance_type = instance['InstanceType']
launch_time = instance['LaunchTime']

How to rename keys in a dictionary and make a dataframe of it?

I have a complex situation which I hope to solve and which might profit us all. I collected data from my API, added a pagination and inserted the complete data package in a tuple named q1 and finally I have made a dictionary named dict_1of that tuple which looks like this:
dict_1 = {100: {'ID': 100, 'DKSTGFase': None, 'DK': False, 'KM': None,
'Country: {'Name': GE', 'City': {'Name': 'Berlin'}},
'Type': {'Name': '219'}, 'DKObject': {'Name': '8555', 'Object': {'Name': 'Car'}},
'Order': {'OrderId': 101, 'CreatedOn': '2018-07-06T16:54:36.783+02:00',
'ModifiedOn': '2018-07-06T16:54:36.783+02:00',
'Name': Audi, 'Client': {‘1’ }}, 'DKComponent': {'Name': ‘John’}},
{200: {'ID': 200, 'DKSTGFase': None, 'DK': False, ' KM ': None,
'Country: {'Name': ES', 'City': {'Name': 'Madrid'}}, 'Type': {'Name': '220'},
'DKObject': {'Name': '8556', 'Object': {'Name': 'Car'}},
'Order': {'OrderId': 102, 'CreatedOn': '2018-07-06T16:54:36.783+02:00',
'ModifiedOn': '2018-07-06T16:54:36.783+02:00',
'Name': Mercedes, 'Client': {‘2’ }}, 'DKComponent': {'Name': ‘Sergio’}},
Please note that in the above dictionary I have just stated 2 records. The actual dictionary has 1400 records till it reaches ID 1500.
Now I want to 2 things:
I want to change some keys for all the records. key DK has to become DK1. Key Name in Country has to become Name1 and Name in Object has to become 'Name2'
The second thing I want is to make a dataFrame of the whole bunch of data. My expected outcome is:
This is my code:
q1 = response_2.json()
next_link = q1['#odata.nextLink']
q1 = [tuple(q1.values())]
while next_link:
new_response = requests.get(next_link, headers=headers, proxies=proxies)
new_data = new_response.json()
q1.append(tuple(new_data.values()))
next_link = new_data.get('#odata.nextLink', None)
dict_1 = {
record['ID']: record
for tup in q1
for record in tup[2]
}
#print(dict_1)
for x in dict_1.values():
x['DK1'] = x['DK']
x['Country']['Name1'] = x['Country']['Name']
x['Object']['Name2'] = x['Object']['Name']
df = pd.DataFrame(dict_1)
When i run this I receive the following Error:
Traceback (most recent call last):
File "c:\data\FF\Desktop\Python\PythongMySQL\Talky.py", line 57, in <module>
x['Country']['Name1'] = x['Country']['Name']
TypeError: 'NoneType' object is not subscriptable

working code
lists=[]
alldict=[{100: {'ID': 100, 'DKSTGFase': None, 'DK': False, 'KM': None,
'Country': {'Name': 'GE', 'City': {'Name': 'Berlin'}},
'Type': {'Name': '219'}, 'DKObject': {'Name': '8555', 'Object': {'Name': 'Car'}},
'Order': {'OrderId': 101, 'CreatedOn': '2018-07-06T16:54:36.783+02:00',
'ModifiedOn': '2018-07-06T16:54:36.783+02:00',
'Name': 'Audi', 'Client': {'1' }}, 'DKComponent': {'Name': 'John'}}}]
for eachdict in alldict:
key=list(eachdict.keys())[0]
eachdict[key]['DK1']=eachdict[key]['DK']
del eachdict[key]['DK']
eachdict[key]['Country']['Name1']=eachdict[key]['Country']['Name']
del eachdict[key]['Country']['Name']
eachdict[key]['DKObject']['Object']['Name2']=eachdict[key]['DKObject']['Object']['Name']
del eachdict[key]['DKObject']['Object']['Name']
lists.append([key, eachdict[key]['DK1'], eachdict[key]['KM'], eachdict[key]['Country']['Name1'],
eachdict[key]['Country']['City']['Name'], eachdict[key]['DKObject']['Object']['Name2'], eachdict[key]['Order']['Client']])
pd.DataFrame(lists, columns=[<columnNamesHere>])
Output:
{100: {'ID': 100,
'DKSTGFase': None,
'KM': None,
'Country': {'City': {'Name': 'Berlin'}, 'Name1': 'GE'},
'Type': {'Name': '219'},
'DKObject': {'Name': '8555', 'Object': {'Name2': 'Car'}},
'Order': {'OrderId': 101,
'CreatedOn': '2018-07-06T16:54:36.783+02:00',
'ModifiedOn': '2018-07-06T16:54:36.783+02:00',
'Name': 'Audi',
'Client': {'1'}},
'DKComponent': {'Name': 'John'},
'DK1': False}}

From MongoDB convert from dictionary to row with Pandas

This is a test coming from MongoDB, I need to convert to MySQL. But! Sometimes there is more then one "agents", if that's the case I need each agent on their own row and that agent should have the same "display_name". For example Walter should have Gloria on one row and Barb on next and both have Walt Mosley under "display_name".
[{'name': 'Loomis, Gloria',
'primaryemail': 'gloria#gmail.com',
'primaryphone': '212-382-1121'},
{'name': 'Hogson, Barb',
'primaryemail': 'bho124#aol.com',
'primaryphone': ''}]
I've tried this but it just splits out the key/values.
a,b,c = [[d[e] for d in test] for e in sorted(test[0].keys())]
print(a,b,c)
This is the original JSON format:
{'_id': ObjectId('58e6ececafb08d6'),
'item_type': 'Contributor',
'role': 0,
'short_bio': 'Walter Mosley (b. 1952)',
'firebrand_id': 1588,
'display_name': 'Walter Mosley',
'first_name': 'Walter',
'last_name': 'Mosley',
'slug': 'walter-mosley',
'updated': datetime.datetime(2020, 1, 7, 8, 17, 11, 926000),
'image': 'https://s3.amazonaws.com/8588-book-contributor.jpg',
'social_media_name': '',
'social_media_link': '',
'website': '',
'agents': [{'name': 'Loomis, Gloria',
'primaryemail': 'gloria#gmail.com',
'primaryphone': '212-382-1121'},
{'name': 'Hogson, Barb',
'primaryemail': 'bho124#aol.com',
'primaryphone': ''}],
'estates': [],
'deleted': False}

If you've an array of dictionaries from your JSON file, try this :
JSON input :
inputJSON = [{'item_type': 'Contributor',
'role': 0,
'short_bio': 'Walter Mosley (b. 1952)',
'firebrand_id': 1588,
'display_name': 'Walter Mosley',
'first_name': 'Walter',
'last_name': 'Mosley',
'slug': 'walter-mosley',
'image': 'https://s3.amazonaws.com/8588-book-contributor.jpg',
'social_media_name': '',
'social_media_link': '',
'website': '',
'agents': [{'name': 'Loomis, Gloria',
'primaryemail': 'gloria#gmail.com',
'primaryphone': '212-382-1121'},
{'name': 'Hogson, Barb',
'primaryemail': 'bho124#aol.com',
'primaryphone': ''}],
'estates': [],
'deleted': False}]
Code :
import copy
finalJSON = []
for each in inputJSON:
for agnt in each.get('agents'):
newObj = copy.deepcopy(each)
newObj['agents'] = agnt
finalJSON.append(newObj)
print(finalJSON)

TypeError: an integer is required when select subset of rows dataframe pandas

{'contributors': None,
'coordinates': None,
'created_at': 'Tue Aug 02 19:51:58 +0000 2016',
'entities': {'hashtags': [],
'symbols': [],
'urls': [],
'user_mentions': [{'id': 873491544,
'id_str': '873491544',
'indices': [0, 13],
'name': 'Kenel M',
'screen_name': 'KxSweaters13'}]},
'favorite_count': 1,
'favorited': False,
'geo': None,
'id': 760563814450491392,
'id_str': '760563814450491392',
'in_reply_to_screen_name': 'KxSweaters13',
'in_reply_to_status_id': None,
'in_reply_to_status_id_str': None,
'in_reply_to_user_id': 873491544,
'in_reply_to_user_id_str': '873491544',
'is_quote_status': False,
'lang': 'en',
'metadata': {'iso_language_code': 'en', 'result_type': 'recent'},
'place': {'attributes': {},
'bounding_box': {'coordinates': [[[-71.813501, 42.4762],
[-71.702186, 42.4762],
[-71.702186, 42.573956],
[-71.813501, 42.573956]]],
'type': 'Polygon'},
'contained_within': [],
'country': 'Australia',
'country_code': 'AUS',
'full_name': 'Melbourne, V',
'id': 'c4f1830ea4b8caaf',
'name': 'Melbourne',
'place_type': 'city',
'url': 'https://api.twitter.com/1.1/geo/id/c4f1830ea4b8caaf.json'},
'retweet_count': 0,
'retweeted': False,
'source': 'Twitter for Android',
'text': '#KxSweaters13 are you the kenelx13 I see owning leominster for team valor?',
'truncated': False,
'user': {'contributors_enabled': False,
'created_at': 'Thu Apr 21 17:09:52 +0000 2011',
'default_profile': False,
'default_profile_image': False,
'description': "Arbys when it's cold. Kimballs when it's warm. #Ally__09 all year. Comp sci classes sometimes.",
'entities': {'description': {'urls': []}},
'favourites_count': 1106,
'follow_request_sent': None,
'followers_count': 167,
'following': None,
'friends_count': 171,
'geo_enabled': True,
'has_extended_profile': False,
'id': 285715182,
'id_str': '285715182',
'is_translation_enabled': False,
'is_translator': False,
'lang': 'en',
'listed_count': 2,
'location': 'MA',
'name': 'Steve',
'notifications': None,
'profile_background_color': '131516',
'profile_background_image_url': 'http://abs.twimg.com/images/themes/theme14/bg.gif',
'profile_background_image_url_https': 'https://abs.twimg.com/images/themes/theme14/bg.gif',
'profile_background_tile': True,
'profile_banner_url': 'https://pbs.twimg.com/profile_banners/285715182/1462218226',
'profile_image_url': 'http://pbs.twimg.com/profile_images/727223698332200961/bGPjGjHK_normal.jpg',
'profile_image_url_https': 'https://pbs.twimg.com/profile_images/727223698332200961/bGPjGjHK_normal.jpg',
'profile_link_color': '4A913C',
'profile_sidebar_border_color': 'FFFFFF',
'profile_sidebar_fill_color': 'EFEFEF',
'profile_text_color': '333333',
'profile_use_background_image': True,
'protected': False,
'screen_name': 'StephenBurke_',
'statuses_count': 5913,
'time_zone': 'Eastern Time (US & Canada)',
'url': None,
'utc_offset': -14400,
'verified': False}}
I have a json file which contains a list of json objects (each has the structure like above)
So I read it into a dataframe:
df = pd.read_json('data.json')
and then I try to get all the rows which are the 'city' type by:
df = df[df['place']['place_type'] == 'city']
but then I got the 'TypeError: an integer is required' During handling of the above exception, another exception occurred: KeyError: 'place_type'
Then I tried:
df['place'].head(3)
=>
0 {'id': '01864a8a64df9dc4', 'url': 'https://api...
1 {'id': '01864a8a64df9dc4', 'url': 'https://api...
2 {'id': '0118c71c0ed41109', 'url': 'https://api...
Name: place, dtype: object
So df['place'] return a series where keys are the indexes and that's why I got the TypeError
I've also tried to select the place_type of the first row and it works just fine:
df.iloc[0]['place']['place_type']
=>
city
The question is how can I filter out the rows in this case?
Solution:
Okay, so the problem lies in the fact that the pd.read_json cannot deal with nested JSON structure, so what I have done is to normalize the json object:
with open('data.json') as jsonfile:
data = json.load(jsonfile)
df = pd.io.json.json_normalize(data)
df = df[df['place.place_type'] == 'city']

You can use the a list comprehension to do the filtering you need.
df = [loc for loc in df if d['place']['place_type'] == 'city']
This will give you an array where the elements place_type is 'city'.

I don't know if you have to use the place_type that is the index, to show all the rows that contains city.
"and then I try to get all the rows which are the city type by:"
This way you can get all the rows that contains city in the column place:
df = df[(df['place'] == 'city')]

Reading Json objects from text file into pandas

I have extracted json objects from an api library and wrote them into a text file. I am now stuck on how to take the json structure saved in the .txt file and read that back into python pandas library.
There are many resources that walk through how to import a json file into pandas but since this is a text file and I'm new to programming and working with json structure I'm not sure how to efficiently perform this task.
There are numerous json objects in the text file and I would share an example but it has a bunch of url shorteners which is preventing me from being able to post this question so unless someone really needs to see the structure Ill hold off. I already tried pd.read_csv() and pd.read_json() but since this is a json structure in a .txt file its not working properly for either so far.
Here has been my best guess so far to get the data back into python:
data = []
with open('tweet_json.txt') as f:
for line in f:
data.append(json.loads(line))
But I got the following error message when I tried that: JSONDecodeError: Extra data: line 1 column 4626 (char 4625)
Here are two tweets that you can copy and save to a .txt file to replicate:
{'contributors': None,
'coordinates': None,
'created_at': 'Tue Aug 01 16:23:56 +0000 2017',
'display_text_range': [0, 85],
'entities': {'hashtags': [],
'media': [{'display_url': 'pic.twitter.com/MgUWQ76dJU',
'expanded_url': 'https://twitter.com/dog_rates/status/892420643555336193/photo/1',
'id': 892420639486877696,
'id_str': '892420639486877696',
'indices': [86, 109],
'media_url': 'http://pbs.twimg.com/media/DGKD1-bXoAAIAUK.jpg',
'media_url_https': 'https://pbs.twimg.com/media/DGKD1-bXoAAIAUK.jpg',
'sizes': {'large': {'h': 528, 'resize': 'fit', 'w': 540},
'medium': {'h': 528, 'resize': 'fit', 'w': 540},
'small': {'h': 528, 'resize': 'fit', 'w': 540},
'thumb': {'h': 150, 'resize': 'crop', 'w': 150}},
'type': 'photo',
'url': na}],
'symbols': [],
'urls': [],
'user_mentions': []},
'extended_entities': {'media': [{'display_url': 'pic.twitter.com/MgUWQ76dJU',
'expanded_url': 'https://twitter.com/dog_rates/status/892420643555336193/photo/1',
'id': 892420639486877696,
'id_str': '892420639486877696',
'indices': [86, 109],
'media_url': 'http://pbs.twimg.com/media/DGKD1-bXoAAIAUK.jpg',
'media_url_https': 'https://pbs.twimg.com/media/DGKD1-bXoAAIAUK.jpg',
'sizes': {'large': {'h': 528, 'resize': 'fit', 'w': 540},
'medium': {'h': 528, 'resize': 'fit', 'w': 540},
'small': {'h': 528, 'resize': 'fit', 'w': 540},
'thumb': {'h': 150, 'resize': 'crop', 'w': 150}},
'type': 'photo',
'url': na}]},
'favorite_count': 39311,
'favorited': False,
'full_text': "This is Phineas. He's a mystical boy. Only ever appears in the hole of a donut. 13/10 na ",
'geo': None,
'id': 892420643555336193,
'id_str': '892420643555336193',
'in_reply_to_screen_name': None,
'in_reply_to_status_id': None,
'in_reply_to_status_id_str': None,
'in_reply_to_user_id': None,
'in_reply_to_user_id_str': None,
'is_quote_status': False,
'lang': 'en',
'place': None,
'possibly_sensitive': False,
'possibly_sensitive_appealable': False,
'retweet_count': 8778,
'retweeted': False,
'source': 'Twitter for iPhone',
'truncated': False,
'user': {'contributors_enabled': False,
'created_at': 'Sun Nov 15 21:41:29 +0000 2015',
'default_profile': False,
'default_profile_image': False,
'description': 'Only Legit Source for Professional Dog Ratings STORE: #ShopWeRateDogs | IG, FB & SC: WeRateDogs | MOBILE APP: #GoodDogsGame Business: dogratingtwitter#gmail.com',
'entities': {'description': {'urls': []},
'url': {'urls': [{'display_url': 'weratedogs.com',
'expanded_url': 'http://weratedogs.com',
'indices': [0, 23],
'url': na }]}},
'favourites_count': 126135,
'follow_request_sent': False,
'followers_count': 4730764,
'following': False,
'friends_count': 109,
'geo_enabled': True,
'has_extended_profile': True,
'id': 4196983835,
'id_str': '4196983835',
'is_translation_enabled': False,
'is_translator': False,
'lang': 'en',
'listed_count': 3700,
'location': 'DM YOUR DOGS. WE WILL RATE',
'name': 'WeRateDogs™',
'notifications': False,
'profile_background_color': '000000',
'profile_background_image_url': 'http://abs.twimg.com/images/themes/theme1/bg.png',
'profile_background_image_url_https': 'https://abs.twimg.com/images/themes/theme1/bg.png',
'profile_background_tile': False,
'profile_banner_url': 'https://pbs.twimg.com/profile_banners/4196983835/1510812288',
'profile_image_url': 'http://pbs.twimg.com/profile_images/936608706107772929/GwbLQRxf_normal.jpg',
'profile_image_url_https': 'https://pbs.twimg.com/profile_images/936608706107772929/GwbLQRxf_normal.jpg',
'profile_link_color': 'F5ABB5',
'profile_sidebar_border_color': '000000',
'profile_sidebar_fill_color': '000000',
'profile_text_color': '000000',
'profile_use_background_image': False,
'protected': False,
'screen_name': 'dog_rates',
'statuses_count': 6301,
'time_zone': None,
'translator_type': 'none',
'url': n/a,
'utc_offset': None,
'verified': True}}
{'contributors': None,
'coordinates': None,
'created_at': 'Tue Aug 01 00:17:27 +0000 2017',
'display_text_range': [0, 138],
'entities': {'hashtags': [],
'media': [{'display_url': 'pic.twitter.com/0Xxu71qeIV',
'expanded_url': 'https://twitter.com/dog_rates/status/892177421306343426/photo/1',
'id': 892177413194625024,
'id_str': '892177413194625024',
'indices': [139, 162],
'media_url': 'http://pbs.twimg.com/media/DGGmoV4XsAAUL6n.jpg',
'media_url_https': 'https://pbs.twimg.com/media/DGGmoV4XsAAUL6n.jpg',
'sizes': {'large': {'h': 1600, 'resize': 'fit', 'w': 1407},
'medium': {'h': 1200, 'resize': 'fit', 'w': 1055},
'small': {'h': 680, 'resize': 'fit', 'w': 598},
'thumb': {'h': 150, 'resize': 'crop', 'w': 150}},
'type': 'photo',
'url': na}],
'symbols': [],
'urls': [],
'user_mentions': []},
'extended_entities': {'media': [{'display_url': 'pic.twitter.com/0Xxu71qeIV',
'expanded_url': 'https://twitter.com/dog_rates/status/892177421306343426/photo/1',
'id': 892177413194625024,
'id_str': '892177413194625024',
'indices': [139, 162],
'media_url': 'http://pbs.twimg.com/media/DGGmoV4XsAAUL6n.jpg',
'media_url_https': 'https://pbs.twimg.com/media/DGGmoV4XsAAUL6n.jpg',
'sizes': {'large': {'h': 1600, 'resize': 'fit', 'w': 1407},
'medium': {'h': 1200, 'resize': 'fit', 'w': 1055},
'small': {'h': 680, 'resize': 'fit', 'w': 598},
'thumb': {'h': 150, 'resize': 'crop', 'w': 150}},
'type': 'photo',
'url': na}]},
'favorite_count': 33662,
'favorited': False,
'full_text': "This is Tilly. She's just checking pup on you. Hopes you're doing ok. If not, she's available for pats, snugs, boops, the whole bit. 13/10 na,
'geo': None,
'id': 892177421306343426,
'id_str': '892177421306343426',
'in_reply_to_screen_name': None,
'in_reply_to_status_id': None,
'in_reply_to_status_id_str': None,
'in_reply_to_user_id': None,
'in_reply_to_user_id_str': None,
'is_quote_status': False,
'lang': 'en',
'place': None,
'possibly_sensitive': False,
'possibly_sensitive_appealable': False,
'retweet_count': 6431,
'retweeted': False,
'source': 'Twitter for iPhone',
'truncated': False,
'user': {'contributors_enabled': False,
'created_at': 'Sun Nov 15 21:41:29 +0000 2015',
'default_profile': False,
'default_profile_image': False,
'description': 'Only Legit Source for Professional Dog Ratings STORE: #ShopWeRateDogs | IG, FB & SC: WeRateDogs | MOBILE APP: #GoodDogsGame Business: dogratingtwitter#gmail.com',
'entities': {'description': {'urls': []},
'url': {'urls': [{'display_url': 'weratedogs.com',
'expanded_url': 'http://weratedogs.com',
'indices': [0, 23],
'url': na}]}},
'favourites_count': 126135,
'follow_request_sent': False,
'followers_count': 4730865,
'following': False,
'friends_count': 109,
'geo_enabled': True,
'has_extended_profile': True,
'id': 4196983835,
'id_str': '4196983835',
'is_translation_enabled': False,
'is_translator': False,
'lang': 'en',
'listed_count': 3728,
'location': 'DM YOUR DOGS. WE WILL RATE',
'name': 'WeRateDogs™',
'notifications': False,
'profile_background_color': '000000',
'profile_background_image_url': 'http://abs.twimg.com/images/themes/theme1/bg.png',
'profile_background_image_url_https': 'https://abs.twimg.com/images/themes/theme1/bg.png',
'profile_background_tile': False,
'profile_banner_url': 'https://pbs.twimg.com/profile_banners/4196983835/1510812288',
'profile_image_url': 'http://pbs.twimg.com/profile_images/936608706107772929/GwbLQRxf_normal.jpg',
'profile_image_url_https': 'https://pbs.twimg.com/profile_images/936608706107772929/GwbLQRxf_normal.jpg',
'profile_link_color': 'F5ABB5',
'profile_sidebar_border_color': '000000',
'profile_sidebar_fill_color': '000000',
'profile_text_color': '000000',
'profile_use_background_image': False,
'protected': False,
'screen_name': 'dog_rates',
'statuses_count': 6301,
'time_zone': None,
'translator_type': 'none',
'url': na,
'utc_offset': None,
'verified': True}}
Update
The following code produces this error: JSONDecodeError: Expecting ',' delimiter: line 1 column 4627 (char 4626)
with open('tweet_json.txt', 'r') as f:
datastore = json.load(f)
This post is the closest I've found so far to help me solve my issue:
Python json.loads shows ValueError: Expecting , delimiter: line 1

Thanks everyone for the feedback. I had to adjust the code regarding how I was extracting the data from the API and then it was pretty straight-forward to get the data into a list of dictionaries after that.
with open('tweet_json.txt', 'a+', encoding='utf-8') as file:
for tweet_id in twitter_archive_df['tweet_id']:
try:
tweet = api.get_status(id = tweet_id, tweet_mode='extended')
file.write(json.dumps(tweet))
file.write('\n')
except:
pass
file.close()
then I ran the following code to import the json objects from the .txt file into a list of dictionaries:
with open('tweet_json.txt') as file:
status = []
for line in file:
status.append(json.loads(line))