If I have a json file with multiple json objects such as following
{"created_at":"Sun Apr 16 02:00:14 +0000 2017","id":853427785339084800,"id_str":"853427785339084800"}
{"created_at":"Sun Apr 16 02:03:24 +0000 2017","id":853428582613475332,"id_str":"853428582613475332"}
I want to loop all the json objects add add new element together with value through user input in command line one by one. Is it possible because my format not in json array?
import json
import pandas as pd
from pprint import pprint
tweets_data_path = 'data.json'
tweets_data = []
tweets_file = open(tweets_data_path, "r")
for line in tweets_file:
try:
tweet = json.loads(line)
tweets_data.append(tweet)
except:
continue
pprint(tweets_data)
Your code runs fine, so I am assuming the question is on how to add user input as a new key-value pair for each json you load from the file. For python 2.7 use raw_input, for python 3 raw_input was renamed to input.
import json
import pandas as pd
from pprint import pprint
tweets_data_path = 'data.json'
tweets_data = []
tweets_file = open(tweets_data_path, "r")
for line in tweets_file:
try:
tweet = json.loads(line)
tweet["new_key"] = raw_input('provide input: ')
tweets_data.append(tweet)
except:
continue
pprint(tweets_data)
Related
I'm trying to parse JSON files into CSV. I've been able to get the headers of the JSON file to be output into the CSV but I can't figure out how to get the data into the file.
# Python program to convert
# JSON file to CSV
import json
import csv
# Opening JSON file and loading the data
# into the variable data
with open('test1.json') as json_file:
data = json.load(json_file)
for i in range(len(data)):
training_data = data[i]['profile']
# now we will open a file for writing
data_file = open('data_file.csv', 'w')
# create the csv writer object
csv_writer = csv.writer(data_file)
# Counter variable used for writing
# headers to the CSV file
count = 0
#type(training_data)
for profile in training_data:
if count == 0:
header = training_data.keys()
csv_writer.writerow(header)
count += 1
csv_writer.writerow(training_data.values())
data_file.close()
This is the file im trying to parse
https://textdoc.co/OuphoV5saiwWYS8g
If someone could help me out I'd be eternally grateful
would something like this work for you?
import pandas as pd
df = pd.read_json(json_file)
df.to_csv('data_file.csv')
or for more complex nested json, you may have to load as a dictionary and manipulate:
data = json.loads(json_str)
data_transformed = [i for i in data['data']]
df = pd.DataFrame(data_transformed )
df.to_csv('data_file.csv')
How to dump data into Json file
*as can see in the below python code I am trying the dump data in Json file so but I am struggling to do it in python code *
import time
import json
import os
def long_function(name):
cache_path = 'cache.json'
if not os.path.isfile(cache_path):
with open(cache_path, 't') as json_file:
cache_file_data = [name]
jsondump(cache_file_data, json_file)
else:
with open(cache_path, 'r') as json_file:
cache_file_data = json.load(json_file)
if name in cache_file_data:
print("Name already exist")
return name
else:
cache_file_data.append(name)
for e in range(5):
time.sleep(1)
print(e+1)
with open(cache_path, 'w') as json_file:
jsondump(cache_file_data, json_file)
print("New Name added in cache")
return name
print(long_function('nitu'))
so please resolve my problem......please help me
import json
# JSON data:
x = '{ "organization":"New_holn",
"city":"Noida",
"country":"India"}'
# python object to be appended
y = {"pin":117845}
# parsing JSON string:
z = json.loads(x)
# appending the data
z.update(y)
# the result is a JSON string:
print(json.dumps(z))
This is nothing but follow this pattern and your so your code error is ..you are not defined file mode correctly in if condition
with open (cache_path. "t") as json_file:
Instead of
with open (cache_path. "w") as json_file:
And second thing is you are not doing dump data
this is my json file
{"_index":"core-bvd-locations","_type":"_doc","_id":"75b82cba4a80784f4fa36d14c86f6d85","_score":1,"_source":{"a_id":"FR518077177","a_id_type":"BVD ID","a_name":"Moisan Patrick Roger","a_name_normal":"MOISAN PATRICK ROGER","a_country_code":"FR","a_country":"France","a_in_compliance_db":false,"a_nationality":"FR","a_street_address":"Les Carmes","a_city":"Decize","a_postcode":"58300","a_region":"Bourgogne-Franche-Comte|Nievre","a_phone":"+33 603740000","a_latitude":46.79402777777778,"a_longitude":3.496277777777778,"a_national_ids":{"European VAT number":["FR58 518077177"],"SIREN number":["518077177"],"TIN":["518077177"],"SIRET number":["518077177-00013"]},"relationship":"Location info","file_name":"/media/hedwig/iforce/data/BvD/s3-transfer/SuperTable_v3_json/locations/part-00021-1f62c713-17a0-410d-9b18-32328d9836d6-c000.json","a_geo_point":{"lat":46.79402777777778,"lon":3.496277777777778}}}
this is my code
import csv
import json
import sys
import codecs
def trans(path):
jsonData = codecs.open('F:\\1.json', 'r', 'utf-8')
# csvfile = open(path+'.csv', 'w') #
# csvfile = open(path+'.csv', 'wb') # python2
csvfile = open('F:\\1.csv', 'w', encoding='utf-8', newline='') #
writer = csv.writer(csvfile, delimiter=',')
flag = True
for line in jsonData:
dic = json.loads(line)
if flag:
keys = list(dic.keys())
print(keys)
writer.writerow(keys)
flag = False
writer.writerow(list(dic.values()))
jsonData.close()
csvfile.close()
if __name__ == '__main__':
path=str(sys.argv[0]) #
print(path)
trans(path)
C:\Users\jeri\PycharmProjects\pythonProject9\venv\Scripts\python.exe C:\Users\jeri\PycharmProjects\pythonProject9\zwc_count_file.py
C:\Users\jeri\PycharmProjects\pythonProject9\zwc_count_file.py
['_index', '_type', '_id', '_score', '_source']
Process finished with exit code 0
output jie
enter image description here
Information in nested json file cannot be parse, how can i modify the code
import json
import pandas as pd
file_data = open("json_filname.json",'r').read()
data= json.loads(file_data)
df = pd.json_normalize(data)
df
json.load(): json.load() accepts file object, parses the JSON data, populates a Python dictionary with the data and returns it back to you.
import json
# Opening JSON file
f = open('data.json')
# returns JSON object as
# a dictionary
data = json.load(f)
writer.writerow write the entire row, rigth sintaxis
writer.writerow(#iterable_object#)
I have a json file out of which one field has list data as shown below
{
"broker_address":"0.0.0.0",
"serial_id": "YYMMSSSSSSVV",
"auto_foc": true,
"timer": [0,23,30]
}
I am taking user input for timer field so I want to replace the timer data with the input value received from user. On trying it I am getting following error
Traceback (most recent call last):
File "test.py", line 23, in <module>
time, final)
TypeError: Can't convert 'list' object to str implicitly
My code snippet is as follows
import json
import os
import time
val = input("Enter your value: ")
print(val)
str1 = " "
with open('/home/pi/config.json', 'r+') as filer:
print("file read")
az = filer.read()
print(az)
read_file = az.rstrip('/n')
data = json.loads(read_file)
#print("printing file",json.loads(read_file))
time=data["timer"]
#print(read_file)
print(time)
print("Waiting.....................")
#time.sleep(2)
final = str(val)
print(final)
read_file = read_file.replace(
time, final)
with open('/home/pi/config.json', 'w') as filer:
filer.write(read_file)
Please let me know how to resolve this error.
Try this:
import json
import os
import time
val = input("Enter your value: ")
print(val)
str1 = " "
with open('/home/pi/config.json', 'r+') as filer:
print("file read")
az = filer.read()
print(az)
read_file = az.rstrip('/n')
data = json.loads(read_file)
#print("printing file",json.loads(read_file))
time=data["timer"]
#print(read_file)
print(time)
print("Waiting.....................")
#time.sleep(2)
final = str(val).split()
final = [int(i) for i in final]
print(final)
print(str(time))
read_file = read_file.replace(str(time), str(final))
print(read_file)
with open('/home/pi/config.json', 'w') as filer:
filer.write(read_file)
And update the json file from "timer": [0,23,30] to "timer": [0, 23, 30] i.e. add spaces
One thing avoid using the name time when you use that name as a variable it will replace the imported name time. Secondly the issue is that the data is a list not a string and replace is expecting a string not a list.
What you will want to do is just take advantage of json for what it is a serializer and deserializer and modify the data itself and use json to write it to a file. This also ensures you will be able to read it back out as json.
import json
import os
import time
val = input("Enter your value: ")
print(val)
str1 = " "
with open('/home/pi/config.json', 'r+') as filer:
print("file read")
data = json.load(filer)
timer=data["timer"] #DONT USE time
print(timer)
print("Waiting.....................")
#time.sleep(2)
final = str(val)
print(final)
#This next part will be up to you,
# do you want this to be the list it was before?
# or the string as input
data['timer'] = final
with open('/home/pi/config.json', 'w') as filer:
json.dump(data,filer)
My current professor is using Python 2.7 for examples in class, but other professors that I will be taking classes from in the future have suggested I use Python 3.5. I am trying to convert my current Professor's examples from 2.7 to 3.5. Right now I'm having an issue with the urllib2 package, which I understand has been split in Python 3.
The original code in the iPython notebook looks like this :
import csv
import urllib2
data_url = 'http://archive.ics.uci.edu/ml/machine-learning- databases/adult/adult.data'
response = urllib2.urlopen(data_url)
myreader = csv.reader(response)
for i in range(5):
row = next(myreader)
print ','.join(row)
Which I have converted to:
import csv
import urllib.request
data_url = 'http://archive.ics.uci.edu/ml/machine-learning- databases/adult/adult.data'
response = urllib.request.urlopen(data_url)
myreader = csv.reader(response)
for i in range(5):
row = next(myreader)
print(','.join(row))
But that leaves me with the error:
Error Traceback (most recent call last)
<ipython-input-19-20da479e256f> in <module>()
7 myreader = csv.reader(response)
8 for i in range(5):
----> 9 row = next(myreader)
10 print(','.join(row))
Error: iterator should return strings, not bytes (did you open the file in text mode?)
I'm unsure how to proceed from here. Any ideas?
Wrap response with another iterator which decode bytes to string and yield the strings:
import csv
import urllib.request
def decode_iter(it):
# iterate line by line
for line in it:
# convert bytes to string using `bytes.decode`
yield line.decode()
data_url = 'http://archive.ics.uci.edu/ml/machine-learning-databases/adult/adult.data'
response = urllib.request.urlopen(data_url)
myreader = csv.reader(decode_iter(response))
for i in range(5):
row = next(myreader)
print(','.join(row))
UPDATE
Instead of decode_iter, you can use codecs.iter_decode:
import csv
import codecs
import urllib.request
data_url = 'http://archive.ics.uci.edu/ml/machine-learning-databases/adult/adult.data'
response = urllib.request.urlopen(data_url)
myreader = csv.reader(codecs.iterdecode(response, 'utf-8'))
for i in range(5):
row = next(myreader)
print(','.join(row))