Large Json file send batches wise to HubSpot API - json

Question

I tried many ways and tested many scenarios I did R&D a lot but unable to found issue/solution
I have a requirement, The HubSpot API accepts only 15k rec every time so we have large json file so we need to split/divide like batches wise 15k rec need to send api once 15k added in api it sleeps 10 sec and capture each response like this, the process would continue until all rec finished
I try with chunk code and modulus operator but didn't get any response
Not sure below code work or not can anyone please suggest better way
How to send batches wise to HubSpot API, How to post
Thanks in advance, this would great help for me!!!!!!!!
with open(r'D:\Users\lakshmi.vijaya\Desktop\Invalidemail\allhubusers_data.json', 'r') as run:
dict_run = run.readlines()
dict_ready = (''.join(dict_run))
count = 1000
subsets = (dict_ready[x:x + count] for x in range(0, len(dict_ready), count))
url = 'https://api.hubapi.com/contacts/v1/contact/batch'
headers = {'Authorization' : "Bearer pat-na1-**************************", 'Accept' : 'application/json', 'Content-Type' : 'application/json','Transfer-encoding':'chunked'}
for subset in subsets:
#print(subset)
urllib3.disable_warnings()
r = requests.post(url, data=subset, headers=headers,verify=False,
timeout=(15,20), stream=True)
print(r.status_code)
print(r.content)
ERROR:;;
400
b'\r\n400 Bad Request\r\n\r\n400 Bad Request\r\ncloudflare\r\n\r\n\r\n'
This is other method:
with open(r'D:\Users\lakshmi.vijaya\Desktop\Invalidemail\allhubusers_data.json', 'r') as run:
dict_run = run.readlines()
dict_ready = (''.join(dict_run))
url = 'https://api.hubapi.com/contacts/v1/contact/batch'
headers = {'Authorization' : "Bearer pat-na1***********-", 'Accept' : 'application/json', 'Content-Type' : 'application/json','Transfer-encoding':'chunked'}
urllib3.disable_warnings()
r = requests.post(url, data=dict_ready, headers=headers,verify=False,
timeout=(15,20), stream=True)
r.iter_content(chunk_size=1000000)
print(r.status_code)
print(r.content)
ERROR::::
raise SSLError(e, request=request)
requests.exceptions.SSLError: HTTPSConnectionPool(host='api.hubapi.com', port=443): Max retries exceeded with url: /contacts/v1/contact/batch
(Caused by SSLError(SSLEOFError(8, 'EOF occurred in violation of protocol (_ssl.c:2396)')))
This how json data looks like in large json file
{
"email": "aaazaj21#yahoo.com",
"properties": [
{
"property": "XlinkUserID",
"value": 422211111
},
{
"property": "register_time",
"value": "2021-09-02"
},
{
"property": "linked_alexa",
"value": 1
},
{
"property": "linked_googlehome",
"value": 0
},
{
"property": "fan_speed_switch_0x51_",
"value": 2
}
]
},
{
"email": "zzz7#gmail.com",
"properties": [
{
"property": "XlinkUserID",
"value": 13333666
},
{
"property": "register_time",
"value": "2021-04-24"
},
{
"property": "linked_alexa",
"value": 1
},
{
"property": "linked_googlehome",
"value": 0
},
{
"property": "full_colora19_st_0x06_",
"value": 2
}
]
}
I try with adding list of objects
[
{
"email": "aaazaj21#yahoo.com",
"properties": [
{
"property": "XlinkUserID",
"value": 422211111
},
{
"property": "register_time",
"value": "2021-09-02"
},
{
"property": "linked_alexa",
"value": 1
},
{
"property": "linked_googlehome",
"value": 0
},
{
"property": "fan_speed_switch_0x51_",
"value": 2
}
]
},
{
"email": "zzz7#gmail.com",
"properties": [
{
"property": "XlinkUserID",
"value": 13333666
},
{
"property": "register_time",
"value": "2021-04-24"
},
{
"property": "linked_alexa",
"value": 1
},
{
"property": "linked_googlehome",
"value": 0
},
{
"property": "full_colora19_st_0x06_",
"value": 2
}
]
}
]

Answer 1

You haven't said if your JSON file is a representation of an array of objects or just one object. Arrays are converted to Python lists by json.load and objects are converted to Python dictionaries.
Here is some code that assumes it is an array of objects if is is not an array of objects see https://stackoverflow.com/a/22878842/839338 but the same principle can be used
Assuming you want 15k bytes not records if it is the number of records you can simplify the code and just pass 15000 as the second argument to chunk_list().
import json
import math
import pprint
# See https://stackoverflow.com/a/312464/839338
def chunk_list(list_to_chunk, number_of_list_items):
"""Yield successive chunk_size-sized chunks from list."""
for i in range(0, len(list_to_chunk), number_of_list_items):
yield list_to_chunk[i:i + number_of_list_items]
with open('./allhubusers_data.json', 'r') as run:
json_data = json.load(run)
desired_size = 15000
json_size = len(json.dumps(json_data))
print(f'{json_size=}')
print(f'Divide into {math.ceil(json_size/desired_size)} sub-sets')
print(f'Number of list items per subset = {len(json_data)//math.ceil(json_size/desired_size)}')
if isinstance(json_data, list):
print("Found a list")
sub_sets = chunk_list(json_data, len(json_data)//math.ceil(json_size/desired_size))
else:
exit("Data not list")
for sub_set in sub_sets:
pprint.pprint(sub_set)
print(f'Length of sub-set {len(json.dumps(sub_set))}')
# Do stuff with the sub sets...
text_subset = json.dumps(sub_set) # ...
you may need to adjust the value of desired_size downwards if the sub_sets vary in length of text.
UPDATED IN RESPONSE TO COMMENT
If you just need 15000 records per request this code should work for you
import json
import pprint
import requests
# See https://stackoverflow.com/a/312464/839338
def chunk_list(list_to_chunk, number_of_list_items):
"""Yield successive chunk_size-sized chunks from list."""
for i in range(0, len(list_to_chunk), number_of_list_items):
yield list_to_chunk[i:i + number_of_list_items]
url = 'https://api.hubapi.com/contacts/v1/contact/batch'
headers = {
'Authorization': "Bearer pat-na1-**************************",
'Accept': 'application/json',
'Content-Type': 'application/json',
'Transfer-encoding': 'chunked'
}
with open(r'D:\Users\lakshmi.vijaya\Desktop\Invalidemail\allhubusers_data.json', 'r') as run:
json_data = json.load(run)
desired_size = 15000
if isinstance(json_data, list):
print("Found a list")
sub_sets = chunk_list(json_data, desired_size)
else:
exit("Data not list")
for sub_set in sub_sets:
# pprint.pprint(sub_set)
print(f'Length of sub-set {len(sub_set)}')
r = requests.post(
url,
data=json.dumps(sub_set),
headers=headers,
verify=False,
timeout=(15, 20),
stream=True
)
print(r.status_code)
print(r.content)