I'm new to pymongo and mongodb and I have a json file with 157 documents that I want to insert in a collection called Students. I load the json file line by line and import each document inside a list called data. Then I try using the insert_one() method in a loop to insert each document inside the Students collection and I get many errors bellow The format of the json file is:
//example of an entry
{"_id":{"$oid":"5e99cb577a781a4aac69da3c"},"name":"Tanner Wilson","email":"tannerwilson@ontagene.com","yearOfBirth":{"$numberInt":"1962"},"address":[{"street":"Halsey Street","city":"Greenwich","postcode":{"$numberInt":"13832"}}]}
My code:
import pymongo
from pymongo import MongoClient
import json
client = MongoClient('localhost:27017')
db = client['InfoSys']
collection=db['Students']
data=[]
with open('students.json') as f:
for json_data in f:
element =json.loads(json_data)
data.append(element)
'''print(data)''' // the json data can be printed perfectly
for k in data :
collection.insert_one(k) //this is where the error happens
And I get the errors bellow: File "C:\Users\User\Anaconda3\lib\site-packages\pymongo\collection.py", line 698, in insert_one session=session), File "C:\Users\User\Anaconda3\lib\site-packages\pymongo\collection.py", line 612, in _insert bypass_doc_val, session) File "C:\Users\User\Anaconda3\lib\site-packages\pymongo\collection.py", line 600, in _insert_one acknowledged, _insert_command, session) File "C:\Users\User\Anaconda3\lib\site-packages\pymongo\mongo_client.py", line 1491, in _retryable_write return self._retry_with_session(retryable, func, s, None) File "C:\Users\User\Anaconda3\lib\site-packages\pymongo\mongo_client.py", line 1384, in _retry_with_session return func(session, sock_info, retryable) File "C:\Users\User\Anaconda3\lib\site-packages\pymongo\collection.py", line 595, in _insert_command retryable_write=retryable_write) File "C:\Users\User\Anaconda3\lib\site-packages\pymongo\pool.py", line 618, in command self._raise_connection_failure(error) File "C:\Users\User\Anaconda3\lib\site-packages\pymongo\pool.py", line 613, in command user_fields=user_fields) File "C:\Users\User\Anaconda3\lib\site-packages\pymongo\network.py", line 129, in command codec_options, ctx=compression_ctx) File "C:\Users\User\Anaconda3\lib\site-packages\pymongo\message.py", line 707, in _op_msg flags, command, identifier, docs, check_keys, opts) bson.errors.InvalidDocument: key '$oid' must not start with '$'
File "C:\Users\User\Anaconda3\lib\site-packages\pymongo\collection.py", line 698, in insert_one session=session), File "C:\Users\User\Anaconda3\lib\site-packages\pymongo\collection.py", line 612, in _insert bypass_doc_val, session) File "C:\Users\User\Anaconda3\lib\site-packages\pymongo\collection.py", line 600, in _insert_one acknowledged, _insert_command, session) File "C:\Users\User\Anaconda3\lib\site-packages\pymongo\mongo_client.py", line 1491, in _retryable_write return self._retry_with_session(retryable, func, s, None) File "C:\Users\User\Anaconda3\lib\site-packages\pymongo\mongo_client.py", line 1384, in _retry_with_session return func(session, sock_info, retryable) File "C:\Users\User\Anaconda3\lib\site-packages\pymongo\collection.py", line 595, in _insert_command retryable_write=retryable_write) File "C:\Users\User\Anaconda3\lib\site-packages\pymongo\pool.py", line 618, in command self._raise_connection_failure(error) File "C:\Users\User\Anaconda3\lib\site-packages\pymongo\pool.py", line 613, in command user_fields=user_fields) File "C:\Users\User\Anaconda3\lib\site-packages\pymongo\network.py", line 129, in command codec_options, ctx=compression_ctx) File "C:\Users\User\Anaconda3\lib\site-packages\pymongo\message.py", line 707, in _op_msg flags, command, identifier, docs, check_keys, opts) bson.errors.InvalidDocument: key '$oid' must not start with '$'
I would appreciate your help with guiding me to solve this issue.
Assuming you have data in a string format, you need to use loads()
from the bson.json_util
library; eg
from pymongo import MongoClient
import bson.json_util
client = MongoClient()
db = client['InfoSys']
collection=db['Students']
data='{"_id":{"$oid":"5e99cb577a781a4aac69da3c"},"name":"Tanner Wilson","email":"tannerwilson@ontagene.com","yearOfBirth":{"$numberInt":"1962"},"address":[{"street":"Halsey Street","city":"Greenwich","postcode":{"$numberInt":"13832"}}]}'
collection.insert_one(bson.json_util.loads(data))
print(collection.find_one())
result:
{'_id': ObjectId('5e99cb577a781a4aac69da3c'), 'name': 'Tanner Wilson', 'email': 'tannerwilson@ontagene.com', 'yearOfBirth': 1962, 'address': [{'street': 'Halsey Street', 'city': 'Greenwich', 'postcode': 13832}]}
The technical post webpages of this site follow the CC BY-SA 4.0 protocol. If you need to reprint, please indicate the site URL or the original address.Any question please contact:yoyou2525@163.com.