-
-
Save mprajwala/849b5909f5b881c8ce6a to your computer and use it in GitHub Desktop.
#!/usr/bin/env python | |
import sys | |
import pandas as pd | |
import pymongo | |
import json | |
def import_content(filepath): | |
mng_client = pymongo.MongoClient('localhost', 27017) | |
mng_db = mng_client['mongodb_name'] // Replace mongo db name | |
collection_name = 'collection_name' // Replace mongo db collection name | |
db_cm = mng_db[collection_name] | |
cdir = os.path.dirname(__file__) | |
file_res = os.path.join(cdir, filepath) | |
data = pd.read_csv(file_res) | |
data_json = json.loads(data.to_json(orient='records')) | |
db_cm.remove() | |
db_cm.insert(data_json) | |
if __name__ == "__main__": | |
filepath = '/path/to/csv/path' // pass csv file path | |
import_content(filepath) |
i need to map a csv which has an id field already to be imported to mongo with the _id as this id field.How to do that?
(rhis csv file has an id field)
try:
client = MongoClient(mongouri)
database = client['automation']
database.create_collection('testTableMongo'+str(suffix))
coll = database['testTableMongo'+str(suffix)]
data = pd.read_csv(os.path.abspath('../data/' + file))
payload = json.loads(data.to_json(orient='records'))
coll.remove()
coll.insert(payload)
except OperationFailure as msg:
print("Command skipped: %s", msg)
I'm with the error "name 'file' is not defined"
I'm with the error "name 'file' is not defined"
Hey, kindly post a snippet of your code for easier help
when you use file in python interactive mode, this error occur.
So you should write this line os.path.dirname(__file__)
in file.py
.
for more reference consider this : https://stackoverflow.com/questions/16771894/python-nameerror-global-name-file-is-not-defined
I need help to load data into mongo database with collection creation from worksheet which contain multiple excel sheets
I need help to load data into mongo database with collection creation from worksheet which contain multiple excel sheets
you can read a sheet with pandas with the sheet_name att.
df = pd.read_excel('my_excel.xlsx', sheet_name='Sheet 1')
Thanks for your help !