I am new to Python and started off with sqlite.
I have two csv transaction.csv and users.csv from where I am reading the data and writing to the sqlite database.Below is the snippet
import csv
import sqlite3 as db
def readCSV_users():
with open('users.csv',mode='r') as data:
dr = csv.DictReader(data, delimiter=',')
users_data = [(i['user_id'], i['is_active']) for i in dr if i['is_active']=='True']
#---------------------
return users_data
def readCSV_transactions():
with open('transactions.csv',mode='r') as d:
dr = csv.DictReader(d, delimiter=',')
trans_data = [(i['user_id'], i['is_blocked'],i['transaction_amount'],i['transaction_category_id']) for i in dr if i['is_blocked']=='False']
#---------------------
return trans_data
def SQLite_connection(database):
try:
# connect to the database
conn = db.connect(database)
print("Database connection is established successfully!")
conn = db.connect(':memory:')
print("Established database connection to a database\
that resides in the memory!")
cur = conn.cursor()
return cur,conn
except exception as Err:
print(Err)
def dbQuery(users_data,trans_data,cur,conn):
try:
cur.executescript(""" CREATE TABLE if not exists users(user_id text,is_active text);
CREATE TABLE if not exists transactions(user_id text,is_blocked text,transaction_amount text,transaction_category_id text);
INSERT INTO users VALUES (?,?),users_data;
INSERT INTO transactions VALUES (?,?,?,?),trans_data""")
conn.commit()
a=[]
rows = curr.execute("SELECT * FROM users").fetchall()
for r in rows:
a.append(r)
return a
except Err:
print(Err)
finally:
conn.close()
if __name__ == "__main__":
database='uit'
users_data=readCSV_users()
trans_data=readCSV_transactions()
curr,conn=SQLite_connection(database)
print(dbQuery(users_data,trans_data,curr,conn))
But I am facing below error.I believe the ? is throwing the error in executescript
cur.executescript(""" CREATE TABLE if not exists users(user_id text,is_active text);
sqlite3.OperationalError: near "users_data": syntax error
Any pointers to resolve this?
Putting users_data directly in query is wrong. It treats it as normal string.
But it seems executescript can't use arguments.
You would have to put values directly in place of ?.
Or you have to use execute()
cur.execute("INSERT INTO users VALUES (?,?);", users_data)
cur.execute("INSERT INTO transactions VALUES (?,?,?,?)", trans_data)
Related
using python,I am looping through csv file to read data, then I am ding some modifications on the readied row and call a save function to insert the modified data into MySQL.
def save(Id, modifiedData,):
try:
mydb = mysql.connector.connect(host="localhost",user="use",password="pass",database="data")
sql = "INSERT INTO data (Id, modifiedData) VALUES (%s, %s)"
recordTuple = (Id, modifiedData)
mycursor = mydb.cursor()
mycursor.execute(sql,recordTuple)
mydb.commit()
print("Record inserted successfully into table")
except mysql.connector.Error as error:
print("Failed to insert into MySQL table {}".format(error))
def main():
for row in csv:
#modify row
#creat Id
save(Id, modifiedData,)
but I don't think this is good solution to do MYSQL connection and insert data with each iteration, it will be time and resources consuming , specially when I move to real server in production
how can I improve my solution?
Ideally, connections should be managed by connection pool, should be committed bulky. But amount of csv at most, need not to mind so much. Anyway, If you don't wanna bother it, I recommend using ORM like SQLAlchemy.
You only need to create the connection once, and that should be in function main, who then passes the connection to function save as follows:
def save(mydb, Id, modifiedData):
try:
sql = "INSERT INTO data (Id, modifiedData) VALUES (%s, %s)"
recordTuple = (Id, modifiedData)
mycursor = mydb.cursor()
mycursor.execute(sql,recordTuple)
mydb.commit()
print("Record inserted successfully into table")
except mysql.connector.Error as error:
print("Failed to insert into MySQL table {}".format(error))
def main():
try:
mydb = mysql.connector.connect(host="localhost",user="use",password="pass",database="data")
except mysql.connector.Error as error:
print("Failed to create connection: {}".format(error))
return
for row in csv:
#modify row
#creat Id
save(mydb, Id, modifiedData)
For perhaps even greater performance you can try executemany:
def save(mydb, modified_records):
try:
sql = "INSERT INTO data (Id, modifiedData) VALUES (%s, %s)"
mycursor = mydb.cursor()
mycursor.executemany(sql, modified_records)
mydb.commit()
print("Records inserted successfully into table")
except mysql.connector.Error as error:
print("Failed to insert into MySQL table {}".format(error))
def main():
try:
mydb = mysql.connector.connect(host="localhost",user="use",password="pass",database="data")
except mysql.connector.Error as error:
print("Failed to create connection: {}".format(error))
return
modified_records = []
for row in csv:
#modify row
#creat Id
modified_records.append([id, modifiedData])
save(mydb, modified_records)
I used Python and the package SQLite to create table and insert data into the table. However, there is nothing in the table after I fired the execution. Can anyone help me figure it out? Thanks.
def conSqlite():
conn = sqlite3.connect('C:\\Users\jet.cai\Documents\Logsitic.db')
json_path = r'C:\Users\jet.cai\PycharmProjects\VJSF\txtToJson.json'
try:
create_table = ('''
CREATE TABLE IF NOT EXISTS CODE2
(Delivery TEXT,
Customer_Name NCHAR(50),
Shipment_Priority TEXT
)''')
conn.execute(create_table)
except:
print("Table Failed")
return False
with open(json_path, 'r') as jsonf:
lines = json.load(jsonf)
for line in lines:
sql = "insert into CODE2(Delivery,Customer_Name,Shipment_Priority) values('%s','%s','%s')"%(line['Delivery'],line['Customer Name'],line['Shipment Priority'])
conn.execute(sql)
# No results can be selected out
df = pd.read_sql("select Delivery from CODE2", conn)
print(df)
I have some python code that gets data from one database (SQL server) and inserts it into another database (MySQL). I am trying to add a WHERE NOT EXIST to the INSERT query so only new rows are inserted, but need to use one of the values in the tuple SageResults a second time for the primary key.
Code:
import mysql.connector
import pyodbc
def insert_VPS(SageResult):
query = """
INSERT INTO SOPOrderReturn(SOPOrderReturnID, DocumentTypeID, DocumentNo, DocumentDate, CustomerID, CustomerTypeID, CurrencyID, SubtotalGoodsValue, TotalNetValue, TotalTaxValue, TotalGrossValue, SourceTypeID, SourceDocumentNo)
VALUES(%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s)
WHERE NOT EXISTS (SELECT * FROM SOPOrderReturn WHERE SOPOrderReturnID = %1$s)"""
try:
mydbVPS = mysql.connector.connect(
host="address",
user="user",
passwd="password",
database="database"
)
VPScursor = mydbVPS.cursor()
#print(SageResult)
VPScursor.executemany(query, SageResult)
mydbVPS.commit()
except Exception as e:
print('InsertError:', e)
finally:
VPScursor.close()
mydbVPS.close()
def main():
selectQuery = """
SELECT TOP 51 [SOPOrderReturnID]
,[DocumentTypeID]
,[DocumentNo]
,[DocumentDate]
,[CustomerID]
,[CustomerTypeID]
,[CurrencyID]
,[SubtotalGoodsValue]
,[TotalNetValue]
,[TotalTaxValue]
,[TotalGrossValue]
,[SourceTypeID]
,[SourceDocumentNo]
FROM [Live].[dbo].[SOPOrderReturn]
"""
try:
mydbSage = pyodbc.connect('Driver={SQL Server};'
'Server=CRMTEST;'
'Database=Live;'
'UID=sa;'
'PWD=password;')
Sagecursor = mydbSage.cursor()
Sagecursor.execute(selectQuery)
#SageResult = tuple(Sagecursor.fetchall())
SageResult = []
while True:
row = Sagecursor.fetchone()
if row:
SageResult.append(tuple(row))
else:
break
#SageResult = Sagecursor.fetchall()
mydbSage.commit()
except Exception as e:
print('MainError:', e)
finally:
Sagecursor.close()
mydbSage.close()
insert_VPS(SageResult)
if __name__ == '__main__':
main()
Output:
D:\xampp\htdocs\stripe\group\beta>sql-sync.py
InsertError: 1064 (42000): You have an error in your SQL syntax; check the manual that corresponds to your MariaDB server version for the right syntax to use ne
ar 'WHERE NOT EXISTS (SELECT * FROM SOPOrderReturn WHERE SOPOrderReturnID = %1$s),(1' at line 3
The part in question is the query string variable. Everything else in here works fine. I basically need to use the SOPOrderReturnID value from the tuple a second time where I currently have %1$s
What is the issue with the query syntax? Is my use of %1$s correct?
I know there are some other posts out there, but I was not able to find the specific question I had in mind.
I'm using US_baby_names csv file. and want to import this csv file line by line into sqlite3 as a table.
I'm able to create the table called storage.
I'm then trying to read lines in the csv file and put it into that table, but I must be doing something wrong.
import sqlite3 as sql
from sqlite3 import Error
import csv
def CreateConnection ( dbFileName ):
try:
conn = sql.connect(dbFileName)
return conn
except Error as e:
print(e)
return None
def CreateNew( dbConnection, new):
sql = """INSERT INTO storage (dat, Id, Name, Year, group, subgroup, Count)
VALUES (?,?,?,?,?,?,?)"""
try:
cursor = dbConnection.cursor()
cursor.execute(sql, new)
return cursor.lastrowid
except Error as e:
print(e)
def Main():
database = "storage.db"
dbConnection = CreateConnection(database)
with open('storage.csv', 'rb') as fin:
dr = csv.DictReader(fin)
to_db = [(i['dat'], i['Id'], i['Name'], i['Year'], i['group'], i['subgroup'], i['Count']) \
for i in dr]
cursor.executemany(CreateNew(sql, to_db))
dbConnection.close()
if __name__ == "__main__":
Main()
I believe my cursor.executemany is wrong, but I'm not able to figure out what else to do..
Thanks
You are almost right with much of your code, but:
in cursor.execute(sql, new) you are passing an iterable, new, to sqlite3.execute() (which requires a simple SQL statement), instead of sqlite3.executemany().
Moreover, the result of CreateNew() is an integer, lastrowid, and you pass that result to executemany().
You must use Connection.commit() to save the changes to the database, and Connection.rollback() to discard them.
You must open the file for the csv.DictReader class as a text file, in r or rt mode.
Finally, remember that sqlite3.Connection is a context manager, so you can use it in a with statement.
This should be your desired outcome:
import sqlite3 as sql
from sqlite3 import Error
import csv
def create_table(conn):
sql = "CREATE TABLE IF NOT EXISTS baby_names("\
"dat TEXT,"\
"Id INTEGER PRIMARY KEY,"\
"Name TEXT NOT NULL,"\
"Year INTEGER NOT NULL,"\
"Gender TEXT NOT NULL,"\
"State TEXT NOT NULL,"\
"Count INTEGER)"
conn.execute(sql)
conn.execute("DELETE FROM baby_names")
def select_all(conn):
for r in conn.execute("SELECT * FROM baby_names").fetchall():
print(r)
def execute_sql_statement(conn, data):
sql = "INSERT INTO baby_names "\
"(dat, Id, Name, Year, Gender, State, Count) "\
"VALUES (?,?,?,?,?,?,?)"
try:
cursor = conn.executemany(sql, data)
except Error as e:
print(e)
conn.rollback()
return None
else:
conn.commit()
return cursor.lastrowid
def main():
with sql.connect('baby_names.db') as conn, open('US_Baby_Names_right.csv', 'r') as fin:
create_table(conn)
dr = csv.DictReader(fin)
data = [(i['dat'], i['Id'], i['Name'], i['Year'], i['Gender'], i['State'], i['Count']) for i in dr ]
lastrowid = execute_sql_statement(conn, data)
select_all(conn)
main()
I added a create_table() function just to test my code. I also made up a sample test file as follows:
dat,Id,Name,Year,Gender,State,Count
1,1,John,1998,M,Washington,2
2,2,Luke,2000,M,Arkansas,10
3,3,Carrie,1999,F,Texas,3
The output of the select_all() function is:
('1',1,'John',1998,'M','Washington',2)
('2',2,'Luke',2000,'M','Arkansas',10)
('3',3,'Carrie',1999,'F','Texas',3)
I have an SQLite DB file and I am parsing the data from each column in a table of the db to a .txt file. At the moment it is writing the column contents to the file but it won't pull the column names and write those. How can I go about it as I have tried to use this guide Is there a way to get a list of column names in sqlite? but i cannot seem to get it to work. Here is my code with an attempt at pulling the column names from the table.
import sqlite3
from sqlite3 import Error
# create a database connection to the SQLite database specified by the db_file
def create_connection(db_file,detect_types=sqlite3.PARSE_DECLTYPES):
try:
conn = sqlite3.connect(db_file)
return conn
except Error as e:
print(e)
return None
# Query specific rows in the sms table
def select_data(conn):
cur = conn.cursor()
cur.execute("SELECT _id, address, strftime('%d-%m-%Y', date / 1000, 'unixepoch'),read, type, body, seen FROM sms")
print("Writing the contents of the sms table to an evidence file")
print("\t")
# Trying to pull out column names from db table
def get_col_names():
conn = sqlite3.connect("mmssms.db")
c = conn.cursor()
c.execute("SELECT _id, address, strftime('%d-%m-%Y', date / 1000, 'unixepoch'),read, type, body, seen FROM sms")
return [member[0] for member in c.description]
# Write the data to a smsEvidence.txt file
with open('EvidenceExtractionFiles/smsInfo.txt', 'a+') as f:
rows = cur.fetchall()
for row in rows:
#print(row)
f.write("%s\n" % str(row))
print("SMS Data is written to the evidence File")
# path to where the db files are stored
def main():
database = "H:\College Fourth Year\Development Project\Final Year Project 2018\mmssms.db"
# create a database connection
conn = create_connection(database)
with conn:
# print("Query specific columns")
select_data(conn)
# close db connection
if(conn):
conn.close()
print("Database closed")
if __name__ == '__main__':
main()
You may use cursor.description which holds info about the column names:
[ ... ]
cur = cursor.execute('SELECT * FROM test_table LIMIT 100')
col_names = [ name[0] for name in cur.description ]
print (col_names)
[ ... ]