Importer un fichier CSV dans une table de base de données sqlite3 en utilisant Python

Question

J'ai un fichier CSV et je veux l'importer en masse dans ma base de données sqlite3 en utilisant Python. La commande est ".import .....". Mais il semble que cela ne puisse pas fonctionner ainsi. Quelqu'un peut-il me donner un exemple de comment le faire dans sqlite3 ? J'utilise Windows, au cas où. Merci

Answer 1

import csv, sqlite3

def _get_col_datatypes(fin):
    dr = csv.DictReader(fin) # comma is default delimiter
    fieldTypes = {}
    for entry in dr:
        feildslLeft = [f for f in dr.fieldnames if f not in fieldTypes.keys()]        
        if not feildslLeft: break # We're done
        for field in feildslLeft:
            data = entry[field]

        # Need data to decide
        if len(data) == 0:
            continue

        if data.isdigit():
            fieldTypes[field] = "INTEGER"
        else:
            fieldTypes[field] = "TEXT"
    # TODO: Currently there's no support for DATE in sqllite

if len(feildslLeft) > 0:
    raise Exception("Failed to find all the columns data types - Maybe some are empty?")

return fieldTypes

def escapingGenerator(f):
    for line in f:
        yield line.encode("ascii", "xmlcharrefreplace").decode("ascii")

def csvToDb(csvFile,dbFile,tablename, outputToFile = False):

    # TODO: implement output to file

    with open(csvFile,mode='r', encoding="ISO-8859-1") as fin:
        dt = _get_col_datatypes(fin)

        fin.seek(0)

        reader = csv.DictReader(fin)

        # Keep the order of the columns name just as in the CSV
        fields = reader.fieldnames
        cols = []

        # Set field and type
        for f in fields:
            cols.append("\"%s\" %s" % (f, dt[f]))

        # Generate create table statement:
        stmt = "create table if not exists \"" + tablename + "\" (%s)" % ",".join(cols)
        print(stmt)
        con = sqlite3.connect(dbFile)
        cur = con.cursor()
        cur.execute(stmt)

        fin.seek(0)

        reader = csv.reader(escapingGenerator(fin))

        # Generate insert statement:
        stmt = "INSERT INTO \"" + tablename + "\" VALUES(%s);" % ','.join('?' * len(cols))

        cur.executemany(stmt, reader)
        con.commit()
        con.close()

Answer 2

J'ai constaté qu'il peut être nécessaire d'interrompre le transfert des données du csv vers la base de données par morceaux pour ne pas manquer de mémoire. Cela peut être fait comme suit :

import csv
import sqlite3
from operator import itemgetter

# Establish connection
conn = sqlite3.connect("mydb.db")

# Create the table 
conn.execute(
    """
    CREATE TABLE persons(
        person_id INTEGER,
        last_name TEXT, 
        first_name TEXT, 
        address TEXT
    )
    """
)

# These are the columns from the csv that we want
cols = ["person_id", "last_name", "first_name", "address"]

# If the csv file is huge, we instead add the data in chunks
chunksize = 10000

# Parse csv file and populate db in chunks
with conn, open("persons.csv") as f:
    reader = csv.DictReader(f)

    chunk = []
    for i, row in reader: 

        if i % chunksize == 0 and i > 0:
            conn.executemany(
                """
                INSERT INTO persons
                    VALUES(?, ?, ?, ?)
                """, chunk
            )
            chunk = []

        items = itemgetter(*cols)(row)
        chunk.append(items)