Created a script to update the csv imports that don't have the date

This commit is contained in:
Jonas Linter
2025-11-20 11:14:07 +01:00
parent 8308be3e49
commit ce1fd140c9
7 changed files with 318968 additions and 1158 deletions

101
update_csv_import_dates.py Normal file
View File

@@ -0,0 +1,101 @@
#!/usr/bin/env python3
"""
Update the created_at timestamps for CSV-imported leads with the new email receive dates.
"""
import asyncio
import csv
from datetime import datetime
from sqlalchemy import text, select
from sqlalchemy.ext.asyncio import create_async_engine, AsyncSession
from sqlalchemy.orm import sessionmaker
from src.alpine_bits_python.config_loader import load_config
from src.alpine_bits_python.db import Reservation, Customer
async def main():
# Load config
config = load_config()
db_url = config["database"]["url"]
schema = config["database"]["schema"]
# Create async engine
engine = create_async_engine(db_url)
async_session = sessionmaker(engine, class_=AsyncSession, expire_on_commit=False)
async with engine.begin() as conn:
await conn.execute(text(f"SET search_path TO {schema}"))
# Load the CSV with the new dates
csv_dates = {}
try:
with open("leads_export.csv", "r", encoding="utf-8") as f:
reader = csv.DictReader(f)
for row in reader:
name = row.get("name", "").strip()
lastname = row.get("lastname", "").strip()
email = row.get("mail", "").strip()
received_date = row.get("received_date", "").strip()
if email and received_date:
# Use email as primary key since it's unique
csv_dates[email.lower()] = {
"name": name,
"lastname": lastname,
"received_date": received_date,
}
except FileNotFoundError:
print("ERROR: leads_export.csv not found. Run extract_leads.py first.")
return
print(f"Loaded {len(csv_dates)} date entries from CSV")
# Fetch CSV-imported reservations
async with async_session() as session:
async with engine.begin() as conn:
await conn.execute(text(f"SET search_path TO {schema}"))
# Query for CSV imports
result = await session.execute(
select(Reservation, Customer).join(
Customer, Reservation.customer_id == Customer.id
).where(Reservation.unique_id.like("csv_%"))
)
rows = result.all()
print(f"\nFound {len(rows)} CSV-imported reservations to update")
updated = 0
failed = 0
for reservation, customer in rows:
email = customer.email_address
if email and email.lower() in csv_dates:
new_date_str = csv_dates[email.lower()]["received_date"]
try:
# Parse ISO format date
new_date = datetime.fromisoformat(new_date_str)
old_date = reservation.created_at
print(f" Updating: {customer.given_name} ({email})")
print(f" Old: {old_date}")
print(f" New: {new_date}")
reservation.created_at = new_date
updated += 1
except ValueError as e:
print(f" FAILED to parse date for {email}: {e}")
failed += 1
elif email:
print(f" WARNING: No CSV date found for {customer.given_name} ({email})")
print(f"\nSummary: {updated} updated, {failed} failed")
if updated > 0:
await session.commit()
print("Changes committed to database")
else:
print("No changes made")
await engine.dispose()
if __name__ == "__main__":
asyncio.run(main())