Sort Wells Fargo CSV account activity by actual payment date, not post date

wellsfargo-csv.py

#!/usr/bin/env python
# Sort Wells Fargo CSV account activity by actual payment date, not post date
# By Joonas Kuorilehto. This script is Public Domain.

# Input: CSV file downloaded from Wells Fargo account activity
# Output: list of payments by transaction date

import re
import csv
import sys
from datetime import datetime, date

PATTERNS = [re.compile(p) for p in [
  r'\b(?P<month>\d\d)/(?P<day>\d\d)\b',
  r'\bON (?P<month>\d\d)-(?P<day>\d\d)',
	r'[^\d](?P<month>\d\d)/(?P<day>\d\d)([^\d]|$)',
]]

def parse(lines):
	for line in lines:
		if len(line) == 0:
			continue # skip line
		date_raw, amount, unknown, checkno, description = line
		postdate = datetime.strptime(date_raw, "%m/%d/%Y")

		# Use this year as the default year
		month, day, year = None, None, datetime.now().year
		for pattern in PATTERNS:
			match = re.search(pattern, description)
			if match:
				if match.group("month"):
					month = match.group("month")
				if match.group("day"):
					day = match.group("day")
		if not day or not month:
			year, month, day = 1999, 12, 31
		paydate = date(int(year), int(month), int(day))
		yield dict(postdate=postdate, amount=amount, checkno=checkno,
				   description=description, paydate=paydate)

def main():
	if len(sys.argv) != 2:
		print "Usage: %s <file>" % sys.argv[0]
		sys.exit(1)
	with open(sys.argv[1]) as f:
		payments = parse(csv.reader(f))
		payments = sorted(payments, key=lambda x: x["paydate"])
		for p in payments:
			date = datetime.strftime(p["paydate"], "%Y-%m-%d")
			print "%s %9s %s" % (date, p["amount"], p["description"])

if __name__ == "__main__":
	main()