2 muutettua tiedostoa jossa 265 lisäystä ja 319 poistoa
Yhdistetty näkymä
Diff Options
-
+0 -251ynab-karianne.py
-
+265 -68ynab.py
+ 0
- 251
ynab-karianne.py
Näytä tiedosto
| @@ -1,251 +0,0 @@ | |||||
| #!/usr/bin/env python3 | |||||
| """ | |||||
| Bank Statement to YNAB Converter | |||||
| Converts bank statements from various formats to YNAB-compatible CSV files | |||||
| """ | |||||
| import os | |||||
| import sys | |||||
| import glob | |||||
| import pandas as pd | |||||
| from pathlib import Path | |||||
| def parse_norwegian_number(value): | |||||
| """Convert Norwegian number format (comma decimal) to float""" | |||||
| if pd.isna(value) or value == '': | |||||
| return 0.0 | |||||
| # Convert to string and replace comma with dot | |||||
| str_value = str(value).replace(',', '.') | |||||
| try: | |||||
| return float(str_value) | |||||
| except ValueError: | |||||
| return 0.0 | |||||
| def parse_norwegian_date(date_str): | |||||
| """Convert DD.MM.YYYY format to YYYY-MM-DD""" | |||||
| if pd.isna(date_str) or date_str == '': | |||||
| return '' | |||||
| try: | |||||
| # Parse DD.MM.YYYY and convert to date object | |||||
| return pd.to_datetime(date_str, format='%d.%m.%Y') | |||||
| except (ValueError, TypeError): | |||||
| print(f"Invalid date format: {date_str}") | |||||
| exit(1) | |||||
| def parse_bank_sparebank1(data): | |||||
| """ | |||||
| Parse Sparebank 1 bank data | |||||
| Expected columns: Dato, Beskrivelse, Rentedato, Inn, Ut, Til konto, Fra konto | |||||
| """ | |||||
| result = [] | |||||
| for _, row in data.iterrows(): | |||||
| inflow = parse_norwegian_number(row.get('Inn')) | |||||
| outflow = parse_norwegian_number(row.get('Ut')) | |||||
| # Convert outflow to positive if negative | |||||
| if outflow < 0: | |||||
| outflow = -outflow | |||||
| result.append({ | |||||
| 'Date': parse_norwegian_date(row.get('Dato', '')), | |||||
| 'Payee': row.get('Beskrivelse', ''), | |||||
| 'Memo': row.get('Til konto', ''), | |||||
| 'Outflow': outflow, | |||||
| 'Inflow': inflow | |||||
| }) | |||||
| return pd.DataFrame(result) | |||||
| def parse_bank_norwegian(data): | |||||
| """ | |||||
| Parse Norwegian bank data | |||||
| Expected columns: TransactionDate, Text, Memo, Amount | |||||
| """ | |||||
| result = [] | |||||
| for _, row in data.iterrows(): | |||||
| amount = row.get('Amount', 0) | |||||
| inflow = amount if amount > 0 else 0 | |||||
| outflow = -amount if amount < 0 else 0 # Make outflow positive | |||||
| result.append({ | |||||
| 'Date': row.get('TransactionDate', ''), | |||||
| 'Payee': row.get('Text', ''), | |||||
| 'Memo': row.get('Memo', ''), | |||||
| 'Outflow': outflow, | |||||
| 'Inflow': inflow | |||||
| }) | |||||
| return pd.DataFrame(result) | |||||
| # Dictionary of banks, filename patterns, and parsing functions | |||||
| BANKS = { | |||||
| "Sparebank1": { | |||||
| "patterns": ["OversiktKonti*.csv"], | |||||
| "output_filename": "YNAB-{bank}-FROM-{first_date}-TO-{last_date}", | |||||
| "parse_function": parse_bank_sparebank1, | |||||
| "delimiter": ";" | |||||
| }, | |||||
| "Norwegian": { | |||||
| "patterns": ["BankNorwegian*.xlsx", "Statement*.xlsx"], | |||||
| "output_filename": "YNAB-{bank}-FROM-{first_date}-TO-{last_date}", | |||||
| "parse_function": parse_bank_norwegian | |||||
| } | |||||
| # Add more banks and patterns as needed | |||||
| } | |||||
| def process_bank_statement(file_path, parse_function, delimiter): | |||||
| """ | |||||
| Process a single bank statement file | |||||
| Args: | |||||
| file_path (str): Path to the bank statement file | |||||
| parse_function (callable): Function to parse the specific bank format | |||||
| delimiter (Optional<str>): Field delimiter | |||||
| Returns: | |||||
| pd.DataFrame: Processed YNAB-compatible data | |||||
| """ | |||||
| file_extension = Path(file_path).suffix.lower() | |||||
| try: | |||||
| # Handle CSV files | |||||
| if file_extension == ".csv": | |||||
| data = pd.read_csv(file_path, delimiter=delimiter) | |||||
| # Handle Excel files | |||||
| elif file_extension in [".xlsx", ".xls"]: | |||||
| data = pd.read_excel(file_path) | |||||
| else: | |||||
| print(f"Skipping unsupported file type: {file_path}") | |||||
| return pd.DataFrame() | |||||
| # Call the appropriate bank-specific parsing function | |||||
| ynab_data = parse_function(data) | |||||
| return ynab_data | |||||
| except Exception as e: | |||||
| print(f"Error processing file {file_path}: {e}") | |||||
| raise e | |||||
| return pd.DataFrame() | |||||
| def find_bank_config(filename): | |||||
| """ | |||||
| Find the appropriate bank configuration for a given filename | |||||
| Args: | |||||
| filename (str): Name of the file to match | |||||
| Returns: | |||||
| tuple: (bank_name, bank_config) or (None, None) if no match | |||||
| """ | |||||
| import fnmatch | |||||
| for bank_name, bank_config in BANKS.items(): | |||||
| for pattern in bank_config["patterns"]: | |||||
| if fnmatch.fnmatch(filename, pattern): | |||||
| return bank_name, bank_config | |||||
| return None, None | |||||
| def convert_bank_statements_to_ynab(input_files=None): | |||||
| """ | |||||
| Convert bank statements to YNAB format | |||||
| Args: | |||||
| input_files (list): Optional list of specific files to process | |||||
| If None, processes all files in current directory | |||||
| """ | |||||
| current_directory = Path.cwd() | |||||
| output_directory = current_directory / "YNAB_Outputs" | |||||
| # Create output directory if it doesn't exist | |||||
| output_directory.mkdir(exist_ok=True) | |||||
| # Get list of files to process | |||||
| if input_files: | |||||
| print(f"Processing {len(input_files)} dragged file(s)...") | |||||
| files_to_process = [Path(f) for f in input_files if Path(f).exists()] | |||||
| else: | |||||
| print("Processing all files in current directory...") | |||||
| files_to_process = [] | |||||
| # Collect all files matching any bank pattern | |||||
| for bank_config in BANKS.values(): | |||||
| for pattern in bank_config["patterns"]: | |||||
| matching_files = glob.glob(str(current_directory / pattern)) | |||||
| files_to_process.extend([Path(f) for f in matching_files]) | |||||
| files_processed = False | |||||
| # Process each file | |||||
| for file_path in files_to_process: | |||||
| if not file_path.exists(): | |||||
| print(f"File not found: {file_path}") | |||||
| continue | |||||
| # Find matching bank configuration | |||||
| bank_name, bank_config = find_bank_config(file_path.name) | |||||
| if not bank_config: | |||||
| print(f"No bank configuration found for file: {file_path.name}") | |||||
| continue | |||||
| print(f"Processing file: {file_path} for {bank_name}") | |||||
| parse_function = bank_config["parse_function"] | |||||
| delimiter = bank_config.get("delimiter", ",") | |||||
| # Process the file | |||||
| ynab_data = process_bank_statement(str(file_path), parse_function, delimiter) | |||||
| if ynab_data.empty: | |||||
| print(f"No data processed for {file_path}") | |||||
| continue | |||||
| filename_placeholders = { | |||||
| 'bank': bank_name, | |||||
| 'first_date': ynab_data['Date'].min().date(), | |||||
| 'last_date': ynab_data['Date'].max().date(), | |||||
| } | |||||
| file_retry_count = 0 | |||||
| while True: | |||||
| output_filename = bank_config["output_filename"].format(**filename_placeholders) | |||||
| if file_retry_count > 0: | |||||
| output_filename += f" ({file_retry_count})" | |||||
| output_filename += ".csv" | |||||
| output_file = output_directory / output_filename | |||||
| if not output_file.exists(): | |||||
| break | |||||
| file_retry_count += 1 | |||||
| # Export to CSV for YNAB import | |||||
| ynab_data.to_csv(output_file, index=False) | |||||
| print(f"Data saved to {output_file}") | |||||
| files_processed = True | |||||
| if not files_processed: | |||||
| print("No files were processed. Make sure your files match the expected patterns.") | |||||
| if __name__ == "__main__": | |||||
| # Check if files were dragged onto the script | |||||
| if len(sys.argv) > 1: | |||||
| # Files were dragged - process them | |||||
| files = sys.argv[1:] | |||||
| convert_bank_statements_to_ynab(files) | |||||
| else: | |||||
| # No files dragged - run normal directory processing | |||||
| convert_bank_statements_to_ynab() | |||||
| # Keep window open on Mac so user can see results | |||||
| input("\nPress Enter to close...") | |||||
+ 265
- 68
ynab.py
Näytä tiedosto
| @@ -1,39 +1,49 @@ | |||||
| #!/bin/python3 | |||||
| #!/usr/bin/env python3 | |||||
| """ | |||||
| Bank Statement to YNAB Converter | |||||
| Converts bank statements from various formats to YNAB-compatible CSV files | |||||
| """ | |||||
| import os | |||||
| import sys | import sys | ||||
| import csv | |||||
| import glob | |||||
| import re | import re | ||||
| import pandas as pd | |||||
| from pathlib import Path | from pathlib import Path | ||||
| whitelist_cards = ["7756"] | |||||
| def parse_norwegian_number(value): | |||||
| """Convert Norwegian number format (comma decimal) to float""" | |||||
| if pd.isna(value) or value == '': | |||||
| return 0.0 | |||||
| # Convert to string and replace comma with dot | |||||
| str_value = str(value).replace(',', '.') | |||||
| try: | |||||
| return float(str_value) | |||||
| except ValueError: | |||||
| return 0.0 | |||||
| in_header = ['Utført dato', 'Bokført dato', 'Rentedato', 'Beskrivelse', 'Type', 'Undertype', 'Fra konto', 'Avsender', 'Til konto', 'Mottakernavn', 'Beløp inn', 'Beløp ut', 'Valuta', 'Status', 'Melding'] | |||||
| out_header = ['Date', 'Payee', 'Memo', 'Outflow', 'Inflow'] | |||||
| def usage(): | |||||
| print('Usage: ynab.py <filename>') | |||||
| def is_reserved(row): | |||||
| return row['Status'] == "Reservert" | |||||
| def parse_norwegian_date(date_str): | |||||
| """Convert DD.MM.YYYY format to YYYY-MM-DD""" | |||||
| if pd.isna(date_str) or date_str == '': | |||||
| return '' | |||||
| try: | |||||
| # Parse DD.MM.YYYY and convert to date object | |||||
| return pd.to_datetime(date_str, format='%d.%m.%Y') | |||||
| except (ValueError, TypeError): | |||||
| print(f"Invalid date format: {date_str}") | |||||
| exit(1) | |||||
| def convert_memo(original): | def convert_memo(original): | ||||
| original = original.replace(" Kurs: 1.0000", "") | original = original.replace(" Kurs: 1.0000", "") | ||||
| words = original.split(" ") | words = original.split(" ") | ||||
| for i in range(20): | |||||
| while len(words) > 0: | |||||
| if words[0] == "": | if words[0] == "": | ||||
| # It's empty | # It's empty | ||||
| del words[0] | del words[0] | ||||
| elif m := re.match(r'\*(\d{4})', words[0]): | elif m := re.match(r'\*(\d{4})', words[0]): | ||||
| # It's the last four digits of a card | |||||
| if m.groups()[0] in whitelist_cards: | |||||
| # It's an expected card, ignore it | |||||
| del words[0] | |||||
| else: | |||||
| # It's an unexpected card, move it to the end | |||||
| words.append(words.pop(0)) | |||||
| # It's the last four numbers of the card, ignore it | |||||
| del words[0] | |||||
| elif m := re.match(r'\d{2}\.\d{2}', words[0]): | elif m := re.match(r'\d{2}\.\d{2}', words[0]): | ||||
| # It's the date. Move it to the end | # It's the date. Move it to the end | ||||
| words.append(words.pop(0)) | words.append(words.pop(0)) | ||||
| @@ -49,71 +59,258 @@ def convert_memo(original): | |||||
| words.append(words.pop(0)) | words.append(words.pop(0)) | ||||
| else: | else: | ||||
| break | break | ||||
| else: | |||||
| raise Exception(f"Infinite loop while parsing \"{original}\"") | |||||
| return " ".join(words) | return " ".join(words) | ||||
| def parse_bank_sor(data): | |||||
| """ | |||||
| Parse Sparebank 1 bank data | |||||
| Expected columns: Dato, Beskrivelse, Rentedato, Inn, Ut, Til konto, Fra konto | |||||
| """ | |||||
| result = [] | |||||
| for _, row in data.iterrows(): | |||||
| if row.get('Status') != "Bokført": | |||||
| continue | |||||
| def convert_row(row): | |||||
| if is_reserved(row): | |||||
| return None | |||||
| if row.get('Valuta') != 'NOK': | |||||
| raise ValueError(f"Unknown currency {row['Valuta']}") | |||||
| if row['Valuta'] != 'NOK': | |||||
| raise ValueError(f"Unknown currency {row['Valuta']}") | |||||
| payee = convert_memo(row.get('Beskrivelse', '')) | |||||
| memo = convert_memo(row.get('Melding/KID/Fakt.nr', '')) | |||||
| return [ | |||||
| row['Bokført dato'], | |||||
| row['Beskrivelse'], | |||||
| convert_memo(row['Melding']), | |||||
| -float(row['Beløp ut'] or '0'), | |||||
| float(row['Beløp inn'] or '0'), | |||||
| ] | |||||
| result.append({ | |||||
| 'Date': parse_norwegian_date(row.get('Bokført dato')), | |||||
| 'Payee': payee, | |||||
| 'Memo': memo, | |||||
| 'Outflow': -float(row['Beløp ut'] or '0'), | |||||
| 'Inflow': float(row['Beløp inn'] or '0'), | |||||
| }) | |||||
| return pd.DataFrame(result) | |||||
| def parse_bank_sparebank1(data): | |||||
| """ | |||||
| Parse Sparebank 1 bank data | |||||
| Expected columns: Dato, Beskrivelse, Rentedato, Inn, Ut, Til konto, Fra konto | |||||
| """ | |||||
| result = [] | |||||
| for _, row in data.iterrows(): | |||||
| inflow = parse_norwegian_number(row.get('Inn')) | |||||
| outflow = parse_norwegian_number(row.get('Ut')) | |||||
| # Convert outflow to positive if negative | |||||
| if outflow < 0: | |||||
| outflow = -outflow | |||||
| result.append({ | |||||
| 'Date': parse_norwegian_date(row.get('Dato', '')), | |||||
| 'Payee': row.get('Beskrivelse', ''), | |||||
| 'Memo': row.get('Til konto', ''), | |||||
| 'Outflow': outflow, | |||||
| 'Inflow': inflow | |||||
| }) | |||||
| return pd.DataFrame(result) | |||||
| def convert(reader, writer): | |||||
| writer.writerow(out_header) | |||||
| # Ignore header | |||||
| reader.__next__() | |||||
| def parse_bank_norwegian(data): | |||||
| """ | |||||
| Parse Norwegian bank data | |||||
| Expected columns: TransactionDate, Text, Memo, Amount | |||||
| """ | |||||
| result = [] | |||||
| for _, row in data.iterrows(): | |||||
| amount = row.get('Amount', 0) | |||||
| inflow = amount if amount > 0 else 0 | |||||
| outflow = -amount if amount < 0 else 0 # Make outflow positive | |||||
| result.append({ | |||||
| 'Date': row.get('TransactionDate', ''), | |||||
| 'Payee': row.get('Text', ''), | |||||
| 'Memo': row.get('Memo', ''), | |||||
| 'Outflow': outflow, | |||||
| 'Inflow': inflow | |||||
| }) | |||||
| return pd.DataFrame(result) | |||||
| for raw_row in reader: | |||||
| # Stop when we hit an empty row | |||||
| for field in raw_row: | |||||
| if field: | |||||
| break | |||||
| # Dictionary of banks, filename patterns, and parsing functions | |||||
| BANKS = { | |||||
| "SparebankenNorge": { | |||||
| "patterns": ["Transaksjoner*.csv"], | |||||
| "encoding": "latin1", | |||||
| "output_filename": "YNAB-{bank}-FROM-{first_date}-TO-{last_date}", | |||||
| "parse_function": parse_bank_sor, | |||||
| "delimiter": ";" | |||||
| }, | |||||
| "Sparebank1": { | |||||
| "patterns": ["OversiktKonti*.csv"], | |||||
| "output_filename": "YNAB-{bank}-FROM-{first_date}-TO-{last_date}", | |||||
| "parse_function": parse_bank_sparebank1, | |||||
| "delimiter": ";" | |||||
| }, | |||||
| "Norwegian": { | |||||
| "patterns": ["BankNorwegian*.xlsx", "Statement*.xlsx"], | |||||
| "output_filename": "YNAB-{bank}-FROM-{first_date}-TO-{last_date}", | |||||
| "parse_function": parse_bank_norwegian | |||||
| } | |||||
| # Add more banks and patterns as needed | |||||
| } | |||||
| def process_bank_statement(file_path, parse_function, delimiter, encoding): | |||||
| """ | |||||
| Process a single bank statement file | |||||
| Args: | |||||
| file_path (str): Path to the bank statement file | |||||
| parse_function (callable): Function to parse the specific bank format | |||||
| delimiter (Optional<str>): Field delimiter | |||||
| Returns: | |||||
| pd.DataFrame: Processed YNAB-compatible data | |||||
| """ | |||||
| file_extension = Path(file_path).suffix.lower() | |||||
| try: | |||||
| # Handle CSV files | |||||
| if file_extension == ".csv": | |||||
| data = pd.read_csv(file_path, delimiter=delimiter, encoding=encoding) | |||||
| # Handle Excel files | |||||
| elif file_extension in [".xlsx", ".xls"]: | |||||
| data = pd.read_excel(file_path) | |||||
| else: | else: | ||||
| break | |||||
| print(f"Skipping unsupported file type: {file_path}") | |||||
| return pd.DataFrame() | |||||
| # Call the appropriate bank-specific parsing function | |||||
| ynab_data = parse_function(data) | |||||
| return ynab_data | |||||
| except Exception as e: | |||||
| print(f"Error processing file {file_path}: {e}") | |||||
| raise e | |||||
| return pd.DataFrame() | |||||
| # Create dictionary with proper field names | |||||
| row = {x[0]: x[1] for x in zip(in_header, raw_row)} | |||||
| try: | |||||
| if (result := convert_row(row)) is not None: | |||||
| writer.writerow(result) | |||||
| except Exception as e: | |||||
| print(f'Error in row {row}') | |||||
| raise e | |||||
| def find_bank_config(filename): | |||||
| """ | |||||
| Find the appropriate bank configuration for a given filename | |||||
| Args: | |||||
| filename (str): Name of the file to match | |||||
| Returns: | |||||
| tuple: (bank_name, bank_config) or (None, None) if no match | |||||
| """ | |||||
| import fnmatch | |||||
| for bank_name, bank_config in BANKS.items(): | |||||
| for pattern in bank_config["patterns"]: | |||||
| if fnmatch.fnmatch(filename, pattern): | |||||
| return bank_name, bank_config | |||||
| return None, None | |||||
| def main(): | |||||
| if len(sys.argv) != 2: | |||||
| usage() | |||||
| exit(1) | |||||
| def convert_bank_statements_to_ynab(input_files=None): | |||||
| """ | |||||
| Convert bank statements to YNAB format | |||||
| Args: | |||||
| input_files (list): Optional list of specific files to process | |||||
| If None, processes all files in current directory | |||||
| """ | |||||
| current_directory = Path.cwd() | |||||
| output_directory = current_directory / "YNAB_Outputs" | |||||
| # Create output directory if it doesn't exist | |||||
| output_directory.mkdir(exist_ok=True) | |||||
| # Get list of files to process | |||||
| if input_files: | |||||
| print(f"Processing {len(input_files)} dragged file(s)...") | |||||
| files_to_process = [Path(f) for f in input_files if Path(f).exists()] | |||||
| else: | |||||
| print("Processing all files in current directory...") | |||||
| files_to_process = [] | |||||
| # Collect all files matching any bank pattern | |||||
| for bank_config in BANKS.values(): | |||||
| for pattern in bank_config["patterns"]: | |||||
| matching_files = glob.glob(str(current_directory / pattern)) | |||||
| files_to_process.extend([Path(f) for f in matching_files]) | |||||
| files_processed = False | |||||
| # Process each file | |||||
| for file_path in files_to_process: | |||||
| if not file_path.exists(): | |||||
| print(f"File not found: {file_path}") | |||||
| continue | |||||
| # Find matching bank configuration | |||||
| bank_name, bank_config = find_bank_config(file_path.name) | |||||
| if not bank_config: | |||||
| print(f"No bank configuration found for file: {file_path.name}") | |||||
| continue | |||||
| print(f"Processing file: {file_path} for {bank_name}") | |||||
| parse_function = bank_config["parse_function"] | |||||
| delimiter = bank_config.get("delimiter", ",") | |||||
| encoding = bank_config.get("encoding", "utf-8") | |||||
| # Process the file | |||||
| ynab_data = process_bank_statement(str(file_path), parse_function, delimiter, encoding) | |||||
| if ynab_data.empty: | |||||
| print(f"No data processed for {file_path}") | |||||
| continue | |||||
| filename_placeholders = { | |||||
| 'bank': bank_name, | |||||
| 'first_date': ynab_data['Date'].min().date(), | |||||
| 'last_date': ynab_data['Date'].max().date(), | |||||
| } | |||||
| filepath = Path(sys.argv[1]) | |||||
| file_retry_count = 0 | |||||
| while True: | |||||
| output_filename = bank_config["output_filename"].format(**filename_placeholders) | |||||
| new_basename = f'ynab-{filepath.name}' | |||||
| new_filepath = filepath.parent / new_basename | |||||
| if file_retry_count > 0: | |||||
| output_filename += f" ({file_retry_count})" | |||||
| output_filename += ".csv" | |||||
| output_file = output_directory / output_filename | |||||
| with filepath.open(mode='r', encoding='latin1') as old_file: | |||||
| reader = csv.reader(old_file, delimiter=';') | |||||
| if not output_file.exists(): | |||||
| break | |||||
| with new_filepath.open(mode='w') as new_file: | |||||
| writer = csv.writer(new_file) | |||||
| convert(reader, writer) | |||||
| file_retry_count += 1 | |||||
| # Export to CSV for YNAB import | |||||
| ynab_data.to_csv(output_file, index=False) | |||||
| print(f"Data saved to {output_file}") | |||||
| files_processed = True | |||||
| if not files_processed: | |||||
| print("No files were processed. Make sure your files match the expected patterns.") | |||||
| if __name__ == '__main__': | |||||
| main() | |||||
| if __name__ == "__main__": | |||||
| # Check if files were dragged onto the script | |||||
| if len(sys.argv) > 1: | |||||
| # Files were dragged - process them | |||||
| files = sys.argv[1:] | |||||
| convert_bank_statements_to_ynab(files) | |||||
| else: | |||||
| # No files dragged - run normal directory processing | |||||
| convert_bank_statements_to_ynab() | |||||
| # Keep window open on Mac so user can see results | |||||
| input("\nPress Enter to close...") | |||||