From e3505a9d76e5a5ca5df2d22593331770e14342f1 Mon Sep 17 00:00:00 2001
From: Tanguy Herbron <tanguy.herbron@outlook.com>
Date: Sat, 20 Jul 2024 18:42:19 +0200
Subject: [PATCH] feat(parsing): Parse columns via names

---
 main.py | 51 +++++++++++++++++++++++++++++++--------------------
 1 file changed, 31 insertions(+), 20 deletions(-)

diff --git a/main.py b/main.py
index 39c0831..1b8b83f 100644
--- a/main.py
+++ b/main.py
@@ -1,5 +1,7 @@
 import csv
 import json
+import pandas as pd
+import re
 from datetime import datetime
 from argparse import ArgumentParser
 
@@ -11,6 +13,8 @@ parser.add_argument("-o", "--output", dest="output_filename",
 
 args = parser.parse_args()
 
+dividend_expression_re = re.compile(r'(\d+\.?\d*?) ([A-Z]{3})')
+
 NORDNET_ACCOUNT_ID="cae3d45f-53bc-4dee-83a4-4448b409f8b2"
 
 format = "%Y-%m-%d"
@@ -22,42 +26,41 @@ data = {
 splits = {
     "NOVO B": {
         "2023-09-20 00:00:00 UTC": 0.5
+    },
+    "NVDA": {
+        "2024-06-10 00:00:00 UTC": 0.1
     }
 }
 
 symbol_translations = {
     "NOVO B": "NOVO-B.CO",
-    "XZEC": "XZEC.DE"
+    "NOVO B.OLD": "NOVO-B.CO",
+    "Xtrackers MSCI Eur CDisc ESG Scr ETF 1C": "XZEC.DE"
 }
 
-#print("Date", "Code", "DataSource", "Currency", "Price", "Quantity", "Action", "Fee", "account", sep=',')
-
 # Date, Code, DataSource, Currency, Price, Quantity, Action, Free, Note
-with open(args.input_filename, newline='') as csvfile:
-    reader = csv.reader(csvfile, delimiter='\t', quotechar='|')
+with open(args.input_filename, newline='', encoding="utf16") as csvfile:
+    df = pd.read_csv(csvfile, sep='\t', encoding='utf16', index_col=0)
 
-    for row in reader:
-        if row[5] in ("INDBETALING", "HÆVNING", "INDSÆTTELSE", "AFKASTSKAT ASK", "MAKULERING AFKASTSKAT ASK", "Transaktionstype", ""):
-            continue
-        
+    for index, row in df.iterrows():
         date = None
         t_type = None
         price = 0
 
         try:
-            date = datetime.strptime(row[2], format)
+            date = datetime.strptime(row['Handelsdag'], format)
         except ValueError:
             data = None
             print("Failed parsing date")
 
-        price = row[10].replace('.', '')
+        price = str(row['Kurs']).replace('.', '')
         price = price.replace(',', '.')
-        quantity = row[9]
-        fee = row[27]
-        symbol = row[6]
-        currency = row[17]
+        quantity = row['Antal']
+        fee = float(str(row['Samlede afgifter']).replace(',', '.'))
+        symbol = row['Værdipapirer']
+        currency = row['Valuta.3']
 
-        match row[5]:
+        match row['Transaktionstype']:
             case "KØBT":
                 t_type = "BUY"
             case "SOLGT":
@@ -65,21 +68,29 @@ with open(args.input_filename, newline='') as csvfile:
             case "UDB.":
                 t_type = "DIVIDEND"
                 fee = 0
-                currency = row[15]
-                
-        if symbol in splits:
+                div = dividend_expression_re.findall(row['Transaktionstekst'])
+                price = div[0][0]
+                price = price.replace(',', '.')
+                currency = div[0][1]
+            case _:
+                continue
+
+        if symbol in splits and row['Transaktionstype'] != "UDB.":
             key = list(splits[symbol].keys())[0]
             if date.isoformat() < key:
                 ratio = splits[symbol][key]
                 price = float(price) * ratio;
                 quantity = float(quantity) * (1 / ratio);                
 
+        if row['Valuta'] != row['Valuta.3'] and row['Transaktionstype'] != "UDB.":
+            fee = float(fee) / float(str(row['Vekslingskurs']).replace(',', '.'))
+
         if symbol in symbol_translations:
             symbol = symbol_translations[symbol]
         
         data['activities'].append({
             'accountId': NORDNET_ACCOUNT_ID,
-            'fee': float(str(fee).replace(',', '.')),
+            'fee': fee,
             'quantity': int(quantity),
             'type': t_type,
             'unitPrice': float(price),