From 5e840c14292f199cca107d89808d63aa9c88eb15 Mon Sep 17 00:00:00 2001
From: jethro <jethro.cotton3@gmail.com>
Date: Wed, 13 May 2026 16:44:54 +1200
Subject: [PATCH] added a parser to format output transactions

---
 emoneyscraper/main.py    |  4 +++-
 emoneyscraper/scraper.py | 40 ++++++++++++++++++++++++++++++++++++++++
 2 files changed, 43 insertions(+), 1 deletion(-)

diff --git a/emoneyscraper/main.py b/emoneyscraper/main.py
index 3be8e99..3a50f2e 100755
--- a/emoneyscraper/main.py
+++ b/emoneyscraper/main.py
@@ -4,6 +4,8 @@ from playwright.sync_api import sync_playwright, Playwright
 playwright = sync_playwright().start()
 scraper = Scraper(playwright, True)
 print(scraper.get_balance())
-print(scraper.get_transactions())
+transactions = scraper.get_transactions()
+parsed = scraper.parse_transactions(transactions)
+print(parsed)
 scraper.close()
 
diff --git a/emoneyscraper/scraper.py b/emoneyscraper/scraper.py
index d42ca8d..b351ff2 100755
--- a/emoneyscraper/scraper.py
+++ b/emoneyscraper/scraper.py
@@ -1,6 +1,8 @@
 from playwright.sync_api import sync_playwright, Playwright
 import os
 from dotenv import load_dotenv
+import re
+from datetime import datetime
 
 load_dotenv()
 class Scraper:
@@ -23,6 +25,44 @@ class Scraper:
         transaction_body = self.page.locator("xpath=/html/body/form/div[3]/div[3]/div[2]/div/div[2]/div[3]/table/tbody").inner_text()
         return transaction_body
 
+    def parse_transactions(self, raw: str = None) -> list[dict[str, any]]:
+        """
+        Parse raw transactions text into a list of dicts:
+        [{'date': date, 'description': str, 'amount': float, 'balance': float}, ...]
+        Lines containing 'INSUFF FUNDS' (case-insensitive) are ignored.
+        If raw is None, get_transactions() is called to fetch the data.
+        """
+        if raw is None:
+            raw = self.get_transactions() or ""
+        lines = [ln.strip() for ln in raw.splitlines() if ln.strip()]
+        pattern = re.compile(
+            r'^(?P<date>\d{2}-\d{2}-\d{4})\s+(?P<desc>.*?)\s+(?P<amount>[-\$\d,\.]+)\s+(?P<balance>[-\$\d,\.]+)\s*$'
+        )
+        parsed: list[dict[str, any]] = []
+        for ln in lines:
+            m = pattern.match(ln)
+            if not m:
+                # skip lines that don't match the expected pattern
+                continue
+            desc = m.group('desc').strip()
+            if 'INSUFF FUNDS' in desc.upper():
+                continue
+            def _to_float(s: str) -> float:
+                return float(s.replace('$', '').replace(',', '').strip())
+            try:
+                amount = _to_float(m.group('amount'))
+                balance = _to_float(m.group('balance'))
+                date_obj = datetime.strptime(m.group('date'), '%d-%m-%Y').date()
+            except Exception:
+                continue
+            parsed.append({
+                'date': date_obj,
+                'description': desc,
+                'amount': amount,
+                'balance': balance,
+            })
+        return parsed
+
     def close(self):
         self.browser.close()