add revolut

nlb-export/trade_republic.py

@@ -5,7 +5,7 @@ import sys
 from datetime import datetime
 from decimal import Decimal
 from pathlib import Path
-# extract transactions from trade republic account statement (pdf or pdftotext -layout txt)
+# extract transactions from trade republic account statement pdf
 HEADER = re.compile(r"^\s*DATE\b.*\bMONEY IN\b.*\bMONEY OUT\b.*\bBALANCE\b")
 TEXT_COLUMNS = ("DATE", "TYPE", "DESCRIPTION")
 MONEY_COLUMNS = ("MONEY IN", "MONEY OUT", "BALANCE")
@@ -16,14 +16,12 @@ IBAN = re.compile(r"\b[A-Z]{2}\d{2}[A-Z0-9]{11,30}\b")
 AMOUNT_SLACK = 5
 
 
-def read_text(path):
-    if path.suffix.lower() == ".pdf":
-        result = subprocess.run(
-            ["pdftotext", "-layout", str(path), "-"],
-            capture_output=True, text=True, check=True,
-        )
-        return result.stdout
-    return path.read_text(encoding="utf-8")
+def pdf_to_text(pdf_path):
+    result = subprocess.run(
+        ["pdftotext", "-layout", str(pdf_path), "-"],
+        capture_output=True, text=True, check=True,
+    )
+    return result.stdout
 
 
 def column_starts(header_line):
@@ -110,7 +108,7 @@ def blocks(lines):
 def extract_transactions(path):
     print(path)
     rows = []
-    for page_text in read_text(path).split("\f"):
+    for page_text in pdf_to_text(path).split("\f"):
         page_lines = page_text.split("\n")
         header = next((i for i, l in enumerate(page_lines) if HEADER.match(l)), None)
         if header is None:
@@ -134,25 +132,14 @@ def check_balances(rows, path):
 
 def main():
     target = Path(sys.argv[1])
-    if target.is_dir():
-        paths = sorted(p for p in target.iterdir() if p.suffix.lower() in {".pdf", ".txt"})
-    else:
-        paths = [target]
+    paths = sorted(target.glob("*.pdf")) if target.is_dir() else [target]
     out_path = target.with_suffix(".csv")
 
     all_rows = []
-    seen = set()
-    duplicates = 0
     for path in paths:
         rows = extract_transactions(path)
         check_balances(rows, path)
-        for row in rows:
-            key = (row["date"], row["desc"], row["amount"], row["balance"])
-            if key in seen:
-                duplicates += 1
-                continue
-            seen.add(key)
-            all_rows.append(row)
+        all_rows.extend(rows)
 
     with open(out_path, "w", newline="") as f:
         writer = csv.DictWriter(
@@ -161,8 +148,6 @@ def main():
         writer.writeheader()
         writer.writerows(all_rows)
 
-    if duplicates:
-        print(f"Skipped {duplicates} transactions already seen in an earlier statement")
     print(f"Wrote {len(all_rows)} transactions to {out_path}")