rename

nlb-export/nlb.py

@@ -0,0 +1,90 @@
+import csv
+import re
+import subprocess
+import sys
+from pathlib import Path
+# extract transaction from izpisek pdf
+TRANSACTION_START = re.compile(r"^\d{2}\.\d{2}\.\d{2}\s")
+TRANSACTION_LINE = re.compile(
+    r"^(?P<date>\d{2}\.\d{2}\.\d{2})\s+"
+    r"(?P<middle>.*?)\s+"
+    r"(?P<amount>[+-][\d.,]+)\s+"
+    r"(?P<balance>-?[\d.,]+-?)\s*$"
+)
+CONTINUATION_INDENT = 15
+FIELD_SPLIT = re.compile(r"\s{4,}")
+ACCOUNT = re.compile(r"^SI\d{2}(?:\s?\d{4}){3}\s?\d{3}$")
+
+
+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 parse_transaction(line):
+    m = TRANSACTION_LINE.match(line.rstrip())
+    account = ""
+    desc_parts = []
+    for f in FIELD_SPLIT.split(m.group("middle").strip()):
+        if ACCOUNT.match(f):
+            account = f
+        else:
+            desc_parts.append(f)
+    balance = m.group("balance")
+    if balance.endswith("-"):
+        balance = "-" + balance[:-1]
+    return {
+        "date": m.group("date"),
+        "desc": " ".join(desc_parts),
+        "account": account,
+        "amount": m.group("amount"),
+        "balance": balance,
+        "currency": "EUR",
+    }
+
+
+def extract_transactions(pdf_path):
+    print(pdf_path)
+    rows = []
+    full_text = pdf_to_text(pdf_path)
+    for page_text in full_text.split("\f"):
+        page_start = len(rows)
+        for line in page_text.split("\n"):
+            if not line.strip():
+                continue
+            if TRANSACTION_START.match(line):
+                rows.append(parse_transaction(line))
+                continue
+            if len(rows) <= page_start:
+                continue
+            indent = len(line) - len(line.lstrip(" "))
+            if indent < CONTINUATION_INDENT:
+                continue
+            parts = FIELD_SPLIT.split(line.strip())
+            rows[-1]["desc"] += " " + parts[0]
+            if len(parts) > 1:
+                rows[-1]["account"] = (rows[-1]["account"] + " " + parts[1]).strip()
+    return rows
+
+
+def main():
+    pdf_dir = Path(sys.argv[1])
+    out_path = pdf_dir.with_suffix(".csv")
+
+    all_rows = []
+    for pdf_path in sorted(pdf_dir.glob("*.pdf")):
+        all_rows.extend(extract_transactions(pdf_path))
+
+    with open(out_path, "w", newline="") as f:
+        writer = csv.DictWriter(f, fieldnames=["date", "desc", "account", "amount", "balance", "currency"])
+        writer.writeheader()
+        writer.writerows(all_rows)
+
+    print(f"Wrote {len(all_rows)} transactions to {out_path}")
+
+
+if __name__ == "__main__":
+    main()