initial upload

process_invoices.py

@@ -0,0 +1,95 @@
+#!/usr/bin/env python3
+"""
+Extract invoice data from PDFs in to_process/ and append to a dated CSV.
+Processed PDFs are moved to processed/.
+"""
+
+import csv
+import os
+import re
+import shutil
+from datetime import date, datetime
+from pathlib import Path
+
+import pdfplumber
+
+TO_PROCESS = Path("to_process")
+PROCESSED = Path("processed")
+CSV_FILENAME = f"{date.today().strftime('%Y-%m-%d')}.csv"
+CSV_HEADERS = ["Invoice Date", "Services From", "Services To", "Invoice Number", "Amount"]
+
+
+def extract_invoice_data(pdf_path: Path) -> dict:
+    with pdfplumber.open(pdf_path) as pdf:
+        text = "\n".join(page.extract_text() or "" for page in pdf.pages)
+
+    # Invoice Date - look for pattern like "16Mar2026"
+    invoice_date = ""
+    m = re.search(r"(\d{1,2}\w+\d{4})", text)
+    if m:
+        date_str = m.group(1)
+        # Parse and reformat to dd/MM/yyyy
+        try:
+            parsed_date = datetime.strptime(date_str, "%d%b%Y")
+            invoice_date = parsed_date.strftime("%d/%m/%Y")
+        except ValueError:
+            invoice_date = date_str  # Fallback to original if parsing fails
+
+    # Invoice Number - look for 7-digit number after customer name
+    invoice_number = ""
+    m = re.search(r"JosephBasten\s+(\d{7})", text)
+    if not m:
+        # Fallback: look for Invoice Number followed by digits
+        m = re.search(r"InvoiceNumber\s*(\d{7,})", text)
+    if m:
+        invoice_number = m.group(1)
+
+    # Total Amount
+    amount = ""
+    m = re.search(r"TOTALAUD\s*([\d,]+\.\d{2})", text)
+    if m:
+        amount = m.group(1)
+
+    # Service dates: lines containing "@ DD/MM/YYYY" (no spaces)
+    service_dates = re.findall(r"@(\d{2}/\d{2}/\d{4})", text)
+    services_from = service_dates[0] if service_dates else ""
+    services_to = service_dates[-1] if service_dates else ""
+
+    return {
+        "Invoice Date": invoice_date,
+        "Services From": services_from,
+        "Services To": services_to,
+        "Invoice Number": invoice_number,
+        "Amount": amount,
+    }
+
+
+def main():
+    pdfs = sorted(TO_PROCESS.glob("*.pdf"))
+    if not pdfs:
+        print("No PDFs found in to_process/")
+        return
+
+    csv_path = Path(CSV_FILENAME)
+    write_header = not csv_path.exists()
+
+    with csv_path.open("a", newline="") as f:
+        writer = csv.DictWriter(f, fieldnames=CSV_HEADERS)
+        if write_header:
+            writer.writeheader()
+
+        for pdf_path in pdfs:
+            print(f"Processing {pdf_path.name} ...")
+            try:
+                data = extract_invoice_data(pdf_path)
+                writer.writerow(data)
+                shutil.move(str(pdf_path), str(PROCESSED / pdf_path.name))
+                print(f"  -> Invoice {data['Invoice Number']} | {data['Invoice Date']} | {data['Services From']} to {data['Services To']} | AUD {data['Amount']}")
+            except Exception as e:
+                print(f"  ERROR processing {pdf_path.name}: {e}")
+
+    print(f"\nDone. Results written to {csv_path}")
+
+
+if __name__ == "__main__":
+    main()