Upload files to "/"

extract.py

@@ -0,0 +1,86 @@
+import camelot
+import pandas as pd
+import re
+import csv
+
+def clean_amount(val):
+    """Removes '=' and whitespace from amount strings."""
+    if not val: return ""
+    return val.replace('=', '').strip()
+
+def extract_account(text):
+    """Extracts IBAN (SI56...) from a text block."""
+    match = re.search(r'[A-Z]{2}\d{2}\s?(?:\d{4}\s?){4}\d{1,3}', text)
+    return match.group(0).strip() if match else ""
+
+def process_bank_statement(pdf_path, output_csv):
+    # Load all pages. 'stream' flavor is ideal for this layout.
+    tables = camelot.read_pdf(pdf_path, pages='all', flavor='stream', split_text=True)
+    
+    all_transactions = []
+    current_tx = None
+    
+    # Regex to identify a date (DD.MM.YY) which anchors a new transaction
+    date_pattern = re.compile(r'\d{2}\.\d{2}\.\d{2}')
+
+    for table in tables:
+        df = table.df
+        for index, row in df.iterrows():
+            # Skip the header rows (usually contains 'Creditor' or 'value date')
+            if "Creditor" in row[0] or "value date" in str(row.iloc[-1]):
+                continue
+                
+            # Detect if this row contains a date in the last column (Column 4)
+            date_val = str(row.iloc[-1]).strip()
+            is_new_tx = bool(date_pattern.search(date_val))
+
+            if is_new_tx:
+                # If we were already building a transaction, save it before starting a new one
+                if current_tx:
+                    all_transactions.append(current_tx)
+                
+                # Initialize a new transaction object
+                current_tx = {
+                    'value date': date_pattern.search(date_val).group(0),
+                    'raw_text': row[0],
+                    'debit': clean_amount(row[1]),
+                    'credit': clean_amount(row[2])
+                }
+            else:
+                # If it's not a new date, it's a continuation of the previous transaction's text
+                if current_tx and row[0].strip():
+                    current_tx['raw_text'] += " " + row[0].strip()
+
+    # Append the last transaction processed
+    if current_tx:
+        all_transactions.append(current_tx)
+
+    # Final formatting: Split raw_text into Name, Account, and Details
+    final_data = []
+    for tx in all_transactions:
+        text = tx['raw_text']
+        account = extract_account(text)
+        
+        # Simple split logic: First part is Name, rest is Details (excluding account)
+        # Note: This logic can be refined based on specific name lengths
+        details = text.replace(account, "").strip()
+        parts = details.split("  ", 1) # Try to find a larger gap
+        name = parts[0].strip()
+        payment_details = parts[1].strip() if len(parts) > 1 else details
+        
+        final_data.append({
+            "value date": tx['value date'],
+            "Creditor / Debtor": name,
+            "account": account,
+            "payment details": payment_details,
+            "debit": tx['debit'],
+            "credit": tx['credit']
+        })
+
+    # Export to CSV with semicolon delimiter
+    output_df = pd.DataFrame(final_data)
+    output_df.to_csv(output_csv, index=False, sep=';', encoding='utf-8-sig', quoting=csv.QUOTE_ALL)
+    print(f"Successfully exported {len(final_data)} transactions to {output_csv}")
+
+# Execution
+process_bank_statement("MSDataReport (1).pdf", "Processed_Transactions.csv")