Initial income_calculator project

Co-authored-by: Cursor <cursoragent@cursor.com>

backend/parsers/bank_s.py

@@ -0,0 +1,87 @@
+import re
+from datetime import datetime
+from pathlib import Path
+from typing import List
+
+import pdfplumber
+
+from backend.parsers.base import BaseBankParser, ParsedTransaction
+
+
+def _normalize_amount(s: str) -> float:
+    """Пробелы убрать, запятая — десятичный разделитель."""
+    return float(s.replace("\u00a0", " ").replace(" ", "").replace(",", "."))
+
+
+def _parse_datetime_s(date_str: str, time_str: str) -> str:
+    """DD.MM.YYYY + HH:MM -> ISO."""
+    try:
+        part = date_str.strip() + " " + (time_str or "00:00").strip()
+        dt = datetime.strptime(part, "%d.%m.%Y %H:%M")
+        return dt.strftime("%Y-%m-%dT%H:%M:%S")
+    except ValueError:
+        return date_str.strip()[:10].replace(".", "-") + "T00:00:00"
+
+
+class BankSParser(BaseBankParser):
+    """Парсер выписок Сбербанка. Файлы С-MM-YY.pdf."""
+
+    # Первая строка: дата время код_авторизации категория сумма остаток (сумма с + = приход, без = расход)
+    ROW_RE = re.compile(
+        r"^(\d{2}\.\d{2}\.\d{4})\s+(\d{1,2}:\d{2})\s+(\d{6})\s+(.+?)\s+([+-]?[\d\s]+,\d{2})\s+([\d\s]+,\d{2})\s*$",
+        re.UNICODE,
+    )
+    # Вторая строка: дата описание ... Операция по (перенос)
+    DESC_LINE1_RE = re.compile(r"^(\d{2}\.\d{2}\.\d{4})\s+(.+?)\s+Операция по\s*$", re.UNICODE)
+    # Третья строка: карте ****0566
+    CARD_LINE_RE = re.compile(r"^карте\s+\*\*\*\*(\d{4})\s*$", re.UNICODE)
+
+    def can_parse(self, filename: str) -> bool:
+        name = Path(filename).name
+        return name.startswith("С-") and name.lower().endswith(".pdf")
+
+    def parse(self, file_path: str) -> List[ParsedTransaction]:
+        result: List[ParsedTransaction] = []
+        with pdfplumber.open(file_path) as pdf:
+            lines: List[str] = []
+            for page in pdf.pages:
+                text = page.extract_text()
+                if text:
+                    lines.extend(text.split("\n"))
+
+        i = 0
+        while i < len(lines):
+            line = lines[i].strip()
+            m = self.ROW_RE.match(line)
+            if m:
+                date_op, time_op, _code, category, amount_str, _balance = m.groups()
+                amount = _normalize_amount(amount_str)
+                if not amount_str.strip().startswith("+"):
+                    amount = -amount
+                desc_extra = ""
+                card_tail = ""
+                if i + 1 < len(lines):
+                    d1 = self.DESC_LINE1_RE.match(lines[i + 1].strip())
+                    if d1:
+                        desc_extra = " " + d1.group(2).strip()
+                        i += 1
+                        if i + 1 < len(lines):
+                            c2 = self.CARD_LINE_RE.match(lines[i + 1].strip())
+                            if c2:
+                                card_tail = c2.group(1)
+                                i += 1
+                if not card_tail:
+                    card_tail = "0000"
+                description = (category + desc_extra).strip()
+                result.append(
+                    ParsedTransaction(
+                        operation_date=_parse_datetime_s(date_op, time_op),
+                        debit_date=None,
+                        amount=amount,
+                        amount_card_currency=None,
+                        description=description,
+                        card_tail=card_tail,
+                    )
+                )
+            i += 1
+        return result