85 lines
3.2 KiB
Python
85 lines
3.2 KiB
Python
import re
|
||
from datetime import datetime
|
||
from pathlib import Path
|
||
from typing import List
|
||
|
||
import pdfplumber
|
||
|
||
from backend.parsers.base import BaseBankParser, ParsedTransaction
|
||
|
||
# Я-банк использует EN DASH (U+2013) для минуса
|
||
MINUS_CHARS = "\u2013-"
|
||
|
||
|
||
def _normalize_amount(s: str) -> float:
|
||
s = s.replace("\u00a0", " ").replace(" ", "").replace(",", ".")
|
||
for c in MINUS_CHARS:
|
||
s = s.replace(c, "-")
|
||
if s.startswith("−"):
|
||
s = "-" + s[1:]
|
||
return float(s)
|
||
|
||
|
||
def _parse_datetime_y(date_str: str, time_str: str = "") -> str:
|
||
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().replace(".", "-")[:10] + "T00:00:00"
|
||
|
||
|
||
class BankYParser(BaseBankParser):
|
||
"""Парсер выписок Яндекс Банка. Файлы Я-MM-YY.pdf."""
|
||
|
||
# Строка: описание ... DD.MM.YYYY DD.MM.YYYY [*XXXX] сумма ₽ сумма ₽ (минус может быть – U+2013, карта опциональна)
|
||
ROW_RE = re.compile(
|
||
r"^(.+?)\s+(\d{2}\.\d{2}\.\d{4})\s+(\d{2}\.\d{2}\.\d{4})\s+(?:\*(\d{4})\s+)?([+\u2013\-]?[\d\s,]+)\s*₽\s+([+\u2013\-]?[\d\s,]+)\s*₽\s*$",
|
||
re.UNICODE,
|
||
)
|
||
# Вторая строка может содержать время: "в 18:13" или "клиента в 21:35"
|
||
TIME_RE = re.compile(r"^(?:.*\s+)?в\s+(\d{1,2}:\d{2})\s*$", re.UNICODE)
|
||
|
||
PIGGY_MARKER = "Перевод между счетами одного клиента"
|
||
|
||
def can_parse(self, filename: str) -> bool:
|
||
name = Path(filename).name
|
||
return name.startswith("Я-") 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:
|
||
desc, date_op, date_proc, card_tail, amt1, amt2 = m.groups()
|
||
card_tail = card_tail or "0000"
|
||
amount = _normalize_amount(amt1)
|
||
time_str = ""
|
||
if i + 1 < len(lines):
|
||
tm = self.TIME_RE.match(lines[i + 1].strip())
|
||
if tm:
|
||
time_str = tm.group(1)
|
||
desc = (desc + " " + lines[i + 1].strip()).strip()
|
||
i += 1
|
||
result.append(
|
||
ParsedTransaction(
|
||
operation_date=_parse_datetime_y(date_op, time_str),
|
||
debit_date=_parse_datetime_y(date_proc),
|
||
amount=amount,
|
||
amount_card_currency=_normalize_amount(amt2) if amt2 else None,
|
||
description=desc.strip(),
|
||
card_tail=card_tail,
|
||
)
|
||
)
|
||
i += 1
|
||
return result
|