Files

100 lines
3.1 KiB
Python

#!/usr/bin/env python3
"""S-13: чеки из Paperless → CSV для импорта в Firefly.
Ищет документы, вытаскивает сумму, пишет CSV в формате Firefly III.
"""
import csv
import json
import os
import re
import subprocess
import urllib.parse
import urllib.request
from datetime import datetime
PAPERLESS = "http://192.168.1.105:8000"
TOKEN = open("/root/.paperless-token", encoding="utf-8").read().strip()
OUT_DIR = "/mnt/media/finance"
STATE = "/var/lib/hub-finance/processed.json"
AMOUNT_RE = re.compile(
r"(?:итого|к\s*оплате|всего|сумма)[^\d]{0,20}([\d\s]{1,12}[.,]\d{2})",
re.IGNORECASE)
FALLBACK_RE = re.compile(r"(\d{1,6}[.,]\d{2})\s*(?:руб|₽)?", re.IGNORECASE)
def api(path):
req = urllib.request.Request(PAPERLESS + path,
headers={"Authorization": "Token " + TOKEN,
"Accept": "application/json"})
with urllib.request.urlopen(req, timeout=25) as r:
return json.loads(r.read() or b"{}")
def text_of(doc_id):
"""Достаёт текст документа (OCR/content)."""
req = urllib.request.Request(f"{PAPERLESS}/api/documents/{doc_id}/",
headers={"Authorization": "Token " + TOKEN,
"Accept": "application/json"})
with urllib.request.urlopen(req, timeout=25) as r:
d = json.loads(r.read() or b"{}")
return d.get("content") or ""
def extract_amount(text):
m = AMOUNT_RE.search(text)
if not m:
m = FALLBACK_RE.search(text)
if not m:
return None
raw = re.sub(r"\s", "", m.group(1)).replace(",", ".")
try:
return round(float(raw), 2)
except Exception:
return None
def main():
os.makedirs(OUT_DIR, exist_ok=True)
os.makedirs(os.path.dirname(STATE), exist_ok=True)
try:
processed = set(json.load(open(STATE, encoding="utf-8")))
except Exception:
processed = set()
docs = api("/api/documents/?page_size=50&ordering=-created")
rows = []
for d in docs.get("results", []):
did = str(d.get("id"))
if did in processed:
continue
text = text_of(did)
amount = extract_amount(text)
if not amount:
continue
title = (d.get("title") or "чек")[:60]
date = (d.get("created") or datetime.now().isoformat())[:10]
rows.append([date, title, amount])
processed.add(did)
if not rows:
print("новых чеков с суммой не найдено")
return
out = os.path.join(OUT_DIR, f"receipts-{datetime.now():%Y%m}.csv")
new_file = not os.path.exists(out)
with open(out, "a", newline="", encoding="utf-8") as f:
w = csv.writer(f)
if new_file:
w.writerow(["date", "description", "amount", "currency_code"])
for r in rows:
w.writerow(r + ["RUB"])
json.dump(sorted(processed), open(STATE, "w", encoding="utf-8"))
print(f"добавлено чеков: {len(rows)} → {out}")
for r in rows[:5]:
print(" ", r)
if __name__ == "__main__":
main()