209 lines
8.5 KiB
Python
209 lines
8.5 KiB
Python
#!/usr/bin/env python3
|
||
"""将平台账单 Excel 导入本地 SQLite，供后续按店铺和时间汇总。
|
||
|
||
示例（仓库根目录）：
|
||
python3 scripts/import_bills_sqlite.py
|
||
python3 scripts/import_bills_sqlite.py --input-dir /path/to/账单数据 \
|
||
--db runtime/bills.sqlite --reset
|
||
|
||
运行环境需要 openpyxl；项目桌面运行时可使用 Codex bundled Python。
|
||
"""
|
||
|
||
from __future__ import annotations
|
||
|
||
import argparse
|
||
import json
|
||
import re
|
||
import sqlite3
|
||
import sys
|
||
from datetime import date, datetime, time, timedelta
|
||
from decimal import Decimal, InvalidOperation
|
||
from pathlib import Path
|
||
from typing import Any, Iterable
|
||
|
||
|
||
PLATFORMS: tuple[tuple[str, str, tuple[str, ...]], ...] = (
|
||
("dewu", "得物", ("得物",)),
|
||
("douyin", "抖音", ("头条放心购", "抖音")),
|
||
("taobao", "淘系", ("淘系",)),
|
||
("jd", "京东", ("京东商城", "京东")),
|
||
("pinduoduo", "拼多多", ("拼多多",)),
|
||
)
|
||
|
||
TIME_HEADERS = {
|
||
"dewu": "支付/退款时间",
|
||
"douyin": "结算时间",
|
||
"taobao": "入账时间",
|
||
"jd": "费用结算时间",
|
||
"pinduoduo": "发生时间",
|
||
}
|
||
|
||
|
||
def platform_for_file(path: Path) -> tuple[str, str]:
|
||
for key, label, markers in PLATFORMS:
|
||
if any(marker in path.name for marker in markers):
|
||
return key, label
|
||
raise ValueError(f"无法从文件名识别平台：{path.name}")
|
||
|
||
|
||
def clean(value: Any) -> str | None:
|
||
if value is None:
|
||
return None
|
||
text = str(value).strip()
|
||
return text or None
|
||
|
||
|
||
def money(value: Any) -> str:
|
||
if value is None or value == "":
|
||
return "0.00"
|
||
text = str(value).replace(",", "").replace("￥", "").replace("¥", "").strip()
|
||
try:
|
||
return format(Decimal(text), ".2f")
|
||
except InvalidOperation as exc:
|
||
raise ValueError(f"金额无法解析：{value!r}") from exc
|
||
|
||
|
||
def iso_time(value: Any) -> str | None:
|
||
if value is None or value == "":
|
||
return None
|
||
if isinstance(value, datetime):
|
||
return value.strftime("%Y-%m-%d %H:%M:%S")
|
||
if isinstance(value, date):
|
||
return datetime.combine(value, time()).strftime("%Y-%m-%d %H:%M:%S")
|
||
if isinstance(value, (int, float)):
|
||
# Excel 1900 date system; openpyxl normally converts typed date cells,
|
||
# but this covers numeric exports as well.
|
||
converted = datetime(1899, 12, 30) + timedelta(days=float(value))
|
||
return converted.strftime("%Y-%m-%d %H:%M:%S")
|
||
text = str(value).strip().replace("/", "-")
|
||
for fmt in ("%Y-%m-%d %H:%M:%S", "%Y-%m-%d %H:%M", "%Y-%m-%d", "%Y-%m-%dT%H:%M:%S"):
|
||
try:
|
||
return datetime.strptime(text, fmt).strftime("%Y-%m-%d %H:%M:%S")
|
||
except ValueError:
|
||
continue
|
||
# 得物偶尔出现 2026/8/13 14:11:19 这种非零填充形式。
|
||
match = re.fullmatch(r"(\d{4})-(\d{1,2})-(\d{1,2})(?:\s+|T)(\d{1,2}):(\d{2})(?::(\d{2}))?", text)
|
||
if match:
|
||
y, m, d, hh, mm, ss = (int(x or 0) for x in match.groups())
|
||
return f"{y:04d}-{m:02d}-{d:02d} {hh:02d}:{mm:02d}:{ss:02d}"
|
||
raise ValueError(f"时间无法解析：{value!r}")
|
||
|
||
|
||
def json_default(value: Any) -> str:
|
||
if isinstance(value, (datetime, date)):
|
||
return value.isoformat(sep=" ")
|
||
return str(value)
|
||
|
||
|
||
def init_db(connection: sqlite3.Connection) -> None:
|
||
connection.executescript(
|
||
"""
|
||
PRAGMA journal_mode = WAL;
|
||
CREATE TABLE IF NOT EXISTS bills (
|
||
id INTEGER PRIMARY KEY AUTOINCREMENT,
|
||
platform TEXT NOT NULL,
|
||
type TEXT NOT NULL,
|
||
store_name TEXT NOT NULL,
|
||
occurred_at TEXT,
|
||
income NUMERIC NOT NULL DEFAULT 0,
|
||
expense NUMERIC NOT NULL DEFAULT 0,
|
||
bill_item TEXT,
|
||
record_code TEXT NOT NULL,
|
||
source_file TEXT NOT NULL,
|
||
raw_json TEXT NOT NULL,
|
||
imported_at TEXT NOT NULL DEFAULT CURRENT_TIMESTAMP,
|
||
UNIQUE(platform, record_code)
|
||
);
|
||
CREATE INDEX IF NOT EXISTS idx_bills_store_time
|
||
ON bills(store_name, occurred_at);
|
||
CREATE INDEX IF NOT EXISTS idx_bills_platform_store_time
|
||
ON bills(platform, store_name, occurred_at);
|
||
CREATE VIEW IF NOT EXISTS bill_daily_summary AS
|
||
SELECT platform, type, store_name, substr(occurred_at, 1, 10) AS bill_date,
|
||
ROUND(SUM(income), 2) AS income, ROUND(SUM(expense), 2) AS expense,
|
||
COUNT(*) AS row_count
|
||
FROM bills
|
||
WHERE occurred_at IS NOT NULL AND occurred_at <> ''
|
||
GROUP BY platform, type, store_name, substr(occurred_at, 1, 10);
|
||
"""
|
||
)
|
||
|
||
|
||
def rows_from_file(path: Path, platform: str, label: str) -> Iterable[tuple[Any, ...]]:
|
||
try:
|
||
import openpyxl
|
||
except ImportError as exc:
|
||
raise RuntimeError("缺少 openpyxl，请使用项目提供的 bundled Python 运行此脚本。") from exc
|
||
workbook = openpyxl.load_workbook(path, read_only=True, data_only=True)
|
||
try:
|
||
for sheet in workbook.worksheets:
|
||
iterator = sheet.iter_rows(values_only=True)
|
||
header_row = next(iterator, None)
|
||
if not header_row:
|
||
continue
|
||
headers = [clean(item) or "" for item in header_row]
|
||
required = {"店铺", "记录编码", TIME_HEADERS[platform], "收入金额" if platform != "douyin" else "收入", "支出金额" if platform != "douyin" else "支出"}
|
||
missing = required.difference(headers)
|
||
if missing:
|
||
raise ValueError(f"{path.name}/{sheet.title} 缺少列：{', '.join(sorted(missing))}")
|
||
index = {name: position for position, name in enumerate(headers)}
|
||
income_header = "收入" if platform == "douyin" else "收入金额"
|
||
expense_header = "支出" if platform == "douyin" else "支出金额"
|
||
for row in iterator:
|
||
if not row or all(item in (None, "") for item in row):
|
||
continue
|
||
get = lambda name: row[index[name]] if index[name] < len(row) else None
|
||
record_code = clean(get("记录编码"))
|
||
store_name = clean(get("店铺"))
|
||
if not record_code or not store_name:
|
||
continue
|
||
raw = {headers[i]: row[i] for i in range(min(len(headers), len(row))) if row[i] not in (None, "")}
|
||
yield (platform, label, store_name, iso_time(get(TIME_HEADERS[platform])), money(get(income_header)), money(get(expense_header)), clean(get("账单项目")), record_code, path.name, json.dumps(raw, ensure_ascii=False, default=json_default))
|
||
finally:
|
||
workbook.close()
|
||
|
||
|
||
def main() -> int:
|
||
parser = argparse.ArgumentParser(description="导入得物/抖音/淘系/京东/拼多多账单到 SQLite")
|
||
parser.add_argument("--input-dir", type=Path, default=Path("/Users/dodo/AI系统/账单数据"))
|
||
parser.add_argument("--db", type=Path, default=Path("runtime/bills.sqlite"))
|
||
parser.add_argument("--reset", action="store_true", help="清空已有 bills 后重新导入")
|
||
args = parser.parse_args()
|
||
files = sorted(args.input_dir.glob("*.xlsx"))
|
||
if not files:
|
||
print(f"未找到 Excel 文件：{args.input_dir}", file=sys.stderr)
|
||
return 2
|
||
args.db.parent.mkdir(parents=True, exist_ok=True)
|
||
connection = sqlite3.connect(args.db)
|
||
init_db(connection)
|
||
if args.reset:
|
||
connection.execute("DELETE FROM bills")
|
||
counts: dict[str, int] = {}
|
||
try:
|
||
for path in files:
|
||
platform, label = platform_for_file(path)
|
||
count = 0
|
||
for row in rows_from_file(path, platform, label):
|
||
connection.execute(
|
||
"""INSERT INTO bills(platform,type,store_name,occurred_at,income,expense,bill_item,record_code,source_file,raw_json)
|
||
VALUES(?,?,?,?,?,?,?,?,?,?)
|
||
ON CONFLICT(platform,record_code) DO UPDATE SET
|
||
type=excluded.type, store_name=excluded.store_name, occurred_at=excluded.occurred_at,
|
||
income=excluded.income, expense=excluded.expense, bill_item=excluded.bill_item,
|
||
source_file=excluded.source_file, raw_json=excluded.raw_json, imported_at=CURRENT_TIMESTAMP""",
|
||
row,
|
||
)
|
||
count += 1
|
||
counts[platform] = counts.get(platform, 0) + count
|
||
connection.commit()
|
||
finally:
|
||
connection.close()
|
||
print(f"导入完成：{args.db}")
|
||
for platform, count in counts.items():
|
||
print(f" {platform}: {count} 条")
|
||
return 0
|
||
|
||
|
||
if __name__ == "__main__":
|
||
raise SystemExit(main())
|