添加docker文件

This commit is contained in:
2026-03-13 18:55:33 +08:00
parent fff6504412
commit 5bf8a012ce
7 changed files with 378 additions and 0 deletions
+9
View File
@@ -0,0 +1,9 @@
.git
.gitignore
.vscode
__pycache__
*.pyc
*.pyo
*.pyd
.DS_Store
project.zip
+86
View File
@@ -0,0 +1,86 @@
# Docker + Prefect
## 1. 构建镜像
```bash
cd /Users/idss/YXT_Project/gmv-analytics
docker build -t gmv-analytics-prefect:latest .
```
## 2. 单次执行
```bash
docker run --rm \
--env-file /Users/idss/YXT_Project/gmv-analytics/.env \
-e PROJECT_MAPPING_FILE=/app/店铺映射表.xlsx \
gmv-analytics-prefect:latest \
python prefect_gmv_scheduler.py
```
## 3. 启动每天 09:00 的 Prefect 调度
这会连接 `.env` 中已经配置的 `PREFECT_API_URL`,并在 Prefect 中启动一个 deployment。
```bash
docker run --rm \
--env-file /Users/idss/YXT_Project/gmv-analytics/.env \
-e PROJECT_MAPPING_FILE=/app/店铺映射表.xlsx \
gmv-analytics-prefect:latest
```
容器默认执行:
```bash
python prefect_gmv_scheduler.py --serve
```
也可以直接用 Compose:
```bash
cd /Users/idss/YXT_Project/gmv-analytics
docker compose up -d --build
```
停止:
```bash
docker compose down
```
## 4. 如果你是用 Prefect worker 跑容器
先保证你的 Prefect worker 已经连到同一个 `PREFECT_API_URL`。
推荐命令示例:
```bash
prefect worker start --pool default-agent-pool --type process
```
如果你后面要改成真正的 Docker work pool,再在 Prefect UI 中把 deployment 的基础设施切到 Docker,并指定镜像:
```text
gmv-analytics-prefect:latest
```
## 5. 常用覆盖参数
单次 dry-run:
```bash
docker run --rm \
--env-file /Users/idss/YXT_Project/gmv-analytics/.env \
-e PROJECT_MAPPING_FILE=/app/店铺映射表.xlsx \
gmv-analytics-prefect:latest \
python prefect_gmv_scheduler.py --dry-run
```
指定时间范围:
```bash
docker run --rm \
--env-file /Users/idss/YXT_Project/gmv-analytics/.env \
-e PROJECT_MAPPING_FILE=/app/店铺映射表.xlsx \
gmv-analytics-prefect:latest \
python prefect_gmv_scheduler.py --start-date 2026-03-01 --end-date 2026-03-12
```
+19
View File
@@ -0,0 +1,19 @@
FROM python:3.12-slim
ENV PYTHONDONTWRITEBYTECODE=1 \
PYTHONUNBUFFERED=1 \
TZ=Asia/Shanghai
WORKDIR /app
COPY requirements-docker.txt /app/requirements-docker.txt
RUN pip install --no-cache-dir --upgrade pip \
&& pip install --no-cache-dir -r /app/requirements-docker.txt
COPY . /app
RUN chmod +x /app/docker-entrypoint.sh
ENTRYPOINT ["/app/docker-entrypoint.sh"]
CMD ["python", "prefect_gmv_scheduler.py", "--serve"]
+13
View File
@@ -0,0 +1,13 @@
services:
gmv-prefect-scheduler:
build:
context: .
dockerfile: Dockerfile
image: gmv-analytics-prefect:latest
container_name: gmv-prefect-scheduler
restart: unless-stopped
env_file:
- .env
environment:
PROJECT_MAPPING_FILE: /app/店铺映射表.xlsx
command: ["python", "prefect_gmv_scheduler.py", "--serve"]
+19
View File
@@ -0,0 +1,19 @@
#!/bin/sh
set -eu
APP_DIR="/app"
DEFAULT_MAPPING_FILE="$APP_DIR/店铺映射表.xlsx"
if [ -f "$APP_DIR/.env" ]; then
set -a
. "$APP_DIR/.env"
set +a
fi
if [ -f "$DEFAULT_MAPPING_FILE" ]; then
if [ -z "${PROJECT_MAPPING_FILE:-}" ] || [ ! -f "${PROJECT_MAPPING_FILE}" ]; then
export PROJECT_MAPPING_FILE="$DEFAULT_MAPPING_FILE"
fi
fi
exec "$@"
+228
View File
@@ -0,0 +1,228 @@
import argparse
import os
from dataclasses import dataclass
from datetime import date
from pathlib import Path
def bootstrap_prefect_env() -> None:
env_file = Path(__file__).resolve().parent / ".env"
if not env_file.exists():
return
for raw_line in env_file.read_text(encoding="utf-8").splitlines():
line = raw_line.strip()
if not line or line.startswith("#") or "=" not in line:
continue
key, value = line.split("=", 1)
key = key.strip()
if key.startswith("PREFECT_"):
os.environ.setdefault(key, value.strip())
bootstrap_prefect_env()
from prefect import flow, task
from prefect.logging import get_run_logger
from project_bitable_common import (
get_base_url,
get_default_end_date,
get_default_start_date,
get_feishu_chat_id,
get_feishu_report_image_path,
get_group_webhook_url,
get_mapping_file,
get_store_field_name,
iter_dates,
load_dotenv,
log_step,
run_gmv_sync,
run_metric_sync,
send_feishu_app_card,
send_feishu_sync_card,
validate_date,
)
@dataclass(frozen=True)
class SyncConfig:
start_date: str
end_date: str
base_url: str
mapping_file: str
store_field_name: str
chat_id: str
report_image_path: str
group_webhook: str
table_map_file: str
dry_run: bool
skip_missing_tables: bool
def load_sync_config(
start_date: str | None = None,
end_date: str | None = None,
dry_run: bool = False,
skip_missing_tables: bool = False,
table_map_file: str = "",
) -> SyncConfig:
load_dotenv()
return SyncConfig(
start_date=start_date or get_default_start_date(),
end_date=end_date or get_default_end_date(),
base_url=get_base_url(),
mapping_file=str(get_mapping_file()),
store_field_name=get_store_field_name(),
chat_id=get_feishu_chat_id(),
report_image_path=get_feishu_report_image_path(),
group_webhook=get_group_webhook_url(),
table_map_file=table_map_file,
dry_run=dry_run,
skip_missing_tables=skip_missing_tables,
)
@task(name="sync-sales")
def sync_sales_for_day(stat_date_text: str, config: SyncConfig) -> None:
stat_date = validate_date(stat_date_text)
run_metric_sync(
metric_name="sales",
start_date=stat_date,
end_date=stat_date,
base_url=config.base_url,
mapping_file=Path(config.mapping_file),
store_field_name=config.store_field_name,
table_map_file=config.table_map_file,
dry_run=config.dry_run,
skip_missing_tables=config.skip_missing_tables,
)
@task(name="sync-refund")
def sync_refund_for_day(stat_date_text: str, config: SyncConfig) -> None:
stat_date = validate_date(stat_date_text)
run_metric_sync(
metric_name="refund",
start_date=stat_date,
end_date=stat_date,
base_url=config.base_url,
mapping_file=Path(config.mapping_file),
store_field_name=config.store_field_name,
table_map_file=config.table_map_file,
dry_run=config.dry_run,
skip_missing_tables=config.skip_missing_tables,
)
@task(name="sync-gmv")
def sync_gmv_for_day(stat_date_text: str, config: SyncConfig) -> None:
stat_date = validate_date(stat_date_text)
run_gmv_sync(
start_date=stat_date,
end_date=stat_date,
base_url=config.base_url,
store_field_name=config.store_field_name,
dry_run=config.dry_run,
skip_missing_tables=config.skip_missing_tables,
)
@task(name="notify-feishu")
def notify_feishu(title: str, config: SyncConfig) -> None:
if config.dry_run:
log_step("dry-run 模式下跳过飞书群推送")
return
start_date = validate_date(config.start_date)
end_date = validate_date(config.end_date)
if config.chat_id:
send_feishu_app_card(
chat_id=config.chat_id,
title=title,
base_url=config.base_url,
start_date=start_date,
end_date=end_date,
image_path=config.report_image_path,
)
return
send_feishu_sync_card(
webhook_url=config.group_webhook,
title=title,
base_url=config.base_url,
start_date=start_date,
end_date=end_date,
)
@flow(name="gmv-daily-sync")
def gmv_daily_sync_flow(
start_date: str | None = None,
end_date: str | None = None,
dry_run: bool = False,
skip_missing_tables: bool = False,
table_map_file: str = "",
) -> None:
logger = get_run_logger()
config = load_sync_config(
start_date=start_date,
end_date=end_date,
dry_run=dry_run,
skip_missing_tables=skip_missing_tables,
table_map_file=table_map_file,
)
start_date_value = validate_date(config.start_date)
end_date_value = validate_date(config.end_date)
if end_date_value < start_date_value:
raise ValueError("end-date 不能早于 start-date")
logger.info("Prefect 调度开始: %s -> %s", config.start_date, config.end_date)
try:
for stat_date in iter_dates(start_date_value, end_date_value):
stat_date_text = stat_date.isoformat()
logger.info("开始处理日期: %s", stat_date_text)
sync_sales_for_day(stat_date_text, config)
sync_refund_for_day(stat_date_text, config)
sync_gmv_for_day(stat_date_text, config)
logger.info("日期处理完成: %s", stat_date_text)
except Exception:
notify_feishu.with_options(name="notify-feishu-failed")("GMV数据同步失败", config)
raise
notify_feishu("GMV数据同步", config)
logger.info("Prefect 调度完成")
def parse_args() -> argparse.Namespace:
parser = argparse.ArgumentParser(description="Prefect 调度:每天上午 9 点执行 GMV 数据同步。")
parser.add_argument("--start-date", default="", help="开始日期,格式 YYYY-MM-DD,默认读取 .env 中的 SYNC_START_DATE")
parser.add_argument("--end-date", default="", help="结束日期,格式 YYYY-MM-DD,默认昨天")
parser.add_argument("--table-map-file", default="", help="可选,项目到表名的映射 JSON 文件路径")
parser.add_argument("--dry-run", action="store_true", help="只输出将要更新的内容,不调用飞书写接口")
parser.add_argument("--skip-missing-tables", action="store_true", help="找不到对应月份的飞书表时跳过")
parser.add_argument("--serve", action="store_true", help="启动 Prefect deployment,并按每天上午 9 点定时执行")
return parser.parse_args()
def main() -> None:
args = parse_args()
flow_kwargs = {
"start_date": args.start_date or None,
"end_date": args.end_date or None,
"dry_run": args.dry_run,
"skip_missing_tables": args.skip_missing_tables,
"table_map_file": args.table_map_file,
}
if args.serve:
gmv_daily_sync_flow.serve(
name="gmv-daily-sync-9am",
cron="0 9 * * *",
timezone="Asia/Shanghai",
parameters=flow_kwargs,
tags=["gmv", "feishu", "bitable"],
)
return
gmv_daily_sync_flow(**flow_kwargs)
if __name__ == "__main__":
main()
+4
View File
@@ -0,0 +1,4 @@
openpyxl>=3.1.2
prefect>=3.0.0
psycopg2-binary>=2.9.9
requests>=2.31.0