42 lines
1.6 KiB
Python
42 lines
1.6 KiB
Python
"""短剧采集 CLI
|
|
用法:
|
|
.venv/bin/python scripts/collect_short_dramas.py # 全量增量同步
|
|
.venv/bin/python scripts/collect_short_dramas.py --pages 1 --size 3 # 试跑
|
|
.venv/bin/python scripts/collect_short_dramas.py --drama-id 130 # 手动更新单部
|
|
"""
|
|
import argparse
|
|
import asyncio
|
|
import logging
|
|
import sys
|
|
from pathlib import Path
|
|
|
|
sys.path.insert(0, str(Path(__file__).resolve().parent.parent))
|
|
|
|
from app.database import SessionFactory # noqa: E402
|
|
from app.services.collection_service import sync_drama_by_id, sync_short_dramas # noqa: E402
|
|
|
|
logging.basicConfig(level=logging.INFO, format="%(asctime)s %(levelname)s %(message)s")
|
|
|
|
|
|
async def main() -> None:
|
|
parser = argparse.ArgumentParser(description="短剧采集")
|
|
parser.add_argument("--drama-id", type=int, default=0, help="只同步指定源站短剧 id")
|
|
parser.add_argument("--pages", type=int, default=0, help="最多同步的列表页数，0=全部")
|
|
parser.add_argument("--size", type=int, default=20, help="每页条数")
|
|
parser.add_argument("--sort", choices=["heat", "latest"], default="heat")
|
|
parser.add_argument("--delay", type=float, default=0.25, help="上游请求间隔秒")
|
|
args = parser.parse_args()
|
|
|
|
async with SessionFactory() as db:
|
|
if args.drama_id:
|
|
stat = await sync_drama_by_id(db, args.drama_id)
|
|
else:
|
|
stat = await sync_short_dramas(
|
|
db, max_pages=args.pages, page_size=args.size, sort_by=args.sort, delay=args.delay
|
|
)
|
|
print("同步完成:", stat)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
asyncio.run(main())
|