# 项目文件：demos/resume_run.py
# 两次打开同一个进度库；第二次只采剩余详情，目录页和前两本不再重复请求。
import asyncio
from pathlib import Path
from tempfile import TemporaryDirectory

from crawlsite import running_site
from catalogcrawl.runner import crawl
from catalogcrawl.state import CrawlState


if __name__ == "__main__":
    with running_site() as site, TemporaryDirectory() as folder:
        path = Path(folder) / "crawl.sqlite3"
        start = site.base_url + "/catalog/?page=1"
        with CrawlState(path, start) as state:
            asyncio.run(crawl(state, interval=0, stop_after=2))
            print("暂停", state.stats())
        with CrawlState(path, start) as state:
            asyncio.run(crawl(state, interval=0))
            print("恢复", state.stats())
        print("目录请求", site.state.counts["/catalog/"])
        print("第一本请求", site.state.counts["/books/b101"])