- 新增 runtime.py:抽离共享核心 launch_and_prepare / dispatch_task / run_heartbeat /
probe_* / launch_anneng / RuntimeContext,常量 SITES_CONFIG 等;main_router 复用
- 新增 server.py:FastAPI(主线程)+ Playwright worker(独立线程)+ 任务队列;
API:POST/GET /tasks、GET /status、GET /data/{file}(防路径穿越)
- state_store:加 task_history 表 + create/update/get/list 接口
- 5 站点 with_retry 改为返回 True/False,供 dispatch_task 判成败
- main_router:重写为复用 runtime 的交互模式(行为不变)
- requirements:加 fastapi、uvicorn
- CLAUDE.md:补充运行模式与共享核心架构说明
线程模型:主线程 FastAPI 不碰 Playwright,worker 线程独占 page,经 Queue + SQLite 通信。
Co-Authored-By: Claude <noreply@anthropic.com>
231 lines
7.6 KiB
Python
231 lines
7.6 KiB
Python
# state_store.py
|
||
# 阶段0:站点状态持久化(SQLite)。记录各站登录态 + 应到/实到数据文件生成时间,
|
||
# 供后台心跳刷新、菜单状态盘展示,以及未来 FastAPI / Web 前端读取。
|
||
# 重启不丢——程序重启后状态从本库恢复(登录态会随心跳重新探测校正)。
|
||
#
|
||
# 设计:纯 Python(sqlite3 标准库,无新依赖),每次读写开短连接,主线程使用。
|
||
|
||
import os
|
||
import sqlite3
|
||
from datetime import datetime
|
||
|
||
from paths import STATE_DB_PATH
|
||
|
||
# 登录态枚举
|
||
LOGIN_UNKNOWN = "unknown" # 尚未探测过
|
||
LOGIN_IN = "logged_in"
|
||
LOGIN_OUT = "logged_out"
|
||
|
||
# 任务状态枚举(task_history.status)
|
||
TASK_PENDING = "pending" # 已入队,待执行
|
||
TASK_RUNNING = "running" # 正在执行
|
||
TASK_SUCCESS = "success" # 成功(有数据)
|
||
TASK_NO_DATA = "no_data" # 成功但本站本次无数据
|
||
TASK_FAILED = "failed" # 失败(重试耗尽 / 未登录 / 异常)
|
||
|
||
|
||
def _now():
|
||
"""本地时间的字符串(到秒),用于时间戳列。"""
|
||
return datetime.now().strftime("%Y-%m-%d %H:%M:%S")
|
||
|
||
|
||
def init_db():
|
||
"""建库建表(幂等)。确保 state 目录存在。"""
|
||
os.makedirs(os.path.dirname(STATE_DB_PATH), exist_ok=True)
|
||
with sqlite3.connect(STATE_DB_PATH) as conn:
|
||
conn.execute("""
|
||
CREATE TABLE IF NOT EXISTS site_status (
|
||
site TEXT PRIMARY KEY,
|
||
login_state TEXT,
|
||
login_checked_at TEXT,
|
||
expected_ready INTEGER,
|
||
expected_generated_at TEXT,
|
||
actual_ready INTEGER,
|
||
actual_generated_at TEXT,
|
||
updated_at TEXT
|
||
)
|
||
""")
|
||
conn.execute("""
|
||
CREATE TABLE IF NOT EXISTS task_history (
|
||
id INTEGER PRIMARY KEY AUTOINCREMENT,
|
||
site TEXT,
|
||
kind TEXT,
|
||
status TEXT,
|
||
started_at TEXT,
|
||
finished_at TEXT,
|
||
error TEXT
|
||
)
|
||
""")
|
||
conn.commit()
|
||
|
||
|
||
def _upsert(conn, site, **fields):
|
||
"""更新(或插入)单站:保留未传字段,刷新 updated_at。"""
|
||
row = conn.execute(
|
||
"SELECT login_state, login_checked_at, expected_ready, expected_generated_at, "
|
||
"actual_ready, actual_generated_at FROM site_status WHERE site = ?",
|
||
(site,),
|
||
).fetchone()
|
||
cur = {
|
||
"login_state": LOGIN_UNKNOWN,
|
||
"login_checked_at": "",
|
||
"expected_ready": 0,
|
||
"expected_generated_at": "",
|
||
"actual_ready": 0,
|
||
"actual_generated_at": "",
|
||
}
|
||
if row:
|
||
(
|
||
cur["login_state"],
|
||
cur["login_checked_at"],
|
||
cur["expected_ready"],
|
||
cur["expected_generated_at"],
|
||
cur["actual_ready"],
|
||
cur["actual_generated_at"],
|
||
) = row
|
||
cur.update(fields)
|
||
cur["updated_at"] = _now()
|
||
|
||
values = (
|
||
site,
|
||
cur["login_state"],
|
||
cur["login_checked_at"],
|
||
cur["expected_ready"],
|
||
cur["expected_generated_at"],
|
||
cur["actual_ready"],
|
||
cur["actual_generated_at"],
|
||
cur["updated_at"],
|
||
)
|
||
if row:
|
||
conn.execute(
|
||
"UPDATE site_status SET login_state=?, login_checked_at=?, expected_ready=?, "
|
||
"expected_generated_at=?, actual_ready=?, actual_generated_at=?, updated_at=? "
|
||
"WHERE site=?",
|
||
values[1:] + (site,),
|
||
)
|
||
else:
|
||
conn.execute(
|
||
"INSERT INTO site_status (site, login_state, login_checked_at, expected_ready, "
|
||
"expected_generated_at, actual_ready, actual_generated_at, updated_at) "
|
||
"VALUES (?, ?, ?, ?, ?, ?, ?, ?)",
|
||
values,
|
||
)
|
||
conn.commit()
|
||
|
||
|
||
def set_login_state(site, logged_in):
|
||
"""更新单站登录态。logged_in: bool。"""
|
||
state = LOGIN_IN if logged_in else LOGIN_OUT
|
||
with sqlite3.connect(STATE_DB_PATH) as conn:
|
||
_upsert(conn, site, login_state=state, login_checked_at=_now())
|
||
|
||
|
||
def set_data_state(site, kind, ready, generated_at):
|
||
"""更新单站数据态。kind: 'expected'/'actual';ready: bool;generated_at: str 或 ''。"""
|
||
key_ready = "expected_ready" if kind == "expected" else "actual_ready"
|
||
key_at = "expected_generated_at" if kind == "expected" else "actual_generated_at"
|
||
with sqlite3.connect(STATE_DB_PATH) as conn:
|
||
_upsert(
|
||
conn, site, **{key_ready: 1 if ready else 0, key_at: generated_at or ""}
|
||
)
|
||
|
||
|
||
def get_all_status():
|
||
"""返回 {site: {各字段}};库不存在则返回 {}。"""
|
||
if not os.path.exists(STATE_DB_PATH):
|
||
return {}
|
||
with sqlite3.connect(STATE_DB_PATH) as conn:
|
||
rows = conn.execute(
|
||
"SELECT site, login_state, login_checked_at, expected_ready, "
|
||
"expected_generated_at, actual_ready, actual_generated_at, updated_at "
|
||
"FROM site_status"
|
||
).fetchall()
|
||
return {
|
||
r[0]: {
|
||
"login_state": r[1],
|
||
"login_checked_at": r[2],
|
||
"expected_ready": bool(r[3]),
|
||
"expected_generated_at": r[4],
|
||
"actual_ready": bool(r[5]),
|
||
"actual_generated_at": r[6],
|
||
"updated_at": r[7],
|
||
}
|
||
for r in rows
|
||
}
|
||
|
||
|
||
# ============================ 任务历史 ============================
|
||
|
||
|
||
def create_task(site, kind):
|
||
"""新建一条 pending 任务,返回其 id。"""
|
||
now = _now()
|
||
with sqlite3.connect(STATE_DB_PATH) as conn:
|
||
cur = conn.execute(
|
||
"INSERT INTO task_history (site, kind, status, started_at, finished_at, error) "
|
||
"VALUES (?, ?, ?, ?, '', '')",
|
||
(site, kind, TASK_PENDING, now),
|
||
)
|
||
conn.commit()
|
||
return cur.lastrowid
|
||
|
||
|
||
def update_task(task_id, status, error=None):
|
||
"""更新任务状态。终态(success/no_data/failed)写入 finished_at。"""
|
||
finished = _now() if status in (TASK_SUCCESS, TASK_NO_DATA, TASK_FAILED) else ""
|
||
with sqlite3.connect(STATE_DB_PATH) as conn:
|
||
if finished:
|
||
conn.execute(
|
||
"UPDATE task_history SET status=?, finished_at=?, error=? WHERE id=?",
|
||
(status, finished, error or "", task_id),
|
||
)
|
||
else:
|
||
conn.execute(
|
||
"UPDATE task_history SET status=?, error=? WHERE id=?",
|
||
(status, error or "", task_id),
|
||
)
|
||
conn.commit()
|
||
|
||
|
||
def get_task(task_id):
|
||
"""返回单条任务 dict,不存在返回 None。"""
|
||
with sqlite3.connect(STATE_DB_PATH) as conn:
|
||
row = conn.execute(
|
||
"SELECT id, site, kind, status, started_at, finished_at, error "
|
||
"FROM task_history WHERE id=?",
|
||
(task_id,),
|
||
).fetchone()
|
||
if not row:
|
||
return None
|
||
return {
|
||
"id": row[0],
|
||
"site": row[1],
|
||
"kind": row[2],
|
||
"status": row[3],
|
||
"started_at": row[4],
|
||
"finished_at": row[5],
|
||
"error": row[6],
|
||
}
|
||
|
||
|
||
def list_tasks(limit=20):
|
||
"""返回最近 limit 条任务(按 id 倒序)。"""
|
||
with sqlite3.connect(STATE_DB_PATH) as conn:
|
||
rows = conn.execute(
|
||
"SELECT id, site, kind, status, started_at, finished_at, error "
|
||
"FROM task_history ORDER BY id DESC LIMIT ?",
|
||
(limit,),
|
||
).fetchall()
|
||
return [
|
||
{
|
||
"id": r[0],
|
||
"site": r[1],
|
||
"kind": r[2],
|
||
"status": r[3],
|
||
"started_at": r[4],
|
||
"finished_at": r[5],
|
||
"error": r[6],
|
||
}
|
||
for r in rows
|
||
]
|