Files
InboundVerify/server.py
Misaka 82c80fc859 未到数据按站独立 + 百世并入汇总 + 全量跑比对(失败容错)
- state_store:site_status 加 undelivered_ready 字段(旧库 ALTER 迁移);init_db 提早到启动最前(server lifespan + launch_and_prepare 第0步),避免 /api/status 早于迁移报错
- expected_undelivered:重构为 process(name)/process_baishi/write_site_file/build_full_report;build_summary 支持百世(仅未到件、无基数,不计入合计/图表)与失败容错(未成功站保留行无数据)
- runtime:4 站 ("站","undelivered") = 下应到+实到 → 比对写 <站>-未到数据.xlsx;("__compare__","compare") 改 run_all(顺序跑5站、记成功清单 → build_full_report,未登录/失败跳过);DATA_FILENAMES 加 undelivered、心跳探测之;_site_undelivered_handler 用 is not False 与 dispatch 一致
- site_shunxin:shunxin_expected/actual_download 改为 return with_retry 结果(修复返回 None 致调用方误判失败、以及 with_retry 失败被当成功的潜在 bug)
- server:lifespan 启动时 init_db

Co-Authored-By: Claude <noreply@anthropic.com>
2026-07-17 23:19:21 +08:00

179 lines
5.9 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
# server.py
#
# 服务模式入口FastAPI主线程uvicorn/asyncio+ Playwright worker独立线程
# 客户端经 HTTP 触发任务、查状态、下载数据worker 串行执行任务并跑心跳。
#
# 线程模型(关键):
# - 主线程uvicorn + FastAPI。路由【绝不】访问 Playwright 对象,只经
# task_queue投递任务+ state_store查状态/任务)+ 文件系统(下载数据)。
# - worker 线程runtime.launch_and_preparesync_playwright 在此)+ 任务循环,
# 独占所有 page 操作;与主线程仅经 Queue + SQLite 通信。
# 违反"路由不碰 Playwright"会崩sync 对象跨线程访问)。
#
# 运行python server.py (默认监听 0.0.0.0:8000
import os
import queue
import threading
import time
from contextlib import asynccontextmanager
import uvicorn
from fastapi import FastAPI, HTTPException
from fastapi.responses import FileResponse
from pydantic import BaseModel
from paths import DOWNLOAD_DIR
import state_store
from runtime import (
HEARTBEAT_INTERVAL,
TASK_HANDLERS,
dispatch_task,
launch_and_prepare,
run_heartbeat,
)
# 全部站点;百世固定下载当天,不可配置偏移
ALL_SITES = ["顺心", "百世", "中通", "韵达", "安能"]
CONFIGURABLE_SITES = {"顺心", "中通", "韵达", "安能"}
# 任务队列:元素 (task_id, task_spec)。主线程投递worker 消费。
task_queue: "queue.Queue" = queue.Queue()
# worker 运行状态主线程只读worker 写)
worker_state = {
"ctx": None,
"stop": False,
"thread": None,
"ready": False, # launch_and_prepare 完成(各站就绪,可接任务)
"error": None, # worker 启动失败原因
}
def _worker_loop():
"""worker 线程:启动 Playwright + 等就绪 + 任务循环(执行任务 + 心跳)。"""
try:
ctx = launch_and_prepare()
worker_state["ctx"] = ctx
worker_state["ready"] = True
print(">> [worker] 各站就绪,开始接收任务 ...")
except Exception as e:
worker_state["error"] = str(e)
print(f"❌ [worker] 启动失败: {e}")
return
last_heartbeat = 0.0
while not worker_state["stop"]:
try:
task_id, task_spec = task_queue.get(timeout=1)
except queue.Empty:
# 空闲时跑心跳
if time.monotonic() - last_heartbeat >= HEARTBEAT_INTERVAL:
run_heartbeat(ctx)
last_heartbeat = time.monotonic()
continue
state_store.update_task(task_id, state_store.TASK_RUNNING)
print(f">> [worker] 执行任务 #{task_id}: {task_spec}")
status, error = dispatch_task(ctx, task_spec)
state_store.update_task(task_id, status, error)
print(f">> [worker] 任务 #{task_id} 完成: {status} {error or ''}")
try:
ctx.stop()
except Exception:
pass
worker_state["ready"] = False
print(">> [worker] 已退出。")
@asynccontextmanager
async def lifespan(_app):
"""服务启停:起 worker 线程 / 通知 worker 停。"""
state_store.init_db() # 先建表/迁移状态库,确保早于 worker 就绪的 /api/status 可用
t = threading.Thread(target=_worker_loop, daemon=True)
worker_state["thread"] = t
t.start()
yield
worker_state["stop"] = True
t.join(timeout=10)
app = FastAPI(title="InboundVerify 服务端", lifespan=lifespan)
class TaskRequest(BaseModel):
site: str
kind: str
@app.post("/tasks")
def create_task(req: TaskRequest):
"""提交任务 {site, kind} → 入队,返回 task_id。"""
if (req.site, req.kind) not in TASK_HANDLERS:
raise HTTPException(status_code=400, detail=f"无效任务: {req.site}/{req.kind}")
task_id = state_store.create_task(req.site, req.kind)
task_queue.put((task_id, {"site": req.site, "kind": req.kind}))
return {"task_id": task_id}
@app.get("/tasks/{task_id}")
def get_task(task_id: int):
t = state_store.get_task(task_id)
if not t:
raise HTTPException(status_code=404, detail="任务不存在")
return t
@app.get("/tasks")
def list_tasks(limit: int = 20):
return state_store.list_tasks(limit)
@app.get("/status")
def get_status():
"""各站登录态 + 数据态(前端状态盘用),另含 worker 就绪状态。"""
return {
"worker_ready": worker_state["ready"],
"worker_error": worker_state["error"],
"sites": state_store.get_all_status(),
}
class OffsetRequest(BaseModel):
date_offset: int
@app.get("/config")
def get_config():
"""各站下载日期偏移0=今天1=昨天…);百世恒 0。"""
offsets = state_store.get_all_offsets()
return {site: offsets.get(site, 0) for site in ALL_SITES}
@app.put("/config/{site}")
def set_config(site: str, req: OffsetRequest):
if site == "百世":
raise HTTPException(status_code=400, detail="百世固定下载当天,不可配置偏移")
if site not in CONFIGURABLE_SITES:
raise HTTPException(status_code=400, detail=f"未知站点: {site}")
stored = state_store.set_offset(site, req.date_offset)
return {"site": site, "date_offset": stored}
@app.get("/data/{filename}")
def download_data(filename: str):
"""下载 downloads/ 下的数据文件(防路径穿越)。"""
if not filename or "/" in filename or "\\" in filename or ".." in filename:
raise HTTPException(status_code=400, detail="非法文件名")
path = os.path.join(DOWNLOAD_DIR, filename)
# 双重校验:解析后绝对路径仍在 DOWNLOAD_DIR 内
if not os.path.abspath(path).startswith(os.path.abspath(DOWNLOAD_DIR) + os.sep):
raise HTTPException(status_code=400, detail="非法路径")
if not os.path.isfile(path):
raise HTTPException(status_code=404, detail="文件不存在")
return FileResponse(path, filename=filename)
if __name__ == "__main__":
uvicorn.run(app, host="0.0.0.0", port=8000)