Files
MediaCrawler/api/routers/websocket.py
T
butubb 4e60524f37
Deploy VitePress site to Pages / build (push) Canceled after 0s
Deploy VitePress site to Pages / Deploy (push) Canceled after 0s
feat: 监控面板 / 登录鉴权 / 多平台切换 / MySQL
在上游 MediaCrawler 之上新增一层:

- 监控层 api/monitor/ —— 多博主/多笔记的定时采集、指标快照差分、报表、
  企业微信通知。每轮采集写入独立目录,差分才成立。
- WebUI 登录鉴权 api/auth.py —— PBKDF2 口令 + 服务端会话,/api 全接口防护。
  WebSocket 单独加依赖:BaseHTTPMiddleware 对 ws 作用域直接放行,覆盖不到。
- 全局平台切换 + 能力矩阵 —— 如实区分「爬虫模块支持」与「监控层已接线」,
  未接通的平台直接拒绝建任务,而不是静默跑空。
- 监控库改用 MySQL 5.7(可回退 SQLite 供测试):逐表强制 utf8mb4
  (服务端与库默认都是 latin1),启动校验所连 schema 以防写错库,
  连接池 recycle + pre_ping 应对 MySQL 的 8 小时空闲断连。

修复上游缺陷:

- xhs/core.py: 主页抓取失败会跳掉整个博主,导致一条作品都抓不到,
  而那份资料只喂给一个空函数。改为尽力而为,失败不中断。
- xhs/login.py: cookie 登录只注入 web_session,冷启动签名会失败。
  新增 INJECT_ALL_COOKIES 开关(默认关闭,原有行为不变)。
- requirements.txt: 补上 websockets。它在上游 pyproject.toml 里有声明、
  这里漏了,导致 uvicorn 没有 WebSocket 能力,实时日志流从未工作。

改动过的上游文件清单及合并方式见 UPSTREAM.md。

测试:492 passed(另有 1 个既有的 Windows/gbk 上游测试失败,与本改动无关)
2026-10-07 09:58:40 +08:00

156 lines
5.1 KiB
Python

# -*- coding: utf-8 -*-
# Copyright (c) 2025 [email protected]
#
# This file is part of MediaCrawler project.
# Repository: https://github.com/NanmiCoder/MediaCrawler/blob/main/api/routers/websocket.py
# GitHub: https://github.com/NanmiCoder
# Licensed under NON-COMMERCIAL LEARNING LICENSE 1.1
#
# 声明:本代码仅供学习和研究目的使用。使用者应遵守以下原则:
# 1. 不得用于任何商业用途。
# 2. 使用时应遵守目标平台的使用条款和robots.txt规则。
# 3. 不得进行大规模爬取或对平台造成运营干扰。
# 4. 应合理控制请求频率,避免给目标平台带来不必要的负担。
# 5. 不得用于任何非法或不当的用途。
#
# 详细许可条款请参阅项目根目录下的LICENSE文件。
# 使用本代码即表示您同意遵守上述原则和LICENSE中的所有条款。
import asyncio
from typing import Set, Optional
from fastapi import APIRouter, Depends, WebSocket, WebSocketDisconnect
from ..auth import require_ws_auth
from ..services import crawler_manager
router = APIRouter(tags=["websocket"])
class ConnectionManager:
"""WebSocket connection manager"""
def __init__(self):
self.active_connections: Set[WebSocket] = set()
async def connect(self, websocket: WebSocket):
await websocket.accept()
self.active_connections.add(websocket)
def disconnect(self, websocket: WebSocket):
self.active_connections.discard(websocket)
async def broadcast(self, message: dict):
"""Broadcast message to all connections"""
if not self.active_connections:
return
disconnected = []
for connection in list(self.active_connections):
try:
await connection.send_json(message)
except Exception:
disconnected.append(connection)
# Clean up disconnected connections
for conn in disconnected:
self.disconnect(conn)
manager = ConnectionManager()
async def log_broadcaster():
"""Background task: read logs from queue and broadcast"""
queue = crawler_manager.get_log_queue()
while True:
try:
# Get log entry from queue
entry = await queue.get()
# Broadcast to all WebSocket connections
await manager.broadcast(entry.model_dump())
except asyncio.CancelledError:
break
except Exception as e:
print(f"Log broadcaster error: {e}")
await asyncio.sleep(0.1)
# Global broadcast task
_broadcaster_task: Optional[asyncio.Task] = None
def start_broadcaster():
"""Start broadcast task"""
global _broadcaster_task
if _broadcaster_task is None or _broadcaster_task.done():
_broadcaster_task = asyncio.create_task(log_broadcaster())
# Websocket routes need their own auth dependency: BaseHTTPMiddleware returns
# early for any non-http scope, and HTTP router-level dependencies do not reach
# websocket routes. Without this the live crawl log stream would be wide open.
@router.websocket("/ws/logs", dependencies=[Depends(require_ws_auth)])
async def websocket_logs(websocket: WebSocket):
"""WebSocket log stream"""
print("[WS] New connection attempt")
try:
# Ensure broadcast task is running
start_broadcaster()
await manager.connect(websocket)
print(f"[WS] Connected, active connections: {len(manager.active_connections)}")
# Send existing logs
for log in crawler_manager.logs:
try:
await websocket.send_json(log.model_dump())
except Exception as e:
print(f"[WS] Error sending existing log: {e}")
break
print(f"[WS] Sent {len(crawler_manager.logs)} existing logs, entering main loop")
while True:
# Keep connection alive, receive heartbeat or any message
try:
data = await asyncio.wait_for(
websocket.receive_text(),
timeout=30.0
)
if data == "ping":
await websocket.send_text("pong")
except asyncio.TimeoutError:
# Send ping to keep connection alive
try:
await websocket.send_text("ping")
except Exception as e:
print(f"[WS] Error sending ping: {e}")
break
except WebSocketDisconnect:
print("[WS] Client disconnected")
except Exception as e:
print(f"[WS] Error: {type(e).__name__}: {e}")
finally:
manager.disconnect(websocket)
print(f"[WS] Cleanup done, active connections: {len(manager.active_connections)}")
@router.websocket("/ws/status", dependencies=[Depends(require_ws_auth)])
async def websocket_status(websocket: WebSocket):
"""WebSocket status stream"""
await websocket.accept()
try:
while True:
# Send status every second
status = crawler_manager.get_status()
await websocket.send_json(status)
await asyncio.sleep(1)
except WebSocketDisconnect:
pass
except Exception:
pass