mirror of
https://github.com/NanmiCoder/MediaCrawler.git
synced 2026-02-27 02:30:45 +08:00
508675a251
- Add FastAPI server with WebSocket support for real-time logs - Add crawler management API endpoints (start/stop/status) - Add data browsing API endpoints (list files, preview, download) - Include pre-built WebUI assets for serving frontend API endpoints: - POST /api/crawler/start - Start crawler task - POST /api/crawler/stop - Stop crawler task - GET /api/crawler/status - Get crawler status - WS /api/ws/logs - Real-time log streaming - GET /api/data/files - List data files - GET /api/data/stats - Get data statistics 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
64 lines
2.5 KiB
Python
64 lines
2.5 KiB
Python
# -*- coding: utf-8 -*-
|
|
# Copyright (c) 2025 relakkes@gmail.com
|
|
#
|
|
# This file is part of MediaCrawler project.
|
|
# Repository: https://github.com/NanmiCoder/MediaCrawler/blob/main/api/routers/crawler.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。
|
|
|
|
from fastapi import APIRouter, HTTPException
|
|
|
|
from ..schemas import CrawlerStartRequest, CrawlerStatusResponse
|
|
from ..services import crawler_manager
|
|
|
|
router = APIRouter(prefix="/crawler", tags=["crawler"])
|
|
|
|
|
|
@router.post("/start")
|
|
async def start_crawler(request: CrawlerStartRequest):
|
|
"""启动爬虫任务"""
|
|
success = await crawler_manager.start(request)
|
|
if not success:
|
|
# 处理并发/重复请求：如果进程已经在跑，返回 400 而不是 500
|
|
if crawler_manager.process and crawler_manager.process.poll() is None:
|
|
raise HTTPException(status_code=400, detail="Crawler is already running")
|
|
raise HTTPException(status_code=500, detail="Failed to start crawler")
|
|
|
|
return {"status": "ok", "message": "Crawler started successfully"}
|
|
|
|
|
|
@router.post("/stop")
|
|
async def stop_crawler():
|
|
"""停止爬虫任务"""
|
|
success = await crawler_manager.stop()
|
|
if not success:
|
|
# 处理并发/重复请求：如果进程已退出/不存在，返回 400 而不是 500
|
|
if not crawler_manager.process or crawler_manager.process.poll() is not None:
|
|
raise HTTPException(status_code=400, detail="No crawler is running")
|
|
raise HTTPException(status_code=500, detail="Failed to stop crawler")
|
|
|
|
return {"status": "ok", "message": "Crawler stopped successfully"}
|
|
|
|
|
|
@router.get("/status", response_model=CrawlerStatusResponse)
|
|
async def get_crawler_status():
|
|
"""获取爬虫状态"""
|
|
return crawler_manager.get_status()
|
|
|
|
|
|
@router.get("/logs")
|
|
async def get_logs(limit: int = 100):
|
|
"""获取最近的日志"""
|
|
logs = crawler_manager.logs[-limit:] if limit > 0 else crawler_manager.logs
|
|
return {"logs": [log.model_dump() for log in logs]}
|