Python asyncio 异步编程实战：从协程到高并发爬虫

import asyncio
import time

async def say_after(delay, msg):
    await asyncio.sleep(delay)
    print(msg)

async def main():
    print(f"开始 {time.strftime('%X')}")
    await say_after(1, 'hello')
    await say_after(2, 'world')
    print(f"结束 {time.strftime('%X')}")

asyncio.run(main())   # 总耗时 3s（串行）

async def main():
    task1 = asyncio.create_task(say_after(1, 'hello'))
    task2 = asyncio.create_task(say_after(2, 'world'))
    await task1
    await task2
# 总耗时 2s

import aiohttp
import asyncio

async def fetch(session, url, sem):
    async with sem:   # 限制并发
        try:
            async with session.get(url, timeout=10) as resp:
                return await resp.text()
        except Exception as e:
            print(f'失败 {url}: {e}')
            return None

async def main(urls):
    sem = asyncio.Semaphore(50)
    async with aiohttp.ClientSession() as session:
        tasks = [fetch(session, u, sem) for u in urls]
        return await asyncio.gather(*tasks)

urls = [f'https://example.com/page/{i}' for i in range(1000)]
results = asyncio.run(main(urls))
print(f'成功 {sum(1 for r in results if r)} 个')

# ❌ 在协程中使用同步阻塞调用
async def bad():
    time.sleep(1)        # 阻塞整个事件循环！
    requests.get(url)    # 同样阻塞

# ✅ 正确
async def good():
    await asyncio.sleep(1)
    # 或用 run_in_executor 包装同步代码
    loop = asyncio.get_running_loop()
    await loop.run_in_executor(None, requests.get, url)

# 1. 超时控制
await asyncio.wait_for(fetch(url), timeout=5)

# 2. 逐个完成
for coro in asyncio.as_completed(tasks):
    result = await coro

# 3. 取消任务
task.cancel()
try:
    await task
except asyncio.CancelledError:
    print('已取消')

# 4. 同步接口转异步（如数据库）
await loop.run_in_executor(None, cursor.execute, sql)