python 协程

import time

def crawl_page(url):
    print('crawling {}'.format(url))
    sleep_time = int(url.split('_')[-1])
    time.sleep(sleep_time)
    print('OK {}'.format(url))

def main(urls):
    for url in urls:
        crawl_page(url)

%time main(['url_1', 'url_2', 'url_3', 'url_4'])

########## 输出 ##########

crawling url_1
OK url_1
crawling url_2
OK url_2
crawling url_3
OK url_3
crawling url_4
OK url_4
Wall time: 10 s

node2:/root/python3#time python3 p13.py 
crawling url_1
OK url_1
crawling url_2
OK url_2
crawling url_3
OK url_3
crawling url_4
OK url_4

real    0m10.035s
user    0m0.014s
sys    0m0.008s

花费了10S,

使用协程脚本:

import asyncio

async def crawl_page(url):
    print('crawling {}'.format(url))
    sleep_time = int(url.split('_')[-1])
    await asyncio.sleep(sleep_time)
    print('OK {}'.format(url))

async def main(urls):
    for url in urls:
        await crawl_page(url)

%time asyncio.run(main(['url_1', 'url_2', 'url_3', 'url_4']))

########## 输出 ##########

crawling url_1
OK url_1
crawling url_2
OK url_2
crawling url_3
OK url_3
crawling url_4
OK url_4
Wall time: 10 s

await 程序会阻塞,和同步效果一样。

import asyncio

async def crawl_page(url):
    print('crawling {}'.format(url))
    sleep_time = int(url.split('_')[-1])
    await asyncio.sleep(sleep_time)
    print('OK {}'.format(url))

async def main(urls):
    tasks = [asyncio.create_task(crawl_page(url)) for url in urls]
    for task in tasks:
        await task

%time asyncio.run(main(['url_1', 'url_2', 'url_3', 'url_4']))

########## 输出 ##########

crawling url_1
crawling url_2
crawling url_3
crawling url_4
OK url_1
OK url_2
OK url_3
OK url_4
Wall time: 3.99 s

node2:/root/python3#time python3 p15.py 
crawling url_1
crawling url_2
crawling url_3
crawling url_4
OK url_1
OK url_2
OK url_3
OK url_4

real    0m4.104s
user    0m0.083s
sys    0m0.019s

另外一种写法:

import asyncio

async def crawl_page(url):
    print('crawling {}'.format(url))
    sleep_time = int(url.split('_')[-1])
    await asyncio.sleep(sleep_time)
    print('OK {}'.format(url))

async def main(urls):
    tasks = [asyncio.create_task(crawl_page(url)) for url in urls]
    await asyncio.gather(*tasks)

%time asyncio.run(main(['url_1', 'url_2', 'url_3', 'url_4']))

########## 输出 ##########

crawling url_1
crawling url_2
crawling url_3
crawling url_4
OK url_1
OK url_2
OK url_3
OK url_4
Wall time: 4.01 s

node2:/root/python3#time python3 p16.py 
crawling url_1
crawling url_2
crawling url_3
crawling url_4
OK url_1
OK url_2
OK url_3
OK url_4

real    0m4.088s
user    0m0.061s
sys    0m0.027s
node2:/root/python3#