Python异步库asyncio、aiohttp详解_Python

asyncio

版本支持

asyncio 模块在 python3.4 时发布。
async 和 await 关键字最早在 python3.5 中引入。
python3.3 之前不支持。

关键概念

event_loop 事件循环：程序开启一个无限的循环，程序员会把一些函数（协程）注册到事件循环上。当满足事件发生的时候，调用相应的协程函数。
coroutine 协程：协程对象，指一个使用async关键字定义的函数，它的调用不会立即执行函数，而是会返回一个协程对象。协程对象需要注册到事件循环，由事件循环调用。
future 对象：代表将来执行或没有执行的任务的结果。它和task上没有本质的区别
task 任务：一个协程对象就是一个原生可以挂起的函数，任务则是对协程进一步封装，其中包含任务的各种状态。task 对象是 future 的子类，它将 coroutine 和 future 联系在一起，将 coroutine 封装成一个 future 对象。
async/await 关键字：python3.5 用于定义协程的关键字，async定义一个协程，await用于挂起阻塞的异步调用接口。其作用在一定程度上类似于yield。

工作流程

定义/创建协程对象
将协程转为task任务
定义事件循环对象容器
将task任务放到事件循环对象中触发

import asyncio

async def hello(name):
    print('hello,', name)

# 定义协程对象
coroutine = hello("world")

# 定义事件循环对象容器
loop = asyncio.get_event_loop()

# 将协程转为task任务
# task = asyncio.ensure_future(coroutine)
task = loop.create_task(coroutine)

# 将task任务扔进事件循环对象中并触发
loop.run_until_complete(task)

并发

1. 创建多个协程的列表 tasks：

import asyncio


async def do_some_work(x):
    print('waiting: ', x)
    await asyncio.sleep(x)
    return 'done after {}s'.format(x)

tasks = [do_some_work(1), do_some_work(2), do_some_work(4)]

2. 将协程注册到事件循环中：

方法一：使用 asyncio.wait()

loop = asyncio.get_event_loop()
loop.run_until_complete(asyncio.wait(tasks))

方法二：使用 asyncio.gather()

loop = asyncio.get_event_loop()
loop.run_until_complete(asyncio.gather(*tasks))

3. 查看 return 结果：

for task in tasks:
    print('task ret: ', task.result())

4. asyncio.wait() 与 asyncio.gather() 的区别：

接收参数不同：

asyncio.wait()：必须是一个 list 对象，list 对象里存放多个 task 任务。

# 使用 asyncio.ensure_future 转换为 task 对象
tasks=[
       asyncio.ensure_future(factorial("a", 2)),
       asyncio.ensure_future(factorial("b", 3)),
       asyncio.ensure_future(factorial("c", 4))
]

# 也可以不转为 task 对象
# tasks=[
#        factorial("a", 2),
#        factorial("b", 3),
#        factorial("c", 4)
# ]

loop = asyncio.get_event_loop()
loop.run_until_complete(asyncio.wait(tasks))

asyncio.gather()：比较广泛，注意接收 list 对象时 * 不能省略。

tasks=[
       asyncio.ensure_future(factorial("a", 2)),
       asyncio.ensure_future(factorial("b", 3)),
       asyncio.ensure_future(factorial("c", 4))
]

# tasks=[
#        factorial("a", 2),
#        factorial("b", 3),
#        factorial("c", 4)
# ]

loop = asyncio.get_event_loop()
loop.run_until_complete(asyncio.gather(*tasks))

loop = asyncio.get_event_loop()

group1 = asyncio.gather(*[factorial("a" ,i) for i in range(1, 3)])
group2 = asyncio.gather(*[factorial("b", i) for i in range(1, 5)])
group3 = asyncio.gather(*[factorial("b", i) for i in range(1, 7)])

loop.run_until_complete(asyncio.gather(group1, group2, group3))

返回结果不同：

asyncio.wait()：返回 dones（已完成任务）和 pendings（未完成任务）

dones, pendings = await asyncio.wait(tasks)

for task in dones:
    print('task ret: ', task.result())

asyncio.gather()：直接返回结果

results = await asyncio.gather(*tasks)

for result in results:
    print('task ret: ', result)

aiohttp

clientsession 会话管理

import aiohttp
import asyncio


async def main():
    async with aiohttp.clientsession() as session:
        async with session.get('http://httpbin.org/get') as resp:
            print(resp.status)
            print(await resp.text())

asyncio.run(main())

其他请求：

session.post('http://httpbin.org/post', data=b'data')
session.put('http://httpbin.org/put', data=b'data')
session.delete('http://httpbin.org/delete')
session.head('http://httpbin.org/get')
session.options('http://httpbin.org/get')
session.patch('http://httpbin.org/patch', data=b'data')

url 参数传递

async def main():
    async with aiohttp.clientsession() as session:
        params = {'key1': 'value1', 'key2': 'value2'}
        async with session.get('http://httpbin.org/get', params=params) as r:
            expect = 'http://httpbin.org/get?key1=value1&key2=value2'
            assert str(r.url) == expect

async def main():
    async with aiohttp.clientsession() as session:
        params = [('key', 'value1'), ('key', 'value2')]
        async with session.get('http://httpbin.org/get', params=params) as r:
            expect = 'http://httpbin.org/get?key=value2&key=value1'
            assert str(r.url) == expect

获取响应内容

async def main():
    async with aiohttp.clientsession() as session:
        async with session.get('http://httpbin.org/get') as r:
            # 状态码
            print(r.status)
            # 响应内容，可以自定义编码
            print(await r.text(encoding='utf-8'))
            # 非文本内容
            print(await r.read())
            # json 内容
            print(await r.json())

自定义请求头

headers = {
        "user-agent": "mozilla/5.0 (windows nt 10.0; win64; x64) applewebkit/537.36 (khtml, like gecko) chrome/91.0.4472.106 safari/537.36"
    }


async def main():
    async with aiohttp.clientsession() as session:
        async with session.get('http://httpbin.org/get', headers=headers) as r:
            print(r.status)

为所有会话设置请求头：

headers = {
        "user-agent": "mozilla/5.0 (windows nt 10.0; win64; x64) applewebkit/537.36 (khtml, like gecko) chrome/91.0.4472.106 safari/537.36"
    }


async def main():
    async with aiohttp.clientsession(headers=headers) as session:
        async with session.get('http://httpbin.org/get') as r:
            print(r.status)

自定义 cookies

async def main():
    cookies = {'cookies_are': 'working'}
    async with aiohttp.clientsession() as session:
        async with session.get('http://httpbin.org/cookies', cookies=cookies) as resp:
            assert await resp.json() == {"cookies": {"cookies_are": "working"}}

为所有会话设置 cookies：

async def main():
    cookies = {'cookies_are': 'working'}
    async with aiohttp.clientsession(cookies=cookies) as session:
        async with session.get('http://httpbin.org/cookies') as resp:
            assert await resp.json() == {"cookies": {"cookies_are": "working"}}

设置代理

注意：只支持 http 代理。

async def main():
    async with aiohttp.clientsession() as session:
        proxy = "http://127.0.0.1:1080"
        async with session.get("http://python.org", proxy=proxy) as r:
            print(r.status)

需要用户名密码授权的代理：

async def main():
    async with aiohttp.clientsession() as session:
        proxy = "http://127.0.0.1:1080"
        proxy_auth = aiohttp.basicauth('username', 'password')
        async with session.get("http://python.org", proxy=proxy, proxy_auth=proxy_auth) as r:
            print(r.status)

也可以直接传递：

async def main():
    async with aiohttp.clientsession() as session:
        proxy = "http://username:password@127.0.0.1:1080"
        async with session.get("http://python.org", proxy=proxy) as r:
            print(r.status)

异步爬虫示例

import asyncio
import aiohttp

from lxml import etree
from datetime import datetime

headers = {"user-agent": "mozilla/5.0 (windows nt 10.0; win64; x64) applewebkit/537.36 (khtml, like gecko) chrome/91.0.4472.106 safari/537.36"}


async def get_movie_url():
    req_url = "https://movie.douban.com/chart"
    async with aiohttp.clientsession() as session:
        async with session.get(url=req_url, headers=headers) as response:
            result = await response.text()
            result = etree.html(result)
        return result.xpath("//*[@id='content']/div/div[1]/div/div/table/tr/td/a/@href")


async def get_movie_content(movie_url):
    async with aiohttp.clientsession() as session:
        async with session.get(url=movie_url, headers=headers) as response:
            result = await response.text()
            result = etree.html(result)
        movie = dict()
        name = result.xpath('//*[@id="content"]/h1/span[1]//text()')
        author = result.xpath('//*[@id="info"]/span[1]/span[2]//text()')
        movie["name"] = name
        movie["author"] = author
    return movie


def run():
    start = datetime.now()
    loop = asyncio.get_event_loop()
    movie_url_list = loop.run_until_complete(get_movie_url())
    tasks = [get_movie_content(url) for url in movie_url_list]
    movies = loop.run_until_complete(asyncio.gather(*tasks))
    print(movies)
    print("异步用时为：{}".format(datetime.now() - start))


if __name__ == '__main__':
    run()