python爬虫进阶之协程详解

import asyncio
async def request(url):
    print('正在请求的url是:',url)
    print('请求成功：',url)
#async修饰的函数，调用之后返回的一个协程对象
c = request('www.baidu.com')
# #创建一个事件循环对象
# loop = asyncio.get_event_loop()
#
# #将携程对象注册到loop中，然后启动loop
# loop.run_until_complete(c)
# #task的使用
# loop = asyncio.get_event_loop()
# #基于loop创建一个task对象
# task = loop.create_task(c)
# print(task)
# loop.run_until_complete(task)
# print(task)
#future的使用
loop = asyncio.get_event_loop()
task = asyncio.ensure_future(c)
print(task)
loop.run_until_complete(task)
print(task)

import asyncio
import time
async def request(url):
    print('正在请求的url是:',url)
    #在异步协程中如果出现同步模块相关的代码，那么就无法实现异步
    #time.sleep(2)
    await asyncio.sleep(2)
    print('请求成功：',url)
#async修饰的函数，调用之后返回的一个协程对象
start = time.time()
urls = {
    'www.123.com',
    'www.234.com',
    'www.345.com'
}
#存放多个任务对象
stask = []
for url in urls:
    c = request(url)
    task = asyncio.ensure_future(c)
    stask.append(task)
loop = asyncio.get_event_loop()
loop.run_until_complete(asyncio.wait(stask))
print(time.time()-start)

from flask import Flask
import time
app = Flask(__name__)
@app.route('/azb')
def index_azb():
    time.sleep(2)
    return 'Hello azb'
@app.route('/xx')
def index_xx():
    time.sleep(2)
    return 'Hello xx'
@app.route('/hh')
def index_hh():
    time.sleep(2)
    return 'Hello hh'
if __name__ == '__main__':
    app.run(threaded=True)

import requests,asyncio,time
start = time.time()
urls = [
    'http://127.0.0.1:5000/azb','http://127.0.0.1:5000/xx','http://127.0.0.1:5000/hh'
]
async def get_page(url):
    print('正在下载',url)
    #request是基于同步，必须使用基于异步的网络请求模块
    response = requests.get(url=url)
    print('下载成功！',url)
tasks = []
for url in urls:
    c = get_page(url)
    task = asyncio.ensure_future(c)
    tasks.append(task)
loop = asyncio.get_event_loop()
loop.run_until_complete(asyncio.wait(tasks))
print('总耗时',time.time()-start)

import requests,asyncio,time,aiohttp
start = time.time()
urls = [
    'http://127.0.0.1:5000/azb','http://127.0.0.1:5000/xx','http://127.0.0.1:5000/hh'
]
async def get_page(url):
    async with aiohttp.ClientSession() as session:
        async with await session.get(url) as response:
            #text()返回字符串形式的响应数据
            #read()返回的二进制形式的响应数据
            #json()返回的就是json对象
            #获取响应数据操作之前一定要使用await进行手动挂起
            page_text = await response.text()
            print(page_text)
tasks = []
for url in urls:
    c = get_page(url)
    task = asyncio.ensure_future(c)
    tasks.append(task)
loop = asyncio.get_event_loop()
loop.run_until_complete(asyncio.wait(tasks))
print('总耗时',time.time()-start)