import asyncio
from aiohttp import request
from aiomultiprocess import Pool
async def get(url):
async with request("GET", url) as response:
return await response.text("utf-8")
async def main():
urls = ["https://jreese.sh", ...]
async with Pool() as pool:
async for result in pool.map(get, urls):
... # process result
if __name__ == '__main__':
# Python 3.7
asyncio.run(main())
# Python 3.6
# loop = asyncio.get_event_loop()
# loop.run_until_complete(main())
import asyncio
from concurrent.futures import ProcessPoolExecutor, ThreadPoolExecutor
async def with_processing():
with ProcessPoolExecutor() as executor:
tasks = [...]
for task in asyncio.as_completed(tasks):
result = await task
...
async def with_threading():
with ThreadPoolExecutor() as executor:
tasks = [...]
for task in asyncio.as_completed(tasks):
result = await task
...
async def main():
await asyncio.gather(with_processing(), with_threading())
asyncio.run(main())
from concurrent.futures import ThreadPoolExecutor
import requests
def get_data(url):
return requests.get(url).json()["data"]
urls = [...]
with ThreadPoolExecutor() as executor:
for data in executor.map(get_data, urls):
print(data)
from concurrent.futures import ThreadPoolExecutor
import requests
urls = [...]
with ThreadPoolExecutor() as executor:
for response in executor.map(requests.get, urls):
print(response.json()["data"])
import asyncio
import requests
async def get_data(url):
# A lot of code.
...
# The specific part that needs threading.
response = await asyncio.to_thread(requests.get, url, some_other_params)
# A lot of code.
...
return data
urls = [...]
async def main():
tasks = [get_data(url) for url in urls]
for task in asyncio.as_completed(tasks):
data = await task
print(data)
asyncio.run(main())
使用英特尔(R)酷睿(TM) i7-8700K CPU @ 3.70GHz和32.0 gb内存，我用2流程， 2个线程和2个asyncio任务计算了在2和100000之间有多少素数，如下所示。这是CPU上限计算:
多处理
多线程
asyncio
23.87秒
45.24秒
44.77秒
因为多处理可以运行平行，所以如上所示，多处理比多线程和asyncio快一倍。
我使用了以下3组代码:
多处理:
# "process_test.py"
from multiprocessing import Process
import time
start_time = time.time()
def test():
num = 100000
primes = 0
for i in range(2, num + 1):
for j in range(2, i):
if i % j == 0:
break
else:
primes += 1
print(primes)
if __name__ == "__main__": # This is needed to run processes on Windows
process_list = []
for _ in range(0, 2): # 2 processes
process = Process(target=test)
process_list.append(process)
for process in process_list:
process.start()
for process in process_list:
process.join()
print(round((time.time() - start_time), 2), "seconds") # 23.87 seconds
结果:
...
9592
9592
23.87 seconds
多线程:
# "thread_test.py"
from threading import Thread
import time
start_time = time.time()
def test():
num = 100000
primes = 0
for i in range(2, num + 1):
for j in range(2, i):
if i % j == 0:
break
else:
primes += 1
print(primes)
thread_list = []
for _ in range(0, 2): # 2 threads
thread = Thread(target=test)
thread_list.append(thread)
for thread in thread_list:
thread.start()
for thread in thread_list:
thread.join()
print(round((time.time() - start_time), 2), "seconds") # 45.24 seconds
结果:
...
9592
9592
45.24 seconds
Asyncio:
# "asyncio_test.py"
import asyncio
import time
start_time = time.time()
async def test():
num = 100000
primes = 0
for i in range(2, num + 1):
for j in range(2, i):
if i % j == 0:
break
else:
primes += 1
print(primes)
async def call_tests():
tasks = []
for _ in range(0, 2): # 2 asyncio tasks
tasks.append(test())
await asyncio.gather(*tasks)
asyncio.run(call_tests())
print(round((time.time() - start_time), 2), "seconds") # 44.77 seconds
