异步IO、多线程、多进程_异步io线程数

在编写爬虫时，性能的消耗主要在IO请求中，当单进程单线程模式下请求URL时必然会引起等待，从而使得请求整体变慢。
1.同步

#!/usr/bin/env python
#-*- coding:utf-8 -*-
import requests

def fetch_async(url):
    response = requests.get(url)
    return response

url_list = ['http://www.github.com', 'http://www.bing.com']

for url in url_list:
    fetch_async(url)
1
2
3
4
5
6
7
8
9
10
11
12

2.多线程

#!/usr/bin/env python
#-*- coding:utf-8 -*-

from concurrent.futures import ThreadPoolExecutor
import requests

def fetch_async(url):
    response = requests.get(url)
    return response

url_list = ['http://www.github.com', 'http://www.bing.com']

pool = ThreadPoolExecutor(5)     #创建线程池
for url in url_list:
    pool.submit(fetch_async, url)
pool.shutdown(wait=True)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16

3.多线程+回调函数执行

#!/usr/bin/env python
#-*- coding:utf-8 -*-

from concurrent.futures import ThreadPoolExecutor
import requests

def fetch_async(url):
    response = requests.get(url)
    return response

def callback(future):
    print(future.result())

url_list = ['http://www.github.com', 'http://www.bing.com']

pool = ThreadPoolExecutor(5)    #创建线程池
for url in url_list:
    v = pool.submit(fetch_async, url)
    v.add_done_callback(callback)
pool.shutdown(wait=True)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20

4.多进程

#!/usr/bin/env python
#-*- coding:utf-8 -*-

from concurrent.futures import ProcessPoolExecutor
import requests

def fetch_async(url):
    response = requests.get(url)
    return response

url_list = ['http://www.github.com', 'http://www.bing.com']

pool = ProcessPoolExecutor(5)     #创建进程池
for url in url_list:
    pool.submit(fetch_async, url)
pool.shutdown(wait=True)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16

5.多进程+回调函数执行

#!/usr/bin/env python
#-*- coding:utf-8 -*-

from concurrent.futures import ProcessPoolExecutor
import requests

def fetch_async(url):
    response = requests.get(url)
    return response

def callback(future):
    print(future.result())

url_list = ['http://www.github.com', 'http://www.bing.com']
pool = ProcessPoolExecutor(5)    #创建进程池
for url in url_list:
    v = pool.submit(fetch_async, url)
    v.add_done_callback(callback)
pool.shutdown(wait=True)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19

通过上述代码均可以完成对请求性能的提高，对于多线程和多进行的缺点是在IO阻塞时会造成了线程和进程的浪费，所以异步IO回事首选：

1.asyncio示例

#!/usr/bin/env python
#-*- coding:utf-8 -*-
import asyncio

@asyncio.coroutine
def func1():
    print('before...func1......')
    yield from asyncio.sleep(5)
    print('end...func1......')

tasks = [func1(), func1()]

loop = asyncio.get_event_loop()
loop.run_until_complete(asyncio.gather(*tasks))
loop.close()
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15

2.asyncio示例

#!/usr/bin/env python
#-*- coding:utf-8 -*-
import asyncio

@asyncio.coroutine
def fetch_async(host, url='/'):
    print(host, url)
    reader, writer = yield from asyncio.open_connection(host, 80)

    request_header_content = """GET %s HTTP/1.0\r\nHost: %s\r\n\r\n""" % (url, host,)
    request_header_content = bytes(request_header_content, encoding='utf-8')

    writer.write(request_header_content)
    yield from writer.drain()
    text = yield from reader.read()
    print(host, url, text)
    writer.close()

tasks = [
    fetch_async('blog.csdn.net', '/m0_37886429/'),
    fetch_async('dig.chouti.com', '/pic/show?nid=4073644713430508&lid=10273091')
]
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22

3.asyncio + aiohttp

#!/usr/bin/env python
#-*- coding:utf-8 -*-
import aiohttp
import asyncio

@asyncio.coroutine
def fetch_async(url):
    print(url)
    response = yield from aiohttp.request('GET', url)
    # data = yield from response.read()
    # print(url, data)
    print(url, response)
    response.close()

tasks = [fetch_async('http://www.google.com/'), fetch_async('http://www.chouti.com/')]

event_loop = asyncio.get_event_loop()
results = event_loop.run_until_complete(asyncio.gather(*tasks))
event_loop.close()
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19

4.asyncio + requests

#!/usr/bin/env python
#-*- coding:utf-8 -*-
import asyncio
import requests

@asyncio.coroutine
def fetch_async(func, *args):
    loop = asyncio.get_event_loop()
    future = loop.run_in_executor(None, func, *args)
    response = yield from future
    print(response.url, response.content)

tasks = [
    fetch_async(requests.get, 'https://blog.csdn.net/m0_37886429'),
    fetch_async(requests.get, 'http://dig.chouti.com/pic/show?nid=4073644713430508&lid=10273091')
]

loop = asyncio.get_event_loop()
results = loop.run_until_complete(asyncio.gather(*tasks))
loop.close()
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20

5.gevent + requests

#!/usr/bin/env python
#-*- coding:utf-8 -*-
import gevent,requests
from gevent import monkey

monkey.patch_all()

def fetch_async(method, url, req_kwargs):
    print(method, url, req_kwargs)
    response = requests.request(method=method, url=url, **req_kwargs)
    print(response.url, response.content)

# ##### 发送请求 #####
gevent.joinall([
    gevent.spawn(fetch_async, method='get', url='https://www.python.org/', req_kwargs={}),
    gevent.spawn(fetch_async, method='get', url='https://www.baidu.com/', req_kwargs={}),
    gevent.spawn(fetch_async, method='get', url='https://github.com/', req_kwargs={}),
])

# ##### 发送请求（协程池控制最大协程数量） #####
# from gevent.pool import Pool
# pool = Pool(None)
# gevent.joinall([
#     pool.spawn(fetch_async, method='get', url='https://www.python.org/', req_kwargs={}),
#     pool.spawn(fetch_async, method='get', url='https://www.yahoo.com/', req_kwargs={}),
#     pool.spawn(fetch_async, method='get', url='https://www.github.com/', req_kwargs={}),
# ])
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27

6.grequests

#!/usr/bin/env python
#-*- coding:utf-8 -*-
import grequests

request_list = [
    grequests.get('http://httpbin.org/delay/1', timeout=0.001),
    grequests.get('http://fakedomain/'),
    grequests.get('http://httpbin.org/status/500')
]

# ##### 执行并获取响应列表 #####
# response_list = grequests.map(request_list)
# print(response_list)


# ##### 执行并获取响应列表（处理异常） #####
# def exception_handler(request, exception):
# print(request,exception)
#     print("Request failed")

# response_list = grequests.map(request_list, exception_handler=exception_handler)
# print(response_list)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22

7.Twisted示例

#!/usr/bin/env python
#-*- coding:utf-8 -*-
from twisted.web.client import getPage, defer
from twisted.internet import reactor

def all_done(arg):
    reactor.stop()

def callback(contents):
    print(contents)

deferred_list = []

url_list = ['http://www.bing.com', 'http://www.baidu.com', ]
for url in url_list:
    deferred = getPage(bytes(url, encoding='utf8'))
    deferred.addCallback(callback)
    deferred_list.append(deferred)

dlist = defer.DeferredList(deferred_list)
dlist.addBoth(all_done)

reactor.run()
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23

8.Tornado

#!/usr/bin/env python
#-*- coding:utf-8 -*-
from tornado.httpclient import AsyncHTTPClient
from tornado.httpclient import HTTPRequest
from tornado import ioloop

def handle_response(response):
    """
    处理返回值内容（需要维护计数器，来停止IO循环），调用 ioloop.IOLoop.current().stop()
    :param response:
    :return:
    """
    if response.error:
        print("Error:", response.error)
    else:
        print(response.body)

def func():
    url_list = [
        'http://www.baidu.com',
        'http://www.bing.com',
    ]
    for url in url_list:
        print(url)
        http_client = AsyncHTTPClient()
        http_client.fetch(HTTPRequest(url), handle_response)

ioloop.IOLoop.current().add_callback(func)
ioloop.IOLoop.current().start()
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29

9.Twisted更多

#!/usr/bin/env python
#-*- coding:utf-8 -*-
from twisted.internet import reactor
from twisted.web.client import getPage
import urllib.parse

def one_done(arg):
    print(arg)
    reactor.stop()

post_data = urllib.parse.urlencode({'check_data': 'adf'})
post_data = bytes(post_data, encoding='utf8')
headers = {b'Content-Type': b'application/x-www-form-urlencoded'}
response = getPage(bytes('http://dig.chouti.com/login', encoding='utf8'),
                   method=bytes('POST', encoding='utf8'),
                   postdata=post_data,
                   cookies={},
                   headers=headers)
response.addBoth(one_done)
reactor.run()
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20

以上均是Python内置以及第三方模块提供异步IO请求模块，使用简便大大提高效率，而对于异步IO请求的本质则是【非阻塞Socket】+【IO多路复用】

备注：
一、windows上安装Twisted

1、进入到 https://www.lfd.uci.edu/~gohlke/pythonlibs/#twisted ，下载 Twisted‑18.7.0‑cp35‑cp35m‑win_amd64.whl （我的python版本是3.5的，根据需要下载对应的文件）
2、进入文件所在目录
3、pip install Twisted‑18.7.0‑cp35‑cp35m‑win_amd64.whl

二、windows安装scrapy

1、pip install wheel
2、pip install Twisted‑18.7.0‑cp35‑cp35m‑win_amd64.whl
3、pip install pywin32
4、pip install scrapy

windows安装scrapy，需要依赖 https://sourceforge.net/projects/pywin32/files/
1
2
3
4
5
6