实现单线程多并发的几种方式
相关标签： # python# 爬虫# git# github
单线程爬虫适用于小规模爬虫项目，如果应对大型项目就得实现多线程多并发，那么单线程如何实现多并发，下面几个示例可以一起看看。
1、asyncio
2、gevent
3、Twisted
4、Tornado
下面分别是这四种代码的实现例子：
asyncio例子1：
import asyncio
@asyncio.coroutine #通过这个装饰器装饰
def func1():
print('before...func1......')
# 这里必须用yield from，并且这里必须是asyncio.sleep不能是time.sleep
yield from asyncio.sleep(2)
print('end...func1......')
tasks = [func1(), func1()]
loop = asyncio.get_event_loop()
loop.run_until_complete(asyncio.gather(*tasks))
loop.close()
上述的效果是同时会打印两个before的内容，然后等待2秒打印end内容。
这里asyncio并没有提供我们发送http请求的方法，但是我们可以在yield from这里构造http请求的方法。
asyncio例子2：
import asyncio
@asyncio.coroutine
def fetch_async(host, url='/'):
print("----",host, url)
reader, writer = yield from asyncio.open_connection(host, 80)
#构造请求头内容
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')
#发送请求
writer.write(request_header_content)
yield from writer.drain()
text = yield from reader.read()
print(host, url, text)
writer.close()
tasks = [
fetch_async('www.cnblogs.com', '/zhaof/'),
fetch_async('dig.chouti.com', '/pic/show?nid=4073644713430508&lid=10273091')
]
loop = asyncio.get_event_loop()
results = loop.run_until_complete(asyncio.gather(*tasks))
loop.close()
asyncio + aiohttp 代码例子：
import aiohttp
import asyncio
@asyncio.coroutine
def fetch_async(url):
print(url)
response = yield from aiohttp.request('GET', url)
print(url, response)
response.close()
tasks = [fetch_async('http://baidu.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()
asyncio+requests代码例子
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, 'http://www.cnblogs.com/wupeiqi/'),
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()
gevent+requests代码例子
import gevent
import 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.yahoo.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={}),
# ])
grequests代码例子
这个是讲requests+gevent进行了封装
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)
twisted代码例子
#getPage相当于requets模块，defer特殊的返回值，rector是做事件循环
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)
#这里就是进就行一种检测，判断所有的请求知否执行完毕
dlist = defer.DeferredList(deferred_list)
dlist.addBoth(all_done)
reactor.run()
tornado代码例子
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()
文章来源： https://blog.51cto.com/u_13488918/6025412
特别声明：以上内容（图片及文字）均为互联网收集或者用户上传发布，本站仅提供信息存储服务！如有侵权或有涉及法律问题请联系我们。
举报
