py爬虫高性能用法

多线程：python的线程是全局解释器锁，所有只能使用一个线程，但是在IO密集型操作可以提高效率。

多进程：多进程适用于CPU密集的操作，但是比较浪费资源。

协程：利用一个线程，切换执行某段程序。

异步非阻塞：异步就是程序执行完成执行回调函数，非阻塞就是不等待，连不上就换下一个。

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是首选：

asyncio模块示例1

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()

asyncio模块示例2

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
Host: %s

""" % (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('www.cnblogs.com', '/wupeiqi/'),
    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

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()

asyncio + requests

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

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

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示例

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()

Tornado

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()