Day95

#爬虫性能相关
# 1.多线程
# """
# 可以实现并发
# 但是，请求发送出去后和返回之前，中间时期线程空闲
# 编写方式：
#     - 直接返回处理
#     - 通过回调函数处理
# """
# ########### 编写方式一 ###########
# """
# from concurrent.futures import ThreadPoolExecutor
# import requests
# import time
#
# def task(url):
#     response = requests.get(url)
#     print(url,response)
#     # 写正则表达式
#
#
# pool = ThreadPoolExecutor(7)
# url_list = [
#     ‘http://www.cnblogs.com/wupeiqi‘,
#     ‘http://huaban.com/favorite/beauty/‘,
#     ‘http://www.bing.com‘,
#     ‘http://www.zhihu.com‘,
#     ‘http://www.sina.com‘,
#     ‘http://www.baidu.com‘,
#     ‘http://www.autohome.com.cn‘,
# ]
# for url in url_list:
#     pool.submit(task,url)
#
# pool.shutdown(wait=True)
# """
#
# ########### 编写方式二 ###########
# from concurrent.futures import ThreadPoolExecutor
# import requests
# import time
#
# def task(url):
#     """
#     下载页面
#     :param url:
#     :return:
#     """
#     response = requests.get(url)
#     return response
#
# def done(future,*args,**kwargs):
#     response = future.result()
#     print(response.status_code,response.content)
#
# pool = ThreadPoolExecutor(7)
# url_list = [
#     ‘http://www.cnblogs.com/wupeiqi‘,
#     ‘http://huaban.com/favorite/beauty/‘,
#     ‘http://www.bing.com‘,
#     ‘http://www.zhihu.com‘,
#     ‘http://www.sina.com‘,
#     ‘http://www.baidu.com‘,
#     ‘http://www.autohome.com.cn‘,
# ]
# for url in url_list:
#     v = pool.submit(task,url)
#     v.add_done_callback(done)
#
# pool.shutdown(wait=True)
#

##########################多进程
"""
# 可以实现并发
# 但是，请求发送出去后和返回之前，中间时期进程空闲
# 编写方式：
#     - 直接返回处理
#     - 通过回调函数处理
# """
#
# ########### 编写方式一 ###########
# """
# from concurrent.futures import ProcessPoolExecutor
# import requests
# import time
#
# def task(url):
#     response = requests.get(url)
#     print(url,response)
#     # 写正则表达式
#
#
# pool = ProcessPoolExecutor(7)
# url_list = [
#     ‘http://www.cnblogs.com/wupeiqi‘,
#     ‘http://huaban.com/favorite/beauty/‘,
#     ‘http://www.bing.com‘,
#     ‘http://www.zhihu.com‘,
#     ‘http://www.sina.com‘,
#     ‘http://www.baidu.com‘,
#     ‘http://www.autohome.com.cn‘,
# ]
# for url in url_list:
#     pool.submit(task,url)
#
# pool.shutdown(wait=True)
# """
#
# ########### 编写方式二 ###########
# from concurrent.futures import ProcessPoolExecutor
# import requests
# import time
#
# def task(url):
#     response = requests.get(url)
#     return response
#
# def done(future,*args,**kwargs):
#     response = future.result()
#     print(response.status_code,response.content)
#
# pool = ProcessPoolExecutor(7)
# url_list = [
#     ‘http://www.cnblogs.com/wupeiqi‘,
#     ‘http://huaban.com/favorite/beauty/‘,
#     ‘http://www.bing.com‘,
#     ‘http://www.zhihu.com‘,
#     ‘http://www.sina.com‘,
#     ‘http://www.baidu.com‘,
#     ‘http://www.autohome.com.cn‘,
# ]
# for url in url_list:
#     v = pool.submit(task,url)
#     v.add_done_callback(done)
#
# pool.shutdown(wait=True)



########################################################################################################
# 线程与进程的区别
# 1.一个线程共享进程里的所有资源
# IO密集型用多线程
# 计算密集型用多进程
# 应用程序就是一个软件，一个软件就是一个进程，进程可以包含多个线程
# Pyhton里有JIL锁，同一时刻只能有一个线程会被CPU调度，如果用线程会被限制，即使开了多线程，效率反而不高
# 对于IO操作是不用通过CPU的
#
# 并发
# 异步IO
# 协程：一个线程在做很多事情，让一个线程先执行一个函数，执行时终止再执行其他，都是仅仅是切换
# 协程与异步IO可以共同完成并发请求
# Python内置模块：asyncio

Day95

原文：https://www.cnblogs.com/pandaboy1123/p/9185770.html