Python之进程池与回调函数

# 进程池相比于Process效率高，因为创建进程和开启进程需要时间
# 进程数并非越多越好，操作系统调度进程需要耗时
# 进程池与Process效率比对

# Process 50个进程效率测试
# from multiprocessing import Process
# from multiprocessing import Queue
# import time
#
# def func(q):
#     ret = q.get()
#     ret -= 1
#     q.put(ret)
# if __name__ == '__main__':
#     q = Queue()
#     q.put(50)
#     p_lst = []
#     start_time = time.time()
#     for i in range(50):
#         p = Process(target=func,args=(q,))
#         p.start()
#         p_lst.append(p)
#     for p in p_lst:p.join()
#     print('50个进程从50减到：',q.get(),'耗时：',time.time() - start_time)
#
# # 进程池效率测试
# from multiprocessing import Pool
#
# if __name__ == '__main__':
#     q = Queue()
#     # 使用5个进程去跑50个任务
#     p = Pool(5)
#     q.put(50)
#     start_time = time.time()
#     for i in range(50):
#         p.apply_async(func,args=(q,)) # 异步提交方式
#     p.close() # 结束往进程池提交任务
#     p.join() # 感知进程池中任务结束
#     print('5个进程从50减到：', q.get(), '耗时：', time.time() - start_time)
'''
50个进程从50减到： 0 耗时： 2.6329572200775146
5个进程从50减到： 50 耗时： 0.09228920936584473
'''
# 进程池最优进程个数：cpu个数加1

# 获取子进程执行结果
# from multiprocessing import Pool
# import time
#
# def func(i):
#     time.sleep(0.5)
#     return i*2
# if __name__ == '__main__':
#     p = Pool(5)
#     for i in range(10):
#         res = p.apply_async(func,args=(i,))
#         print(res.get()) # get会阻塞等待进程返回结果,放在此处则变为同步执行
#     p.close()
#     p.join()

# 修改方式让进程异步执行
# from multiprocessing import Pool
# import time
#
# def func(i):
#     time.sleep(0.5)
#     return i*2
# if __name__ == '__main__':
#     p = Pool(5)
#     res_lst = []
#     for i in range(10):
#         res = p.apply_async(func,args=(i,))
#         res_lst.append(res)
#     for i in res_lst:print(i.get())
#     p.close()
#     p.join()

# 回调函数
# from multiprocessing import Pool
# import os
#
# def func1(n):
#     print('in func1',os.getpid())
#     return n*n
#
# def func2(n2):
#     print('in func2',os.getpid())
#     print(n2)
#
# if __name__ == '__main__':
#     p = Pool(5)
#     print(os.getpid())
#     for i in range(5):
#         p.apply_async(func1,args=(i,),callback=func2)
#     p.close()
#     p.join()
'''
7232
in func1 16532
in func1 16532
in func1 8028
in func1 16532
in func1 16100
in func2 7232
0
in func2 7232
9
in func2 7232
16
in func2 7232
4
in func2 7232
1
'''
# 回调函数接收一个参数(没有限制数据类型)，参数是子进程的返回值，且回调函数在主进程中执行
# 回调函数在爬虫案例中使用的比较多，爬取网页网络延迟造成爬取数据时间长，用回调函数取处理数据可以提高效率
# requests简单用法
# import requests
# response = requests.get('http://www.baidu.com')
# print(response) # 直接打印responce返回网页状态码
# print(response.content) # 获取网页內蓉(byte类型)
# print(response.content.decode('utf-8')) # 解码

# 爬虫小例子requests版
# import requests
# from multiprocessing import Pool
# url_lst = [
#     'https://www.cnblogs.com',
#     'https://www.sogou.com',
#     'https://www.baidu.com',
#     'http://www.sohu.com'
# ]
#
# def get(url):
#     response = requests.get(url)
#     if response.status_code == 200:
#         return (url,response.content.decode('utf-8'))
# def coll_back(url_info):
#     print(url_info)
#
# if __name__ == '__main__':
#     p = Pool(5)
#     for url in url_lst:
#         p.apply_async(get,args=(url,),callback=coll_back)
#     p.close()
#     p.join()

# urllib版
# from urllib.request import urlopen
# from multiprocessing import Pool
# url_lst = [
#     'https://www.cnblogs.com',
#     'https://www.sogou.com',
#     'https://www.baidu.com',
#     'http://www.sohu.com'
# ]
# def get(url):
#     response = urlopen(url)
#     return (url,response.read().decode('utf-8'))
# def coll_back(url_info):
#     print(url_info)
#
# if __name__ == '__main__':
#     p = Pool(5)
#     for url in url_lst:
#         p.apply_async(get,args=(url,),callback=coll_back)
#     p.close()
#     p.join()

# 爬虫小例子2--爬取猫眼电影网top100
# 正则测试网站：http://tool.chinaz.com/regex/
# url = 'https://maoyan.com/board'
# import re
'''content =
                <dd>
                        <i class="board-index board-index-9">9</i>
    <a href="/films/247295" title="驯龙高手3" class="image-link" data-act="boarditem-click" data-val="{movieId:247295}">
      <img src="//s3plus.meituan.net/v1/mss_e2821d7f0cfe4ac1bf9202ecf9590e67/cdn-prod/file:5788b470/image/loading_2.e3d934bf.png" alt="" class="poster-default" />
      <img data-src="https://p0.meituan.net/movie/9ef02a501fee7f62d49d2096b52175d32155331.jpg@160w_220h_1e_1c" alt="驯龙高手3" class="board-img" />
    </a>
    <div class="board-item-main">
      <div class="board-item-content">
              <div class="movie-item-info">
        <p class="name"><a href="/films/247295" title="驯龙高手3" data-act="boarditem-click" data-val="{movieId:247295}">驯龙高手3</a></p>
        <p class="star">
                主演：杰伊·巴鲁切尔,刘昊然,亚美莉卡·费雷拉
        </p>
<p class="releasetime">上映时间：2019-03-01</p>    </div>
    <div class="movie-item-number score-num">
<p class="score"><i class="integer">9.</i><i class="fraction">0</i></p>        
    </div>

      </div>
    </div>

                </dd>
'''

# partten = '<dd>.*?<i class=.*?>(?P<index>\d+)</i>.*?<p class="name"><a.*?>(?P<movename>.*?)</a></p>.*?<p class="star">(?P<star>.*?)</p>.*?<p class="releasetime">(?P<time>.*?)</p>.*?</dd>'
# regex = re.compile(partten,re.S)
# ret = re.search(regex,content)
# print(ret.group('index'),ret.group('movename'),ret.group('star').strip(),ret.group('time'))
# 以上为正则需要匹配的內容

from multiprocessing import Pool
import re
# 编译正则表达式
partten = '<dd>.*?<i class=.*?>(?P<index>\d+)</i>.*?<p class="name"><a.*?>(?P<movename>.*?)</a></p>.*?<p class="star">(?P<star>.*?)</p>.*?<p class="releasetime">(?P<time>.*?)</p>.*?</dd>'
regex = re.compile(partten,re.S)
# 定义爬去网页內容得函数
import requests
def get_content(url,n):
    response = requests.get(url)
    if response.status_code == 200:
        # 将爬取得网页內蓉保存下来，以免调试过程多次访问IP被禁止
        # filename = 'movelist/test' + str(n)
        # with open(filename,'wb') as f:
        #     f.write(response.content)
        return response.content.decode('utf-8')
# 定义一个从保存好得文件里获取网页內容得函数
def getContentFromfile(filename):
    content = ''
    with open(filename,'rb') as f:
        for line in f:
            content += line.decode('utf-8')
    return content

# 定义一个解析网页內容的函数
def parse_content(content):
    ret = re.findall(regex,content)
    move_lst = []
    for move_info in ret:
        move_dic = {
            '榜单排名':move_info[0].strip(),
            '电影名':move_info[1].strip(),
            '演员':move_info[2].strip(),
            '上映时间':move_info[3].strip()
        }
        print(move_dic)
if __name__ == '__main__':
    url = 'https://maoyan.com/board/4?offset='
    p = Pool(5)
    # 直接从网页上爬去数据
    for i in range(0,91,10):
        p.apply_async(get_content,args=(url+str(i),i),callback=parse_content)
    p.close()
    p.join()
    # filepath = 'movelist/test'
    # for i in range(0,91,10):
    #     p.apply_async(getContentFromfile,args=(filepath + str(i),),callback=parse_content)
    # p.close()
    # p.join()