回调函数
需要回调函数的场景:进程池中任何一个任务一旦处理完了,就立即告知主进程:我好了额,你可以处理我的结果了。主进程则调用一个函数去处理该结果,该函数即回调函数
我们可以把耗时间(阻塞)的任务放到进程池中,然后指定回调函数(主进程负责执行),这样主进程在执行回调函数时就省去了I/O的过程,直接拿到的是任务的结果。
from multiprocessing import Pool import requests import json import os def get_page(url): print('<进程%s> get %s' %(os.getpid(),url)) respone=requests.get(url) if respone.status_code == 200: return {'url':url,'text':respone.text} def pasrse_page(res): print('<进程%s> parse %s' %(os.getpid(),res['url'])) parse_res='url:<%s> size:[%s]\n' %(res['url'],len(res['text'])) with open('db.txt','a') as f: f.write(parse_res) if __name__ == '__main__': urls=[ 'https://www.baidu.com', 'https://www.python.org', 'https://www.openstack.org', 'https://help.github.com/', 'http://www.sina.com.cn/' ] p=Pool(3) res_l=[] for url in urls: res=p.apply_async(get_page,args=(url,),callback=pasrse_page) res_l.append(res) p.close() p.join() print([res.get() for res in res_l]) #拿到的是get_page的结果,其实完全没必要拿该结果,该结果已经传给回调函数处理了 ''' 打印结果: <进程3388> get https://www.baidu.com <进程3389> get https://www.python.org <进程3390> get https://www.openstack.org <进程3388> get https://help.github.com/ <进程3387> parse https://www.baidu.com <进程3389> get http://www.sina.com.cn/ <进程3387> parse https://www.python.org <进程3387> parse https://help.github.com/ <进程3387> parse http://www.sina.com.cn/ <进程3387> parse https://www.openstack.org [{'url': 'https://www.baidu.com', 'text': '<!DOCTYPE html>\r\n...',...}] '''
爬虫案例 from multiprocessing import Pool import time,random import requests import re def get_page(url,pattern): response=requests.get(url) if response.status_code == 200: return (response.text,pattern) def parse_page(info): page_content,pattern=info res=re.findall(pattern,page_content) for item in res: dic={ 'index':item[0], 'title':item[1], 'actor':item[2].strip()[3:], 'time':item[3][5:], 'score':item[4]+item[5] } print(dic) if __name__ == '__main__': pattern1=re.compile(r'<dd>.*?board-index.*?>(\d+)<.*?title="(.*?)".*?star.*?>(.*?)<.*?releasetime.*?>(.*?)<.*?integer.*?>(.*?)<.*?fraction.*?>(.*?)<',re.S) url_dic={ 'http://maoyan.com/board/7':pattern1, } p=Pool() res_l=[] for url,pattern in url_dic.items(): res=p.apply_async(get_page,args=(url,pattern),callback=parse_page) res_l.append(res) for i in res_l: i.get() # res=requests.get('http://maoyan.com/board/7') # print(re.findall(pattern,res.text))
如果在主进程中等待进程池中所有任务都执行完毕后,再统一处理结果,则无需回调函数
from multiprocessing import Pool import time,random,os def work(n): time.sleep(1) return n**2 if __name__ == '__main__': p=Pool() res_l=[] for i in range(10): res=p.apply_async(work,args=(i,)) res_l.append(res) p.close() p.join() #等待进程池中所有进程执行完毕 nums=[] for res in res_l: nums.append(res.get()) #拿到所有结果 print(nums) #主进程拿到所有的处理结果,可以在主进程中进行统一进行处理
进程池的其他实现方式:https://docs.python.org/dev/library/concurrent.futures.html