Question

我正在尝试使用multiprocessing.Pool下载和解压缩zip文件。但是，每次执行脚本时，只会下载 3个zip ，并且在目录中看不到其余文件（CPU ％也触及100％）。有人可以帮助我如何解决此问题/建议更好的方法以及遵循我尝试过的代码段。我对多处理技术完全陌生。我的目标是在不达到最大CPU的情况下并行下载多个文件。

import StringIO
import os
import sys
import zipfile
from multiprocessing import Pool, cpu_count

import requests

filePath = os.path.dirname(os.path.abspath(__file__))
print("filePath is %s " % filePath)
sys.path.append(filePath)
url = ["http://mlg.ucd.ie/files/datasets/multiview_data_20130124.zip",
       "http://mlg.ucd.ie/files/datasets/movielists_20130821.zip",
       "http://mlg.ucd.ie/files/datasets/bbcsport.zip",
       "http://mlg.ucd.ie/files/datasets/movielists_20130821.zip",
       "http://mlg.ucd.ie/files/datasets/3sources.zip"]


def download_zips(url):
    file_name = url.split("/")[-1]
    response = requests.get(url)
    sourceZip = zipfile.ZipFile(StringIO.StringIO(response.content))
    print("\n Downloaded {} ".format(file_name))
    sourceZip.extractall(filePath)
    print("extracted {} \n".format(file_name))
    sourceZip.close()


if __name__ == "__main__":
    print("There are {} CPUs on this machine ".format(cpu_count()))
    pool = Pool(cpu_count())
    results = pool.map(download_zips, url)
    pool.close()
    pool.join()

下面的输出

filePath is C:\Users\Documents\GitHub\Python-Examples-Internet\multi_processing 
There are 4 CPUs on this machine 
filePath is C:\Users\Documents\GitHub\Python-Examples-Internet\multi_processing 
filePath is C:\Users\Documents\GitHub\Python-Examples-Internet\multi_processing 
filePath is C:\Users\Documents\GitHub\Python-Examples-Internet\multi_processing 
filePath is C:\Users\Documents\GitHub\Python-Examples-Internet\multi_processing 

 Downloaded bbcsport.zip 
extracted bbcsport.zip 


 Downloaded 3sources.zip 
extracted 3sources.zip 


 Downloaded multiview_data_20130124.zip 

 Downloaded movielists_20130821.zip 

 Downloaded movielists_20130821.zip 
extracted multiview_data_20130124.zip 

extracted movielists_20130821.zip 

extracted movielists_20130821.zip

Answer 1

我在您的工作中做了几个小礼拜，效果很好。请注意：

文件".../movielists_20130821.zip"出现在列表中两次，因此您要两次重载相同的内容（可能是拼写错误？）
提取的文件".../multiview_data_20130124.zip"，".../movielists_20130821.zip"和".../3sources.zip"产生一个新目录。不过，提取后的文件".../bbcsport.zip"会将其放置在当前工作目录的根文件夹中（请参见下图）。也许您错过了这张支票？
我在donwload函数中添加了一个try / except块。为什么？多处理通过创建新的（子）流程来运行东西而起作用。 如果子流程引发异常，则父流程不会捕获该异常。因此，如果此子过程中出现任何错误，则必须在此处记录/处理。

import sys, os
import zipfile
import requests
from multiprocessing import Pool, cpu_count
from functools import partial
from io import BytesIO


def download_zip(url, filePath):
    try:
        file_name = url.split("/")[-1]
        response = requests.get(url)
        sourceZip = zipfile.ZipFile(BytesIO(response.content))
        print(" Downloaded {} ".format(file_name))
        sourceZip.extractall(filePath)
        print(" extracted {}".format(file_name))
        sourceZip.close()
    except Exception as e:
        print(e)


if __name__ == "__main__":
    filePath = os.path.dirname(os.path.abspath(__file__))
    print("filePath is %s " % filePath)
    # sys.path.append(filePath) # why do you need this?
    urls = ["http://mlg.ucd.ie/files/datasets/multiview_data_20130124.zip",
            "http://mlg.ucd.ie/files/datasets/movielists_20130821.zip",
            "http://mlg.ucd.ie/files/datasets/bbcsport.zip",
            "http://mlg.ucd.ie/files/datasets/movielists_20130821.zip",
            "http://mlg.ucd.ie/files/datasets/3sources.zip"]

    print("There are {} CPUs on this machine ".format(cpu_count()))
    pool = Pool(cpu_count())
    download_func = partial(download_zip, filePath = filePath)
    results = pool.map(download_func, urls)
    pool.close()
    pool.join()

Answer 2

我建议您使用多线程进行此操作，因为它受I / O约束，如下所示：

import requests, zipfile, io
import concurrent.futures 
url = ["http://mlg.ucd.ie/files/datasets/multiview_data_20130124.zip",
   "http://mlg.ucd.ie/files/datasets/movielists_20130821.zip",
   "http://mlg.ucd.ie/files/datasets/bbcsport.zip",
   "http://mlg.ucd.ie/files/datasets/movielists_20130821.zip",
   "http://mlg.ucd.ie/files/datasets/3sources.zip"]

def download_zips(url):
   file_name = url.split("/")[-1]
   response = requests.get(url)
   sourceZip = zipfile.ZipFile(io.BytesIO(response.content))
   print("\n Downloaded {} ".format(file_name))
   sourceZip.extractall(filePath)
   print("extracted {} \n".format(file_name))
   sourceZip.close()

with concurrent.futures.ThreadPoolExecutor() as exector : 
   exector.map(download_zip, urls)

Python如何使用multiprocessing.pool并行下载多个文件

2 个答案: