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

Question

我正在尝试使用multiprocessing.Pool.下载和提取 zip 文件。但是每次执行脚本时，只会下载3 个zip ，并且目录中看不到剩余的文件（CPU % 也达到 100%）。有人可以帮助我如何解决这个问题/建议更好的方法并遵循我尝试过的代码段。我对多处理完全陌生。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

我在您的函数中做了一些小调整，效果很好。请注意：

1. 该文件".../movielists_20130821.zip"在您的列表中出现两次，因此您将相同的内容下载了两次（可能是打字错误？）
2. 文件".../multiview_data_20130124.zip",".../movielists_20130821.zip"和".../3sources.zip"提取后，会生成一个新目录。".../bbcsport.zip"但是，该文件在提取时会将其文件放在根文件夹中，即您当前的工作目录（见下图）。也许你错过了这张支票？
3. 我在下载函数中添加了一个 try/except 块。为什么？多处理通过创建新的（子）进程来运行东西。如果子进程抛出异常，父进程不会捕获它。因此，如果此子流程中出现任何错误，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()