Skip to content

Instantly share code, notes, and snippets.

@dukn
Created August 23, 2018 09:55
Show Gist options
  • Save dukn/19a8e693d5443efd40f18a5bdb723b2a to your computer and use it in GitHub Desktop.
Save dukn/19a8e693d5443efd40f18a5bdb723b2a to your computer and use it in GitHub Desktop.
download image form link farallel
import os
import sys
import wget
import pandas as pd
from multiprocessing import Pool
FILE_PATH = sys.argv[1]
def get_file_paths(FILE_PATH):
df = pd.read_csv(FILE_PATH, header=None)
res = df[0].tolist()
print (len(res))
return res
def downloader(link):
try:
wget.download(link, 'data/' + link.split('/')[-1])
return 1
except Exception as e:
print (e)
return 0
def main():
if not os.path.isdir('data'):
os.mkdir('data')
list_file = list(get_file_paths(FILE_PATH))
p = Pool(8)
data = p.map(downloader, list_file)
print (sum(data)/float(len(data)))
if __name__ == '__main__':
#get_file_paths(FILE_PATH)
main()
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment