To download files using multiple threads:
#!/usr/bin/env python
import shutil
from contextlib import closing
from multiprocessing.dummy import Pool # use threads
from urllib2 import urlopen
def generate_urls(some, params): #XXX pass whatever parameters you need
for restart in range(*params):
# ... generate url, filename
yield url, filename
def download((url, filename)):
try:
with closing(urlopen(url)) as response, open(filename, 'wb') as file:
shutil.copyfileobj(response, file)
except Exception as e:
return (url, filename), repr(e)
else: # success
return (url, filename), None
def main():
pool = Pool(20) # at most 20 concurrent downloads
urls = generate_urls(some, params)
for (url, filename), error in pool.imap_unordered(download, urls):
if error is not None:
print("Can't download {url} to {filename}, "
"reason: {error}".format(**locals())
if __name__ == "__main__":
main()