-
-
Save vijaiaeroastro/6a3f4986a383b367b463 to your computer and use it in GitHub Desktop.
Download images in parallel using python
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
from BeautifulSoup import BeautifulSoup | |
from functools import partial | |
from urllib import urlretrieve | |
from urlparse import urljoin, urlparse | |
import argparse | |
import multiprocessing | |
import os | |
import sys | |
import urllib2 | |
def get_url(): | |
parser = argparse.ArgumentParser(description='Download images from a website') | |
parser.add_argument('-w', type=str, help='website url') | |
options = parser.parse_args() | |
if options.w is None: | |
print parser.print_help() | |
sys.exit() | |
return options.w | |
def save_image(image, site_url, folder): | |
filename = image['src'].split('/')[-1] | |
outpath = os.path.join(folder, filename) | |
url = urljoin(site_url, image['src']) | |
urlretrieve(url, outpath) | |
print 'Saved image ' + outpath | |
if __name__ == '__main__': | |
url = get_url() | |
os.mkdir(urlparse(url).netloc) | |
page = BeautifulSoup(urllib2.urlopen(url).read()) | |
images = page.findAll('img') | |
pool = multiprocessing.Pool() | |
partial_save_image = partial(save_image, site_url=url, folder=urlparse(url).netloc) | |
pool.map(partial_save_image, images) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment