>>26499372Ah, found it.
<pre class="prettyprint">#!/usr/bin/env python
import os
import re
import sys
import urllib
import urllib2
import urlparse
import multiprocessing
IMAGE_URL_REGEX = r'"(\/\/images\.4chan\.org\/.+?\/src\/\d+\..+?)"'
PROCESSES = 8
def download(url, path):
if os.path.exists(path):
return
urllib.urlretrieve(url, path)
def main(argument):
pool = multiprocessing.Pool(PROCESSES)
source = urllib2.urlopen(argument).read()
tokens = argument.split('/')
path = '%s#%d' % (tokens[3], int(tokens[5]))
if not os.path.exists(path):
os.mkdir(path)
for image_url in set(re.findall(IMAGE_URL_REGEX, source)):
url = urlparse.urljoin(argument, image_url).replace('https', 'http')
filename = url.split('/')[-1]
path_ = os.path.join(path, filename)
pool.apply_async(download, [url, path_])
pool.close()
pool.join()
if __name__ == '__main__':
map(main, sys.argv[1:])
</pre>