Created
March 4, 2013 10:28
-
-
Save xatier/5081360 to your computer and use it in GitHub Desktop.
This file contains hidden or 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
#!/usr/bin/python | |
import urllib2 | |
import urlparse | |
import BeautifulSoup | |
import os | |
import re | |
def find_tags(url): | |
c = urllib2.urlopen(url).read() | |
soup = BeautifulSoup.BeautifulSoup(c); | |
return soup.findAll('img') | |
def get_src(url, re_): | |
r = re.compile(re_) | |
tags = find_tags(url) | |
for tag in tags: | |
img = tag['src'] | |
if r.search(img): | |
yield img | |
def get_basename(url): | |
return os.path.basename(urlparse.urlsplit(url)[2]) | |
def download(url, re_=''): | |
for src in get_src(url, re_): | |
content = urllib2.urlopen(src).read() | |
print "[+] download: " + src | |
file_ = open(get_basename(src) , 'wb') | |
file_.write(content) | |
file_.close() | |
if __name__ == '__main__': | |
download(url='http://this-plt-life.tumblr.com', re_='gif') |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment