Created
June 5, 2009 02:46
-
-
Save ericsk/124010 to your computer and use it in GitHub Desktop.
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
#!/usr/bin/env python | |
import sys | |
import os | |
import urllib | |
import urllib2 | |
import re | |
def main(): | |
url = sys.argv[1] | |
pat = url.split('/')[-1].split('&') | |
userid = pat[0] | |
folder = pat[1].split('=')[1] | |
path = 'yam/%s/%s' % (userid, folder) | |
try: | |
os.makedirs(path) | |
except: | |
pass | |
i = 1 | |
while True: | |
cookies = urllib2.HTTPCookieProcessor() | |
opener = urllib2.build_opener(cookies) | |
req = urllib2.Request(url=url + '&page=%d&limit=20' % i, | |
headers={}, | |
data=urllib.urlencode({ | |
'password': folder | |
})) | |
resp = opener.open(req) | |
content = resp.readlines() | |
valid = False | |
for line in content: | |
mat = re.findall('<img src=\"(.*?)\".*>', line) | |
if mat: | |
link = mat[0] | |
if link.find('t_') != -1 and link.find('.jpg') != -1: | |
valid = True | |
orig_link = link.replace('t_', '') | |
f = open('%s/%s' % (path, orig_link.split('/')[-1]), 'w') | |
req = urllib2.Request(orig_link) | |
req.add_header('User-Agent', 'Mozilla 5.0') | |
req.add_header('Referer', url) | |
data = urllib2.urlopen(req) | |
f.write(data.read()) | |
f.close() | |
print 'Fetched: %s.' % orig_link | |
if not valid: | |
break | |
else: | |
i += 1 | |
print 'Pictures are stored in %s' % path | |
if __name__ == '__main__': | |
main() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment