#!/usr/local/bin/python
# vim:fileencoding=<utf-8>
# -*- coding: <utf-8> -*-
# Sankakucomplex.com gallery articles mass downloader script
# You'll need python 2.5+ installed.
# Usage: Sankaku.py articleaddress1 [articleaddress2 ...]
#
# Uses wget (has to be in paths or same dir as the script),
# which allows to skip what has already been downloaded and
# to (resume)download what hasn't.

import os.path
import subprocess
import sys
import re
import urllib

__author__="Kaens Bard"
__date__ ="$Apr 2, 2009 4:54:30 PM$"

#preprocessing the link(s)
for name in sys.argv[1:]:
  toget = name
  if toget[-1:] != '/':
    toget += '/'
  print toget,
  p1 = re.match('http://www\.sankakucomplex\.com/(\d{4})/(\d{2})/(\d{2})/(.*)/',toget)
  if p1:
    print '- retrieving...'
    p1dir = p1.group(1)+'-'+p1.group(2)+'-'+p1.group(3)+' '+p1.group(4)
    if not os.path.exists(p1dir):
      os.mkdir(p1dir)
    finished = False
    if not os.path.exists(p1dir+'.html'):
      urllib.urlretrieve(toget,p1dir+'.html')
    with open(p1dir+'.html','r') as f:
      for l in f:
        if re.search("Toggle Visibility of Mature Content",l):
          finished = True
          break
        p2 = re.search('<a href="(http://www\.sankakucomplex\.com/wp-content/gallery/\S*/)(\S*(\.)(jpg|png|svg))"  ',l)
        if p2:
          pic = p2.group(1)+p2.group(2)
          subprocess.call(['wget', '-ct', '0', pic, '-O',p1dir+'/'+p2.group(2)])
    os.remove(p1dir+'.html')
  else:
    print ' - invalid link, skipping...'