Apkawa/ehentai_dup.py

   1 #!/usr/bin/python
   2 # -*- coding: utf-8 -*-
   3 ###
   4 #This file is part of <name prog> project
   5 #
   6 #<описание программы>
   7 #Copyright (C) <year> <name|nick>
   8 #
   9 #This program is free software; you can redistribute it and/or
  10 #modify it under the terms of the GNU General Public License
  11 #as published by the Free Software Foundation; either version 2
  12 #of the License, or (at your option) any later version.
  13 #
  14 #This program is distributed in the hope that it will be useful,
  15 #but WITHOUT ANY WARRANTY; without even the implied warranty of
  16 #MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  17 #GNU General Public License for more details.
  18 #
  19 #You should have received a copy of the GNU General Public License
  20 #along with this program; if not, write to the Free Software
  21 #Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
  22 #
  23 #You can contact author by email <my email>
  24 ###
  25 import os
  26 import re
  27 import time
  28 import random
  29 import urllib
  30
  31 URL = "http://g.e-hentai.org/"#?f_shash="
  32 SHA1SUM_BIN = '/usr/bin/sha1sum'
  33
  34 def get_sha1_from_file(filepath):
  35     if os.path.isfile(filepath) and os.path.splitext(filepath)[1].lower() in ['.png','.jpg','.jpeg']:
  36         cmd = '%s "%s"' % (SHA1SUM_BIN, filepath)
  37         sha1_res = os.popen( cmd).read()
  38         m = re.search("^([\w]{40})[\s]", sha1_res)
  39         if m:
  40             return m.groups()[0]
  41     return None
  42 def find_by_sha1(sha1):
  43     time.sleep(4)
  44     query = urllib.urlencode( {'f_shash':sha1} )
  45     _url = "%s?%s"%(URL, query)
  46     u = urllib.urlopen( _url)
  47     src = u.read()
  48     test_res = re.findall("class=\"(gtr0)\"", src)
  49     return len(test_res)
  50
  51
  52 def main( *args, **kwargs):
  53     args = os.sys.argv[1:]
  54     for arg in args:
  55         if os.path.isfile(arg):
  56             sha1= get_sha1_from_file( arg )
  57             print find_by_sha1(sha1), " duplicate for ", arg
  58         elif os.path.isdir(arg):
  59             for dirpath, dirnames, filenames in os.walk(arg):
  60                 for f in filenames:
  61                     filename = random.choice(filenames)
  62                     if os.path.splitext(filename)[1].lower() in ['.png','.jpg','.jpeg']:
  63                         filepath = os.path.join(dirpath,filename)
  64                         sha1= get_sha1_from_file( filepath )
  65                         for i in range(3):
  66                             dup_count = find_by_sha1(sha1)
  67                             if dup_count:
  68                                 break
  69                         print dup_count, " duplicate for ", dirpath
  70                         break
  71
  72
  73
  74
  75 if __name__ == "__main__":
  76     main()