libextractor-python

GNU libextractor
Log | Files | Refs | README | LICENSE

extract.py (1663B)

      1 #!/usr/bin/env python
      2 """extract.py
      3 
      4      This file is part of libextractor.
      5      (C) 2002, 2003, 2004, 2005 Vidyut Samanta and Christian Grothoff
      6      (C) 2017 Nikita Gillmann <nikita@n0.is>
      7 
      8      libextractor is free software; you can redistribute it and/or modify
      9      it under the terms of the GNU General Public License as published
     10      by the Free Software Foundation; either version 3, or (at your
     11      option) any later version.
     12 
     13      libextractor is distributed in the hope that it will be useful, but
     14      WITHOUT ANY WARRANTY; without even the implied warranty of
     15      MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
     16      General Public License for more details.
     17 
     18      You should have received a copy of the GNU General Public License
     19      along with libextractor; see the file COPYING.  If not, write to the
     20      Free Software Foundation, Inc., 59 Temple Place - Suite 330,
     21      Boston, MA 02111-1307, USA.
     22 
     23 Little demo how to use the libextractor Python binding.
     24 
     25 """
     26 from __future__ import print_function
     27 from libextractor import extractor
     28 import sys
     29 from ctypes import *
     30 import struct
     31 
     32 xtract = extractor.Extractor()
     33 
     34 
     35 def print_k(xt, plugin, type, format, mime, data, datalen):
     36     mstr = cast(data, c_char_p)
     37     # FIXME: this ignores 'datalen', not that great...
     38     # (in general, depending on the mime type and format, only
     39     # the first 'datalen' bytes in 'data' should be used).
     40     if (format == extractor.EXTRACTOR_METAFORMAT_UTF8):
     41         print("%s - %s" % (xtract.keywordTypes()[type], mstr.value))
     42     return 0
     43 
     44 
     45 for arg in sys.argv[1:]:
     46     print("Keywords from %s:" % arg)
     47     xtract.extract(print_k, None, arg)