olevba: added scanning of multiple files with wildcards, recursive scanning in s…

…ubdirectories, scanning files within password-protected zips

olevba: added scanning of multiple files with wildcards, recursive scanning in s…
…ubdirectories, scanning files within password-protected zips
Philippe Lagadec
1 parent f133f113
Showing 3 changed files with 176 additions and 23 deletions
oletools/olevba.py
oletools/thirdparty/xglob/__init__.py
oletools/thirdparty/xglob/xglob.py
@@ -87,6 +87,9 @@ https://github.com/unixfreak0037/officeparser
 #                      - added pattern extraction
 # 2014-12-25 v0.09 PL: - added suspicious keywords detection
 # 2014-12-27 v0.10 PL: - added OptionParser, main and process_file
+#                      - uses xglob to scan several files with wildcards
+#                      - option -r to recurse subdirectories
+#                      - option -z to scan files in password-protected zips
  
 __version__ = '0.10'
  
@@ -134,6 +137,7 @@ import optparse
  
 import thirdparty.olefile as olefile
 from thirdparty.prettytable import prettytable
+from thirdparty.xglob import xglob
  
 #--- CONSTANTS ----------------------------------------------------------------
  
@@ -806,7 +810,7 @@ class VBA_Parser(object):
     - PowerPoint 2007+ (.pptm, .ppsm)
     """
  
-    def __init__(self, _file, filename=None):
+    def __init__(self, filename, data=None):
         """
         Constructor for VBA_Parser
  
@@ -816,20 +820,26 @@ class VBA_Parser(object):
         """
         #TODO: filename should be mandatory, optional data is a string or file-like object
         #TODO: also support olefile and zipfile as input
-        self.file = _file
+        if data is None:
+            # open file from disk:
+            _file = filename
+        else:
+            # file already read in memory, make it a file-like object for zipfile:
+            _file = cStringIO.StringIO(data)
+        #self.file = _file
         self.ole_file = None
         self.ole_subfiles = []
         self.filename = filename
         self.type = None
         self.vba_projects = None
-        if filename is None:
-            if isinstance(_file, basestring):
-                if len(_file) < olefile.MINIMAL_OLEFILE_SIZE:
-                    self.filename = _file
-                else:
-                    self.filename = '<file in bytes string>'
-            else:
-                self.filename = '<file-like object>'
+        # if filename is None:
+        #     if isinstance(_file, basestring):
+        #         if len(_file) < olefile.MINIMAL_OLEFILE_SIZE:
+        #             self.filename = _file
+        #         else:
+        #             self.filename = '<file in bytes string>'
+        #     else:
+        #         self.filename = '<file-like object>'
         if olefile.isOleFile(_file):
             # This looks like an OLE file
             logging.info('Parsing OLE file %s' % self.filename)
@@ -851,7 +861,7 @@ class VBA_Parser(object):
                     logging.debug('Opening OLE file %s within zip' % subfile)
                     ole_data = z.open(subfile).read()
                     try:
-                        self.ole_subfiles.append(VBA_Parser(ole_data, filename=subfile))
+                        self.ole_subfiles.append(VBA_Parser(filename=subfile, data=ole_data))
                     except:
                         logging.debug('%s is not a valid OLE file' % subfile)
                         continue
@@ -1005,16 +1015,17 @@ class VBA_Parser(object):
             self.ole_file.close()
  
  
-def process_file (filename):
+def process_file (filename, data):
     """
     Process a single file
     """
     #TODO: replace print by writing to a provided output file (sys.stdout by default)
+    print ''
     print '='*79
     print 'File:', filename
     try:
         #TODO: handle olefile errors, when an OLE file is malformed
-        vba = VBA_Parser(filename, filename=filename)
+        vba = VBA_Parser(filename, data)
         print 'Type:', vba.type
         if vba.detect_vba_macros():
             print 'Contains VBA Macros:'
@@ -1075,8 +1086,8 @@ def process_file (filename):
  
         else:
             print 'No VBA macros found.'
-    except TypeError:
-        raise
+    except: #TypeError:
+        #raise
         print sys.exc_value
  
  
@@ -1092,12 +1103,12 @@ def main():
     #     help='output file')
     # parser.add_option('-c', '--csv', dest='csv',
     #     help='export results to a CSV file')
-    # parser.add_option("-r", action="store_true", dest="recursive",
-    #     help='find files recursively in subdirectories.')
-    # parser.add_option("-z", "--zip", dest='zip_password', type='str', default=None,
-    #     help='if the file is a zip archive, open first file from it, using the provided password (requires Python 2.6+)')
-    # parser.add_option("-f", "--zipfname", dest='zip_fname', type='str', default='*',
-    #     help='if the file is a zip archive, file(s) to be opened within the zip. Wildcards * and ? are supported. (default:*)')
+    parser.add_option("-r", action="store_true", dest="recursive",
+        help='find files recursively in subdirectories.')
+    parser.add_option("-z", "--zip", dest='zip_password', type='str', default=None,
+        help='if the file is a zip archive, open first file from it, using the provided password (requires Python 2.6+)')
+    parser.add_option("-f", "--zipfname", dest='zip_fname', type='str', default='*',
+        help='if the file is a zip archive, file(s) to be opened within the zip. Wildcards * and ? are supported. (default:*)')
  
     (options, args) = parser.parse_args()
  
@@ -1109,9 +1120,10 @@ def main():
  
     logging.basicConfig(format='%(levelname)s: %(message)s', level=logging.WARNING) #INFO)
  
-    for filespec in args:
+    for filename, data in xglob.iter_files(args, recursive=options.recursive,
+        zip_password=options.zip_password, zip_fname=options.zip_fname):
         #data = open(filespec, 'rb').read()
-        process_file(filespec)
+        process_file(filename, data)
  
 if __name__ == '__main__':
     main()
+from .xglob import *
 \ No newline at end of file
+#! /usr/bin/env python2
+"""
+xglob
+
+xglob is a python package to list files matching wildcards (*, ?, []),
+extending the functionality of the glob module from the standard python
+library (https://docs.python.org/2/library/glob.html).
+
+Main features:
+- recursive file listing (including subfolders)
+- file listing within Zip archives
+- helper function to open files specified as arguments, supporting files
+  within zip archives encrypted with a password
+
+Author: Philippe Lagadec - http://www.decalage.info
+License: BSD, see source code or documentation
+
+For more info and updates: http://www.decalage.info/xglob
+"""
+
+# LICENSE:
+#
+# xglob is copyright (c) 2013-2014, Philippe Lagadec (http://www.decalage.info)
+# All rights reserved.
+#
+# Redistribution and use in source and binary forms, with or without modification,
+# are permitted provided that the following conditions are met:
+#
+#  * Redistributions of source code must retain the above copyright notice, this
+#    list of conditions and the following disclaimer.
+#  * Redistributions in binary form must reproduce the above copyright notice,
+#    this list of conditions and the following disclaimer in the documentation
+#    and/or other materials provided with the distribution.
+#
+# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND
+# ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+# WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+# DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE
+# FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+# DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
+# SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+# CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
+# OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+# OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+
+
+#------------------------------------------------------------------------------
+# CHANGELOG:
+# 2013-12-04 v0.01 PL: - scan several files from command line args
+# 2014-01-14 v0.02 PL: - added riglob, ziglob
+# 2014-12-26 v0.03 PL: - moved code from balbuzard into a separate package
+
+__version__ = '0.03'
+
+
+#=== IMPORTS =================================================================
+
+import os, fnmatch, glob, zipfile
+
+#=== FUNCTIONS ===============================================================
+
+# recursive glob function to find files in any subfolder:
+# inspired by http://stackoverflow.com/questions/14798220/how-can-i-search-sub-folders-using-glob-glob-module-in-python
+def rglob (path, pattern='*.*'):
+    """
+    Recursive glob:
+    similar to glob.glob, but finds files recursively in all subfolders of path.
+    path: root directory where to search files
+    pattern: pattern for filenames, using wildcards, e.g. *.txt
+    """
+    #TODO: more compatible API with glob: use single param, split path from pattern
+    return [os.path.join(dirpath, f)
+        for dirpath, dirnames, files in os.walk(path)
+        for f in fnmatch.filter(files, pattern)]
+
+
+def riglob (pathname):
+    """
+    Recursive iglob:
+    similar to glob.iglob, but finds files recursively in all subfolders of path.
+    pathname: root directory where to search files followed by pattern for
+    filenames, using wildcards, e.g. *.txt
+    """
+    path, filespec = os.path.split(pathname)
+    for dirpath, dirnames, files in os.walk(path):
+        for f in fnmatch.filter(files, filespec):
+            yield os.path.join(dirpath, f)
+
+
+def ziglob (zipfileobj, pathname):
+    """
+    iglob in a zip:
+    similar to glob.iglob, but finds files within a zip archive.
+    - zipfileobj: zipfile.ZipFile object
+    - pathname: root directory where to search files followed by pattern for
+    filenames, using wildcards, e.g. *.txt
+    """
+    files = zipfileobj.namelist()
+    for f in files: print f
+    for f in fnmatch.filter(files, pathname):
+        yield f
+
+
+def iter_files(files, recursive=False, zip_password=None, zip_fname='*'):
+    """
+    Open each file provided as argument:
+    - files is a list of arguments
+    - if zip_password is None, each file is listed without reading its content.
+      Wilcards are supported.
+    - if not, then each file is opened as a zip archive with the provided password
+    - then files matching zip_fname are opened from the zip archive
+
+    Iterator: yields (filename, data) for each file. If zip_password is None, then
+    only the filename is returned, and data=None. Otherwise data is the file
+    content.
+    """
+    # choose recursive or non-recursive iglob:
+    if recursive:
+        iglob = riglob
+    else:
+        iglob = glob.iglob
+    for filespec in files:
+        for filename in iglob(filespec):
+            if zip_password is not None:
+                # Each file is expected to be a zip archive:
+                print 'Opening zip archive %s with provided password' % filename
+                z = zipfile.ZipFile(filename, 'r')
+                print 'Looking for file(s) matching "%s"' % zip_fname
+                for filename in ziglob(z, zip_fname):
+                    print 'Opening file in zip archive:', filename
+                    data = z.read(filename, zip_password)
+                    yield filename, data
+            else:
+                # normal file
+                # do not read the file content, just yield the filename
+                yield filename, None
+                print 'Opening file', filename
+                #data = open(filename, 'rb').read()
+                #yield filename, data
+