cut-bytes.py

#!/usr/bin/env python

__description__ = 'Cut a section of bytes out of a file'
__author__ = 'Didier Stevens'
__version__ = '0.0.2'
__date__ = '2015/11/10'

"""

Source code put in public domain by Didier Stevens, no Copyright
https://DidierStevens.com
Use at your own risk

History:
  2015/09/13: start
  2015/11/10: 0.0.2 added support for :-number

Todo:
"""

import optparse
import textwrap
import re
import cStringIO
import sys
import os
import zipfile

MALWARE_PASSWORD = 'infected'

def PrintManual():
    manual = '''
Manual:

cut-bytes.py reads a file (from disk, from stdin or from inside a (password protected) ZIP file) and outputs it (partially) to stdout.
cut-bytes.py can be instructed via a cut-expression to only send partial input to stdout.

The cut-expression allows for the partial selection of a stream. Use this expression to "cut out" part of the stream.
This cut-expression is composed of 2 terms separated by a colon (:), like this:
termA:termB
termA and termB can be:
- nothing (an empty string)
- a positive decimal number; example: 10
- an hexadecimal number (to be preceded by 0x); example: 0x10
- a case sensitive string to search for (surrounded by square brackets and single quotes); example: ['MZ']
- an hexadecimal string to search for (surrounded by square brackets); example: [d0cf11e0]
If termA is nothing, then the cut section of bytes starts with the byte at position 0.
If termA is a number, then the cut section of bytes starts with the byte at the position given by the number (first byte has index 0).
If termA is a string to search for, then the cut section of bytes starts with the byte at the position where the string is first found. If the string is not found, the cut is empty (0 bytes).
If termB is nothing, then the cut section of bytes ends with the last byte.
If termB is a number, then the cut section of bytes ends with the byte at the position given by the number (first byte has index 0).
When termB is a number, it can have suffix letter l. This indicates that the number is a length (number of bytes), and not a position.
termB can also be a negative number (decimal or hexademical): in that case the position is counted from the end of the file. For example, :-5 selects the complete file except the last 5 bytes.
If termB is a string to search for, then the cut section of bytes ends with the last byte at the position where the string is first found. If the string is not found, the cut is empty (0 bytes).
No checks are made to assure that the position specified by termA is lower than the position specified by termB. This is left up to the user.
Examples:
This cut-expression can be used to dump the first 256 bytes of a PE file located inside the stream: ['MZ']:0x100l
This cut-expression can be used to dump the OLE file located inside the stream: [d0cf11e0]:
'''
    for line in manual.split('\n'):
        print(textwrap.fill(line))

#Convert 2 Bytes If Python 3
def C2BIP3(string):
    if sys.version_info[0] > 2:
        return bytes([ord(x) for x in string])
    else:
        return string

def IfWIN32SetBinary(io):
    if sys.platform == 'win32':
        import msvcrt
        msvcrt.setmode(io.fileno(), os.O_BINARY)

CUTTERM_NOTHING = 0
CUTTERM_POSITION = 1
CUTTERM_FIND = 2
CUTTERM_LENGTH = 3

def ParseCutTerm(argument):
    if argument == '':
        return CUTTERM_NOTHING, None, ''
    oMatch = re.match(r'\-?0x([0-9a-f]+)', argument, re.I)
    if oMatch == None:
        oMatch = re.match(r'\-?(\d+)', argument)
    else:
        value = int(oMatch.group(1), 16)
        if argument.startswith('-'):
            value = -value
        return CUTTERM_POSITION, value, argument[len(oMatch.group(0)):]
    if oMatch == None:
        oMatch = re.match(r'\[([0-9a-f]+)\]', argument, re.I)
    else:
        value = int(oMatch.group(1))
        if argument.startswith('-'):
            value = -value
        return CUTTERM_POSITION, value, argument[len(oMatch.group(0)):]
    if oMatch == None:
        oMatch = re.match(r"\[\'(.+)\'\]", argument)
    else:
        if len(oMatch.group(1)) % 2 == 1:
            raise
        else:
            return CUTTERM_FIND, binascii.a2b_hex(oMatch.group(1)), argument[len(oMatch.group(0)):]
    if oMatch == None:
        return None, None, argument
    else:
        return CUTTERM_FIND, oMatch.group(1), argument[len(oMatch.group(0)):]

def ParseCutArgument(argument):
    type, value, remainder = ParseCutTerm(argument.strip())
    if type == CUTTERM_NOTHING:
        return CUTTERM_NOTHING, None, CUTTERM_NOTHING, None
    elif type == None:
        if remainder.startswith(':'):
            typeLeft = CUTTERM_NOTHING
            valueLeft = None
            remainder = remainder[1:]
        else:
            return None, None, None, None
    else:
        typeLeft = type
        valueLeft = value
        if typeLeft == CUTTERM_POSITION and valueLeft < 0:
            return None, None, None, None
        if remainder.startswith(':'):
            remainder = remainder[1:]
        else:
            return None, None, None, None
    type, value, remainder = ParseCutTerm(remainder)
    if type == CUTTERM_POSITION and remainder == 'l':
        return typeLeft, valueLeft, CUTTERM_LENGTH, value
    elif type == None or remainder != '':
        return None, None, None, None
    else:
        return typeLeft, valueLeft, type, value

def CutData(stream, cutArgument):
    if cutArgument == '':
        return stream

    typeLeft, valueLeft, typeRight, valueRight = ParseCutArgument(cutArgument)

    if typeLeft == None:
        return stream

    if typeLeft == CUTTERM_NOTHING:
        positionBegin = 0
    elif typeLeft == CUTTERM_POSITION:
        positionBegin = valueLeft
    else:
        positionBegin = stream.find(valueLeft)
        if positionBegin == -1:
            return ''

    if typeRight == CUTTERM_NOTHING:
        positionEnd = len(stream)
    elif typeRight == CUTTERM_POSITION and valueRight < 0:
        positionEnd = len(stream) + valueRight
    elif typeRight == CUTTERM_POSITION:
        positionEnd = valueRight + 1
    elif typeRight == CUTTERM_LENGTH:
        positionEnd = positionBegin + valueRight
    else:
        positionEnd = stream.find(valueRight)
        if positionEnd == -1:
            return ''
        else:
            positionEnd += len(valueRight)

    return stream[positionBegin:positionEnd]

#Fix for http://bugs.python.org/issue11395
def StdoutWriteChunked(data):
    while data != '':
        sys.stdout.write(data[0:10000])
        try:
            sys.stdout.flush()
        except IOError:
            return
        data = data[10000:]

def CutBytes(expression, filename, options):
    if filename == '':
        IfWIN32SetBinary(sys.stdin)
        oStringIO = cStringIO.StringIO(sys.stdin.read())
    elif filename.lower().endswith('.zip'):
        oZipfile = zipfile.ZipFile(filename, 'r')
        oZipContent = oZipfile.open(oZipfile.infolist()[0], 'r', C2BIP3(MALWARE_PASSWORD))
        oStringIO = cStringIO.StringIO(oZipContent.read())
        oZipContent.close()
        oZipfile.close()
    else:
        oStringIO = cStringIO.StringIO(open(filename, 'rb').read())

    IfWIN32SetBinary(sys.stdout)
    StdoutWriteChunked(CutData(oStringIO.read(), expression))

def Main():
    oParser = optparse.OptionParser(usage='usage: %prog [options] cut-expression [file]\n' + __description__, version='%prog ' + __version__)
    oParser.add_option('-m', '--man', action='store_true', default=False, help='Print manual')
    (options, args) = oParser.parse_args()

    if options.man:
        oParser.print_help()
        PrintManual()
        return

    if len(args) == 0 or len(args) > 2:
        oParser.print_help()
        print('')
        print('  Source code put in the public domain by Didier Stevens, no Copyright')
        print('  Use at your own risk')
        print('  https://DidierStevens.com')
        return

    if ParseCutArgument(args[0])[0] == None:
        print('Error: the cut-expression is invalid: %s' % args[0])
        return

    if len(args) == 1:
        CutBytes(args[0], '', options)
    else:
        CutBytes(args[0], args[1], options)

if __name__ == '__main__':
    Main()