Python解包及反编译: PyInstaller Extractor+uncompyle6
风吹落叶花飘荡 2024-10-03 16:35:02 阅读 56
Python解包及反编译: PyInstaller Extractor+uncompyle6
文章目录
Python解包及反编译: PyInstaller Extractor+uncompyle6一、前言二、PyInstaller Extractor解包1、安装pyinstxtractor2、解包
三、反编译uncompyle6工具使用1、pip安装uncompyle62、找到主文件并编译3、解压完成查看源码
四、一键解包并编译
一、前言
有时候会遇到一些人制作一键安装包的时候会把一些程序封装进exe里面，但我们又想拿到里面源码的情况。在这里就涉及到了解包与反编译的。
二、PyInstaller Extractor解包
目前的python主流的打包方式是使用pyinstaller，针对这种情况可以使用pyinstaller Extractor进行解包。
前提
使用pyinstaller进行打包未加密
1、安装pyinstxtractor
新建一个py文件pyinstxtractor.py,然后将下面的内容拷贝进去
然后就安装好了，要使用的时候与待解包的exe文件放在同一文件夹即可
<code>"""
PyInstaller Extractor v2.0 (Supports pyinstaller 6.6.0, 6.5.0, 6.4.0, 6.3.0, 6.2.0, 6.1.0, 6.0.0, 5.13.2, 5.13.1, 5.13.0, 5.12.0, 5.11.0, 5.10.1, 5.10.0, 5.9.0, 5.8.0, 5.7.0, 5.6.2, 5.6.1, 5.6, 5.5, 5.4.1, 5.4, 5.3, 5.2, 5.1, 5.0.1, 5.0, 4.10, 4.9, 4.8, 4.7, 4.6, 4.5.1, 4.5, 4.4, 4.3, 4.2, 4.1, 4.0, 3.6, 3.5, 3.4, 3.3, 3.2, 3.1, 3.0, 2.1, 2.0)
Author : Extreme Coders
E-mail : extremecoders(at)hotmail(dot)com
Web : https://0xec.blogspot.com
Date : 26-March-2020
Url : https://github.com/extremecoders-re/pyinstxtractor
For any suggestions, leave a comment on
https://forum.tuts4you.com/topic/34455-pyinstaller-extractor/
This script extracts a pyinstaller generated executable file.
Pyinstaller installation is not needed. The script has it all.
For best results, it is recommended to run this script in the
same version of python as was used to create the executable.
This is just to prevent unmarshalling errors(if any) while
extracting the PYZ archive.
Usage : Just copy this script to the directory where your exe resides
and run the script with the exe file name as a parameter
C:\\path\\to\\exe\\>python pyinstxtractor.py <filename>
$ /path/to/exe/python pyinstxtractor.py <filename>
Licensed under GNU General Public License (GPL) v3.
You are free to modify this source.
CHANGELOG
================================================
Version 1.1 (Jan 28, 2014)
-------------------------------------------------
- First Release
- Supports only pyinstaller 2.0
Version 1.2 (Sept 12, 2015)
-------------------------------------------------
- Added support for pyinstaller 2.1 and 3.0 dev
- Cleaned up code
- Script is now more verbose
- Executable extracted within a dedicated sub-directory
(Support for pyinstaller 3.0 dev is experimental)
Version 1.3 (Dec 12, 2015)
-------------------------------------------------
- Added support for pyinstaller 3.0 final
- Script is compatible with both python 2.x & 3.x (Thanks to Moritz Kroll @ Avira Operations GmbH & Co. KG)
Version 1.4 (Jan 19, 2016)
-------------------------------------------------
- Fixed a bug when writing pyc files >= version 3.3 (Thanks to Daniello Alto: https://github.com/Djamana)
Version 1.5 (March 1, 2016)
-------------------------------------------------
- Added support for pyinstaller 3.1 (Thanks to Berwyn Hoyt for reporting)
Version 1.6 (Sept 5, 2016)
-------------------------------------------------
- Added support for pyinstaller 3.2
- Extractor will use a random name while extracting unnamed files.
- For encrypted pyz archives it will dump the contents as is. Previously, the tool would fail.
Version 1.7 (March 13, 2017)
-------------------------------------------------
- Made the script compatible with python 2.6 (Thanks to Ross for reporting)
Version 1.8 (April 28, 2017)
-------------------------------------------------
- Support for sub-directories in .pyz files (Thanks to Moritz Kroll @ Avira Operations GmbH & Co. KG)
Version 1.9 (November 29, 2017)
-------------------------------------------------
- Added support for pyinstaller 3.3
- Display the scripts which are run at entry (Thanks to Michael Gillespie @ malwarehunterteam for the feature request)
Version 2.0 (March 26, 2020)
-------------------------------------------------
- Project migrated to github
- Supports pyinstaller 3.6
- Added support for Python 3.7, 3.8
- The header of all extracted pyc's are now automatically fixed
"""
from __future__ import print_function
import os
import struct
import marshal
import zlib
import sys
from uuid import uuid4 as uniquename
class CTOCEntry:
def __init__(self, position, cmprsdDataSize, uncmprsdDataSize, cmprsFlag, typeCmprsData, name):
self.position = position
self.cmprsdDataSize = cmprsdDataSize
self.uncmprsdDataSize = uncmprsdDataSize
self.cmprsFlag = cmprsFlag
self.typeCmprsData = typeCmprsData
self.name = name
class PyInstArchive:
PYINST20_COOKIE_SIZE = 24 # For pyinstaller 2.0
PYINST21_COOKIE_SIZE = 24 + 64 # For pyinstaller 2.1+
MAGIC = b'MEI\014\013\012\013\016' # Magic number which identifies pyinstaller
def __init__(self, path):
self.filePath = path
self.pycMagic = b'\0' * 4
self.barePycList = [] # List of pyc's whose headers have to be fixed
def open(self):
try:
self.fPtr = open(self.filePath, 'rb')
self.fileSize = os.stat(self.filePath).st_size
except:
print('[!] Error: Could not open {0}'.format(self.filePath))
return False
return True
def close(self):
try:
self.fPtr.close()
except:
pass
def checkFile(self):
print('[+] Processing {0}'.format(self.filePath))
searchChunkSize = 8192
endPos = self.fileSize
self.cookiePos = -1
if endPos < len(self.MAGIC):
print('[!] Error : File is too short or truncated')
return False
while True:
startPos = endPos - searchChunkSize if endPos >= searchChunkSize else 0
chunkSize = endPos - startPos
if chunkSize < len(self.MAGIC):
break
self.fPtr.seek(startPos, os.SEEK_SET)
data = self.fPtr.read(chunkSize)
offs = data.rfind(self.MAGIC)
if offs != -1:
self.cookiePos = startPos + offs
break
endPos = startPos + len(self.MAGIC) - 1
if startPos == 0:
break
if self.cookiePos == -1:
print('[!] Error : Missing cookie, unsupported pyinstaller version or not a pyinstaller archive')
return False
self.fPtr.seek(self.cookiePos + self.PYINST20_COOKIE_SIZE, os.SEEK_SET)
if b'python' in self.fPtr.read(64).lower():
print('[+] Pyinstaller version: 2.1+')
self.pyinstVer = 21 # pyinstaller 2.1+
else:
self.pyinstVer = 20 # pyinstaller 2.0
print('[+] Pyinstaller version: 2.0')
return True
def getCArchiveInfo(self):
try:
if self.pyinstVer == 20:
self.fPtr.seek(self.cookiePos, os.SEEK_SET)
# Read CArchive cookie
(magic, lengthofPackage, toc, tocLen, pyver) = \
struct.unpack('!8siiii', self.fPtr.read(self.PYINST20_COOKIE_SIZE))
elif self.pyinstVer == 21:
self.fPtr.seek(self.cookiePos, os.SEEK_SET)
# Read CArchive cookie
(magic, lengthofPackage, toc, tocLen, pyver, pylibname) = \
struct.unpack('!8sIIii64s', self.fPtr.read(self.PYINST21_COOKIE_SIZE))
except:
print('[!] Error : The file is not a pyinstaller archive')
return False
self.pymaj, self.pymin = (pyver//100, pyver%100) if pyver >= 100 else (pyver//10, pyver%10)
print('[+] Python version: {0}.{1}'.format(self.pymaj, self.pymin))
# Additional data after the cookie
tailBytes = self.fileSize - self.cookiePos - (self.PYINST20_COOKIE_SIZE if self.pyinstVer == 20 else self.PYINST21_COOKIE_SIZE)
# Overlay is the data appended at the end of the PE
self.overlaySize = lengthofPackage + tailBytes
self.overlayPos = self.fileSize - self.overlaySize
self.tableOfContentsPos = self.overlayPos + toc
self.tableOfContentsSize = tocLen
print('[+] Length of package: {0} bytes'.format(lengthofPackage))
return True
def parseTOC(self):
# Go to the table of contents
self.fPtr.seek(self.tableOfContentsPos, os.SEEK_SET)
self.tocList = []
parsedLen = 0
# Parse table of contents
while parsedLen < self.tableOfContentsSize:
(entrySize, ) = struct.unpack('!i', self.fPtr.read(4))
nameLen = struct.calcsize('!iIIIBc')
(entryPos, cmprsdDataSize, uncmprsdDataSize, cmprsFlag, typeCmprsData, name) = \
struct.unpack( \
'!IIIBc{0}s'.format(entrySize - nameLen), \
self.fPtr.read(entrySize - 4))
try:
name = name.decode("utf-8").rstrip("\0")
except UnicodeDecodeError:
newName = str(uniquename())
print('[!] Warning: File name {0} contains invalid bytes. Using random name {1}'.format(name, newName))
name = newName
# Prevent writing outside the extraction directory
if name.startswith("/"):
name = name.lstrip("/")
if len(name) == 0:
name = str(uniquename())
print('[!] Warning: Found an unamed file in CArchive. Using random name {0}'.format(name))
self.tocList.append( \
CTOCEntry( \
self.overlayPos + entryPos, \
cmprsdDataSize, \
uncmprsdDataSize, \
cmprsFlag, \
typeCmprsData, \
name \
))
parsedLen += entrySize
print('[+] Found {0} files in CArchive'.format(len(self.tocList)))
def _writeRawData(self, filepath, data):
nm = filepath.replace('\\', os.path.sep).replace('/', os.path.sep).replace('..', '__')
nmDir = os.path.dirname(nm)
if nmDir != '' and not os.path.exists(nmDir): # Check if path exists, create if not
os.makedirs(nmDir)
with open(nm, 'wb') as f:
f.write(data)
def extractFiles(self):
print('[+] Beginning extraction...please standby')
extractionDir = os.path.join(os.getcwd(), os.path.basename(self.filePath) + '_extracted')
if not os.path.exists(extractionDir):
os.mkdir(extractionDir)
os.chdir(extractionDir)
for entry in self.tocList:
self.fPtr.seek(entry.position, os.SEEK_SET)
data = self.fPtr.read(entry.cmprsdDataSize)
if entry.cmprsFlag == 1:
try:
data = zlib.decompress(data)
except zlib.error:
print('[!] Error : Failed to decompress {0}'.format(entry.name))
continue
# Malware may tamper with the uncompressed size
# Comment out the assertion in such a case
assert len(data) == entry.uncmprsdDataSize # Sanity Check
if entry.typeCmprsData == b'd' or entry.typeCmprsData == b'o':
# d -> ARCHIVE_ITEM_DEPENDENCY
# o -> ARCHIVE_ITEM_RUNTIME_OPTION
# These are runtime options, not files
continue
basePath = os.path.dirname(entry.name)
if basePath != '':
# Check if path exists, create if not
if not os.path.exists(basePath):
os.makedirs(basePath)
if entry.typeCmprsData == b's':
# s -> ARCHIVE_ITEM_PYSOURCE
# Entry point are expected to be python scripts
print('[+] Possible entry point: {0}.pyc'.format(entry.name))
if self.pycMagic == b'\0' * 4:
# if we don't have the pyc header yet, fix them in a later pass
self.barePycList.append(entry.name + '.pyc')
self._writePyc(entry.name + '.pyc', data)
elif entry.typeCmprsData == b'M' or entry.typeCmprsData == b'm':
# M -> ARCHIVE_ITEM_PYPACKAGE
# m -> ARCHIVE_ITEM_PYMODULE
# packages and modules are pyc files with their header intact
# From PyInstaller 5.3 and above pyc headers are no longer stored
# https://github.com/pyinstaller/pyinstaller/commit/a97fdf
if data[2:4] == b'\r\n':
# < pyinstaller 5.3
if self.pycMagic == b'\0' * 4:
self.pycMagic = data[0:4]
self._writeRawData(entry.name + '.pyc', data)
else:
# >= pyinstaller 5.3
if self.pycMagic == b'\0' * 4:
# if we don't have the pyc header yet, fix them in a later pass
self.barePycList.append(entry.name + '.pyc')
self._writePyc(entry.name + '.pyc', data)
else:
self._writeRawData(entry.name, data)
if entry.typeCmprsData == b'z' or entry.typeCmprsData == b'Z':
self._extractPyz(entry.name)
# Fix bare pyc's if any
self._fixBarePycs()
def _fixBarePycs(self):
for pycFile in self.barePycList:
with open(pycFile, 'r+b') as pycFile:
# Overwrite the first four bytes
pycFile.write(self.pycMagic)
def _writePyc(self, filename, data):
with open(filename, 'wb') as pycFile:
pycFile.write(self.pycMagic) # pyc magic
if self.pymaj >= 3 and self.pymin >= 7: # PEP 552 -- Deterministic pycs
pycFile.write(b'\0' * 4) # Bitfield
pycFile.write(b'\0' * 8) # (Timestamp + size) || hash
else:
pycFile.write(b'\0' * 4) # Timestamp
if self.pymaj >= 3 and self.pymin >= 3:
pycFile.write(b'\0' * 4) # Size parameter added in Python 3.3
pycFile.write(data)
def _extractPyz(self, name):
dirName = name + '_extracted'
# Create a directory for the contents of the pyz
if not os.path.exists(dirName):
os.mkdir(dirName)
with open(name, 'rb') as f:
pyzMagic = f.read(4)
assert pyzMagic == b'PYZ\0' # Sanity Check
pyzPycMagic = f.read(4) # Python magic value
if self.pycMagic == b'\0' * 4:
self.pycMagic = pyzPycMagic
elif self.pycMagic != pyzPycMagic:
self.pycMagic = pyzPycMagic
print('[!] Warning: pyc magic of files inside PYZ archive are different from those in CArchive')
# Skip PYZ extraction if not running under the same python version
if self.pymaj != sys.version_info.major or self.pymin != sys.version_info.minor:
print('[!] Warning: This script is running in a different Python version than the one used to build the executable.')
print('[!] Please run this script in Python {0}.{1} to prevent extraction errors during unmarshalling'.format(self.pymaj, self.pymin))
print('[!] Skipping pyz extraction')
return
(tocPosition, ) = struct.unpack('!i', f.read(4))
f.seek(tocPosition, os.SEEK_SET)
try:
toc = marshal.load(f)
except:
print('[!] Unmarshalling FAILED. Cannot extract {0}. Extracting remaining files.'.format(name))
return
print('[+] Found {0} files in PYZ archive'.format(len(toc)))
# From pyinstaller 3.1+ toc is a list of tuples
if type(toc) == list:
toc = dict(toc)
for key in toc.keys():
(ispkg, pos, length) = toc[key]
f.seek(pos, os.SEEK_SET)
fileName = key
try:
# for Python > 3.3 some keys are bytes object some are str object
fileName = fileName.decode('utf-8')
except:
pass
# Prevent writing outside dirName
fileName = fileName.replace('..', '__').replace('.', os.path.sep)
if ispkg == 1:
filePath = os.path.join(dirName, fileName, '__init__.pyc')
else:
filePath = os.path.join(dirName, fileName + '.pyc')
fileDir = os.path.dirname(filePath)
if not os.path.exists(fileDir):
os.makedirs(fileDir)
try:
data = f.read(length)
data = zlib.decompress(data)
except:
print('[!] Error: Failed to decompress {0}, probably encrypted. Extracting as is.'.format(filePath))
open(filePath + '.encrypted', 'wb').write(data)
else:
self._writePyc(filePath, data)
def main():
if len(sys.argv) < 2:
print('[+] Usage: pyinstxtractor.py <filename>')
else:
arch = PyInstArchive(sys.argv[1])
if arch.open():
if arch.checkFile():
if arch.getCArchiveInfo():
arch.parseTOC()
arch.extractFiles()
arch.close()
print('[+] Successfully extracted pyinstaller archive: {0}'.format(sys.argv[1]))
print('')
print('You can now use a python decompiler on the pyc files within the extracted directory')
return
arch.close()
if __name__ == '__main__':
main()
2、解包
在使用前：
将需解包的exe与下载的pyinstxtractor.py存入同级文件夹
使用命令行输入如下指令, 得到exe的解包文件夹.
<code>python pyinstxtractor.py { -- -->exe路径}
示例: python pyinstxtractor.py CreatFoder.exe
运行结果：
解包后文件放在以exe名字+_extracted的文件夹中
三、反编译uncompyle6工具使用
目前代码还不能用，打开会看到基本全是乱码。
在这里需要对在线pyc,pyo,pyd文件等进行反编译成py文件
1、pip安装uncompyle6
<code>pip install uncompyle6
2、找到主文件并编译
主文件的命名一般与其他库不同，有比较明显的开发者个人特征，且后缀通常是pyc。
找到之后再同级目录下输入命令行执行
uncompyle6.exe {pyc文件} >{py文件输出路径}
示例
3、解压完成查看源码
无乱码，一切正常
四、一键解包并编译
很多时候我们对于解包和编译是同一流程的。为了加快获取目标源码这一步骤，我将解包和编译的流程集中了起来，源码如下：
新建一个py文件：pyinstxtractorV2.py
<code>"""
PyInstaller Extractor v2.0 (Supports pyinstaller 6.6.0, 6.5.0, 6.4.0, 6.3.0, 6.2.0, 6.1.0, 6.0.0, 5.13.2, 5.13.1, 5.13.0, 5.12.0, 5.11.0, 5.10.1, 5.10.0, 5.9.0, 5.8.0, 5.7.0, 5.6.2, 5.6.1, 5.6, 5.5, 5.4.1, 5.4, 5.3, 5.2, 5.1, 5.0.1, 5.0, 4.10, 4.9, 4.8, 4.7, 4.6, 4.5.1, 4.5, 4.4, 4.3, 4.2, 4.1, 4.0, 3.6, 3.5, 3.4, 3.3, 3.2, 3.1, 3.0, 2.1, 2.0)
Author : Extreme Coders
E-mail : extremecoders(at)hotmail(dot)com
Web : https://0xec.blogspot.com
Date : 26-March-2020
Url : https://github.com/extremecoders-re/pyinstxtractor
For any suggestions, leave a comment on
https://forum.tuts4you.com/topic/34455-pyinstaller-extractor/
This script extracts a pyinstaller generated executable file.
Pyinstaller installation is not needed. The script has it all.
For best results, it is recommended to run this script in the
same version of python as was used to create the executable.
This is just to prevent unmarshalling errors(if any) while
extracting the PYZ archive.
Usage : Just copy this script to the directory where your exe resides
and run the script with the exe file name as a parameter
C:\\path\\to\\exe\\>python pyinstxtractor.py <filename>
$ /path/to/exe/python pyinstxtractor.py <filename>
Licensed under GNU General Public License (GPL) v3.
You are free to modify this source.
CHANGELOG
================================================
Version 1.1 (Jan 28, 2014)
-------------------------------------------------
- First Release
- Supports only pyinstaller 2.0
Version 1.2 (Sept 12, 2015)
-------------------------------------------------
- Added support for pyinstaller 2.1 and 3.0 dev
- Cleaned up code
- Script is now more verbose
- Executable extracted within a dedicated sub-directory
(Support for pyinstaller 3.0 dev is experimental)
Version 1.3 (Dec 12, 2015)
-------------------------------------------------
- Added support for pyinstaller 3.0 final
- Script is compatible with both python 2.x & 3.x (Thanks to Moritz Kroll @ Avira Operations GmbH & Co. KG)
Version 1.4 (Jan 19, 2016)
-------------------------------------------------
- Fixed a bug when writing pyc files >= version 3.3 (Thanks to Daniello Alto: https://github.com/Djamana)
Version 1.5 (March 1, 2016)
-------------------------------------------------
- Added support for pyinstaller 3.1 (Thanks to Berwyn Hoyt for reporting)
Version 1.6 (Sept 5, 2016)
-------------------------------------------------
- Added support for pyinstaller 3.2
- Extractor will use a random name while extracting unnamed files.
- For encrypted pyz archives it will dump the contents as is. Previously, the tool would fail.
Version 1.7 (March 13, 2017)
-------------------------------------------------
- Made the script compatible with python 2.6 (Thanks to Ross for reporting)
Version 1.8 (April 28, 2017)
-------------------------------------------------
- Support for sub-directories in .pyz files (Thanks to Moritz Kroll @ Avira Operations GmbH & Co. KG)
Version 1.9 (November 29, 2017)
-------------------------------------------------
- Added support for pyinstaller 3.3
- Display the scripts which are run at entry (Thanks to Michael Gillespie @ malwarehunterteam for the feature request)
Version 2.0 (March 26, 2020)
-------------------------------------------------
- Project migrated to github
- Supports pyinstaller 3.6
- Added support for Python 3.7, 3.8
- The header of all extracted pyc's are now automatically fixed
"""
from __future__ import print_function
import os
import struct
import marshal
import zlib
import sys
from uuid import uuid4 as uniquename
class CTOCEntry:
def __init__(self, position, cmprsdDataSize, uncmprsdDataSize, cmprsFlag, typeCmprsData, name):
self.position = position
self.cmprsdDataSize = cmprsdDataSize
self.uncmprsdDataSize = uncmprsdDataSize
self.cmprsFlag = cmprsFlag
self.typeCmprsData = typeCmprsData
self.name = name
class PyInstArchive:
PYINST20_COOKIE_SIZE = 24 # For pyinstaller 2.0
PYINST21_COOKIE_SIZE = 24 + 64 # For pyinstaller 2.1+
MAGIC = b'MEI\014\013\012\013\016' # Magic number which identifies pyinstaller
def __init__(self, path):
self.filePath = path
self.pycMagic = b'\0' * 4
self.barePycList = [] # List of pyc's whose headers have to be fixed
def open(self):
try:
self.fPtr = open(self.filePath, 'rb')
self.fileSize = os.stat(self.filePath).st_size
except:
print('[!] Error: Could not open {0}'.format(self.filePath))
return False
return True
def close(self):
try:
self.fPtr.close()
except:
pass
def checkFile(self):
print('[+] Processing {0}'.format(self.filePath))
searchChunkSize = 8192
endPos = self.fileSize
self.cookiePos = -1
if endPos < len(self.MAGIC):
print('[!] Error : File is too short or truncated')
return False
while True:
startPos = endPos - searchChunkSize if endPos >= searchChunkSize else 0
chunkSize = endPos - startPos
if chunkSize < len(self.MAGIC):
break
self.fPtr.seek(startPos, os.SEEK_SET)
data = self.fPtr.read(chunkSize)
offs = data.rfind(self.MAGIC)
if offs != -1:
self.cookiePos = startPos + offs
break
endPos = startPos + len(self.MAGIC) - 1
if startPos == 0:
break
if self.cookiePos == -1:
print('[!] Error : Missing cookie, unsupported pyinstaller version or not a pyinstaller archive')
return False
self.fPtr.seek(self.cookiePos + self.PYINST20_COOKIE_SIZE, os.SEEK_SET)
if b'python' in self.fPtr.read(64).lower():
print('[+] Pyinstaller version: 2.1+')
self.pyinstVer = 21 # pyinstaller 2.1+
else:
self.pyinstVer = 20 # pyinstaller 2.0
print('[+] Pyinstaller version: 2.0')
return True
def getCArchiveInfo(self):
try:
if self.pyinstVer == 20:
self.fPtr.seek(self.cookiePos, os.SEEK_SET)
# Read CArchive cookie
(magic, lengthofPackage, toc, tocLen, pyver) = \
struct.unpack('!8siiii', self.fPtr.read(self.PYINST20_COOKIE_SIZE))
elif self.pyinstVer == 21:
self.fPtr.seek(self.cookiePos, os.SEEK_SET)
# Read CArchive cookie
(magic, lengthofPackage, toc, tocLen, pyver, pylibname) = \
struct.unpack('!8sIIii64s', self.fPtr.read(self.PYINST21_COOKIE_SIZE))
except:
print('[!] Error : The file is not a pyinstaller archive')
return False
self.pymaj, self.pymin = (pyver // 100, pyver % 100) if pyver >= 100 else (pyver // 10, pyver % 10)
print('[+] Python version: {0}.{1}'.format(self.pymaj, self.pymin))
# Additional data after the cookie
tailBytes = self.fileSize - self.cookiePos - (
self.PYINST20_COOKIE_SIZE if self.pyinstVer == 20 else self.PYINST21_COOKIE_SIZE)
# Overlay is the data appended at the end of the PE
self.overlaySize = lengthofPackage + tailBytes
self.overlayPos = self.fileSize - self.overlaySize
self.tableOfContentsPos = self.overlayPos + toc
self.tableOfContentsSize = tocLen
print('[+] Length of package: {0} bytes'.format(lengthofPackage))
return True
def parseTOC(self):
# Go to the table of contents
self.fPtr.seek(self.tableOfContentsPos, os.SEEK_SET)
self.tocList = []
parsedLen = 0
# Parse table of contents
while parsedLen < self.tableOfContentsSize:
(entrySize,) = struct.unpack('!i', self.fPtr.read(4))
nameLen = struct.calcsize('!iIIIBc')
(entryPos, cmprsdDataSize, uncmprsdDataSize, cmprsFlag, typeCmprsData, name) = \
struct.unpack( \
'!IIIBc{0}s'.format(entrySize - nameLen), \
self.fPtr.read(entrySize - 4))
try:
name = name.decode("utf-8").rstrip("\0")
except UnicodeDecodeError:
newName = str(uniquename())
print('[!] Warning: File name {0} contains invalid bytes. Using random name {1}'.format(name, newName))
name = newName
# Prevent writing outside the extraction directory
if name.startswith("/"):
name = name.lstrip("/")
if len(name) == 0:
name = str(uniquename())
print('[!] Warning: Found an unamed file in CArchive. Using random name {0}'.format(name))
self.tocList.append( \
CTOCEntry( \
self.overlayPos + entryPos, \
cmprsdDataSize, \
uncmprsdDataSize, \
cmprsFlag, \
typeCmprsData, \
name \
))
parsedLen += entrySize
print('[+] Found {0} files in CArchive'.format(len(self.tocList)))
def _writeRawData(self, filepath, data):
nm = filepath.replace('\\', os.path.sep).replace('/', os.path.sep).replace('..', '__')
nmDir = os.path.dirname(nm)
if nmDir != '' and not os.path.exists(nmDir): # Check if path exists, create if not
os.makedirs(nmDir)
with open(nm, 'wb') as f:
f.write(data)
def extractFiles(self):
print('[+] Beginning extraction...please standby')
extractionDir = os.path.join(os.getcwd(), os.path.basename(self.filePath) + '_extracted')
if not os.path.exists(extractionDir):
os.mkdir(extractionDir)
os.chdir(extractionDir)
for entry in self.tocList:
self.fPtr.seek(entry.position, os.SEEK_SET)
data = self.fPtr.read(entry.cmprsdDataSize)
if entry.cmprsFlag == 1:
try:
data = zlib.decompress(data)
except zlib.error:
print('[!] Error : Failed to decompress {0}'.format(entry.name))
continue
# Malware may tamper with the uncompressed size
# Comment out the assertion in such a case
assert len(data) == entry.uncmprsdDataSize # Sanity Check
if entry.typeCmprsData == b'd' or entry.typeCmprsData == b'o':
# d -> ARCHIVE_ITEM_DEPENDENCY
# o -> ARCHIVE_ITEM_RUNTIME_OPTION
# These are runtime options, not files
continue
basePath = os.path.dirname(entry.name)
if basePath != '':
# Check if path exists, create if not
if not os.path.exists(basePath):
os.makedirs(basePath)
if entry.typeCmprsData == b's':
# s -> ARCHIVE_ITEM_PYSOURCE
# Entry point are expected to be python scripts
print('[+] Possible entry point: {0}.pyc'.format(entry.name))
if self.pycMagic == b'\0' * 4:
# if we don't have the pyc header yet, fix them in a later pass
self.barePycList.append(entry.name + '.pyc')
self._writePyc(entry.name + '.pyc', data)
elif entry.typeCmprsData == b'M' or entry.typeCmprsData == b'm':
# M -> ARCHIVE_ITEM_PYPACKAGE
# m -> ARCHIVE_ITEM_PYMODULE
# packages and modules are pyc files with their header intact
# From PyInstaller 5.3 and above pyc headers are no longer stored
# https://github.com/pyinstaller/pyinstaller/commit/a97fdf
if data[2:4] == b'\r\n':
# < pyinstaller 5.3
if self.pycMagic == b'\0' * 4:
self.pycMagic = data[0:4]
self._writeRawData(entry.name + '.pyc', data)
else:
# >= pyinstaller 5.3
if self.pycMagic == b'\0' * 4:
# if we don't have the pyc header yet, fix them in a later pass
self.barePycList.append(entry.name + '.pyc')
self._writePyc(entry.name + '.pyc', data)
else:
self._writeRawData(entry.name, data)
if entry.typeCmprsData == b'z' or entry.typeCmprsData == b'Z':
self._extractPyz(entry.name)
# Fix bare pyc's if any
self._fixBarePycs()
def _fixBarePycs(self):
for pycFile in self.barePycList:
with open(pycFile, 'r+b') as pycFile:
# Overwrite the first four bytes
pycFile.write(self.pycMagic)
def _writePyc(self, filename, data):
with open(filename, 'wb') as pycFile:
pycFile.write(self.pycMagic) # pyc magic
if self.pymaj >= 3 and self.pymin >= 7: # PEP 552 -- Deterministic pycs
pycFile.write(b'\0' * 4) # Bitfield
pycFile.write(b'\0' * 8) # (Timestamp + size) || hash
else:
pycFile.write(b'\0' * 4) # Timestamp
if self.pymaj >= 3 and self.pymin >= 3:
pycFile.write(b'\0' * 4) # Size parameter added in Python 3.3
pycFile.write(data)
def _extractPyz(self, name):
dirName = name + '_extracted'
# Create a directory for the contents of the pyz
if not os.path.exists(dirName):
os.mkdir(dirName)
with open(name, 'rb') as f:
pyzMagic = f.read(4)
assert pyzMagic == b'PYZ\0' # Sanity Check
pyzPycMagic = f.read(4) # Python magic value
if self.pycMagic == b'\0' * 4:
self.pycMagic = pyzPycMagic
elif self.pycMagic != pyzPycMagic:
self.pycMagic = pyzPycMagic
print('[!] Warning: pyc magic of files inside PYZ archive are different from those in CArchive')
# Skip PYZ extraction if not running under the same python version
if self.pymaj != sys.version_info.major or self.pymin != sys.version_info.minor:
print(
'[!] Warning: This script is running in a different Python version than the one used to build the executable.')
print(
'[!] Please run this script in Python {0}.{1} to prevent extraction errors during unmarshalling'.format(
self.pymaj, self.pymin))
print('[!] Skipping pyz extraction')
return
(tocPosition,) = struct.unpack('!i', f.read(4))
f.seek(tocPosition, os.SEEK_SET)
try:
toc = marshal.load(f)
except:
print('[!] Unmarshalling FAILED. Cannot extract {0}. Extracting remaining files.'.format(name))
return
print('[+] Found {0} files in PYZ archive'.format(len(toc)))
# From pyinstaller 3.1+ toc is a list of tuples
if type(toc) == list:
toc = dict(toc)
for key in toc.keys():
(ispkg, pos, length) = toc[key]
f.seek(pos, os.SEEK_SET)
fileName = key
try:
# for Python > 3.3 some keys are bytes object some are str object
fileName = fileName.decode('utf-8')
except:
pass
# Prevent writing outside dirName
fileName = fileName.replace('..', '__').replace('.', os.path.sep)
if ispkg == 1:
filePath = os.path.join(dirName, fileName, '__init__.pyc')
else:
filePath = os.path.join(dirName, fileName + '.pyc')
fileDir = os.path.dirname(filePath)
if not os.path.exists(fileDir):
os.makedirs(fileDir)
try:
data = f.read(length)
data = zlib.decompress(data)
except:
print('[!] Error: Failed to decompress {0}, probably encrypted. Extracting as is.'.format(filePath))
open(filePath + '.encrypted', 'wb').write(data)
else:
self._writePyc(filePath, data)
def main():
if len(sys.argv) < 2:
print('[+] Usage: pyinstxtractor.py <filename>')
else:
arch = PyInstArchive(sys.argv[1])
if arch.open():
if arch.checkFile():
if arch.getCArchiveInfo():
arch.parseTOC()
arch.extractFiles()
arch.close()
print('[+] Successfully extracted pyinstaller archive: {0}'.format(sys.argv[1]))
print('')
print('You can now use a python decompiler on the pyc files within the extracted directory')
return
arch.close()
import subprocess,os,concurrent.futures
def handle(filePath):
try:
# 定义要执行的命令
command = "uncompyle6 {} >{}".format(filePath, filePath.replace('pyc', 'py'))
# 使用subprocess模块执行命令
process = subprocess.Popen(command, shell=True)
process.wait() # 等待命令执行完成
print(command)
os.remove(filePath)
return True
except Exception as e:
print(e)
return False
def excutor():
print('检查是否已安装uncompyle6')
# 检查是否已安装uncompyle6
try:
subprocess.check_output(['uncompyle6', '--version'])
print("uncompyle6 is already installed.")
except (subprocess.CalledProcessError,FileNotFoundError):
print("uncompyle6 is not installed. Installing...")
subprocess.call(['pip', 'install', 'uncompyle6'])
currentPath=os.path.dirname(os.path.abspath(__file__))
targe=os.path.basename(sys.argv[1])
print('解包完成，开始反编译')
targeDir=os.path.join(currentPath,targe+'_extracted')
with concurrent.futures.ThreadPoolExecutor(max_workers=8) as excutor:
futures=[]
for root,dirs,files in os.walk(targeDir):
for file in files:
filePath=os.path.join(root,file)
if filePath.endswith('pyc'):
task =excutor.submit(handle,filePath)
futures.append(task)
for future in concurrent.futures.as_completed(futures):
ret=future.result()
if __name__ == '__main__':
main()
excutor()
使用
将pyinstxtractorV2.py文件与待处理的exe文件放置在同一目录并执行：
示例：python .\pyinstxtractorV2.py .\manager232.exe
声明
本文内容仅代表作者观点，或转载于其他网站，本站不以此文作为商业用途
如有涉及侵权，请联系本站进行删除
转载本站原创文章，请注明来源及作者。