encrypted files in Python?
OpenSSL provides a popular (but insecure – see below!) command line interface for AES encryption:
openssl aes-256-cbc -salt -in filename -out filename.enc
Python has support for AES in the shape of the PyCrypto package, but it only provides the tools. How to use Python/PyCrypto to decrypt files that have been encrypted using OpenSSL?
Notice
This question used to also concern encryption in Python using the same scheme. I have since removed that part to discourage anyone from using it. Do NOT encrypt any more data in this way, because it is NOT secure by today's standards. You should ONLY use decryption, for no other reasons than BACKWARD COMPATIBILITY, ie when you have no other choice. Want to encrypt? Use NaCl/libsodium if you possibly can.
Given the popularity of Python, at first I was disappointed that there was no complete answer to this question to be found. It took me a fair amount of reading different answers on this board, as well as other resources, to get it right. I thought I might share the result for future reference and perhaps review; I'm by no means a cryptography expert! However, the code below appears to work seamlessly:
from hashlib import md5
from Crypto.Cipher import AES
from Crypto import Random
def derive_key_and_iv(password, salt, key_length, iv_length):
d = d_i = ''
while len(d) < key_length + iv_length:
d_i = md5(d_i + password + salt).digest()
d += d_i
return d[:key_length], d[key_length:key_length+iv_length]
def decrypt(in_file, out_file, password, key_length=32):
bs = AES.block_size
salt = in_file.read(bs)[len('Salted__'):]
key, iv = derive_key_and_iv(password, salt, key_length, bs)
cipher = AES.new(key, AES.MODE_CBC, iv)
next_chunk = ''
finished = False
while not finished:
chunk, next_chunk = next_chunk, cipher.decrypt(in_file.read(1024 * bs))
if len(next_chunk) == 0:
padding_length = ord(chunk[-1])
chunk = chunk[:-padding_length]
finished = True
out_file.write(chunk)
Usage:
with open(in_filename, 'rb') as in_file, open(out_filename, 'wb') as out_file:
decrypt(in_file, out_file, password)
If you see a chance to improve on this or extend it to be more flexible (eg make it work without salt, or provide Python 3 compatibility), please feel free to do so.
Notice
This answer used to also concern encryption in Python using the same scheme. I have since removed that part to discourage anyone from using it. Do NOT encrypt any more data in this way, because it is NOT secure by today's standards. You should ONLY use decryption, for no other reasons than BACKWARD COMPATIBILITY, ie when you have no other choice. Want to encrypt? Use NaCl/libsodium if you possibly can.
I am re-posting your code with a couple of corrections (I didn't want to obscure your version). While your code works, it does not detect some errors around padding. In particular, if the decryption key provided is incorrect, your padding logic may do something odd. If you agree with my change, you may update your solution.
from hashlib import md5
from Crypto.Cipher import AES
from Crypto import Random
def derive_key_and_iv(password, salt, key_length, iv_length):
d = d_i = ''
while len(d) < key_length + iv_length:
d_i = md5(d_i + password + salt).digest()
d += d_i
return d[:key_length], d[key_length:key_length+iv_length]
# This encryption mode is no longer secure by today's standards.
# See note in original question above.
def obsolete_encrypt(in_file, out_file, password, key_length=32):
bs = AES.block_size
salt = Random.new().read(bs - len('Salted__'))
key, iv = derive_key_and_iv(password, salt, key_length, bs)
cipher = AES.new(key, AES.MODE_CBC, iv)
out_file.write('Salted__' + salt)
finished = False
while not finished:
chunk = in_file.read(1024 * bs)
if len(chunk) == 0 or len(chunk) % bs != 0:
padding_length = bs - (len(chunk) % bs)
chunk += padding_length * chr(padding_length)
finished = True
out_file.write(cipher.encrypt(chunk))
def decrypt(in_file, out_file, password, key_length=32):
bs = AES.block_size
salt = in_file.read(bs)[len('Salted__'):]
key, iv = derive_key_and_iv(password, salt, key_length, bs)
cipher = AES.new(key, AES.MODE_CBC, iv)
next_chunk = ''
finished = False
while not finished:
chunk, next_chunk = next_chunk, cipher.decrypt(in_file.read(1024 * bs))
if len(next_chunk) == 0:
padding_length = ord(chunk[-1])
if padding_length < 1 or padding_length > bs:
raise ValueError("bad decrypt pad (%d)" % padding_length)
# all the pad-bytes must be the same
if chunk[-padding_length:] != (padding_length * chr(padding_length)):
# this is similar to the bad decrypt:evp_enc.c from openssl program
raise ValueError("bad decrypt")
chunk = chunk[:-padding_length]
finished = True
out_file.write(chunk)
The code below should be Python 3 compatible with the small changes documented in the code. Also wanted to use os.urandom instead of Crypto.Random. 'Salted__' is replaced with salt_header that can be tailored or left empty if needed.
from os import urandom
from hashlib import md5
from Crypto.Cipher import AES
def derive_key_and_iv(password, salt, key_length, iv_length):
d = d_i = b'' # changed '' to b''
while len(d) < key_length + iv_length:
# changed password to str.encode(password)
d_i = md5(d_i + str.encode(password) + salt).digest()
d += d_i
return d[:key_length], d[key_length:key_length+iv_length]
def encrypt(in_file, out_file, password, salt_header='', key_length=32):
# added salt_header=''
bs = AES.block_size
# replaced Crypt.Random with os.urandom
salt = urandom(bs - len(salt_header))
key, iv = derive_key_and_iv(password, salt, key_length, bs)
cipher = AES.new(key, AES.MODE_CBC, iv)
# changed 'Salted__' to str.encode(salt_header)
out_file.write(str.encode(salt_header) + salt)
finished = False
while not finished:
chunk = in_file.read(1024 * bs)
if len(chunk) == 0 or len(chunk) % bs != 0:
padding_length = (bs - len(chunk) % bs) or bs
# changed right side to str.encode(...)
chunk += str.encode(
padding_length * chr(padding_length))
finished = True
out_file.write(cipher.encrypt(chunk))
def decrypt(in_file, out_file, password, salt_header='', key_length=32):
# added salt_header=''
bs = AES.block_size
# changed 'Salted__' to salt_header
salt = in_file.read(bs)[len(salt_header):]
key, iv = derive_key_and_iv(password, salt, key_length, bs)
cipher = AES.new(key, AES.MODE_CBC, iv)
next_chunk = ''
finished = False
while not finished:
chunk, next_chunk = next_chunk, cipher.decrypt(
in_file.read(1024 * bs))
if len(next_chunk) == 0:
padding_length = chunk[-1] # removed ord(...) as unnecessary
chunk = chunk[:-padding_length]
finished = True
out_file.write(bytes(x for x in chunk)) # changed chunk to bytes(...)
上一篇: Google AnalyticsSDK是否使用SSL？
下一篇: Python中的加密文件？