Python vigenereHacker 程序失败 raw_input
Python vigenereHacker program fails with raw_input
[我已经发布过一次这个问题，但我没有包含必要的信息，我很抱歉，这是我第一次在 Stack overflow 上]
好的，我有 python2.7 和一本名为 python 的 Hacking secret ciphers 的 pdf 书，里面有这段代码：
import itertools, re
import vigenereCipher, pyperclip, freqAnalysis, detectEnglish
LETTERS = 'ABCDEFGHIJKLMNOPQRSTUVWXYZ'
SILENT_MODE = False # if set to True, program doesn't print attempts
NUM_MOST_FREQ_LETTERS = 4 # attempts this many letters per subkey
MAX_KEY_LENGTH = 16 # will not attempt keys longer than this
NONLETTERS_PATTERN = re.compile('[^A-Z]')
def main():
# Instead of typing this ciphertext out, you can copy & paste it
# from http://invpy.com/vigenereHacker.py
ciphertext = """Adiz Avtzqeci Tmzubb wsa m Pmilqev halpqavtakuoi, lgouqdaf, kdmktsvmztsl, izr xoexghzr kkusitaaf."""
hackedMessage = hackVigenere(ciphertext)
if hackedMessage != None:
print('Copying hacked message to clipboard:')
print(hackedMessage)
pyperclip.copy(hackedMessage)
else:
print('Failed to hack encryption.')
def findRepeatSequencesSpacings(message):
# Goes through the message and finds any 3 to 5 letter sequences
# that are repeated. Returns a dict with the keys of the sequence and
# values of a list of spacings (num of letters between the repeats).
# Use a regular expression to remove non-letters from the message.
message = NONLETTERS_PATTERN.sub('', message.upper())
# Compile a list of seqLen-letter sequences found in the message.
seqSpacings = {} # keys are sequences, values are list of int spacings
for seqLen in range(3, 6):
for seqStart in range(len(message) - seqLen):
# Determine what the sequence is, and store it in seq
seq = message[seqStart:seqStart + seqLen]
# Look for this sequence in the rest of the message
for i in range(seqStart + seqLen, len(message) - seqLen):
if message[i:i + seqLen] == seq:
# Found a repeated sequence.
if seq not in seqSpacings:
seqSpacings[seq] = [] # initialize blank list
# Append the spacing distance between the repeated
# sequence and the original sequence.
seqSpacings[seq].append(i - seqStart)
return seqSpacings
def getUsefulFactors(num):
# Returns a list of useful factors of num. By "useful" we mean factors
# less than MAX_KEY_LENGTH + 1. For example, getUsefulFactors(144)
# returns [2, 72, 3, 48, 4, 36, 6, 24, 8, 18, 9, 16, 12]
if num < 2:
return [] # numbers less than 2 have no useful factors
factors = [] # the list of factors found
# When finding factors, you only need to check the integers up to
# MAX_KEY_LENGTH.
for i in range(2, MAX_KEY_LENGTH + 1): # don't test 1
if num % i == 0:
factors.append(i)
factors.append(int(num / i))
if 1 in factors:
factors.remove(1)
return list(set(factors))
def getItemAtIndexOne(x):
return x[1]
def getMostCommonFactors(seqFactors):
# First, get a count of how many times a factor occurs in seqFactors.
factorCounts = {} # key is a factor, value is how often if occurs
# seqFactors keys are sequences, values are lists of factors of the
# spacings. seqFactors has a value like: {'GFD': [2, 3, 4, 6, 9, 12,
# 18, 23, 36, 46, 69, 92, 138, 207], 'ALW': [2, 3, 4, 6, ...], ...}
for seq in seqFactors:
factorList = seqFactors[seq]
for factor in factorList:
if factor not in factorCounts:
factorCounts[factor] = 0
factorCounts[factor] += 1
# Second, put the factor and its count into a tuple, and make a list
# of these tuples so we can sort them.
factorsByCount = []
for factor in factorCounts:
# exclude factors larger than MAX_KEY_LENGTH
if factor <= MAX_KEY_LENGTH:
# factorsByCount is a list of tuples: (factor, factorCount)
# factorsByCount has a value like: [(3, 497), (2, 487), ...]
factorsByCount.append( (factor, factorCounts[factor]) )
# Sort the list by the factor count.
factorsByCount.sort(key=getItemAtIndexOne, reverse=True)
return factorsByCount
def kasiskiExamination(ciphertext):
# Find out the sequences of 3 to 5 letters that occur multiple times
# in the ciphertext. repeatedSeqSpacings has a value like:
# {'EXG': [192], 'NAF': [339, 972, 633], ... }
repeatedSeqSpacings = findRepeatSequencesSpacings(ciphertext)
# See getMostCommonFactors() for a description of seqFactors.
seqFactors = {}
for seq in repeatedSeqSpacings:
seqFactors[seq] = []
for spacing in repeatedSeqSpacings[seq]:
seqFactors[seq].extend(getUsefulFactors(spacing))
# See getMostCommonFactors() for a description of factorsByCount.
factorsByCount = getMostCommonFactors(seqFactors)
# Now we extract the factor counts from factorsByCount and
# put them in allLikelyKeyLengths so that they are easier to
# use later.
allLikelyKeyLengths = []
for twoIntTuple in factorsByCount:
allLikelyKeyLengths.append(twoIntTuple[0])
return allLikelyKeyLengths
def getNthSubkeysLetters(n, keyLength, message):
# Returns every Nth letter for each keyLength set of letters in text.
# E.g. getNthSubkeysLetters(1, 3, 'ABCABCABC') returns 'AAA'
# getNthSubkeysLetters(2, 3, 'ABCABCABC') returns 'BBB'
# getNthSubkeysLetters(3, 3, 'ABCABCABC') returns 'CCC'
# getNthSubkeysLetters(1, 5, 'ABCDEFGHI') returns 'AF'
# Use a regular expression to remove non-letters from the message.
message = NONLETTERS_PATTERN.sub('', message)
i = n - 1
letters = []
while i < len(message):
letters.append(message[i])
i += keyLength
return ''.join(letters)
def attemptHackWithKeyLength(ciphertext, mostLikelyKeyLength):
# Determine the most likely letters for each letter in the key.
ciphertextUp = ciphertext.upper()
# allFreqScores is a list of mostLikelyKeyLength number of lists.
# These inner lists are the freqScores lists.
allFreqScores = []
for nth in range(1, mostLikelyKeyLength + 1):
nthLetters = getNthSubkeysLetters(nth, mostLikelyKeyLength, ciphertextUp)
# freqScores is a list of tuples like:
# [(<letter>, <Eng. Freq. match score>), ... ]
# List is sorted by match score. Higher score means better match.
# See the englishFreqMatchScore() comments in freqAnalysis.py.
freqScores = []
for possibleKey in LETTERS:
decryptedText = vigenereCipher.decryptMessage(possibleKey, nthLetters)
keyAndFreqMatchTuple = (possibleKey, freqAnalysis.englishFreqMatchScore(decryptedText))
freqScores.append(keyAndFreqMatchTuple)
# Sort by match score
freqScores.sort(key=getItemAtIndexOne, reverse=True)
allFreqScores.append(freqScores[:NUM_MOST_FREQ_LETTERS])
if not SILENT_MODE:
for i in range(len(allFreqScores)):
# use i + 1 so the first letter is not called the "0th" letter
print('Possible letters for letter %s of the key: ' % (i + 1))
for freqScore in allFreqScores[i]:
print('%s ' % freqScore[0])
print() # print a newline
# Try every combination of the most likely letters for each position
# in the key.
for indexes in itertools.product(range(NUM_MOST_FREQ_LETTERS), repeat=mostLikelyKeyLength):
# Create a possible key from the letters in allFreqScores
possibleKey = ''
for i in range(mostLikelyKeyLength):
possibleKey += allFreqScores[i][indexes[i]][0]
if not SILENT_MODE:
print('Attempting with key: %s' % (possibleKey))
decryptedText = vigenereCipher.decryptMessage(possibleKey, ciphertextUp)
if detectEnglish.isEnglish(decryptedText):
# Set the hacked ciphertext to the original casing.
origCase = []
for i in range(len(ciphertext)):
if ciphertext[i].isupper():
origCase.append(decryptedText[i].upper())
else:
origCase.append(decryptedText[i].lower())
decryptedText = ''.join(origCase)
# Check with user to see if the key has been found.
print('Possible encryption hack with key %s:' % (possibleKey))
print(decryptedText[:200]) # only show first 200 characters
print()
print('Enter D for done, or just press Enter to continue hacking:')
response = input('> ')
if response.strip().upper().startswith('D'):
return decryptedText
# No English-looking decryption found, so return None.
return None
def hackVigenere(ciphertext):
# First, we need to do Kasiski Examination to figure out what the
# length of the ciphertext's encryption key is.
allLikelyKeyLengths = kasiskiExamination(ciphertext)
if not SILENT_MODE:
keyLengthStr = ''
for keyLength in allLikelyKeyLengths:
keyLengthStr += '%s ' % (keyLength)
print('Kasiski Examination results say the most likely key lengths are: ' + keyLengthStr + '\n')
for keyLength in allLikelyKeyLengths:
if not SILENT_MODE:
print('Attempting hack with key length %s (%s possible keys)...' % (keyLength, NUM_MOST_FREQ_LETTERS ** keyLength))
hackedMessage = attemptHackWithKeyLength(ciphertext, keyLength)
if hackedMessage != None:
break
# If none of the key lengths we found using Kasiski Examination
# worked, start brute-forcing through key lengths.
if hackedMessage == None:
if not SILENT_MODE:
print('Unable to hack message with likely key length(s). Brute forcing key length...')
for keyLength in range(1, MAX_KEY_LENGTH + 1):
# don't re-check key lengths already tried from Kasiski
if keyLength not in allLikelyKeyLengths:
if not SILENT_MODE:
print('Attempting hack with key length %s (%s possible keys)...' % (keyLength, NUM_MOST_FREQ_LETTERS ** keyLength))
hackedMessage = attemptHackWithKeyLength(ciphertext, keyLength)
if hackedMessage != None:
break
return hackedMessage
# If vigenereHacker.py is run (instead of imported as a module) call
# the main() function.
if __name__ == '__main__':
main()
这个程序很好用，但每次都很难将消息复制到文件中，所以当我将 ciphertext = '''etc''' 更改为 ciphertext = raw_input("Message:") 我得到这个错误：
Message:eurbvrebv
Kasiski Examination results say the most likely key lengths are:
Traceback (most recent call last):
File "vigenereHacker.py", line 206, in <module>
main()
File "vigenereHacker.py", line 12, in main
hackedMessage = hackVigenere(ciphertext)
File "vigenereHacker.py", line 191, in hackVigenere
if hackedMessage == None:
UnboundLocalError: local variable 'hackedMessage' referenced before assignment
唯一的区别是 raw_input 用于密文。为什么会发生这种情况，我该如何解决？谢谢
这一行之前：
for keyLength in allLikelyKeyLengths:
你应该有一个：
hackedMessage == None
这是因为在行：
if hackedMessage == None:
您正在尝试使用从未初始化的变量。
[我已经发布过一次这个问题，但我没有包含必要的信息，我很抱歉，这是我第一次在 Stack overflow 上]
好的，我有 python2.7 和一本名为 python 的 Hacking secret ciphers 的 pdf 书，里面有这段代码：
import itertools, re
import vigenereCipher, pyperclip, freqAnalysis, detectEnglish
LETTERS = 'ABCDEFGHIJKLMNOPQRSTUVWXYZ'
SILENT_MODE = False # if set to True, program doesn't print attempts
NUM_MOST_FREQ_LETTERS = 4 # attempts this many letters per subkey
MAX_KEY_LENGTH = 16 # will not attempt keys longer than this
NONLETTERS_PATTERN = re.compile('[^A-Z]')
def main():
# Instead of typing this ciphertext out, you can copy & paste it
# from http://invpy.com/vigenereHacker.py
ciphertext = """Adiz Avtzqeci Tmzubb wsa m Pmilqev halpqavtakuoi, lgouqdaf, kdmktsvmztsl, izr xoexghzr kkusitaaf."""
hackedMessage = hackVigenere(ciphertext)
if hackedMessage != None:
print('Copying hacked message to clipboard:')
print(hackedMessage)
pyperclip.copy(hackedMessage)
else:
print('Failed to hack encryption.')
def findRepeatSequencesSpacings(message):
# Goes through the message and finds any 3 to 5 letter sequences
# that are repeated. Returns a dict with the keys of the sequence and
# values of a list of spacings (num of letters between the repeats).
# Use a regular expression to remove non-letters from the message.
message = NONLETTERS_PATTERN.sub('', message.upper())
# Compile a list of seqLen-letter sequences found in the message.
seqSpacings = {} # keys are sequences, values are list of int spacings
for seqLen in range(3, 6):
for seqStart in range(len(message) - seqLen):
# Determine what the sequence is, and store it in seq
seq = message[seqStart:seqStart + seqLen]
# Look for this sequence in the rest of the message
for i in range(seqStart + seqLen, len(message) - seqLen):
if message[i:i + seqLen] == seq:
# Found a repeated sequence.
if seq not in seqSpacings:
seqSpacings[seq] = [] # initialize blank list
# Append the spacing distance between the repeated
# sequence and the original sequence.
seqSpacings[seq].append(i - seqStart)
return seqSpacings
def getUsefulFactors(num):
# Returns a list of useful factors of num. By "useful" we mean factors
# less than MAX_KEY_LENGTH + 1. For example, getUsefulFactors(144)
# returns [2, 72, 3, 48, 4, 36, 6, 24, 8, 18, 9, 16, 12]
if num < 2:
return [] # numbers less than 2 have no useful factors
factors = [] # the list of factors found
# When finding factors, you only need to check the integers up to
# MAX_KEY_LENGTH.
for i in range(2, MAX_KEY_LENGTH + 1): # don't test 1
if num % i == 0:
factors.append(i)
factors.append(int(num / i))
if 1 in factors:
factors.remove(1)
return list(set(factors))
def getItemAtIndexOne(x):
return x[1]
def getMostCommonFactors(seqFactors):
# First, get a count of how many times a factor occurs in seqFactors.
factorCounts = {} # key is a factor, value is how often if occurs
# seqFactors keys are sequences, values are lists of factors of the
# spacings. seqFactors has a value like: {'GFD': [2, 3, 4, 6, 9, 12,
# 18, 23, 36, 46, 69, 92, 138, 207], 'ALW': [2, 3, 4, 6, ...], ...}
for seq in seqFactors:
factorList = seqFactors[seq]
for factor in factorList:
if factor not in factorCounts:
factorCounts[factor] = 0
factorCounts[factor] += 1
# Second, put the factor and its count into a tuple, and make a list
# of these tuples so we can sort them.
factorsByCount = []
for factor in factorCounts:
# exclude factors larger than MAX_KEY_LENGTH
if factor <= MAX_KEY_LENGTH:
# factorsByCount is a list of tuples: (factor, factorCount)
# factorsByCount has a value like: [(3, 497), (2, 487), ...]
factorsByCount.append( (factor, factorCounts[factor]) )
# Sort the list by the factor count.
factorsByCount.sort(key=getItemAtIndexOne, reverse=True)
return factorsByCount
def kasiskiExamination(ciphertext):
# Find out the sequences of 3 to 5 letters that occur multiple times
# in the ciphertext. repeatedSeqSpacings has a value like:
# {'EXG': [192], 'NAF': [339, 972, 633], ... }
repeatedSeqSpacings = findRepeatSequencesSpacings(ciphertext)
# See getMostCommonFactors() for a description of seqFactors.
seqFactors = {}
for seq in repeatedSeqSpacings:
seqFactors[seq] = []
for spacing in repeatedSeqSpacings[seq]:
seqFactors[seq].extend(getUsefulFactors(spacing))
# See getMostCommonFactors() for a description of factorsByCount.
factorsByCount = getMostCommonFactors(seqFactors)
# Now we extract the factor counts from factorsByCount and
# put them in allLikelyKeyLengths so that they are easier to
# use later.
allLikelyKeyLengths = []
for twoIntTuple in factorsByCount:
allLikelyKeyLengths.append(twoIntTuple[0])
return allLikelyKeyLengths
def getNthSubkeysLetters(n, keyLength, message):
# Returns every Nth letter for each keyLength set of letters in text.
# E.g. getNthSubkeysLetters(1, 3, 'ABCABCABC') returns 'AAA'
# getNthSubkeysLetters(2, 3, 'ABCABCABC') returns 'BBB'
# getNthSubkeysLetters(3, 3, 'ABCABCABC') returns 'CCC'
# getNthSubkeysLetters(1, 5, 'ABCDEFGHI') returns 'AF'
# Use a regular expression to remove non-letters from the message.
message = NONLETTERS_PATTERN.sub('', message)
i = n - 1
letters = []
while i < len(message):
letters.append(message[i])
i += keyLength
return ''.join(letters)
def attemptHackWithKeyLength(ciphertext, mostLikelyKeyLength):
# Determine the most likely letters for each letter in the key.
ciphertextUp = ciphertext.upper()
# allFreqScores is a list of mostLikelyKeyLength number of lists.
# These inner lists are the freqScores lists.
allFreqScores = []
for nth in range(1, mostLikelyKeyLength + 1):
nthLetters = getNthSubkeysLetters(nth, mostLikelyKeyLength, ciphertextUp)
# freqScores is a list of tuples like:
# [(<letter>, <Eng. Freq. match score>), ... ]
# List is sorted by match score. Higher score means better match.
# See the englishFreqMatchScore() comments in freqAnalysis.py.
freqScores = []
for possibleKey in LETTERS:
decryptedText = vigenereCipher.decryptMessage(possibleKey, nthLetters)
keyAndFreqMatchTuple = (possibleKey, freqAnalysis.englishFreqMatchScore(decryptedText))
freqScores.append(keyAndFreqMatchTuple)
# Sort by match score
freqScores.sort(key=getItemAtIndexOne, reverse=True)
allFreqScores.append(freqScores[:NUM_MOST_FREQ_LETTERS])
if not SILENT_MODE:
for i in range(len(allFreqScores)):
# use i + 1 so the first letter is not called the "0th" letter
print('Possible letters for letter %s of the key: ' % (i + 1))
for freqScore in allFreqScores[i]:
print('%s ' % freqScore[0])
print() # print a newline
# Try every combination of the most likely letters for each position
# in the key.
for indexes in itertools.product(range(NUM_MOST_FREQ_LETTERS), repeat=mostLikelyKeyLength):
# Create a possible key from the letters in allFreqScores
possibleKey = ''
for i in range(mostLikelyKeyLength):
possibleKey += allFreqScores[i][indexes[i]][0]
if not SILENT_MODE:
print('Attempting with key: %s' % (possibleKey))
decryptedText = vigenereCipher.decryptMessage(possibleKey, ciphertextUp)
if detectEnglish.isEnglish(decryptedText):
# Set the hacked ciphertext to the original casing.
origCase = []
for i in range(len(ciphertext)):
if ciphertext[i].isupper():
origCase.append(decryptedText[i].upper())
else:
origCase.append(decryptedText[i].lower())
decryptedText = ''.join(origCase)
# Check with user to see if the key has been found.
print('Possible encryption hack with key %s:' % (possibleKey))
print(decryptedText[:200]) # only show first 200 characters
print()
print('Enter D for done, or just press Enter to continue hacking:')
response = input('> ')
if response.strip().upper().startswith('D'):
return decryptedText
# No English-looking decryption found, so return None.
return None
def hackVigenere(ciphertext):
# First, we need to do Kasiski Examination to figure out what the
# length of the ciphertext's encryption key is.
allLikelyKeyLengths = kasiskiExamination(ciphertext)
if not SILENT_MODE:
keyLengthStr = ''
for keyLength in allLikelyKeyLengths:
keyLengthStr += '%s ' % (keyLength)
print('Kasiski Examination results say the most likely key lengths are: ' + keyLengthStr + '\n')
for keyLength in allLikelyKeyLengths:
if not SILENT_MODE:
print('Attempting hack with key length %s (%s possible keys)...' % (keyLength, NUM_MOST_FREQ_LETTERS ** keyLength))
hackedMessage = attemptHackWithKeyLength(ciphertext, keyLength)
if hackedMessage != None:
break
# If none of the key lengths we found using Kasiski Examination
# worked, start brute-forcing through key lengths.
if hackedMessage == None:
if not SILENT_MODE:
print('Unable to hack message with likely key length(s). Brute forcing key length...')
for keyLength in range(1, MAX_KEY_LENGTH + 1):
# don't re-check key lengths already tried from Kasiski
if keyLength not in allLikelyKeyLengths:
if not SILENT_MODE:
print('Attempting hack with key length %s (%s possible keys)...' % (keyLength, NUM_MOST_FREQ_LETTERS ** keyLength))
hackedMessage = attemptHackWithKeyLength(ciphertext, keyLength)
if hackedMessage != None:
break
return hackedMessage
# If vigenereHacker.py is run (instead of imported as a module) call
# the main() function.
if __name__ == '__main__':
main()
这个程序很好用，但每次都很难将消息复制到文件中，所以当我将 ciphertext = '''etc''' 更改为 ciphertext = raw_input("Message:") 我得到这个错误：
Message:eurbvrebv
Kasiski Examination results say the most likely key lengths are:
Traceback (most recent call last):
File "vigenereHacker.py", line 206, in <module>
main()
File "vigenereHacker.py", line 12, in main
hackedMessage = hackVigenere(ciphertext)
File "vigenereHacker.py", line 191, in hackVigenere
if hackedMessage == None:
UnboundLocalError: local variable 'hackedMessage' referenced before assignment
唯一的区别是 raw_input 用于密文。为什么会发生这种情况，我该如何解决？谢谢
这一行之前：
for keyLength in allLikelyKeyLengths:
你应该有一个：
hackedMessage == None
这是因为在行：
if hackedMessage == None:
您正在尝试使用从未初始化的变量。