Open encrypted PDF file by trying passwords from a word list
$begingroup$
As an exercise, I wrote a program to decrypt a PDF file. The only thing that is known about the encryption password is that it is a single English word (all capital or lowercase).
The program uses a dictionary file containing over 45000 words to unlock the file. It looks like this:
dictionary.txt
AARHUS
AARON
ABABA
ABACK
ABAFT
ABANDON
ABANDONED
ABANDONING
ABANDONMENT
ABANDONS
ABASE
ABASED
ABASEMENT
ABASEMENTS
ABASES
ABASH
ABASHED
ABASHES
⋮
ZEROTH
ZEST
ZEUS
ZIEGFELD
ZIEGFELDS
ZIEGLER
ZIGGY
ZIGZAG
ZILLIONS
ZIMMERMAN
ZINC
ZION
ZIONISM
ZIONIST
ZIONISTS
ZIONS
ZODIAC
ZOE
ZOMBA
ZONAL
ZONALLY
ZONE
ZONED
ZONES
ZONING
ZOO
ZOOLOGICAL
ZOOLOGICALLY
ZOOM
ZOOMS
ZOOS
ZORN
ZOROASTER
ZOROASTRIAN
ZULU
ZULUS
ZURICH
pdf_password_breaker
"""
Brute force password breaker using a dictionary containing
English words.
"""
import sys
import PyPDF2
from pathlib import Path
def get_filename_from_user() -> Path:
"""Asks for a path from the User"""
while True:
filename: str = input("Enter filename in folder of script:")
path: Path = Path(sys.path[0], filename)
if path.is_file():
return path.as_posix()
print("File doesn't existn")
def decrypt(pdf_filename: Path, password: str) -> bool:
"""
Try to decrypt a file. If not successful a false is returned.
If the file passed is not encrypted also a false is passed
"""
with open(pdf_filename, 'rb') as pdf_file:
pdf_reader = PyPDF2.PdfFileReader(pdf_file)
pdf_reader.decrypt(password)
pdf_writer = PyPDF2.PdfFileWriter()
try:
for page_number in range(pdf_reader.numPages):
pdf_writer.addPage(pdf_reader.getPage(page_number))
except PyPDF2.utils.PdfReadError:
return False
new_name: str = pdf_filename.stem + "_decrypted.pdf"
filename_decrypted = pdf_filename.parent / new_name
with open(filename_decrypted, 'wb') as pdf_file_decrypted:
pdf_writer.write(pdf_file_decrypted)
return True
def break_encryption(pdf_filename: Path, dictionary_filename: str) -> bool:
"""Try's out words from a dictionary to break encryption"""
with open(dictionary_filename, 'r') as dictionary_file:
keyword: str = dictionary_file.readline().strip()
if decrypt(pdf_filename, keyword):
return keyword
if decrypt(pdf_filename, keyword.lower()):
return keyword.lower()
while keyword:
keyword = dictionary_file.readline().strip()
if decrypt(pdf_filename, keyword):
return keyword
if decrypt(pdf_filename, keyword.lower()):
return keyword.lower()
return None
def pdf_password_breaker():
"""main loop"""
filename: Path = get_filename_from_user()
password: str = break_encryption(filename, "dictionary.txt")
if password:
print("File unlocked. Password was:" + password)
return
print("File could not be unlocked")
if __name__ == "__main__":
pdf_password_breaker()
I tried a file with a simple password like "hello". It works but it takes a lot of time until it reaches the "hello" in the file.
I wonder if theres a way to improve the speed, or any other aspect of the code.
python performance beginner pdf
$endgroup$
add a comment |
$begingroup$
As an exercise, I wrote a program to decrypt a PDF file. The only thing that is known about the encryption password is that it is a single English word (all capital or lowercase).
The program uses a dictionary file containing over 45000 words to unlock the file. It looks like this:
dictionary.txt
AARHUS
AARON
ABABA
ABACK
ABAFT
ABANDON
ABANDONED
ABANDONING
ABANDONMENT
ABANDONS
ABASE
ABASED
ABASEMENT
ABASEMENTS
ABASES
ABASH
ABASHED
ABASHES
⋮
ZEROTH
ZEST
ZEUS
ZIEGFELD
ZIEGFELDS
ZIEGLER
ZIGGY
ZIGZAG
ZILLIONS
ZIMMERMAN
ZINC
ZION
ZIONISM
ZIONIST
ZIONISTS
ZIONS
ZODIAC
ZOE
ZOMBA
ZONAL
ZONALLY
ZONE
ZONED
ZONES
ZONING
ZOO
ZOOLOGICAL
ZOOLOGICALLY
ZOOM
ZOOMS
ZOOS
ZORN
ZOROASTER
ZOROASTRIAN
ZULU
ZULUS
ZURICH
pdf_password_breaker
"""
Brute force password breaker using a dictionary containing
English words.
"""
import sys
import PyPDF2
from pathlib import Path
def get_filename_from_user() -> Path:
"""Asks for a path from the User"""
while True:
filename: str = input("Enter filename in folder of script:")
path: Path = Path(sys.path[0], filename)
if path.is_file():
return path.as_posix()
print("File doesn't existn")
def decrypt(pdf_filename: Path, password: str) -> bool:
"""
Try to decrypt a file. If not successful a false is returned.
If the file passed is not encrypted also a false is passed
"""
with open(pdf_filename, 'rb') as pdf_file:
pdf_reader = PyPDF2.PdfFileReader(pdf_file)
pdf_reader.decrypt(password)
pdf_writer = PyPDF2.PdfFileWriter()
try:
for page_number in range(pdf_reader.numPages):
pdf_writer.addPage(pdf_reader.getPage(page_number))
except PyPDF2.utils.PdfReadError:
return False
new_name: str = pdf_filename.stem + "_decrypted.pdf"
filename_decrypted = pdf_filename.parent / new_name
with open(filename_decrypted, 'wb') as pdf_file_decrypted:
pdf_writer.write(pdf_file_decrypted)
return True
def break_encryption(pdf_filename: Path, dictionary_filename: str) -> bool:
"""Try's out words from a dictionary to break encryption"""
with open(dictionary_filename, 'r') as dictionary_file:
keyword: str = dictionary_file.readline().strip()
if decrypt(pdf_filename, keyword):
return keyword
if decrypt(pdf_filename, keyword.lower()):
return keyword.lower()
while keyword:
keyword = dictionary_file.readline().strip()
if decrypt(pdf_filename, keyword):
return keyword
if decrypt(pdf_filename, keyword.lower()):
return keyword.lower()
return None
def pdf_password_breaker():
"""main loop"""
filename: Path = get_filename_from_user()
password: str = break_encryption(filename, "dictionary.txt")
if password:
print("File unlocked. Password was:" + password)
return
print("File could not be unlocked")
if __name__ == "__main__":
pdf_password_breaker()
I tried a file with a simple password like "hello". It works but it takes a lot of time until it reaches the "hello" in the file.
I wonder if theres a way to improve the speed, or any other aspect of the code.
python performance beginner pdf
$endgroup$
add a comment |
$begingroup$
As an exercise, I wrote a program to decrypt a PDF file. The only thing that is known about the encryption password is that it is a single English word (all capital or lowercase).
The program uses a dictionary file containing over 45000 words to unlock the file. It looks like this:
dictionary.txt
AARHUS
AARON
ABABA
ABACK
ABAFT
ABANDON
ABANDONED
ABANDONING
ABANDONMENT
ABANDONS
ABASE
ABASED
ABASEMENT
ABASEMENTS
ABASES
ABASH
ABASHED
ABASHES
⋮
ZEROTH
ZEST
ZEUS
ZIEGFELD
ZIEGFELDS
ZIEGLER
ZIGGY
ZIGZAG
ZILLIONS
ZIMMERMAN
ZINC
ZION
ZIONISM
ZIONIST
ZIONISTS
ZIONS
ZODIAC
ZOE
ZOMBA
ZONAL
ZONALLY
ZONE
ZONED
ZONES
ZONING
ZOO
ZOOLOGICAL
ZOOLOGICALLY
ZOOM
ZOOMS
ZOOS
ZORN
ZOROASTER
ZOROASTRIAN
ZULU
ZULUS
ZURICH
pdf_password_breaker
"""
Brute force password breaker using a dictionary containing
English words.
"""
import sys
import PyPDF2
from pathlib import Path
def get_filename_from_user() -> Path:
"""Asks for a path from the User"""
while True:
filename: str = input("Enter filename in folder of script:")
path: Path = Path(sys.path[0], filename)
if path.is_file():
return path.as_posix()
print("File doesn't existn")
def decrypt(pdf_filename: Path, password: str) -> bool:
"""
Try to decrypt a file. If not successful a false is returned.
If the file passed is not encrypted also a false is passed
"""
with open(pdf_filename, 'rb') as pdf_file:
pdf_reader = PyPDF2.PdfFileReader(pdf_file)
pdf_reader.decrypt(password)
pdf_writer = PyPDF2.PdfFileWriter()
try:
for page_number in range(pdf_reader.numPages):
pdf_writer.addPage(pdf_reader.getPage(page_number))
except PyPDF2.utils.PdfReadError:
return False
new_name: str = pdf_filename.stem + "_decrypted.pdf"
filename_decrypted = pdf_filename.parent / new_name
with open(filename_decrypted, 'wb') as pdf_file_decrypted:
pdf_writer.write(pdf_file_decrypted)
return True
def break_encryption(pdf_filename: Path, dictionary_filename: str) -> bool:
"""Try's out words from a dictionary to break encryption"""
with open(dictionary_filename, 'r') as dictionary_file:
keyword: str = dictionary_file.readline().strip()
if decrypt(pdf_filename, keyword):
return keyword
if decrypt(pdf_filename, keyword.lower()):
return keyword.lower()
while keyword:
keyword = dictionary_file.readline().strip()
if decrypt(pdf_filename, keyword):
return keyword
if decrypt(pdf_filename, keyword.lower()):
return keyword.lower()
return None
def pdf_password_breaker():
"""main loop"""
filename: Path = get_filename_from_user()
password: str = break_encryption(filename, "dictionary.txt")
if password:
print("File unlocked. Password was:" + password)
return
print("File could not be unlocked")
if __name__ == "__main__":
pdf_password_breaker()
I tried a file with a simple password like "hello". It works but it takes a lot of time until it reaches the "hello" in the file.
I wonder if theres a way to improve the speed, or any other aspect of the code.
python performance beginner pdf
$endgroup$
As an exercise, I wrote a program to decrypt a PDF file. The only thing that is known about the encryption password is that it is a single English word (all capital or lowercase).
The program uses a dictionary file containing over 45000 words to unlock the file. It looks like this:
dictionary.txt
AARHUS
AARON
ABABA
ABACK
ABAFT
ABANDON
ABANDONED
ABANDONING
ABANDONMENT
ABANDONS
ABASE
ABASED
ABASEMENT
ABASEMENTS
ABASES
ABASH
ABASHED
ABASHES
⋮
ZEROTH
ZEST
ZEUS
ZIEGFELD
ZIEGFELDS
ZIEGLER
ZIGGY
ZIGZAG
ZILLIONS
ZIMMERMAN
ZINC
ZION
ZIONISM
ZIONIST
ZIONISTS
ZIONS
ZODIAC
ZOE
ZOMBA
ZONAL
ZONALLY
ZONE
ZONED
ZONES
ZONING
ZOO
ZOOLOGICAL
ZOOLOGICALLY
ZOOM
ZOOMS
ZOOS
ZORN
ZOROASTER
ZOROASTRIAN
ZULU
ZULUS
ZURICH
pdf_password_breaker
"""
Brute force password breaker using a dictionary containing
English words.
"""
import sys
import PyPDF2
from pathlib import Path
def get_filename_from_user() -> Path:
"""Asks for a path from the User"""
while True:
filename: str = input("Enter filename in folder of script:")
path: Path = Path(sys.path[0], filename)
if path.is_file():
return path.as_posix()
print("File doesn't existn")
def decrypt(pdf_filename: Path, password: str) -> bool:
"""
Try to decrypt a file. If not successful a false is returned.
If the file passed is not encrypted also a false is passed
"""
with open(pdf_filename, 'rb') as pdf_file:
pdf_reader = PyPDF2.PdfFileReader(pdf_file)
pdf_reader.decrypt(password)
pdf_writer = PyPDF2.PdfFileWriter()
try:
for page_number in range(pdf_reader.numPages):
pdf_writer.addPage(pdf_reader.getPage(page_number))
except PyPDF2.utils.PdfReadError:
return False
new_name: str = pdf_filename.stem + "_decrypted.pdf"
filename_decrypted = pdf_filename.parent / new_name
with open(filename_decrypted, 'wb') as pdf_file_decrypted:
pdf_writer.write(pdf_file_decrypted)
return True
def break_encryption(pdf_filename: Path, dictionary_filename: str) -> bool:
"""Try's out words from a dictionary to break encryption"""
with open(dictionary_filename, 'r') as dictionary_file:
keyword: str = dictionary_file.readline().strip()
if decrypt(pdf_filename, keyword):
return keyword
if decrypt(pdf_filename, keyword.lower()):
return keyword.lower()
while keyword:
keyword = dictionary_file.readline().strip()
if decrypt(pdf_filename, keyword):
return keyword
if decrypt(pdf_filename, keyword.lower()):
return keyword.lower()
return None
def pdf_password_breaker():
"""main loop"""
filename: Path = get_filename_from_user()
password: str = break_encryption(filename, "dictionary.txt")
if password:
print("File unlocked. Password was:" + password)
return
print("File could not be unlocked")
if __name__ == "__main__":
pdf_password_breaker()
I tried a file with a simple password like "hello". It works but it takes a lot of time until it reaches the "hello" in the file.
I wonder if theres a way to improve the speed, or any other aspect of the code.
python performance beginner pdf
python performance beginner pdf
edited Jan 16 at 22:37
200_success
129k15153415
129k15153415
asked Jan 16 at 17:25
Sandro4912Sandro4912
1,114221
1,114221
add a comment |
add a comment |
1 Answer
1
active
oldest
votes
$begingroup$
Looking at the documentation of PdfFileReader.decrypt It states that it return 0 if the file fails or 1 if it succeeds.
You can also use isEncrypted to check if the file was encrypted in the first place.
So you can turn the loop around. First open the pdf file see if it was encrypted at all and if so try to call decrypt
with every password in your dictionary.
$endgroup$
1
$begingroup$
And in doing that, only open the PDF file once - opening it twice for every password is a huge slow down.
$endgroup$
– The6P4C
Jan 16 at 23:38
$begingroup$
i tryed that approach. it got quite a bit faster. but to crack hello it still takes quite some time
$endgroup$
– Sandro4912
Jan 17 at 17:00
add a comment |
Your Answer
StackExchange.ifUsing("editor", function () {
return StackExchange.using("mathjaxEditing", function () {
StackExchange.MarkdownEditor.creationCallbacks.add(function (editor, postfix) {
StackExchange.mathjaxEditing.prepareWmdForMathJax(editor, postfix, [["\$", "\$"]]);
});
});
}, "mathjax-editing");
StackExchange.ifUsing("editor", function () {
StackExchange.using("externalEditor", function () {
StackExchange.using("snippets", function () {
StackExchange.snippets.init();
});
});
}, "code-snippets");
StackExchange.ready(function() {
var channelOptions = {
tags: "".split(" "),
id: "196"
};
initTagRenderer("".split(" "), "".split(" "), channelOptions);
StackExchange.using("externalEditor", function() {
// Have to fire editor after snippets, if snippets enabled
if (StackExchange.settings.snippets.snippetsEnabled) {
StackExchange.using("snippets", function() {
createEditor();
});
}
else {
createEditor();
}
});
function createEditor() {
StackExchange.prepareEditor({
heartbeatType: 'answer',
autoActivateHeartbeat: false,
convertImagesToLinks: false,
noModals: true,
showLowRepImageUploadWarning: true,
reputationToPostImages: null,
bindNavPrevention: true,
postfix: "",
imageUploader: {
brandingHtml: "Powered by u003ca class="icon-imgur-white" href="https://imgur.com/"u003eu003c/au003e",
contentPolicyHtml: "User contributions licensed under u003ca href="https://creativecommons.org/licenses/by-sa/3.0/"u003ecc by-sa 3.0 with attribution requiredu003c/au003e u003ca href="https://stackoverflow.com/legal/content-policy"u003e(content policy)u003c/au003e",
allowUrls: true
},
onDemand: true,
discardSelector: ".discard-answer"
,immediatelyShowMarkdownHelp:true
});
}
});
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
StackExchange.ready(
function () {
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fcodereview.stackexchange.com%2fquestions%2f211632%2fopen-encrypted-pdf-file-by-trying-passwords-from-a-word-list%23new-answer', 'question_page');
}
);
Post as a guest
Required, but never shown
1 Answer
1
active
oldest
votes
1 Answer
1
active
oldest
votes
active
oldest
votes
active
oldest
votes
$begingroup$
Looking at the documentation of PdfFileReader.decrypt It states that it return 0 if the file fails or 1 if it succeeds.
You can also use isEncrypted to check if the file was encrypted in the first place.
So you can turn the loop around. First open the pdf file see if it was encrypted at all and if so try to call decrypt
with every password in your dictionary.
$endgroup$
1
$begingroup$
And in doing that, only open the PDF file once - opening it twice for every password is a huge slow down.
$endgroup$
– The6P4C
Jan 16 at 23:38
$begingroup$
i tryed that approach. it got quite a bit faster. but to crack hello it still takes quite some time
$endgroup$
– Sandro4912
Jan 17 at 17:00
add a comment |
$begingroup$
Looking at the documentation of PdfFileReader.decrypt It states that it return 0 if the file fails or 1 if it succeeds.
You can also use isEncrypted to check if the file was encrypted in the first place.
So you can turn the loop around. First open the pdf file see if it was encrypted at all and if so try to call decrypt
with every password in your dictionary.
$endgroup$
1
$begingroup$
And in doing that, only open the PDF file once - opening it twice for every password is a huge slow down.
$endgroup$
– The6P4C
Jan 16 at 23:38
$begingroup$
i tryed that approach. it got quite a bit faster. but to crack hello it still takes quite some time
$endgroup$
– Sandro4912
Jan 17 at 17:00
add a comment |
$begingroup$
Looking at the documentation of PdfFileReader.decrypt It states that it return 0 if the file fails or 1 if it succeeds.
You can also use isEncrypted to check if the file was encrypted in the first place.
So you can turn the loop around. First open the pdf file see if it was encrypted at all and if so try to call decrypt
with every password in your dictionary.
$endgroup$
Looking at the documentation of PdfFileReader.decrypt It states that it return 0 if the file fails or 1 if it succeeds.
You can also use isEncrypted to check if the file was encrypted in the first place.
So you can turn the loop around. First open the pdf file see if it was encrypted at all and if so try to call decrypt
with every password in your dictionary.
answered Jan 16 at 17:31
ratchet freakratchet freak
11.9k1343
11.9k1343
1
$begingroup$
And in doing that, only open the PDF file once - opening it twice for every password is a huge slow down.
$endgroup$
– The6P4C
Jan 16 at 23:38
$begingroup$
i tryed that approach. it got quite a bit faster. but to crack hello it still takes quite some time
$endgroup$
– Sandro4912
Jan 17 at 17:00
add a comment |
1
$begingroup$
And in doing that, only open the PDF file once - opening it twice for every password is a huge slow down.
$endgroup$
– The6P4C
Jan 16 at 23:38
$begingroup$
i tryed that approach. it got quite a bit faster. but to crack hello it still takes quite some time
$endgroup$
– Sandro4912
Jan 17 at 17:00
1
1
$begingroup$
And in doing that, only open the PDF file once - opening it twice for every password is a huge slow down.
$endgroup$
– The6P4C
Jan 16 at 23:38
$begingroup$
And in doing that, only open the PDF file once - opening it twice for every password is a huge slow down.
$endgroup$
– The6P4C
Jan 16 at 23:38
$begingroup$
i tryed that approach. it got quite a bit faster. but to crack hello it still takes quite some time
$endgroup$
– Sandro4912
Jan 17 at 17:00
$begingroup$
i tryed that approach. it got quite a bit faster. but to crack hello it still takes quite some time
$endgroup$
– Sandro4912
Jan 17 at 17:00
add a comment |
Thanks for contributing an answer to Code Review Stack Exchange!
- Please be sure to answer the question. Provide details and share your research!
But avoid …
- Asking for help, clarification, or responding to other answers.
- Making statements based on opinion; back them up with references or personal experience.
Use MathJax to format equations. MathJax reference.
To learn more, see our tips on writing great answers.
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
StackExchange.ready(
function () {
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fcodereview.stackexchange.com%2fquestions%2f211632%2fopen-encrypted-pdf-file-by-trying-passwords-from-a-word-list%23new-answer', 'question_page');
}
);
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown