Last active
December 20, 2015 01:49
-
-
Save bsmt/6052284 to your computer and use it in GitHub Desktop.
Demonstrate how to scrape ciphertext from http://homebrew.herokuapp.com/
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# python blah.py my plaintext here | |
# F3C3ECD09B3238CB8060C2AF55BFC31451FF8C8DA0B6A0FC876FFA54D6D72B9BE3CAD927F8 | |
# http://homebrew.herokuapp.com/?plaintext=my+plaintext+here | |
import requests | |
from HTMLParser import HTMLParser | |
from urllib import quote | |
import sys | |
CIPHER_URL = "http://homebrew.herokuapp.com/?plaintext={}" | |
def main(args): | |
plaintext = " ".join(args[1:]) | |
request_url = CIPHER_URL.format(quote(plaintext)) | |
r = requests.get(request_url) | |
if r.status_code == 200: | |
# all good | |
parser = CipherTextParser() | |
parser.get_ciphertext_data(r.text) | |
print(parser.ret) # <---- ciphertext | |
else: | |
print("failure") | |
class CipherTextParser(HTMLParser): | |
'''Parses the HTML from the website and returns the ciphertext. | |
Most of the useful code was stolen from | |
http://stackoverflow.com/questions/7204056/python-htmlparser | |
''' | |
def get_ciphertext_data(self, html, element="textarea", attr="disabled"): | |
self.tags = [] | |
self.element = element | |
self.attribute = attr | |
self.ret = "" # ciphertext will be placed here | |
self.feed(html) | |
def handle_starttag(self, tag, attrs): | |
self.tags.append((tag.lower(), attrs)) | |
def handle_endtag(self, tag): | |
self.tags.pop() | |
def handle_data(self, data): | |
element = self.tags[-1][0] # so bad | |
attributes = self.tags[-1][1] | |
if element == self.element and (u'disabled', None) in attributes: | |
self.ret = data | |
if __name__ == "__main__": | |
main(sys.argv) # " ".join(sys.argv[1:]) will be the plaintext |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
re.findall('[A-F0-9]{40,}', urllib2.urlopen('http://homebrew.herokuapp.com/?plaintext=' + plaintext).read())[-1]