Created
November 10, 2011 17:16
-
-
Save 9b/1355460 to your computer and use it in GitHub Desktop.
Compare 3 PDFs and output matching hashes
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
__description__ = 'Analyzes Malicious PDF Object in Memory' | |
__author__ = 'Brandon Dixon' | |
__version__ = '1.0' | |
__date__ = '2011/11/07' | |
from object_builder import * | |
import simplejson as json | |
import optparse | |
import malobjclass | |
import codecs | |
#user defined actions here | |
def user_land(pdf): | |
if type(pdf) is not list: | |
for obj in pdf.objs: | |
if obj.stream_encoded_stream != None: | |
print str(obj.id) + "," + obj.stream_encoded_hash | |
else: | |
encoder_holder = [] | |
raw_holder = [] | |
for p in pdf: | |
print "[+] File Data" | |
print "\t[+] MD5 " + p.file_md5 | |
print "\t[+] Object Count " + str(len(p.objs)) | |
raw = [] | |
encoded = [] | |
for obj in p.objs: | |
if obj.stream_encoded_stream != None: | |
encoded.append(obj.stream_encoded_hash) | |
raw.append(obj.raw_hash) | |
encoder_holder.append(encoded) | |
raw_holder.append(raw) | |
matching_hashes = set(encoder_holder[0]) & set(encoder_holder[1]) & set(encoder_holder[2]) | |
print "[+] The following " + str(len(matching_hashes)) + " encoded stream hashes are shared" | |
for match in matching_hashes: | |
obj = p.get_object_by_hash(match,"encoded") | |
print match + " ID: " + str(obj.id) | |
matching_raw = set(raw_holder[0]) & set(raw_holder[1]) & set(raw_holder[2]) | |
print "[+] The following " + str(len(matching_raw)) + " raw hashes are shared" | |
for match in matching_raw: | |
obj = p.get_object_by_hash(match,"raw") | |
print match + " ID: " + str(obj.id) | |
def main(): | |
oParser = optparse.OptionParser(usage='usage: %prog [options]\n' + __description__, version='%prog ' + __version__) | |
oParser.add_option('-f', '--file', default='', type='string', help='file to build an object from') | |
oParser.add_option('-d', '--dir', default='', type='string', help='dir to build an object from') | |
(options, args) = oParser.parse_args() | |
if options.file: | |
output = build_obj(options.file) | |
pdf = malobjclass.jPdf(json.loads(output)) | |
user_land(pdf) | |
elif options.dir: | |
files = [] | |
pdfs = [] | |
dirlist = os.listdir(options.dir) | |
for fname in dirlist: | |
files.append(fname) | |
files.sort() | |
for file in files: | |
print "[+] Analyzing file " + file | |
output = build_obj(options.dir + file) | |
pdf = malobjclass.jPdf(json.loads(output)) | |
pdfs.append(pdf) | |
user_land(pdfs) | |
else: | |
oParser.print_help() | |
return | |
if __name__ == '__main__': | |
main() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment