Last active
March 1, 2021 21:21
-
-
Save rjzak/8293442 to your computer and use it in GitHub Desktop.
Search and Collect scrapes all the Windows executables (PE files) in a Windows system and copies the files into the destination directory. This is the Python version of the code at https://github.com/IOActive/SearchAndCollect.
This file contains hidden or 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
#!/usr/bin/python | |
import os, sys, hashlib, shutil | |
sha256 = lambda data: hashlib.sha256(data).hexdigest() | |
def searchAndCollect(src, dest): | |
print "Searching %s for .exe's, saving to %s" % (src, dest) | |
for dirpath, dirnames, filenames in os.walk(src): | |
if src in dirnames: | |
print "Skipping target directory." | |
continue | |
for filename in filenames: | |
try: | |
data = open(os.path.join(dirpath, fileName), 'rb').read() | |
if data[0:2] == 'MZ' or data[0:2] == 'ZM': | |
datahash = sha256(data) | |
try: | |
if not os.path.exists(os.path.join(dest, datahash)): | |
shutil.copy( os.path.join(dirpath, fileName), os.path.join(dest, datahash) ) | |
except Exception as e: | |
print "Error copying %s: %s" % (fileName, str(e)) | |
except Exception as e: | |
print "Error reading %s: %s" % (fileName, str(e)) | |
if __name__ == '__main__': | |
if len(sys.argv) != 3: | |
print "Usage: %s <SRC_DIR> <DEST_DIR>" % sys.argv[0] | |
print "SearchAndCollect, Python edition, 1.2" | |
print "Collects and Stores Windows executables in the destination directory by SHA-256 hash." | |
sys.exit(1) | |
searchAndCollect(sys.argv[1], sys.argv[2]) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Looks to me that you are missing a for cycle at line 15.
for fileName in filenames: