Refactoring.

ExtensionCrawler/crx.py

@@ -1,7 +1,7 @@
 #!/usr/bin/env python3
 #
 # Copyright (C) 2016,2017 The University of Sheffield, UK
-# 
+#
 # This program is free software: you can redistribute it and/or modify
 # it under the terms of the GNU General Public License as published by
 # the Free Software Foundation, either version 3 of the License, or
@@ -13,20 +13,20 @@
 # GNU General Public License for more details.
 #
 # You should have received a copy of the GNU General Public License
-# along with this program.  If not, see <http://www.gnu.org/licenses/>.
+# along with this program.  If not, see <https://www.gnu.org/licenses/>.
 #
+"""Utility functions for working with Chrome extensionsx archives,
+   i.e., *.crx files."""
 
+import io
+import zipfile
 import binascii
-
 from Crypto.PublicKey import RSA
 from Crypto.Hash import SHA
 from Crypto.Signature import PKCS1_v1_5
 
-import zipfile
-import io
-
-
 class CrxFile:
+    """Record class for storing crx files."""
     def __init__(self, filename, magic, version, pk_len, sig_len, pk, sig,
                  header_len, data):
         self.file = filename
@@ -41,11 +41,12 @@ class CrxFile:
 
 
 def is_valid_magic(magic):
-    return (b'Cr24' == magic)
+    """Check magic matches the magic bytes of the crx specificaton."""
+    return magic == b'Cr24'
 
 
 def is_crxfile(filename):
-    "Check magic number: crx files should start with \"Cr24\"."
+    """Check magic number: crx files should start with \"Cr24\"."""
     file = open(filename, 'rb')
     magic = file.read(4)
     file.close()
@@ -53,13 +54,14 @@ def is_crxfile(filename):
 
 
 def check_signature(pk, sig, data):
+    """Check validity of signature contained in the crx file."""
     key = RSA.importKey(pk)
-    hash = SHA.new(data)
-    return PKCS1_v1_5.new(key).verify(hash, sig)
+    crxhash = SHA.new(data)
+    return PKCS1_v1_5.new(key).verify(crxhash, sig)
 
 
 def read_crx(filename):
-    "Read header of an crx file (https://developer.chrome.com/extensions/crx)."
+    """Read header of an crx file (https://developer.chrome.com/extensions/crx)."""
     file = open(filename, 'rb')
     magic = file.read(4)
     version = int.from_bytes(file.read(4), byteorder='little')
@@ -75,6 +77,7 @@ def read_crx(filename):
 
 
 def print_crx_info(verbose, crx):
+    """Print information extracted from a crx file."""
     if is_valid_magic(crx.magic):
         magic = "valid"
     else:
@@ -96,15 +99,16 @@ def print_crx_info(verbose, crx):
     if verbose:
         print("Signature [" + str(crx.sig_len) + "]: " + str(
             binascii.hexlify(crx.sig)))
-    out = f = io.BytesIO(crx.data)
-    zf = zipfile.ZipFile(out, 'r')
+    out = io.BytesIO(crx.data)
+    ziparchive = zipfile.ZipFile(out, 'r')
     print("Zip content:")
-    for info in zf.infolist():
+    for info in ziparchive.infolist():
         print('{:8d} {:8d}'.format(info.file_size, info.compress_size),
               info.filename)
 
 
 def verify_crxfile(verbose, filename):
+    """Verify integrity of a crx file."""
     if is_crxfile(filename):
         if verbose:
             print("Found correct magic bytes.")
@@ -117,17 +121,21 @@ def verify_crxfile(verbose, filename):
 
 
 def extract_crxfile(verbose, force, filename, destdir):
+    """Extract crxfile into specified destdir."""
     crx = read_crx(filename)
     if is_valid_magic(crx.magic) | force:
-        if ("" == destdir) | (destdir is None):
+        if (destdir == "") | (destdir is None):
             destdir = "."
         if filename.endswith(".crx"):
             dirname = filename[0:len(filename) - 4]
         else:
             dirname = filename
-        out = f = io.BytesIO(crx.data)
-        zf = zipfile.ZipFile(out, 'r')
-        zf.extractall(destdir + "/" + dirname)
-        print("Content extracted into: " + destdir + "/" + dirname)
+        out = io.BytesIO(crx.data)
+        ziparchive = zipfile.ZipFile(out, 'r')
+        ziparchive.extractall(destdir + "/" + dirname)
+        if verbose:
+            print("Content extracted into: " + destdir + "/" + dirname)
+        return 0
     else:
         print("Input file not valid.")
+        return -1

crx-tool

@@ -1,7 +1,7 @@
 #!/usr/bin/env python3
 #
 # Copyright (C) 2016 The University of Sheffield, UK
-# 
+#
 # This program is free software: you can redistribute it and/or modify
 # it under the terms of the GNU General Public License as published by
 # the Free Software Foundation, either version 3 of the License, or
@@ -15,11 +15,15 @@
 # You should have received a copy of the GNU General Public License
 # along with this program.  If not, see <http://www.gnu.org/licenses/>.
 #
+""" A tool for analyzing and extracting `*.crx` files
+    (i.e., Chrome extensions)."""
 
 import argparse
-from ExtensionCrawler.crx import *
+from ExtensionCrawler.crx import extract_crxfile, verify_crxfile
+
 
 def main():
+    """Main function of the extension crawler."""
     parser = argparse.ArgumentParser()
     parser.add_argument("file", help="chrome extension archive (*.crx)")
     parser.add_argument('targetdir', nargs='?', default="")