Added --max-size option to limit extracted file size.

src/bin/binwalk

@@ -110,9 +110,10 @@ def usage(fd):
 	fd.write("\t-D, --dd=<type:ext[:cmd]>     Extract <type> signatures, give the files an extension of <ext>, and execute <cmd>\n")
 	fd.write("\t-e, --extract=[file]          Automatically extract known file types; load rules from file, if specified\n")
 	fd.write("\t-M, --matryoshka=[n]          Recursively scan extracted files, up to n levels deep (8 levels of recursion is the default)\n")
+	fd.write("\t-j, --max-size=<int>          Limit extracted file sizes (default: infinite)\n")      
 	fd.write("\t-r, --rm                      Cleanup extracted files and zero-size files\n")
 	fd.write("\t-d, --honor-footers           Only extract files up to their corresponding footer signatures\n")
-	fd.write("\t-z, --carve                   Carve data from files, but don't execute extraction utilities (iplies -d)\n")
+	fd.write("\t-z, --carve                   Carve data from files, but don't execute extraction utilities (implies -d)\n")
 	fd.write("\n")
 
 	fd.write("Plugin Options:\n")
@@ -156,6 +157,7 @@ def main():
 	matryoshka = 1
 	block_size = 0
 	failed_open_count = 0
+	max_extract_size = None
 	quiet = False
 	do_comp = False
 	do_files = False
@@ -196,7 +198,7 @@ def main():
 
 	config = binwalk.Config()
 
-	short_options = "AaBbCcdEeGHhIiJkLMNnOPpQqrSTtUuvWwz?D:F:f:g:K:o:l:m:R:s:X:x:Y:y:"
+	short_options = "AaBbCcdEeGHhIiJkLMNnOPpQqrSTtUuvWwz?D:F:f:g:j:K:o:l:m:R:s:X:x:Y:y:"
 	long_options = [
 			"rm",
 			"help",
@@ -215,7 +217,6 @@ def main():
 			"show-invalid",
 			"ignore-time-skew",
 			"honor-footers",
-			"carve",
 			"profile",
 			"delay", # delay is depreciated, but kept for backwards compatability
 			"skip-unopened",
@@ -231,12 +232,14 @@ def main():
 			"save-plot",
 			"no-plot",
 			"no-legend", 
-			"matryoshka=",
 			"strings",
+			"carve",
+			"matryoshka=",
 			"list-plugins",
 			"disable-plugins",
 			"disable-plugin=",
 			"enable-plugin=",
+			"max-size=",
 			"marker=",
 			"strlen=",
 			"file=", 
@@ -342,6 +345,8 @@ def main():
 			ignore_time_skew = False
 		elif opt in ("-z", "--carve"):
 			exec_commands = False
+		elif opt in ("-j", "--max-size"):
+			max_extract_size = binwalk.common.str2int(arg)
 
 		elif opt in ("-H", "--heuristic", "--math"):
 			do_comp = True
@@ -467,7 +472,8 @@ def main():
 				ignore_smart_keywords=ignore_signature_keywords, 
 				load_plugins=enable_plugins, 
 				ignore_time_skews=ignore_time_skew, 
-				exec_commands=exec_commands)
+				exec_commands=exec_commands,
+				max_extract_size=max_extract_size)
 
 	# If a custom signature was specified, create a temporary magic file containing the custom signature
 	# and ensure that it is the only magic file that will be loaded when Binwalk.scan() is called.

src/binwalk/__init__.py

@@ -68,7 +68,7 @@ class Binwalk(object):
 	CUSTOM = 0x40
 	ENTROPY = 0x80
 
-	def __init__(self, magic_files=[], flags=magic.MAGIC_NONE, log=None, quiet=False, verbose=0, ignore_smart_keywords=False, ignore_time_skews=False, load_extractor=False, load_plugins=True, exec_commands=True):
+	def __init__(self, magic_files=[], flags=magic.MAGIC_NONE, log=None, quiet=False, verbose=0, ignore_smart_keywords=False, ignore_time_skews=False, load_extractor=False, load_plugins=True, exec_commands=True, max_extract_size=None):
 		'''
 		Class constructor.
 
@@ -82,6 +82,7 @@ class Binwalk(object):
 		@load_extractor         - Set to True to load the default extraction rules automatically.
 		@load_plugins           - Set to False to disable plugin support.
 		@exec_commands          - Set to False to disable the execution of external utilities when extracting data from files.
+		@max_extract_size       - Limit the size of extracted files.
 
 		Returns None.
 		'''
@@ -135,7 +136,7 @@ class Binwalk(object):
 		#	o Specify file extraction rules to be applied during a scan
 		#
 		self.filter = MagicFilter()
-		self.extractor = Extractor(verbose=extractor_verbose, exec_commands=exec_commands)
+		self.extractor = Extractor(verbose=extractor_verbose, exec_commands=exec_commands, max_size=max_extract_size)
 		if load_extractor:
 			self.extractor.load_defaults()
 

src/binwalk/extractor.py

@@ -45,12 +45,13 @@ class Extractor:
 	# Max size of data to read/write at one time when extracting data
 	MAX_READ_SIZE = 10 * 1024 * 1024
 
-	def __init__(self, verbose=False, exec_commands=True):
+	def __init__(self, verbose=False, exec_commands=True, max_size=None):
 		'''
 		Class constructor.
 	
 		@verbose       - Set to True to display the output from any executed external applications.
 		@exec_commands - Set to False to disable the execution of external utilities when extracting data from files.
+		@max_size      - Limit the size of extracted files to max_size.
 
 		Returns None.
 		'''
@@ -58,6 +59,7 @@ class Extractor:
 		self.enabled = False
 		self.delayed = True
 		self.verbose = verbose
+		self.max_size = max_size
 		self.exec_commands = exec_commands
 		self.extract_rules = []
 		self.remove_after_execute = False
@@ -421,6 +423,9 @@ class Extractor:
 		# Default extracted file name is <hex offset>.<extension>
 		default_bname = "%X" % offset
 
+		if self.max_size and size > self.max_size:
+			size = self.max_size
+
 		if not output_file_name or output_file_name is None:
 			bname = default_bname
 		else: