Update doc for css validation (#123)

* update doc for css validation

* pep8 stype coding

* minor change

* pep8 coding update #2

* pep8 codin update #3

* pep8 codin update #4

* pep8 coding update #5

clone.py

@@ -34,15 +34,15 @@
 class Cloner(object):
     def __init__(self, root, max_depth, css_validate):
         self.visited_urls = []
-        self.root, self.error_page  = self.add_scheme(root)
+        self.root, self.error_page = self.add_scheme(root)
         self.max_depth = max_depth
         self.moved_root = None
         if len(self.root.host) < 4:
             sys.exit('invalid taget {}'.format(self.root.host))
         self.target_path = '/opt/snare/pages/{}'.format(self.root.host)
 
         if not os.path.exists(self.target_path):
-            os.mkdir(self.target_path)    
+            os.mkdir(self.target_path)
         self.css_validate = css_validate
         self.new_urls = Queue()
         self.meta = {}
@@ -152,7 +152,7 @@ async def get_body(self, session):
                     response = await session.get(current_url, headers={'Accept': 'text/html'})
                     content_type = response.content_type
                     data = await response.read()
-                    
+
             except (aiohttp.ClientError, asyncio.TimeoutError) as client_error:
                 self.logger.error(client_error)
             else:
@@ -165,8 +165,8 @@ async def get_body(self, session):
                     data = str(soup).encode()
                 with open(os.path.join(self.target_path, hash_name), 'wb') as index_fh:
                     index_fh.write(data)
-                if content_type == 'text/css':                       
-                    css = cssutils.parseString(data, validate=self.css_validate)                   
+                if content_type == 'text/css':
+                    css = cssutils.parseString(data, validate=self.css_validate)
                     for carved_url in cssutils.getUrls(css):
                         if carved_url.startswith('data'):
                             continue
@@ -191,15 +191,16 @@ async def run(self):
         session = aiohttp.ClientSession()
         try:
             await self.new_urls.put((self.root, 0))
-            await self.new_urls.put((self.error_page,0))
+            await self.new_urls.put((self.error_page, 0))
             await self.get_body(session)
         except KeyboardInterrupt:
             raise
         finally:
             with open(os.path.join(self.target_path, 'meta.json'), 'w') as mj:
                 json.dump(self.meta, mj)
             await session.close()
-
+
+
 def str_to_bool(v):
     if v.lower() == 'true':
         return True
@@ -208,6 +209,7 @@ def str_to_bool(v):
     else:
         raise argparse.ArgumentTypeError('Boolean value expected')
 
+
 def main():
     if os.getuid() != 0:
         print('Clone has to be run as root!')
@@ -226,7 +228,7 @@ def main():
     if args.log_path:
         log_err = args.log_path + "clone.err"
     else:
-        log_err = "/opt/snare/clone.err"    
+        log_err = "/opt/snare/clone.err"
     logger.Logger.create_clone_logger(log_err, __package__)
     print("Error logs will be stored in {}\n".format(log_err))
     try:
@@ -244,6 +246,6 @@ def main():
   / /    / /     / / / //  |/ / __/ / /_/ /
  / /___ / /____ / /_/ // /|  / /___/ _, _/
 /_____//______//_____//_/ |_/_____/_/ |_|
-    
+
     """)
     main()

docs/source/cloner.rst

@@ -12,3 +12,4 @@ Description
 
 * **target** -- url of website to be cloned
 * **max--depth** -- maximum depth of the web-pages desired to be cloned (optional), default: full depth of the site 
+* **css--validate** -- set whether css validation is required (optional), default: None

logger.py

@@ -1,49 +1,51 @@
 import logging
 import logging.handlers
 
+
 class LevelFilter(logging.Filter):
     """Filters (lets through) all messages with level < LEVEL"""
 
     def __init__(self, level):
         self.level = level
 
     def filter(self, record):
-        return record.levelno < self.level  # "<" instead of "<=": since logger.setLevel is inclusive, this should be exclusive
+        return record.levelno < self.level
+    # "<" instead of "<=": since logger.setLevel is inclusive, this should be exclusive
+
 
 class Logger:
-	
+
     @staticmethod
     def create_logger(debug_filename, err_filename, logger_name):
         logger = logging.getLogger(logger_name)
         logger.setLevel(logging.DEBUG)
         logger.propagate = False
         formatter = logging.Formatter(
-			fmt='%(asctime)s %(levelname)s:%(name)s:%(funcName)s: %(message)s', datefmt='%Y-%m-%d %H:%M:%S')
-		
+            fmt='%(asctime)s %(levelname)s:%(name)s:%(funcName)s: %(message)s', datefmt='%Y-%m-%d %H:%M:%S')
+
         # ERROR log to 'snare.err'
         error_log_handler = logging.handlers.RotatingFileHandler(err_filename, encoding='utf-8')
         error_log_handler.setLevel(logging.ERROR)
         error_log_handler.setFormatter(formatter)
         logger.addHandler(error_log_handler)
-		
+
         # DEBUG log to 'snare.log'
         debug_log_handler = logging.handlers.RotatingFileHandler(debug_filename, encoding='utf-8')
         debug_log_handler.setLevel(logging.DEBUG)
         debug_log_handler.setFormatter(formatter)
         max_level_filter = LevelFilter(logging.ERROR)
         debug_log_handler.addFilter(max_level_filter)
         logger.addHandler(debug_log_handler)
-		
+
         return logger
-    
+
     @staticmethod
     def create_clone_logger(err_filename, logger_name):
         logger = logging.getLogger(logger_name)
         formatter = logging.Formatter(
-			fmt='%(asctime)s %(levelname)s:%(name)s:%(funcName)s: %(message)s', datefmt='%Y-%m-%d %H:%M:%S')
+            fmt='%(asctime)s %(levelname)s:%(name)s:%(funcName)s: %(message)s', datefmt='%Y-%m-%d %H:%M:%S')
         # ERROR log to 'clone.err'
         error_log_handler = logging.handlers.RotatingFileHandler(err_filename, encoding='utf-8')
         error_log_handler.setLevel(logging.ERROR)
         error_log_handler.setFormatter(formatter)
         logger.addHandler(error_log_handler)
-

snare.py

@@ -55,7 +55,7 @@ def __init__(self, meta, run_args, debug=False, keep_alive=75, **kwargs):
         self.dir = '/opt/snare/pages/{}'.format(run_args.page_dir)
 
         self.meta = meta
-        
+
         self.logger = logging.getLogger(__name__)
 
         self.sroute = StaticRoute(
@@ -223,9 +223,11 @@ async def parse_tanner_response(self, requested_name, detection):
         content = None
         status_code = 200
         headers = {}
-        p = re.compile('/+') # Creating a regex object for the pattern of multiple contiguous forward slashes
-        requested_name = p.sub('/', requested_name) # Substituting all occurrences of the pattern with single forward slash
-
+        # Creating a regex object for the pattern of multiple contiguous forward slashes
+        p = re.compile('/+')
+        # Substituting all occurrences of the pattern with single forward slash
+        requested_name = p.sub('/', requested_name)
+
         if detection['type'] == 1:
             query_start = requested_name.find('?')
             if query_start != -1:
@@ -235,7 +237,7 @@ async def parse_tanner_response(self, requested_name, detection):
                 requested_name = self.run_args.index_page
             try:
                 if requested_name[-1] == '/':
-                    requested_name = requested_name[:-1]  
+                    requested_name = requested_name[:-1]
                 requested_name = unquote(requested_name)
                 file_name = self.meta[requested_name]['hash']
                 content_type = self.meta[requested_name]['content_type']
@@ -248,7 +250,7 @@ async def parse_tanner_response(self, requested_name, detection):
                 with open(path, 'rb') as fh:
                     content = fh.read()
                 content = await self.handle_html_content(content)
-                
+
             else:
                 path = os.path.join(self.dir, file_name)
                 if os.path.isfile(path):
@@ -464,9 +466,9 @@ async def check_tanner():
     base_page_path = '/opt/snare/pages/'
     config = configparser.ConfigParser()
     config.read(os.path.join(base_path, args.config))
-	
+
     log_debug = args.log_dir + "snare.log"
-    log_err = args.log_dir + "snare.err"      
+    log_err = args.log_dir + "snare.err"
     logger.Logger.create_logger(log_debug, log_err, __package__)
 
     if args.list_pages: