2.1.0 build

arjun/core/importer.py

@@ -1,5 +1,28 @@
 import re
-from core.utils import reader, parse_request
+
+def reader(path, mode='string'):
+    """
+    reads a file
+    returns a string/array containing the content of the file
+    """
+    with open(path, 'r', encoding='utf-8') as file:
+        if mode == 'lines':
+            return list(filter(None, [line.rstrip('\n') for line in file]))
+        else:
+            return ''.join([line for line in file])
+
+def parse_request(string):
+    """
+    parses http request
+    returns dict
+    """
+    result = {}
+    match = re.search(r'(?:([a-zA-Z0-9]+) ([^ ]+) [^ ]+\n)?([\s\S]+\n)\n?([\s\S]+)?', string)
+    result['method'] = match.group(1)
+    result['path'] = match.group(2)
+    result['headers'] = parse_headers(match.group(3))
+    result['data'] = match.group(4)
+    return result
 
 burp_regex = re.compile(r'''(?m)^    <url><!\[CDATA\[(.+?)\]\]></url>
     <host ip="[^"]*">[^<]+</host>
@@ -15,44 +38,59 @@ burp_regex = re.compile(r'''(?m)^    <url><!\[CDATA\[(.+?)\]\]></url>
 
 
 def burp_import(path):
-	requests = []
-	content = reader(path)
-	matches = re.finditer(burp_regex, content)
-	for match in matches:
-		request = parse_request(match.group(4))
-		headers = request['headers']
-		if match.group(7) in ('HTML', 'JSON'):
-			requests.append({
-				'url': match.group(1),
-				'method': match.group(2),
-				'extension': match.group(3),
-				'headers': headers,
-				'include': request['data'],
-				'code': match.group(5),
-				'length': match.group(6),
-				'mime': match.group(7)
-			})
-	return requests
+    """
+    imports targets from burp suite
+    returns list (of request objects)
+    """
+    requests = []
+    content = reader(path)
+    matches = re.finditer(burp_regex, content)
+    for match in matches:
+        request = parse_request(match.group(4))
+        headers = request['headers']
+        if match.group(7) in ('HTML', 'JSON'):
+            requests.append({
+                'url': match.group(1),
+                'method': match.group(2),
+                'extension': match.group(3),
+                'headers': headers,
+                'include': request['data'],
+                'code': match.group(5),
+                'length': match.group(6),
+                'mime': match.group(7)
+            })
+    return requests
 
 
 def urls_import(path, method, headers, include):
-	requests = []
-	urls = reader(path, mode='lines')
-	for url in urls:
-		requests.append({
-			'url': url,
-			'method': method,
-			'headers': headers,
-			'data': include
-		})
-	return requests
+    """
+    imports urls from a newline delimited text file
+    returns list (of request objects)
+    """
+    requests = []
+    urls = reader(path, mode='lines')
+    for url in urls:
+        requests.append({
+            'url': url,
+            'method': method,
+            'headers': headers,
+            'data': include
+        })
+    return requests
 
 
 def request_import(path):
-	return parse_request(reader(path))
+    """
+    imports request from a raw request file
+    returns dict
+    """
+    return parse_request(reader(path))
 
 
 def importer(path, method, headers, include):
+    """
+    main importer function that calls other import functions
+    """
     with open(path, 'r', encoding='utf-8') as file:
         for line in file:
             if line.startswith('<?xml'):