use urls from a file as seeds (Resolves #135)

xsstrike.py

@@ -50,6 +50,8 @@
                     dest='find', action='store_true')
 parser.add_argument('--crawl', help='crawl',
                     dest='recursive', action='store_true')
+parser.add_argument(
+    '--seeds', help='load crawling seeds from a file', dest='args_seeds')
 parser.add_argument(
     '-f', '--file', help='load payloads from a file', dest='args_file')
 parser.add_argument('-l', '--level', help='level of crawling',
@@ -87,6 +89,7 @@
 find = args.find
 recursive = args.recursive
 args_file = args.args_file
+args_seeds = args.args_seeds
 level = args.level
 add_headers = args.add_headers
 threadCount = args.threadCount
@@ -107,6 +110,14 @@
                     '\n').encode('utf-8').decode('utf-8'))
         payloadList = list(filter(None, payloadList))
 
+seedList = []
+if args_seeds:
+    with open(args_seeds, 'r') as f:
+        for line in f:
+            seedList.append(line.strip(
+                '\n').encode('utf-8').decode('utf-8'))
+    seedList = list(filter(None, seedList))
+
 encoding = base64 if encode and encode == 'base64' else False
 
 if not proxy:
@@ -116,38 +127,41 @@
     updater()
     quit()  # quitting because files have been changed
 
-if not target:  # if the user hasn't supplied a url
+if not target and not args_seeds:  # if the user hasn't supplied a url
     print('\n' + parser.format_help().lower())
     quit()
 
 if fuzz:
     singleFuzz(target, paramData, verbose, encoding, headers, delay, timeout)
-elif not recursive:
+elif not recursive and not args_seeds:
     if args_file:
         bruteforcer(target, paramData, payloadList, verbose, encoding, headers, delay, timeout)
     else:
         scan(target, paramData, verbose, encoding, headers, delay, timeout, skipDOM, find, skip)
 else:
-    print('%s Crawling the target' % run)
-    scheme = urlparse(target).scheme
-    verboseOutput(scheme, 'scheme', verbose)
-    host = urlparse(target).netloc
-    main_url = scheme + '://' + host
-    crawlingResult = photon(target, headers, level,
-                            threadCount, delay, timeout)
-    forms = crawlingResult[0]
-    domURLs = list(crawlingResult[1])
-    difference = abs(len(domURLs) - len(forms))
-    if len(domURLs) > len(forms):
-        for i in range(difference):
-            forms.append(0)
-    elif len(forms) > len(domURLs):
-        for i in range(difference):
-            domURLs.append(0)
-    threadpool = concurrent.futures.ThreadPoolExecutor(max_workers=threadCount)
-    futures = (threadpool.submit(crawl, scheme, host, main_url, form, domURL, verbose,
-                                 blindXSS, blindPayload, headers, delay, timeout, skipDOM, encoding) for form, domURL in zip(forms, domURLs))
-    for i, _ in enumerate(concurrent.futures.as_completed(futures)):
-        if i + 1 == len(forms) or (i + 1) % threadCount == 0:
-            print('%s Progress: %i/%i' % (info, i + 1, len(forms)), end='\r')
-    print()
+    if target:
+        seedList.append(target)
+    for target in seedList:
+        print('%s Crawling the target' % run)
+        scheme = urlparse(target).scheme
+        verboseOutput(scheme, 'scheme', verbose)
+        host = urlparse(target).netloc
+        main_url = scheme + '://' + host
+        crawlingResult = photon(target, headers, level,
+                                threadCount, delay, timeout)
+        forms = crawlingResult[0]
+        domURLs = list(crawlingResult[1])
+        difference = abs(len(domURLs) - len(forms))
+        if len(domURLs) > len(forms):
+            for i in range(difference):
+                forms.append(0)
+        elif len(forms) > len(domURLs):
+            for i in range(difference):
+                domURLs.append(0)
+        threadpool = concurrent.futures.ThreadPoolExecutor(max_workers=threadCount)
+        futures = (threadpool.submit(crawl, scheme, host, main_url, form, domURL, verbose,
+                                     blindXSS, blindPayload, headers, delay, timeout, skipDOM, encoding) for form, domURL in zip(forms, domURLs))
+        for i, _ in enumerate(concurrent.futures.as_completed(futures)):
+            if i + 1 == len(forms) or (i + 1) % threadCount == 0:
+                print('%s Progress: %i/%i' % (info, i + 1, len(forms)), end='\r')
+        print()