Implementation for an Issue #283

stamparm · stamparm · commit baccbd6f4839 · 2012-12-06T11:57:57.000+01:00
diff --git a/lib/core/common.py b/lib/core/common.py
@@ -3110,6 +3110,17 @@ def geturl(self):
 
     if addToTargets and retVal:
         for target in retVal:
+            url = target[0]
+
+            # flag to know if we are dealing with the same target host
+            _ = reduce(lambda x, y: x == y, map(lambda x: urlparse.urlparse(x).netloc.split(':')[0], (response.geturl(), url)))
+
+            if conf.scope:
+                if not re.search(conf.scope, url, re.I):
+                    continue
+            elif not _:
+                continue
+
             kb.targets.add(target)
 
     return retVal
diff --git a/lib/utils/crawler.py b/lib/utils/crawler.py
@@ -70,12 +70,12 @@ def crawlThread():
                                     url = urlparse.urljoin(conf.url, tag.get("href"))
 
                                     # flag to know if we are dealing with the same target host
-                                    target = reduce(lambda x, y: x == y, map(lambda x: urlparse.urlparse(x).netloc.split(':')[0], [url, conf.url]))
+                                    _ = reduce(lambda x, y: x == y, map(lambda x: urlparse.urlparse(x).netloc.split(':')[0], (url, conf.url)))
 
                                     if conf.scope:
                                         if not re.search(conf.scope, url, re.I):
                                             continue
-                                    elif not target:
+                                    elif not _:
                                         continue
 
                                     if url.split('.')[-1].lower() not in CRAWL_EXCLUDE_EXTENSIONS:
