crawler fix (skip binary files)

extra/beautifulsoup/beautifulsoup.py

@@ -549,9 +549,6 @@ class Tag(PageElement):
                                           val))
         self.attrs = map(convert, self.attrs)
 
-        # Reference: http://bytes.com/topic/python/answers/552874-py-2-5-bug-sgmllib
-        SGMLParser.convert_codepoint = lambda self, codepoint: unichr(codepoint)
-
     def getString(self):
         if (len(self.contents) == 1
             and isinstance(self.contents[0], NavigableString)):

lib/core/settings.py

@@ -354,3 +354,6 @@ HTML_TITLE_REGEX = "<title>(?P<result>[^<]+)</title>"
 
 # Chars used to quickly distinguish if the user provided tainted parameter values
 DUMMY_SQL_INJECTION_CHARS = ";()\"'"
+
+# Extensions skipped by crawler
+CRAWL_EXCLUDE_EXTENSIONS = ("gif","jpg","jar","tif","bmp","war","ear","mpg","wmv","mpeg","scm","iso","dmp","dll","cab","so","avi","bin","exe","iso","tar","png","pdf","ps","mp3","zip","rar","gz")

lib/utils/crawler.py

@@ -18,6 +18,7 @@ from lib.core.data import conf
 from lib.core.data import kb
 from lib.core.data import logger
 from lib.core.exception import sqlmapConnectionException
+from lib.core.settings import CRAWL_EXCLUDE_EXTENSIONS
 from lib.core.threads import getCurrentThreadData
 from lib.core.threads import runThreads
 from lib.request.connect import Connect as Request
@@ -51,10 +52,11 @@ class Crawler:
                         kb.locks.limits.release()
                         break
 
+                    content = None
                     try:
+                        if current.split('.')[-1].lower() not in CRAWL_EXCLUDE_EXTENSIONS:
                             content = Request.getPage(url=current, raise404=False)[0]
                     except sqlmapConnectionException, e:
-                        content = None
                         errMsg = "connection exception detected (%s). skipping " % e
                         errMsg += "url '%s'" % current
                         logger.critical(errMsg)
@@ -62,7 +64,7 @@ class Crawler:
                     if not kb.threadContinue:
                         break
 
-                    if content:
+                    if isinstance(content, unicode):
                         soup = BeautifulSoup(content)
                         for tag in soup('a'):
                             if tag.get("href"):