soutade/iwla
1
0
Fork 0
Code Issues Pull Requests Releases 2 Activity

Remove all trailing slashs of URL before starting analyze

Browse Source
This commit is contained in:
Gregory Soutade 2024-01-30 11:28:10 +01:00
parent d6d216db4d
commit d78739157b
2 changed files with 6 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
iwla.py
View File

@ -391,13 +391,14 @@ class IWLA(object):
super_hit['robot'] = None super_hit['robot'] = None
super_hit['hit_only'] = 0 super_hit['hit_only'] = 0
def _normalizeURI(self, uri, removeFileSlash=False): def _normalizeURI(self, uri, removeFileSlash=True):
if uri == '/': return uri if uri == '/': return uri
# Remove protocol # Remove protocol
uri = self.protocol_re.sub('', uri) uri = self.protocol_re.sub('', uri)
# Remove double / # Remove double /
uri = self.slash_re.sub('/', uri) uri = self.slash_re.sub('/', uri)
if removeFileSlash and uri[-1] == '/': if removeFileSlash:
while len(uri) > 1 and uri[-1] == '/':
uri = uri[:-1] uri = uri[:-1]
return uri return uri
@ -429,7 +430,7 @@ class IWLA(object):
referer_groups = self.uri_re.match(hit['http_referer']) referer_groups = self.uri_re.match(hit['http_referer'])
if referer_groups: if referer_groups:
hit['extract_referer'] = referer_groups.groupdict("") hit['extract_referer'] = referer_groups.groupdict("")
hit['extract_referer']['extract_uri'] = self._normalizeURI(hit['extract_referer']['extract_uri'], True) hit['extract_referer']['extract_uri'] = self._normalizeURI(hit['extract_referer']['extract_uri'])
hit['extract_referer']['extract_parameters'] = self._normalizeParameters(hit['extract_referer']['extract_parameters']) hit['extract_referer']['extract_parameters'] = self._normalizeParameters(hit['extract_referer']['extract_parameters'])
hit['remote_ip'] = hit['remote_addr'] hit['remote_ip'] = hit['remote_addr']

2
plugins/post_analysis/top_pages.py
View File

@ -75,7 +75,7 @@ class IWLAPostAnalysisTopPages(IPlugin):
uri = r['extract_request']['extract_uri'] uri = r['extract_request']['extract_uri']
if self.index_re.match(uri): if self.index_re.match(uri):
uri = '/' uri = ''
uri = "%s%s" % (r.get('server_name', ''), uri) uri = "%s%s" % (r.get('server_name', ''), uri)