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

Make backup before compressing (low memory servers)

Browse Source 
Fix error : Call post hook plugins even in display only mode
Don't compute unordered hits (remove pasts if they are found after current)
Remove tags in stats diff
Don't do geolocalisation is visitor is not valid
Don't try to find search engine on robots
Update robot check rules
Add top_pages_diff plugin
This commit is contained in:
Gregory Soutade
2019-08-30 07:50:54 +02:00
parent ed6ed68706
commit bb268114b2
6 changed files with 131 additions and 36 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
plugins/post_analysis/ip_to_geo.py
View File

@@ -82,6 +82,8 @@ class IWLAPostAnalysisIPToGeo(IPlugin):
(_, cc) = self.iptogeo.ip_to_geo(ip)
cc = cc and cc or 'ip'
visitor['country_code'] = cc
if not self.iwla.isValidVisitor(visitor):
continue
if cc in geo.keys():
geo[cc] += 1
else:

44
plugins/post_analysis/referers.py
View File

@@ -140,30 +140,32 @@ class IWLAPostAnalysisReferers(IPlugin):
uri = r['extract_referer']['extract_uri']
if self.own_domain_re.match(uri): continue
is_search_engine = False
for (name, engine) in self.search_engines.items():
for (hashid, hashid_re) in engine['hashid']:
if not hashid_re.match(uri): continue
not_engine = engine.get('not_search_engine', None)
# Try not engine
if not_engine and not_engine.match(uri): break
is_search_engine = True
uri = name
parameters = r['extract_referer'].get('extract_parameters', None)
key_phrase_re = engine.get('known_url', None)
self._extractKeyPhrase(key_phrase_re, parameters, key_phrases)
break
if is_search_engine:
dictionary = search_engine_referers
elif super_hit['robot']:
if super_hit['robot']:
dictionary = robots_referers
# print '%s => %s' % (uri, super_hit['remote_ip'])
else:
dictionary = referers
is_search_engine = False
for (name, engine) in self.search_engines.items():
for (hashid, hashid_re) in engine['hashid']:
if not hashid_re.match(uri): continue
not_engine = engine.get('not_search_engine', None)
# Try not engine
if not_engine and not_engine.match(uri): break
is_search_engine = True
uri = name
parameters = r['extract_referer'].get('extract_parameters', None)
key_phrase_re = engine.get('known_url', None)
self._extractKeyPhrase(key_phrase_re, parameters, key_phrases)
break
if is_search_engine:
dictionary = search_engine_referers
else:
dictionary = referers
if r['is_page']:
key = 'pages'
else: