39 lines
1.2 KiB
Python
39 lines
1.2 KiB
Python
|
import re
|
||
|
|
||
|
from iwla import IWLA
|
||
|
from iplugin import IPlugin
|
||
|
|
||
|
# Basic rule to detect robots
|
||
|
|
||
|
class IWLAPreAnalysisPageToHit(IPlugin):
|
||
|
|
||
|
def __init__(self, iwla):
|
||
|
super(IWLAPreAnalysisPageToHit, self).__init__(iwla)
|
||
|
self.API_VERSION = 1
|
||
|
|
||
|
def load(self):
|
||
|
# Remove logo from indefero
|
||
|
self.regexps = self.iwla.getConfValue('page_to_hit_conf', [])
|
||
|
if not self.regexps: return False
|
||
|
self.regexps = map(lambda(r): re.compile(r), self.regexps)
|
||
|
|
||
|
return True
|
||
|
|
||
|
def hook(self, iwla):
|
||
|
hits = iwla.getCurrentVisists()
|
||
|
|
||
|
for (k, super_hit) in hits.items():
|
||
|
if super_hit['robot']: continue
|
||
|
|
||
|
for p in super_hit['requests']:
|
||
|
if not p['is_page']: continue
|
||
|
if int(p['status']) != 200: continue
|
||
|
if p['time_decoded'].tm_mday != super_hit['last_access'].tm_mday: continue
|
||
|
uri = p['extract_request']['extract_uri']
|
||
|
for r in self.regexps:
|
||
|
if r.match(uri):
|
||
|
p['is_page'] = False
|
||
|
super_hit['viewed_pages'] -= 1
|
||
|
super_hit['viewed_hits'] += 1
|
||
|
break
|