iwla/plugins/pre_analysis/page_to_hit.py

104 lines
3.0 KiB
Python

# -*- coding: utf-8 -*-
#
# Copyright Grégory Soutadé 2015
# This file is part of iwla
# iwla is free software: you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation, either version 3 of the License, or
# (at your option) any later version.
#
# iwla is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with iwla. If not, see <http://www.gnu.org/licenses/>.
#
import re
from iwla import IWLA
from iplugin import IPlugin
#
# Pre analysis hook
# Change page into hit and hit into page into statistics
#
# Plugin requirements :
# None
#
# Conf values needed :
# page_to_hit_conf*
# hit_to_page_conf*
#
# Output files :
# None
#
# Statistics creation :
# None
#
# Statistics update :
# visits :
# remote_addr =>
# is_page
#
# Statistics deletion :
# None
#
class IWLAPreAnalysisPageToHit(IPlugin):
def __init__(self, iwla):
super(IWLAPreAnalysisPageToHit, self).__init__(iwla)
self.API_VERSION = 1
def load(self):
# Page to hit
self.ph_regexps = self.iwla.getConfValue('page_to_hit_conf', [])
if not self.ph_regexps: return False
self.ph_regexps = map(lambda(r): re.compile(r), self.ph_regexps)
# Hit to page
self.hp_regexps = self.iwla.getConfValue('hit_to_page_conf', [])
if not self.hp_regexps: return False
self.hp_regexps = map(lambda(r): re.compile(r), self.hp_regexps)
return True
def hook(self):
hits = self.iwla.getCurrentVisists()
for (k, super_hit) in hits.items():
if super_hit['robot']: continue
for request in super_hit['requests'][::-1]:
if not self.iwla.isValidForCurrentAnalysis(request):
break
if not self.iwla.hasBeenViewed(request):
continue
uri = request['extract_request']['extract_uri']
if request['is_page']:
# Page to hit
for regexp in self.ph_regexps:
if regexp.match(uri):
#print '%s is a hit' % (uri )
request['is_page'] = False
super_hit['viewed_pages'] -= 1
super_hit['viewed_hits'] += 1
break
else:
# Hit to page
for regexp in self.hp_regexps:
if regexp.match(uri):
#print '%s is a page' % (uri )
request['is_page'] = True
super_hit['viewed_pages'] += 1
super_hit['viewed_hits'] -= 1
break