iwla/plugins/post_analysis/top_hits.py

79 lines
2.0 KiB
Python
Raw Normal View History

2014-12-18 19:54:31 +01:00
# -*- 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/>.
#
2014-11-27 13:47:31 +01:00
from iwla import IWLA
from iplugin import IPlugin
"""
Post analysis hook
Count TOP hits
Plugin requirements :
None
Conf values needed :
None
Output files :
None
Statistics creation :
None
Statistics update :
month_stats:
top_hits =>
2015-01-08 20:58:27 +01:00
uri => count
Statistics deletion :
None
"""
2014-12-10 16:53:50 +01:00
2014-11-27 13:47:31 +01:00
class IWLAPostAnalysisTopHits(IPlugin):
def __init__(self, iwla):
super(IWLAPostAnalysisTopHits, self).__init__(iwla)
self.API_VERSION = 1
def hook(self):
2016-02-06 14:45:09 +01:00
stats = self.iwla.getCurrentVisits()
2014-11-27 13:47:31 +01:00
month_stats = self.iwla.getMonthStats()
top_hits = month_stats.get('top_hits', {})
for (k, super_hit) in stats.items():
if super_hit['robot']: continue
2014-12-14 15:10:13 +01:00
for r in super_hit['requests'][::-1]:
if not self.iwla.isValidForCurrentAnalysis(r):
break
if not self.iwla.hasBeenViewed(r) or\
r['is_page']:
2014-11-27 13:47:31 +01:00
continue
2014-12-14 15:10:13 +01:00
uri = r['extract_request']['extract_uri'].lower()
2014-11-27 13:47:31 +01:00
uri = "%s%s" % (r.get('server_name', ''), uri)
if not uri in top_hits.keys():
top_hits[uri] = 1
else:
top_hits[uri] += 1
month_stats['top_hits'] = top_hits