iwla/plugins/post_analysis/top_downloads.py

95 lines
2.6 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 12:35:41 +01:00
import re
from iwla import IWLA
from iplugin import IPlugin
2014-12-10 07:09:05 +01:00
#
# Post analysis hook
#
# Count TOP downloads
#
# Plugin requirements :
# None
#
# Conf values needed :
2014-12-10 16:53:50 +01:00
# None
2014-12-10 07:09:05 +01:00
#
# Output files :
# None
#
# Statistics creation :
# None
#
# Statistics update :
# month_stats:
# top_downloads =>
# uri
#
# Statistics deletion :
# None
#
2014-11-27 12:35:41 +01:00
class IWLAPostAnalysisTopDownloads(IPlugin):
def __init__(self, iwla):
super(IWLAPostAnalysisTopDownloads, self).__init__(iwla)
self.API_VERSION = 1
self.conf_requires = ['multimedia_files', 'viewed_http_codes']
def hook(self):
stats = self.iwla.getCurrentVisists()
month_stats = self.iwla.getMonthStats()
multimedia_files = self.iwla.getConfValue('multimedia_files')
viewed_http_codes = self.iwla.getConfValue('viewed_http_codes')
top_downloads = month_stats.get('top_downloads', {})
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 13:07:14 +01:00
continue
2014-11-27 12:35:41 +01:00
uri = r['extract_request']['extract_uri'].lower()
isMultimedia = False
for ext in multimedia_files:
if uri.endswith(ext):
isMultimedia = True
break
if isMultimedia: continue
uri = "%s%s" % (r.get('server_name', ''),
r['extract_request']['extract_uri'])
if not uri in top_downloads.keys():
top_downloads[uri] = 1
else:
top_downloads[uri] += 1
month_stats['top_downloads'] = top_downloads