iwla/plugins/post_analysis/hours_stats.py

# -*- 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/>.
#

from iwla import IWLA
from iplugin import IPlugin

"""
Post analysis hook

Count pages, hits and bandwidth by hour/week day

Plugin requirements :
    None

Conf values needed :
    None

Output files :
    None

Statistics creation :
month_stats:
    hours_stats =>
        00 .. 23 =>
            pages
            hits
            bandwidth

    days_stats =>
        0 .. 6 =>
            pages
            hits
            bandwidth

Statistics update :
    None

Statistics deletion :
    None
"""

class IWLAPostAnalysisHoursStats(IPlugin):
    def __init__(self, iwla):
        super(IWLAPostAnalysisHoursStats, self).__init__(iwla)
        self.API_VERSION = 1
        
    def hook(self):
        stats = self.iwla.getCurrentVisits()
        month_stats = self.iwla.getMonthStats()
        
        hours_stats = month_stats.get('hours_stats', {})
        if not hours_stats:
            for i in range(0, 24):
                hours_stats[i] = {'pages':0, 'hits':0, 'bandwidth':0}
        days_stats = month_stats.get('days_stats', {})
        if not days_stats:
            for i in range(0, 7):
                days_stats[i] = {'pages':0, 'hits':0, 'bandwidth':0}

        for super_hit in stats.values():
            if super_hit['robot']: continue
            for r in super_hit['requests'][::-1]:
                if not self.iwla.isValidForCurrentAnalysis(r):
                    break

                if not self.iwla.hasBeenViewed(r): continue

                key = r['is_page'] and 'pages' or 'hits'

                t = r['time_decoded']

                hours_stats[t.tm_hour][key] += 1
                hours_stats[t.tm_hour]['bandwidth'] += int(r['body_bytes_sent'])

                days_stats[t.tm_wday][key] += 1
                days_stats[t.tm_wday]['bandwidth'] += int(r['body_bytes_sent'])

        month_stats['hours_stats'] = hours_stats
        month_stats['days_stats'] = days_stats