iwla/plugins/post_analysis/top_pages.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/>.
#

import re

from iwla import IWLA
from iplugin import IPlugin

"""
Post analysis hook

Count TOP pages

Plugin requirements :
    None

Conf values needed :
    None

Output files :
    None

Statistics creation :
    None

Statistics update :
month_stats:
   top_pages =>
       uri => count

Statistics deletion :
    None
"""

class IWLAPostAnalysisTopPages(IPlugin):
    def __init__(self, iwla):
        super(IWLAPostAnalysisTopPages, self).__init__(iwla)
        self.API_VERSION = 1

    def load(self):
        self.index_re = re.compile(r'/index.*')
        return True
        
    def hook(self):
        stats = self.iwla.getCurrentVisits()
        month_stats = self.iwla.getMonthStats()
        
        top_pages = month_stats.get('top_pages', {})

        for (k, super_hit) in stats.items():
            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) or\
                        not r['is_page']:
                    continue

                uri = r['extract_request']['extract_uri']
                if self.index_re.match(uri):
                    uri = ''
                
                uri = "%s%s" % (r.get('server_name', ''), uri)

                if not uri in top_pages.keys():
                    top_pages[uri] = 1
                else:
                    top_pages[uri] += 1

        month_stats['top_pages'] = top_pages