iwla/plugins/post_analysis/browsers.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

Detect browser information from requests

Plugin requirements :
    None

Conf values needed :
    None

Output files :
    None

Statistics creation :
visits :
   remote_addr =>
       browser

month_stats :
    browsers =>
        browser => count

Statistics update :
    None

Statistics deletion :
    None
"""

browser_order = ['android', 'iphone', 'xbox', 'edge', 'opera', 'chrome', 'safari', 'firefox', 'ie', 'mozilla', 'curl', 'wget', 'w3m']

browser_hashid = {
    'android':'Android',
    'iphone':'iPhone',
    'edge':'Edg',
    'chrome':['Chrom', 'Chrome'],
    'safari':'Safari',
    'firefox':'Firefox',
    'ie':'MSIE',
    'mozilla':'Mozilla',
    'opera':'OPR',
    'xbox':'Xbox',
    'curl':'curl',
    'wget':'Wget',
    'w3m':'w3m'
}

browser_name = {
    'android':'Android',
    'iphone':'iPhone',
    'edge':'Edge',
    'chrome':'Chrome',
    'safari':'Safari',
    'firefox':'Firefox',
    'ie':'Internet Explorer',
    'mozilla':'Mozilla',
    'opera':'Opera',
    'xbox':'Xbox',
    'curl':'Curl',
    'wget':'Wget',
    'w3m':'w3m'
}

class IWLAPostAnalysisBrowsers(IPlugin):

    def hook(self):
        stats = self.iwla.getValidVisitors()
        month_stats = self.iwla.getMonthStats()
        
        browsers = month_stats.get('browsers', {})

        browsers_stats = {}

        for (k, super_hit) in stats.items():
            if not 'browser' in super_hit:
                for r in super_hit['requests'][::-1]:
                    user_agent = r['http_user_agent']
                    if not user_agent: continue
                
                    name = 'Unknown'
                    for browser in browser_order:
                        reference = browser_hashid[browser]
                        if type(reference) == list:
                            for ref in reference:
                                if ref in user_agent:
                                    name = browser_name[browser]
                                    break
                            if name != 'Unknown':
                                break
                        else:
                            if browser_hashid[browser] in user_agent:
                                name = browser_name[browser]
                                break
                        if name == 'Unknown' and 'Macintosh' in user_agent:
                            name = 'Safari'
                    super_hit['browser'] = name
                    break
            else:
                name = super_hit['browser']

            if not name in browsers_stats.keys():
                browsers_stats[name] = 1
            else:
                browsers_stats[name] += 1

        month_stats['browsers'] = browsers_stats