| 1 | # -*- coding: utf-8 -*-␊ |
| 2 | #␊ |
| 3 | # Copyright Grégory Soutadé 2015␊ |
| 4 | ␊ |
| 5 | # This file is part of iwla␊ |
| 6 | ␊ |
| 7 | # iwla is free software: you can redistribute it and/or modify␊ |
| 8 | # it under the terms of the GNU General Public License as published by␊ |
| 9 | # the Free Software Foundation, either version 3 of the License, or␊ |
| 10 | # (at your option) any later version.␊ |
| 11 | #␊ |
| 12 | # iwla is distributed in the hope that it will be useful,␊ |
| 13 | # but WITHOUT ANY WARRANTY; without even the implied warranty of␊ |
| 14 | # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the␊ |
| 15 | # GNU General Public License for more details.␊ |
| 16 | #␊ |
| 17 | # You should have received a copy of the GNU General Public License␊ |
| 18 | # along with iwla. If not, see <http://www.gnu.org/licenses/>.␊ |
| 19 | #␊ |
| 20 | ␊ |
| 21 | import re␊ |
| 22 | import logging␊ |
| 23 | import inspect␊ |
| 24 | ␊ |
| 25 | from iwla import IWLA␊ |
| 26 | from iplugin import IPlugin␊ |
| 27 | ␊ |
| 28 | import awstats_data␊ |
| 29 | ␊ |
| 30 | """␊ |
| 31 | Pre analysis hook␊ |
| 32 | ␊ |
| 33 | Filter robots␊ |
| 34 | ␊ |
| 35 | Plugin requirements :␊ |
| 36 | None␊ |
| 37 | ␊ |
| 38 | Conf values needed :␊ |
| 39 | page_to_hit_conf*␊ |
| 40 | hit_to_page_conf*␊ |
| 41 | ␊ |
| 42 | Output files :␊ |
| 43 | None␊ |
| 44 | ␊ |
| 45 | Statistics creation :␊ |
| 46 | None␊ |
| 47 | ␊ |
| 48 | Statistics update :␊ |
| 49 | visits :␊ |
| 50 | remote_addr =>␊ |
| 51 | robot␊ |
| 52 | ␊ |
| 53 | Statistics deletion :␊ |
| 54 | None␊ |
| 55 | """␊ |
| 56 | ␊ |
| 57 | class IWLAPreAnalysisRobots(IPlugin):␊ |
| 58 | def __init__(self, iwla):␊ |
| 59 | super(IWLAPreAnalysisRobots, self).__init__(iwla)␊ |
| 60 | self.API_VERSION = 1␊ |
| 61 | ␊ |
| 62 | def load(self):␊ |
| 63 | self.awstats_robots = list(map(lambda x : re.compile(('.*%s.*') % (x), re.IGNORECASE), awstats_data.robots))␊ |
| 64 | self.robot_re = re.compile(r'.*bot.*', re.IGNORECASE)␊ |
| 65 | self.crawl_re = re.compile(r'.*crawl.*', re.IGNORECASE)␊ |
| 66 | self.logger = logging.getLogger(self.__class__.__name__)␊ |
| 67 | return True␊ |
| 68 | ␊ |
| 69 | def _setRobot(self, k, super_hit):␊ |
| 70 | callerframerecord = inspect.stack()[1]␊ |
| 71 | frame = callerframerecord[0]␊ |
| 72 | info = inspect.getframeinfo(frame)␊ |
| 73 | ␊ |
| 74 | self.logger.debug('%s is a robot (caller %s:%d)' % (k, info.function, info.lineno))␊ |
| 75 | super_hit['robot'] = 1␊ |
| 76 | ␊ |
| 77 | # Basic rule to detect robots␊ |
| 78 | def hook(self):␊ |
| 79 | hits = self.iwla.getCurrentVisits()␊ |
| 80 | for (k, super_hit) in hits.items():␊ |
| 81 | if super_hit['robot']:␊ |
| 82 | self.logger.debug('%s is a robot' % (k))␊ |
| 83 | continue␊ |
| 84 | ␊ |
| 85 | isRobot = False␊ |
| 86 | referers = 0␊ |
| 87 | ␊ |
| 88 | first_page = super_hit['requests'][0]␊ |
| 89 | ␊ |
| 90 | if self.robot_re.match(first_page['http_user_agent']) or\␊ |
| 91 | self.crawl_re.match(first_page['http_user_agent']):␊ |
| 92 | self.logger.debug(first_page['http_user_agent'])␊ |
| 93 | self._setRobot(k, super_hit)␊ |
| 94 | continue␊ |
| 95 | ␊ |
| 96 | for r in self.awstats_robots:␊ |
| 97 | if r.match(first_page['http_user_agent']):␊ |
| 98 | isRobot = True␊ |
| 99 | break␊ |
| 100 | ␊ |
| 101 | if isRobot:␊ |
| 102 | self.logger.debug(first_page['http_user_agent'])␊ |
| 103 | self._setRobot(k, super_hit)␊ |
| 104 | continue␊ |
| 105 | ␊ |
| 106 | # 1) no pages view --> robot␊ |
| 107 | # if not super_hit['viewed_pages'][0]:␊ |
| 108 | # super_hit['robot'] = 1␊ |
| 109 | # continue␊ |
| 110 | ␊ |
| 111 | # 2) Less than 1 hit per page␊ |
| 112 | if super_hit['viewed_pages'][0] and (super_hit['viewed_hits'][0] < super_hit['viewed_pages'][0]):␊ |
| 113 | self._setRobot(k, super_hit)␊ |
| 114 | continue␊ |
| 115 | ␊ |
| 116 | # 3) no pages and not hit --> robot␊ |
| 117 | if not super_hit['viewed_hits'][0] and not super_hit['viewed_pages'][0]:␊ |
| 118 | self._setRobot(k, super_hit)␊ |
| 119 | continue␊ |
| 120 | ␊ |
| 121 | not_found_pages = 0␊ |
| 122 | for hit in super_hit['requests']:␊ |
| 123 | # 5) /robots.txt read␊ |
| 124 | if hit['extract_request']['http_uri'].endswith('/robots.txt'):␊ |
| 125 | self._setRobot(k, super_hit)␊ |
| 126 | break␊ |
| 127 | ␊ |
| 128 | if int(hit['status']) == 404 or int(hit['status']) == 403:␊ |
| 129 | not_found_pages += 1␊ |
| 130 | ␊ |
| 131 | # 6) Any referer for hits␊ |
| 132 | if not hit['is_page'] and hit['http_referer']:␊ |
| 133 | referers += 1␊ |
| 134 | ␊ |
| 135 | if isRobot:␊ |
| 136 | self._setRobot(k, super_hit)␊ |
| 137 | continue␊ |
| 138 | ␊ |
| 139 | # 7) more than 10 404/403 pages␊ |
| 140 | if not_found_pages > 10:␊ |
| 141 | self._setRobot(k, super_hit)␊ |
| 142 | continue␊ |
| 143 | ␊ |
| 144 | if not super_hit['viewed_pages'][0] and \␊ |
| 145 | (super_hit['viewed_hits'][0] and not referers):␊ |
| 146 | self._setRobot(k, super_hit)␊ |
| 147 | continue␊ |
