diff --git a/plugins/pre_analysis/robots.py b/plugins/pre_analysis/robots.py index 0c4bb96..41c744e 100644 --- a/plugins/pre_analysis/robots.py +++ b/plugins/pre_analysis/robots.py @@ -19,6 +19,7 @@ # import re +import logging from iwla import IWLA from iplugin import IPlugin @@ -61,13 +62,20 @@ class IWLAPreAnalysisRobots(IPlugin): self.awstats_robots = map(lambda (x) : re.compile(('.*%s.*') % (x), re.IGNORECASE), awstats_data.robots) self.robot_re = re.compile(r'.*bot.*', re.IGNORECASE) self.crawl_re = re.compile(r'.*crawl.*', re.IGNORECASE) + self.logger = logging.getLogger(self.__class__.__name__) return True + def _setRobot(self, k, super_hit): + self.logger.debug('%s is a robot' % (k)) + super_hit['robot'] = 1 + # Basic rule to detect robots def hook(self): hits = self.iwla.getCurrentVisists() for (k, super_hit) in hits.items(): - if super_hit['robot']: continue + if super_hit['robot']: + self.logger.debug('%s is a robot' % (k)) + continue isRobot = False referers = 0 @@ -76,7 +84,7 @@ class IWLAPreAnalysisRobots(IPlugin): if self.robot_re.match(first_page['http_user_agent']) or\ self.crawl_re.match(first_page['http_user_agent']): - super_hit['robot'] = 1 + self._setRobot(k, super_hit) continue for r in self.awstats_robots: @@ -85,7 +93,7 @@ class IWLAPreAnalysisRobots(IPlugin): break if isRobot: - super_hit['robot'] = 1 + self._setRobot(k, super_hit) continue # 1) no pages view --> robot @@ -95,13 +103,13 @@ class IWLAPreAnalysisRobots(IPlugin): # 2) pages without hit --> robot if not super_hit['viewed_hits']: - super_hit['robot'] = 1 + self._setRobot(k, super_hit) continue for hit in super_hit['requests']: # 3) /robots.txt read if hit['extract_request']['http_uri'].endswith('/robots.txt'): - isRobot = True + self._setRobot(k, super_hit) break # 4) Any referer for hits @@ -109,10 +117,10 @@ class IWLAPreAnalysisRobots(IPlugin): referers += 1 if isRobot: - super_hit['robot'] = 1 + self._setRobot(k, super_hit) continue if not super_hit['viewed_pages'] and \ (super_hit['viewed_hits'] and not referers): - super_hit['robot'] = 1 + self._setRobot(k, super_hit) continue