| import time␊ |
| import re␊ |
| import HTMLParser␊ |
| import xml.sax.saxutils as saxutils␊ |
| ␊ |
| from iwla import IWLA␊ |
| from iplugin import IPlugin␊ |
|
| super(IWLADisplayReferers, self).__init__(iwla)␊ |
| self.API_VERSION = 1␊ |
| ␊ |
| def _getSearchEngine(self, engine):␊ |
| def _getSearchEngine(self, hashid):␊ |
| #print 'Look for %s' % engine␊ |
| for (k, e) in self.search_engines.items():␊ |
| for hashid in e['hashid']:␊ |
| if hashid.match(engine):␊ |
| for (h,h_re) in e['hashid']:␊ |
| if hashid == h:␊ |
| return k␊ |
| print 'Not found %s' % (engine)␊ |
| #print 'Not found %s' % (hashid)␊ |
| return None␊ |
| ␊ |
| def load(self):␊ |
|
| print 'domain_name required in conf'␊ |
| return False␊ |
| ␊ |
| self.own_domain_re = re.compile('.*%s.*' % (domain_name))␊ |
| self.own_domain_re = re.compile(r'.*%s.*' % (domain_name))␊ |
| self.search_engines = {}␊ |
| ␊ |
| for (engine, known_url) in awstats_data.search_engines_knwown_url.items():␊ |
| self.search_engines[engine] = {␊ |
| 'known_url' : re.compile(known_url + '(?P<key_phrase>.+)'),␊ |
| 'hashid' : []␊ |
| }␊ |
| ␊ |
| for (hashid, engine) in awstats_data.search_engines_hashid.items():␊ |
| hashid_re = re.compile('.*%s.*' % (hashid))␊ |
| if not engine in self.search_engines.keys():␊ |
| self.search_engines[engine] = {␊ |
| 'hashid' : [hashid_re]␊ |
| for (hashid, name) in awstats_data.search_engines_hashid.items():␊ |
| hashid_re = re.compile(r'.*%s.*' % (hashid))␊ |
| if not name in self.search_engines.keys():␊ |
| self.search_engines[name] = {␊ |
| 'hashid' : [(hashid, hashid_re)]␊ |
| }␊ |
| else:␊ |
| self.search_engines[engine]['hashid'].append(hashid_re)␊ |
| print 'Hashid %s => %s' % (engine, hashid)␊ |
| self.search_engines[name]['hashid'].append((hashid, hashid_re))␊ |
| #print 'Hashid %s => %s' % (name, hashid)␊ |
| ␊ |
| for (name, known_url) in awstats_data.search_engines_knwown_url.items():␊ |
| self.search_engines[name]['known_url'] = re.compile(known_url + '(?P<key_phrase>.+)')␊ |
| ␊ |
| for (engine, not_engine) in awstats_data.not_search_engines_keys.items():␊ |
| not_engine_re = re.compile('.*%s.*' % (not_engine))␊ |
| not_engine_re = re.compile(r'.*%s.*' % (not_engine))␊ |
| key = self._getSearchEngine(engine)␊ |
| if key:␊ |
| self.search_engines[key]['not_search_engine'] = not_engine_re␊ |
| ␊ |
| for engine in awstats_data.search_engines:␊ |
| engine_re = re.compile('.*%s.*' % (engine), re.IGNORECASE)␊ |
| key = self._getSearchEngine(engine)␊ |
| if key:␊ |
| self.search_engines[key]['re'] = not_engine_re␊ |
| ␊ |
| for (k,e) in self.search_engines.items():␊ |
| if not 're' in e.keys():␊ |
| print 'Remove %s' % k␊ |
| del self.search_engines[k]␊ |
| ␊ |
| print self.search_engines␊ |
| ␊ |
| self.html_parser = HTMLParser.HTMLParser()␊ |
| #self.html_parser = html.parser.HTMLParser()␊ |
| ␊ |
| return True␊ |
| ␊ |
|
| for p in parameters.split('&'):␊ |
| groups = key_phrase_re.match(p)␊ |
| if groups:␊ |
| print groups.groupddict()␊ |
| key_phrase = self.html_parser.unescape(groups.groupddict()['key_phrase']).lower()␊ |
| key_phrase = groups.groupdict()['key_phrase']␊ |
| key_phrase = key_phrase.replace('+', ' ').lower()␊ |
| key_phrase = saxutils.unescape(key_phrase)␊ |
| if not key_phrase in key_phrases.keys():␊ |
| key_phrases[key_phrase] = 1␊ |
| else:␊ |
| key_phrases[key_phrase] += 1␊ |
| break␊ |
| ␊ |
| def hook(self, iwla):␊ |
| stats = iwla.getCurrentVisists()␊ |
|
| ␊ |
| if self.own_domain_re.match(uri): continue␊ |
| ␊ |
| for e in self.search_engines.values():␊ |
| if e['re'].match(uri):␊ |
| not_engine = e.get('not_search_engine', None)␊ |
| for (name, engine) in self.search_engines.items():␊ |
| for (hashid, hashid_re) in engine['hashid']:␊ |
| if not hashid_re.match(uri): continue␊ |
| ␊ |
| not_engine = engine.get('not_search_engine', None)␊ |
| # Try not engine␊ |
| if not_engine and not_engine.match(uri): break␊ |
| is_search_engine = True␊ |
| uri = e['name']␊ |
| uri = name␊ |
| ␊ |
| parameters = r['extract_referer'].get('extract_parameters', None)␊ |
| key_phrase_re = e.get('known_url', None)␊ |
| ␊ |
| # print parameters␊ |
| # print key_phrase_re␊ |
| key_phrase_re = engine.get('known_url', None)␊ |
| ␊ |
| self._extractKeyPhrase(key_phrase_re, parameters, key_phrases)␊ |
| ␊ |
| break␊ |
| ␊ |
| if is_search_engine:␊ |
|
| page.appendBlock(table)␊ |
| ␊ |
| display.addPage(page)␊ |
| ␊ |
| block = DisplayHTMLRawBlock()␊ |
| block.setRawHTML('<a href=\'%s\'>All key phrases</a>' % (filename))␊ |
| index.appendBlock(block)␊ |
