From e93f5314d745ca389858fdf53f355d8c28928507 Mon Sep 17 00:00:00 2001 From: Cqoicebordel Date: Mon, 15 Jun 2015 20:34:02 +0200 Subject: [PATCH] A bit of cleanup of the code - regexes in a array - regexes applied only on the last part of the url --- searx/plugins/tracker_url_remover.py | 24 ++++++++++++++---------- 1 file changed, 14 insertions(+), 10 deletions(-) diff --git a/searx/plugins/tracker_url_remover.py b/searx/plugins/tracker_url_remover.py index c8459548f..f6ecc2126 100644 --- a/searx/plugins/tracker_url_remover.py +++ b/searx/plugins/tracker_url_remover.py @@ -18,10 +18,9 @@ along with searx. If not, see < http://www.gnu.org/licenses/ >. from flask.ext.babel import gettext import re -re1 = re.compile(r'utm_[^&]+&?') -re2 = re.compile(r'(wkey|wemail)[^&]+&?') -re3 = re.compile(r'&$') -re4 = re.compile(r'^\?$') +regexes = {re.compile(r'utm_[^&]+&?'), + re.compile(r'(wkey|wemail)[^&]+&?'), + re.compile(r'&$')} name = gettext('Tracker URL remover') description = gettext('Remove trackers arguments from the returned URL') @@ -29,12 +28,17 @@ default_on = True def on_result(request, ctx): - url = ctx['result']['url'] + splited_url = ctx['result']['url'].split('?') - url = re1.sub('', url) - url = re2.sub('', url) - url = re3.sub('', url) - url = re4.sub('', url) + if len(splited_url) is not 2: + return True + + for reg in regexes: + splited_url[1] = reg.sub('', splited_url[1]) + + if splited_url[1] == "": + ctx['result']['url'] = splited_url[0] + else: + ctx['result']['url'] = splited_url[0] + '?' + splited_url[1] - ctx['result']['url'] = url return True