mirror of https://github.com/searx/searx
A bit of cleanup of the code
- regexes in a array - regexes applied only on the last part of the url
This commit is contained in:
parent
617495cca8
commit
e93f5314d7
|
@ -18,10 +18,9 @@ along with searx. If not, see < http://www.gnu.org/licenses/ >.
|
||||||
from flask.ext.babel import gettext
|
from flask.ext.babel import gettext
|
||||||
import re
|
import re
|
||||||
|
|
||||||
re1 = re.compile(r'utm_[^&]+&?')
|
regexes = {re.compile(r'utm_[^&]+&?'),
|
||||||
re2 = re.compile(r'(wkey|wemail)[^&]+&?')
|
re.compile(r'(wkey|wemail)[^&]+&?'),
|
||||||
re3 = re.compile(r'&$')
|
re.compile(r'&$')}
|
||||||
re4 = re.compile(r'^\?$')
|
|
||||||
|
|
||||||
name = gettext('Tracker URL remover')
|
name = gettext('Tracker URL remover')
|
||||||
description = gettext('Remove trackers arguments from the returned URL')
|
description = gettext('Remove trackers arguments from the returned URL')
|
||||||
|
@ -29,12 +28,17 @@ default_on = True
|
||||||
|
|
||||||
|
|
||||||
def on_result(request, ctx):
|
def on_result(request, ctx):
|
||||||
url = ctx['result']['url']
|
splited_url = ctx['result']['url'].split('?')
|
||||||
|
|
||||||
|
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]
|
||||||
|
|
||||||
url = re1.sub('', url)
|
|
||||||
url = re2.sub('', url)
|
|
||||||
url = re3.sub('', url)
|
|
||||||
url = re4.sub('', url)
|
|
||||||
|
|
||||||
ctx['result']['url'] = url
|
|
||||||
return True
|
return True
|
||||||
|
|
Loading…
Reference in New Issue