tracker_url_remover.py 1.6 KB

1234567891011121314151617181920212223242526272829303132333435363738394041424344454647484950515253
  1. '''
  2. searx is free software: you can redistribute it and/or modify
  3. it under the terms of the GNU Affero General Public License as published by
  4. the Free Software Foundation, either version 3 of the License, or
  5. (at your option) any later version.
  6. searx is distributed in the hope that it will be useful,
  7. but WITHOUT ANY WARRANTY; without even the implied warranty of
  8. MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
  9. GNU Affero General Public License for more details.
  10. You should have received a copy of the GNU Affero General Public License
  11. along with searx. If not, see < http://www.gnu.org/licenses/ >.
  12. (C) 2015 by Adam Tauber, <asciimoo@gmail.com>
  13. '''
  14. from flask_babel import gettext
  15. import re
  16. from urllib.parse import urlunparse, parse_qsl, urlencode
  17. regexes = {re.compile(r'utm_[^&]+'),
  18. re.compile(r'(wkey|wemail)[^&]*'),
  19. re.compile(r'&$')}
  20. name = gettext('Tracker URL remover')
  21. description = gettext('Remove trackers arguments from the returned URL')
  22. default_on = True
  23. preference_section = 'privacy'
  24. def on_result(request, search, result):
  25. if 'parsed_url' not in result:
  26. return True
  27. query = result['parsed_url'].query
  28. if query == "":
  29. return True
  30. parsed_query = parse_qsl(query)
  31. changes = 0
  32. for i, (param_name, _) in enumerate(list(parsed_query)):
  33. for reg in regexes:
  34. if reg.match(param_name):
  35. parsed_query.pop(i - changes)
  36. changes += 1
  37. result['parsed_url'] = result['parsed_url']._replace(query=urlencode(parsed_query))
  38. result['url'] = urlunparse(result['parsed_url'])
  39. break
  40. return True