1
0
mirror of https://github.com/searxng/searxng.git synced 2024-11-22 12:10:11 +01:00
searxng/searx/plugins/oa_doi_rewrite.py
Markus Heiser 542f7d0d7b [mod] pylint all files with one profile / drop PYLINT_SEARXNG_DISABLE_OPTION
In the past, some files were tested with the standard profile, others with a
profile in which most of the messages were switched off ... some files were not
checked at all.

- ``PYLINT_SEARXNG_DISABLE_OPTION`` has been abolished
- the distinction ``# lint: pylint`` is no longer necessary
- the pylint tasks have been reduced from three to two

  1. ./searx/engines -> lint engines with additional builtins
  2. ./searx ./searxng_extra ./tests -> lint all other python files

Signed-off-by: Markus Heiser <markus.heiser@darmarit.de>
2024-03-11 14:55:38 +01:00

51 lines
1.5 KiB
Python

# SPDX-License-Identifier: AGPL-3.0-or-later
# pylint: disable=missing-module-docstring
import re
from urllib.parse import urlparse, parse_qsl
from flask_babel import gettext
from searx import settings
regex = re.compile(r'10\.\d{4,9}/[^\s]+')
name = gettext('Open Access DOI rewrite')
description = gettext('Avoid paywalls by redirecting to open-access versions of publications when available')
default_on = False
preference_section = 'general'
def extract_doi(url):
match = regex.search(url.path)
if match:
return match.group(0)
for _, v in parse_qsl(url.query):
match = regex.search(v)
if match:
return match.group(0)
return None
def get_doi_resolver(preferences):
doi_resolvers = settings['doi_resolvers']
selected_resolver = preferences.get_value('doi_resolver')[0]
if selected_resolver not in doi_resolvers:
selected_resolver = settings['default_doi_resolver']
return doi_resolvers[selected_resolver]
def on_result(request, _search, result):
if 'parsed_url' not in result:
return True
doi = extract_doi(result['parsed_url'])
if doi and len(doi) < 50:
for suffix in ('/', '.pdf', '.xml', '/full', '/meta', '/abstract'):
if doi.endswith(suffix):
doi = doi[: -len(suffix)]
result['url'] = get_doi_resolver(request.preferences) + doi
result['parsed_url'] = urlparse(result['url'])
if 'doi' not in result:
result['doi'] = doi
return True