mirror of
https://github.com/searxng/searxng.git
synced 2024-11-16 17:40:11 +01:00
dc29f1d826
These py files are linted by `test.pylint`, all other files are linted by `test.pep8`. Signed-off-by: Markus Heiser <markus.heiser@darmarit.de>
76 lines
2.0 KiB
Python
76 lines
2.0 KiB
Python
# SPDX-License-Identifier: AGPL-3.0-or-later
|
|
# lint: pylint
|
|
"""Springer Nature (science)
|
|
|
|
"""
|
|
|
|
# pylint: disable=missing-function-docstring
|
|
|
|
from datetime import datetime
|
|
from json import loads
|
|
from urllib.parse import urlencode
|
|
|
|
from searx import logger
|
|
from searx.exceptions import SearxEngineAPIException
|
|
|
|
logger = logger.getChild('Springer Nature engine')
|
|
|
|
about = {
|
|
"website": 'https://www.springernature.com/',
|
|
"wikidata_id": 'Q21096327',
|
|
"official_api_documentation": 'https://dev.springernature.com/',
|
|
"use_official_api": True,
|
|
"require_api_key": True,
|
|
"results": 'JSON',
|
|
}
|
|
|
|
categories = ['science']
|
|
paging = True
|
|
nb_per_page = 10
|
|
api_key = 'unset'
|
|
|
|
base_url = 'https://api.springernature.com/metadata/json?'
|
|
|
|
def request(query, params):
|
|
if api_key == 'unset':
|
|
raise SearxEngineAPIException('missing Springer-Nature API key')
|
|
args = urlencode({
|
|
'q' : query,
|
|
's' : nb_per_page * (params['pageno'] - 1),
|
|
'p' : nb_per_page,
|
|
'api_key' : api_key
|
|
})
|
|
params['url'] = base_url + args
|
|
logger.debug("query_url --> %s", params['url'])
|
|
return params
|
|
|
|
|
|
def response(resp):
|
|
results = []
|
|
json_data = loads(resp.text)
|
|
|
|
for record in json_data['records']:
|
|
content = record['abstract'][0:500]
|
|
if len(record['abstract']) > len(content):
|
|
content += "..."
|
|
published = datetime.strptime(record['publicationDate'], '%Y-%m-%d')
|
|
|
|
metadata = [record[x] for x in [
|
|
'publicationName',
|
|
'identifier',
|
|
'contentType',
|
|
] if record.get(x) is not None]
|
|
|
|
metadata = ' / '.join(metadata)
|
|
if record.get('startingPage') and record.get('endingPage') is not None:
|
|
metadata += " (%(startingPage)s-%(endingPage)s)" % record
|
|
|
|
results.append({
|
|
'title': record['title'],
|
|
'url': record['url'][0]['value'].replace('http://', 'https://', 1),
|
|
'content' : content,
|
|
'publishedDate' : published,
|
|
'metadata' : metadata
|
|
})
|
|
return results
|