mirror of
https://github.com/searxng/searxng.git
synced 2024-06-02 13:29:22 +00:00
86b4d2f2d0
We have been using a static type checker (pyright) for a long time, but its check was not yet a prerequisite for passing the quality gate. It was checked in the CI, but the error messages were only logged. As is always the case in life, with checks that you have to do but which have no consequences; you neglect them :-) We didn't activate the checks back then because we (even today) have too much monkey patching in our code (not only in the engines, httpx and others objects are also affected). We want to replace monkey patching with clear interfaces for a long time, the basis for this is increased typing and we can only achieve this if we make type checking an integral part of the quality gate. This PR activates the type check; in order to pass the check, a few typings were corrected in the code, but most type inconsistencies were deactivated via inline comments. This was particularly necessary in places where the code uses properties that stick to the objects (monkey patching). The sticking of properties only happens in a few places, but the access to these properties extends over the entire code, which is why there are many `# type: ignore` markers in the code ... which we will hopefully be able to remove again successively in the future. Signed-off-by: Markus Heiser <markus.heiser@darmarit.de>
117 lines
3.1 KiB
Python
Executable file
117 lines
3.1 KiB
Python
Executable file
# SPDX-License-Identifier: AGPL-3.0-or-later
|
|
"""BASE (Scholar publications)
|
|
|
|
"""
|
|
from datetime import datetime
|
|
import re
|
|
|
|
from urllib.parse import urlencode
|
|
from lxml import etree # type: ignore
|
|
from searx.utils import searx_useragent
|
|
|
|
# about
|
|
about = {
|
|
"website": 'https://base-search.net',
|
|
"wikidata_id": 'Q448335',
|
|
"official_api_documentation": 'https://api.base-search.net/',
|
|
"use_official_api": True,
|
|
"require_api_key": False,
|
|
"results": 'XML',
|
|
}
|
|
|
|
categories = ['science']
|
|
|
|
base_url = (
|
|
'https://api.base-search.net/cgi-bin/BaseHttpSearchInterface.fcgi'
|
|
+ '?func=PerformSearch&{query}&boost=oa&hits={hits}&offset={offset}'
|
|
)
|
|
|
|
# engine dependent config
|
|
paging = True
|
|
number_of_results = 10
|
|
|
|
# shortcuts for advanced search
|
|
shorcut_dict = {
|
|
# user-friendly keywords
|
|
'format:': 'dcformat:',
|
|
'author:': 'dccreator:',
|
|
'collection:': 'dccollection:',
|
|
'hdate:': 'dchdate:',
|
|
'contributor:': 'dccontributor:',
|
|
'coverage:': 'dccoverage:',
|
|
'date:': 'dcdate:',
|
|
'abstract:': 'dcdescription:',
|
|
'urls:': 'dcidentifier:',
|
|
'language:': 'dclanguage:',
|
|
'publisher:': 'dcpublisher:',
|
|
'relation:': 'dcrelation:',
|
|
'rights:': 'dcrights:',
|
|
'source:': 'dcsource:',
|
|
'subject:': 'dcsubject:',
|
|
'title:': 'dctitle:',
|
|
'type:': 'dcdctype:',
|
|
}
|
|
|
|
|
|
def request(query, params):
|
|
# replace shortcuts with API advanced search keywords
|
|
for key, val in shorcut_dict.items():
|
|
query = re.sub(key, val, query)
|
|
|
|
# basic search
|
|
offset = (params['pageno'] - 1) * number_of_results
|
|
|
|
string_args = {
|
|
'query': urlencode({'query': query}),
|
|
'offset': offset,
|
|
'hits': number_of_results,
|
|
}
|
|
|
|
params['url'] = base_url.format(**string_args)
|
|
|
|
params['headers']['User-Agent'] = searx_useragent()
|
|
return params
|
|
|
|
|
|
def response(resp):
|
|
results = []
|
|
|
|
search_results = etree.XML(resp.content)
|
|
|
|
for entry in search_results.xpath('./result/doc'):
|
|
content = "No description available"
|
|
|
|
date = datetime.now() # needed in case no dcdate is available for an item
|
|
for item in entry:
|
|
if item.attrib["name"] == "dcdate":
|
|
date = item.text
|
|
|
|
elif item.attrib["name"] == "dctitle":
|
|
title = item.text
|
|
|
|
elif item.attrib["name"] == "dclink":
|
|
url = item.text
|
|
|
|
elif item.attrib["name"] == "dcdescription":
|
|
content = item.text[:300]
|
|
if len(item.text) > 300:
|
|
content += "..."
|
|
|
|
# dates returned by the BASE API are not several formats
|
|
publishedDate = None
|
|
for date_format in ['%Y-%m-%dT%H:%M:%SZ', '%Y-%m-%d', '%Y-%m', '%Y']:
|
|
try:
|
|
publishedDate = datetime.strptime(date, date_format)
|
|
break
|
|
except: # pylint: disable=bare-except
|
|
pass
|
|
|
|
if publishedDate is not None:
|
|
res_dict = {'url': url, 'title': title, 'publishedDate': publishedDate, 'content': content}
|
|
else:
|
|
res_dict = {'url': url, 'title': title, 'content': content}
|
|
|
|
results.append(res_dict)
|
|
|
|
return results
|