mirror of
https://github.com/searxng/searxng.git
synced 2024-11-22 20:17:45 +01:00
dc21cb5d4b
- Use result 'alt_description' as title, if not given use
default title 'unknown'.
- Use result 'description' from unsplash as 'content'
Fix error::
DEBUG:searx:result: invalid title: {..., 'title': None, 'content': '', 'engine': 'unsplash'}
Signed-off-by: Markus Heiser <markus.heiser@darmarit.de>
70 lines
1.7 KiB
Python
70 lines
1.7 KiB
Python
# SPDX-License-Identifier: AGPL-3.0-or-later
|
|
# lint: pylint
|
|
# pylint: disable=missing-function-docstring
|
|
"""Unsplash
|
|
|
|
"""
|
|
|
|
from urllib.parse import urlencode, urlparse, urlunparse, parse_qsl
|
|
from json import loads
|
|
|
|
from searx import logger
|
|
|
|
logger = logger.getChild('unsplash engine')
|
|
# about
|
|
about = {
|
|
"website": 'https://unsplash.com',
|
|
"wikidata_id": 'Q28233552',
|
|
"official_api_documentation": 'https://unsplash.com/developers',
|
|
"use_official_api": False,
|
|
"require_api_key": False,
|
|
"results": 'JSON',
|
|
}
|
|
|
|
base_url = 'https://unsplash.com/'
|
|
search_url = base_url + 'napi/search/photos?'
|
|
categories = ['images']
|
|
page_size = 20
|
|
paging = True
|
|
|
|
|
|
def clean_url(url):
|
|
parsed = urlparse(url)
|
|
query = [(k, v) for (k, v)
|
|
in parse_qsl(parsed.query) if k not in ['ixid', 's']]
|
|
|
|
return urlunparse((
|
|
parsed.scheme,
|
|
parsed.netloc,
|
|
parsed.path,
|
|
parsed.params,
|
|
urlencode(query),
|
|
parsed.fragment
|
|
))
|
|
|
|
|
|
def request(query, params):
|
|
params['url'] = search_url + urlencode({
|
|
'query': query, 'page': params['pageno'], 'per_page': page_size
|
|
})
|
|
logger.debug("query_url --> %s", params['url'])
|
|
return params
|
|
|
|
|
|
def response(resp):
|
|
results = []
|
|
json_data = loads(resp.text)
|
|
|
|
if 'results' in json_data:
|
|
for result in json_data['results']:
|
|
results.append({
|
|
'template': 'images.html',
|
|
'url': clean_url(result['links']['html']),
|
|
'thumbnail_src': clean_url(result['urls']['thumb']),
|
|
'img_src': clean_url(result['urls']['raw']),
|
|
'title': result.get('alt_description') or 'unknown',
|
|
'content': result.get('description') or ''
|
|
})
|
|
|
|
return results
|