2021-02-03 19:13:39 +01:00
|
|
|
# SPDX-License-Identifier: AGPL-3.0-or-later
|
|
|
|
"""
|
|
|
|
|
Pick minor fixes from searxng (#3251)
* [fix] Rename ccengine engine to openverse
The CC engine was merged with WordPress and renamed to Openverse
Source: https://wordpress.org/news/2021/05/welcome-to-openverse/
* [fix] ccengine engine - avoid unwanted redirects
api.openverse.engineering is a little picky and wants to have a trailing slash
in the path:
/v1/images? -->/ v1/images/?
otherwise it redirects, here is the debug log:
DEBUG searx.network.openverse : HTTP Request: GET https://api.openverse.engineering/v1/images?&page=1&page_size=20&format=json&q=foo "HTTP/2 301 Moved Permanently" (text/html; charset=utf-8)
DEBUG searx.network.openverse : HTTP Request: GET https://api.openverse.engineering/v1/images/?&page=1&page_size=20&format=json&q=foo "HTTP/2 200 OK" (application/json)
WARNING searx.engines.openverse : ErrorContext('searx/search/processors/online.py', 105, 'count_error(', None, '1 redirects, maximum: 0', ('200', 'OK', 'api.openverse.engineering')) True
Signed-off-by: Markus Heiser <markus.heiser@darmarit.de>
* [fix] FutureWarning from lxml
Just in case if content is None, the original code will skip extract_text(), and
just append the None value to 'content'. So just add allow_none=True, and this
will return None without raising a ValueError in extract_text().
* [enh] Add pagination to Brave
Also added ```&spellcheck=1``` because now it is disabled by default, not returning any ```suggestion_xpath```.
Co-authored-by: Léon Tiekötter <leon@tiekoetter.com>
Co-authored-by: Markus Heiser <markus.heiser@darmarit.de>
Co-authored-by: capric98 <42015599+capric98@users.noreply.github.com>
Co-authored-by: Allen <64094914+allendema@users.noreply.github.com>
2022-06-06 00:01:27 +02:00
|
|
|
Openverse (formerly known as: Creative Commons search engine) [Images]
|
2021-02-03 19:13:39 +01:00
|
|
|
|
|
|
|
"""
|
|
|
|
|
|
|
|
from json import loads
|
|
|
|
from urllib.parse import urlencode
|
|
|
|
|
|
|
|
|
|
|
|
about = {
|
|
|
|
"website": 'https://search.creativecommons.org/',
|
|
|
|
"wikidata_id": None,
|
|
|
|
"official_api_documentation": 'https://api.creativecommons.engineering/v1/',
|
|
|
|
"use_official_api": True,
|
|
|
|
"require_api_key": False,
|
|
|
|
"results": 'JSON',
|
|
|
|
}
|
|
|
|
|
|
|
|
categories = ['images']
|
|
|
|
|
|
|
|
paging = True
|
|
|
|
nb_per_page = 20
|
|
|
|
|
Pick minor fixes from searxng (#3251)
* [fix] Rename ccengine engine to openverse
The CC engine was merged with WordPress and renamed to Openverse
Source: https://wordpress.org/news/2021/05/welcome-to-openverse/
* [fix] ccengine engine - avoid unwanted redirects
api.openverse.engineering is a little picky and wants to have a trailing slash
in the path:
/v1/images? -->/ v1/images/?
otherwise it redirects, here is the debug log:
DEBUG searx.network.openverse : HTTP Request: GET https://api.openverse.engineering/v1/images?&page=1&page_size=20&format=json&q=foo "HTTP/2 301 Moved Permanently" (text/html; charset=utf-8)
DEBUG searx.network.openverse : HTTP Request: GET https://api.openverse.engineering/v1/images/?&page=1&page_size=20&format=json&q=foo "HTTP/2 200 OK" (application/json)
WARNING searx.engines.openverse : ErrorContext('searx/search/processors/online.py', 105, 'count_error(', None, '1 redirects, maximum: 0', ('200', 'OK', 'api.openverse.engineering')) True
Signed-off-by: Markus Heiser <markus.heiser@darmarit.de>
* [fix] FutureWarning from lxml
Just in case if content is None, the original code will skip extract_text(), and
just append the None value to 'content'. So just add allow_none=True, and this
will return None without raising a ValueError in extract_text().
* [enh] Add pagination to Brave
Also added ```&spellcheck=1``` because now it is disabled by default, not returning any ```suggestion_xpath```.
Co-authored-by: Léon Tiekötter <leon@tiekoetter.com>
Co-authored-by: Markus Heiser <markus.heiser@darmarit.de>
Co-authored-by: capric98 <42015599+capric98@users.noreply.github.com>
Co-authored-by: Allen <64094914+allendema@users.noreply.github.com>
2022-06-06 00:01:27 +02:00
|
|
|
base_url = 'https://api.openverse.engineering/v1/images/'
|
|
|
|
search_string = '?page={page}&page_size={nb_per_page}&format=json&{query}'
|
2021-02-03 19:13:39 +01:00
|
|
|
|
|
|
|
|
|
|
|
def request(query, params):
|
|
|
|
|
|
|
|
search_path = search_string.format(
|
|
|
|
query=urlencode({'q': query}),
|
|
|
|
nb_per_page=nb_per_page,
|
|
|
|
page=params['pageno'])
|
|
|
|
|
|
|
|
params['url'] = base_url + search_path
|
|
|
|
|
|
|
|
return params
|
|
|
|
|
|
|
|
|
|
|
|
def response(resp):
|
|
|
|
results = []
|
|
|
|
|
|
|
|
json_data = loads(resp.text)
|
|
|
|
|
|
|
|
for result in json_data['results']:
|
|
|
|
results.append({'url': result['foreign_landing_url'],
|
|
|
|
'title': result['title'],
|
|
|
|
'img_src': result['url'],
|
|
|
|
'template': 'images.html'})
|
|
|
|
|
|
|
|
return results
|