mirror of
https://github.com/searxng/searxng.git
synced 2024-12-23 17:50:29 +00:00
43dc9eb7d6
Upstream example query: https://petalsearch.com/search?query=test&channel=image&ps=50&pn=1®ion=de-de&ss_mode=off&ss_type=normal Depending on locale it will internally use some/all results from other engines. See: https://seirdy.one/posts/2021/03/10/search-engines-with-own-indexes/#general-indexing-search-engines
94 lines
2.2 KiB
Python
94 lines
2.2 KiB
Python
# SPDX-License-Identifier: AGPL-3.0-or-later
|
|
"""Petalsearch Images
|
|
|
|
"""
|
|
|
|
from json import loads
|
|
from urllib.parse import urlencode
|
|
from datetime import datetime
|
|
|
|
from lxml import html
|
|
|
|
from searx.utils import extract_text
|
|
|
|
about = {
|
|
"website": 'https://petalsearch.com/',
|
|
"wikidata_id": 'Q104399280',
|
|
"official_api_documentation": False,
|
|
"use_official_api": False,
|
|
"require_api_key": False,
|
|
"results": 'JSON',
|
|
}
|
|
|
|
categories = ['images']
|
|
paging = True
|
|
time_range_support = False
|
|
|
|
safesearch = True
|
|
safesearch_table = {0: 'off', 1: 'moderate', 2: 'on'}
|
|
|
|
base_url = 'https://petalsearch.com/'
|
|
search_string = 'search?{query}&channel=image&ps=50&pn={page}®ion={lang}&ss_mode={safesearch}&ss_type=normal'
|
|
|
|
|
|
def request(query, params):
|
|
|
|
search_path = search_string.format(
|
|
query=urlencode({'query': query}),
|
|
page=params['pageno'],
|
|
lang=params['language'].lower(),
|
|
safesearch=safesearch_table[params['safesearch']],
|
|
)
|
|
|
|
params['url'] = base_url + search_path
|
|
|
|
return params
|
|
|
|
|
|
def response(resp):
|
|
results = []
|
|
|
|
tree = html.fromstring(resp.text)
|
|
root = tree.findall('.//script[3]')
|
|
|
|
# Convert list to JSON
|
|
json_content = extract_text(root)
|
|
|
|
# Manipulate with JSON
|
|
data = loads(json_content)
|
|
|
|
for result in data['newImages']:
|
|
url = result['url']
|
|
title = result['title']
|
|
thumbnail_src = result['image']
|
|
|
|
pic_dict = result.get('extrainfo')
|
|
|
|
date_from_api = pic_dict.get('publish_time')
|
|
width = pic_dict.get('width')
|
|
height = pic_dict.get('height')
|
|
img_src = pic_dict.get('real_url')
|
|
|
|
# Continue if img_src is missing
|
|
if img_src is None or '':
|
|
continue
|
|
|
|
# Get and convert published date
|
|
if date_from_api is not None:
|
|
publishedDate = datetime.fromtimestamp(int(date_from_api))
|
|
|
|
# Append results
|
|
results.append(
|
|
{
|
|
'template': 'images.html',
|
|
'url': url,
|
|
'title': title,
|
|
'img_src': img_src,
|
|
'thumbnail_src': thumbnail_src,
|
|
'width': width,
|
|
'height': height,
|
|
'publishedDate': publishedDate,
|
|
}
|
|
)
|
|
|
|
return results
|