searxng/searx/engines/bing_images.py

110 lines
3.1 KiB
Python
Raw Normal View History

# SPDX-License-Identifier: AGPL-3.0-or-later
# lint: pylint
"""Bing-Images: description see :py:obj:`searx.engines.bing`.
"""
# pylint: disable=invalid-name
2014-09-01 12:39:18 +00:00
from typing import TYPE_CHECKING
import json
from urllib.parse import urlencode
2014-09-01 12:39:18 +00:00
from lxml import html
from searx.enginelib.traits import EngineTraits
from searx.engines.bing import set_bing_cookies
from searx.engines.bing import fetch_traits # pylint: disable=unused-import
if TYPE_CHECKING:
import logging
logger = logging.getLogger()
traits: EngineTraits
# about
about = {
"website": 'https://www.bing.com/images',
"wikidata_id": 'Q182496',
"official_api_documentation": 'https://www.microsoft.com/en-us/bing/apis/bing-image-search-api',
"use_official_api": False,
"require_api_key": False,
"results": 'HTML',
}
2014-09-01 12:39:18 +00:00
# engine dependent config
2021-12-22 15:58:52 +00:00
categories = ['images', 'web']
2014-09-01 12:39:18 +00:00
paging = True
safesearch = True
2016-10-30 19:58:34 +00:00
time_range_support = True
2014-09-01 12:39:18 +00:00
base_url = 'https://www.bing.com/images/async'
"""Bing (Images) search URL"""
time_map = {
'day': 60 * 24,
'week': 60 * 24 * 7,
'month': 60 * 24 * 31,
'year': 60 * 24 * 365,
}
2014-09-02 15:13:44 +00:00
2015-02-08 21:01:24 +00:00
2014-09-01 12:39:18 +00:00
def request(query, params):
"""Assemble a Bing-Image request."""
engine_region = traits.get_region(params['searxng_locale'], traits.all_locale) # type: ignore
engine_language = traits.get_language(params['searxng_locale'], 'en') # type: ignore
set_bing_cookies(params, engine_language, engine_region)
2014-09-01 12:39:18 +00:00
# build URL query
# - example: https://www.bing.com/images/async?q=foo&async=content&first=1&count=35
query_params = {
'q': query,
'async': '1',
# to simplify the page count lets use the default of 35 images per page
'first': (int(params.get('pageno', 1)) - 1) * 35 + 1,
'count': 35,
}
# time range
# - example: one year (525600 minutes) 'qft=+filterui:age-lt525600'
if params['time_range']:
query_params['qft'] = 'filterui:age-lt%s' % time_map[params['time_range']]
2014-09-01 12:39:18 +00:00
params['url'] = base_url + '?' + urlencode(query_params)
2014-09-01 12:39:18 +00:00
return params
def response(resp):
"""Get response from Bing-Images"""
2014-09-01 12:39:18 +00:00
results = []
dom = html.fromstring(resp.text)
2014-09-01 12:39:18 +00:00
for result in dom.xpath('//ul[contains(@class, "dgControl_list")]/li'):
metadata = result.xpath('.//a[@class="iusc"]/@m')
if not metadata:
continue
metadata = json.loads(result.xpath('.//a[@class="iusc"]/@m')[0])
title = ' '.join(result.xpath('.//div[@class="infnmpt"]//a/text()')).strip()
img_format = ' '.join(result.xpath('.//div[@class="imgpt"]/div/span/text()')).strip()
source = ' '.join(result.xpath('.//div[@class="imgpt"]//div[@class="lnkw"]//a/text()')).strip()
results.append(
{
'template': 'images.html',
'url': metadata['purl'],
'thumbnail_src': metadata['turl'],
'img_src': metadata['murl'],
'content': metadata['desc'],
'title': title,
'source': source,
'img_format': img_format,
}
)
2014-09-01 12:39:18 +00:00
return results