mirror of
https://github.com/searxng/searxng.git
synced 2026-09-12 17:26:05 +00:00
923a307454
The ``mkt`` argument does no longer exists and the ``async`` argument has been renamed to ``mmasync``. For still unknown reasons (IP based?), some users had to observe that the title was missing [1]. I myself was not able to reproduce this error, however the evaluation of the title was additionally expanded by the attribute value of the ``<a title=".."`` element. Related: - [1] https://github.com/searxng/searxng/pull/6690#issuecomment-5636811572 Signed-off-by: Markus Heiser <markus.heiser@darmarit.de>
101 lines
3.0 KiB
Python
101 lines
3.0 KiB
Python
# SPDX-License-Identifier: AGPL-3.0-or-later
|
|
"""Bing-Images: description see :py:obj:`searx.engines.bing`."""
|
|
|
|
import json
|
|
from urllib.parse import urlencode
|
|
|
|
from lxml import html
|
|
|
|
from searx.engines.bing import fetch_traits # pylint: disable=unused-import
|
|
|
|
# about
|
|
about = {
|
|
"website": "https://www.bing.com/images",
|
|
"wikidata_id": "Q182496",
|
|
"official_api_documentation": "https://github.com/MicrosoftDocs/bing-docs",
|
|
"use_official_api": False,
|
|
"require_api_key": False,
|
|
"results": "HTML",
|
|
}
|
|
|
|
# engine dependent config
|
|
categories = ["images", "web"]
|
|
paging = True
|
|
enable_http3 = True
|
|
safesearch = True
|
|
time_range_support = True
|
|
time_map = {
|
|
"day": 60 * 24,
|
|
"week": 60 * 24 * 7,
|
|
"month": 60 * 24 * 31,
|
|
"year": 60 * 24 * 365,
|
|
}
|
|
|
|
base_url = "https://www.bing.com"
|
|
"""Bing-Image search URL"""
|
|
|
|
|
|
def request(query, params):
|
|
"""Assemble a Bing-Image request."""
|
|
|
|
engine_region = traits.get_region(params["searxng_locale"], traits.all_locale)
|
|
|
|
# build URL query
|
|
# - example: https://www.bing.com/images/async?q=foo&mmasync=1&first=1&count=35
|
|
|
|
query_params = {
|
|
"q": query,
|
|
"mmasync": "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,
|
|
}
|
|
|
|
if engine_region and engine_region != "clear":
|
|
lang, _, cc = engine_region.partition("-")
|
|
query_params["setlang"] = lang
|
|
if cc:
|
|
query_params["cc"] = cc
|
|
|
|
# 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"]]
|
|
|
|
params["url"] = base_url + "/images/async?" + urlencode(query_params)
|
|
|
|
|
|
def response(resp):
|
|
"""Get response from Bing-Image"""
|
|
|
|
results = []
|
|
|
|
dom = html.fromstring(resp.text)
|
|
|
|
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()
|
|
if not title:
|
|
title = result.xpath('.//div[@class="infnmpt"]//a/@title')[0]
|
|
|
|
img_format = " ".join(result.xpath('.//div[@class="imgpt"]/div/span/text()')).strip().split(" · ")
|
|
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.get("desc"),
|
|
"title": title,
|
|
"source": source,
|
|
"resolution": img_format[0],
|
|
"img_format": img_format[1] if len(img_format) >= 2 else None,
|
|
}
|
|
)
|
|
return results
|