mirror of
https://github.com/searxng/searxng.git
synced 2026-09-23 06:36:12 +00:00
280aceb1ae
Engines like Pexels provide images that one would more likely expect in a category named ``stock_images``. By classifying engines like Pexels more precisely, we enable a more specific handling of them, which also helps to avoid mixing them with the more general image search on the internet. [1] We leave these engines *enabled* by default, take them out of ``images`` and move them into the specialization ``stock_images``. This makes it possible, on the one hand, for the admin to configure a tab in the UI, and on the other hand, the user can always select the group directly using the search syntax ``!stock_images ...``. What we need to keep in mind: 1. Technically speaking, there are no subcategories in the strict sense. Organizationally, the *subcategories* are derived from the `categories_as_tabs`. 2. From an admin’s perspective, `categories_as_tabs` is the tool for structuring their content. 3. In the context of “enabled/disabled by default”: We should avoid having the admin have to activate many individual engines when they want to structure their content (UI tabs). So if we leave an engine enabled by default and **move** it from `images` to a new category, the admin only needs to add the new category to `categories_as_tabs` to restructure their content. If the new category is also part of the translations (see `searx/searxng.msg` in this PR), this UI structure would also be available internationally. [1] https://github.com/searxng/searxng/pull/6690#issuecomment-5646291679 Signed-off-by: Markus Heiser <markus.heiser@darmarit.de>
121 lines
3.5 KiB
Python
121 lines
3.5 KiB
Python
# SPDX-License-Identifier: AGPL-3.0-or-later
|
|
"""Pexels (images)"""
|
|
|
|
import re
|
|
import typing as t
|
|
|
|
from urllib.parse import urlencode
|
|
|
|
from searx.result_types import EngineResults
|
|
from searx.utils import eval_xpath_list
|
|
from searx.enginelib import EngineCache
|
|
from searx.exceptions import SearxEngineAPIException, SearxEngineAccessDeniedException
|
|
from searx.network import get
|
|
|
|
if t.TYPE_CHECKING:
|
|
from extended_types import SXNG_Response
|
|
from search.processors.online import OnlineParams
|
|
|
|
about = {
|
|
"website": "https://www.pexels.com",
|
|
"wikidata_id": "Q101240504",
|
|
"official_api_documentation": "https://www.pexels.com/api/",
|
|
"use_official_api": False,
|
|
"require_api_key": False,
|
|
"results": "JSON",
|
|
}
|
|
|
|
base_url = "https://www.pexels.com"
|
|
categories = ["stock_images"]
|
|
|
|
api_key = "H2jk9uKnhRmL6WPwh89zBezWvr"
|
|
"""
|
|
Fallback API key to use when SearXNG fails to automatically extract one from the website.
|
|
"""
|
|
results_per_page = 20
|
|
|
|
paging = True
|
|
time_range_support = True
|
|
time_range_map = {"day": "last_24_hours", "week": "last_week", "month": "last_month", "year": "last_year"}
|
|
|
|
SECRET_KEY_RE = re.compile('"secret-key":\b*"(.*?)"')
|
|
SECRET_KEY_DB_KEY = "secret-key"
|
|
|
|
|
|
CACHE: EngineCache
|
|
"""Cache to store the secret API key for the engine."""
|
|
|
|
|
|
def setup(engine_settings: dict[str, t.Any]) -> bool:
|
|
global CACHE # pylint: disable=global-statement
|
|
CACHE = EngineCache(engine_settings["name"])
|
|
return True
|
|
|
|
|
|
def _get_secret_key():
|
|
resp = get(
|
|
base_url,
|
|
headers={"Referer": base_url},
|
|
)
|
|
|
|
if resp.status_code != 200:
|
|
raise SearxEngineAPIException("failed to obtain secret key")
|
|
|
|
doc = resp.html()
|
|
for script_src in eval_xpath_list(doc, "//script/@src"):
|
|
script = get(script_src)
|
|
if script.status_code != 200:
|
|
raise SearxEngineAPIException("failed to obtain secret key")
|
|
|
|
match = SECRET_KEY_RE.search(script.text)
|
|
if match:
|
|
return match.groups()[0]
|
|
|
|
# all scripts checked, but secret key was not found
|
|
raise SearxEngineAPIException("failed to obtain secret key")
|
|
|
|
|
|
def request(query: str, params: "OnlineParams"):
|
|
args = {
|
|
"query": query,
|
|
"page": params["pageno"],
|
|
"per_page": results_per_page,
|
|
}
|
|
if params["time_range"]:
|
|
args["date_from"] = time_range_map[params["time_range"]]
|
|
|
|
params["url"] = f"{base_url}/en-us/api/v3/search/photos?{urlencode(args)}"
|
|
|
|
# cache api key for future requests
|
|
secret_key = CACHE.get(SECRET_KEY_DB_KEY)
|
|
if not secret_key:
|
|
try:
|
|
secret_key = _get_secret_key()
|
|
CACHE.set(SECRET_KEY_DB_KEY, secret_key)
|
|
except (SearxEngineAPIException, SearxEngineAccessDeniedException) as e:
|
|
logger.debug("failed to extract API key %s" % e)
|
|
secret_key = api_key
|
|
|
|
params["headers"]["secret-key"] = secret_key
|
|
|
|
|
|
def response(resp: "SXNG_Response") -> EngineResults:
|
|
res = EngineResults()
|
|
json_data = resp.json()
|
|
|
|
for result in json_data.get("data", []):
|
|
attrs = result["attributes"]
|
|
res.add(
|
|
res.types.Image(
|
|
url=f"{base_url}/photo/{attrs['slug']}-{attrs['id']}/",
|
|
title=attrs["title"],
|
|
content=attrs["description"],
|
|
thumbnail_src=attrs["image"]["small"],
|
|
img_src=attrs["image"]["download_link"],
|
|
resolution=f"{attrs['width']}x{attrs['height']}",
|
|
author=f"{attrs['user']['username']}",
|
|
)
|
|
)
|
|
|
|
return res
|