mirror of
https://github.com/searxng/searxng
synced 2024-01-01 19:24:07 +01:00
5fca26f0b3
This patch adds the boilerplate code, needed to fetch properties from engines.
In the past we only fetched *languages* but some engines need *regions* to
parameterize the engine request.
To fit into our *fetch language* procedures the boilerplate is implemented in
the `searxng_extra/update/update_languages.py` and the *engine_properties* are
stored along in the `searx/data/engines_languages.json`.
This implementation is downward compatible to the `_fetch_fetch_languages()`
infrastructure we have. If there comes the day we have all
`_fetch_fetch_languages()` implementations moved to `_fetch_engine_properties()`
implementations, we can rename the files and scripts.
The new type `engine_properties` is a dictionary with keys `languages` and
`regions`. The values are dictionaries to map from SearXNG's language & region
to option values the engine does use::
engine_properties = {
'type' : 'engine_properties', # <-- !!!
'regions': {
# 'ca-ES' : <engine's region name>
},
'languages': {
# 'ca' : <engine's language name>
},
}
Similar to the `supported_languages`, in the engine the properties are available
under the name `supported_properties`.
Initial we start with languages & regions, but in a wider sense the type is
named *engine properties*. Engines can store in whatever options they need and
may be in the future there is a need to fetch additional or complete different
properties.
Signed-off-by: Markus Heiser <markus.heiser@darmarit.de>
103 lines
2.7 KiB
Python
103 lines
2.7 KiB
Python
# SPDX-License-Identifier: AGPL-3.0-or-later
|
|
# lint: pylint
|
|
"""Yahoo (News)
|
|
|
|
Yahoo News is "English only" and do not offer localized nor language queries.
|
|
|
|
"""
|
|
|
|
# pylint: disable=invalid-name
|
|
|
|
import re
|
|
from urllib.parse import urlencode
|
|
from datetime import datetime, timedelta
|
|
from dateutil import parser
|
|
from lxml import html
|
|
|
|
from searx.utils import (
|
|
eval_xpath_list,
|
|
eval_xpath_getindex,
|
|
extract_text,
|
|
)
|
|
|
|
from searx.engines.yahoo import parse_url
|
|
|
|
# about
|
|
about = {
|
|
"website": 'https://news.yahoo.com',
|
|
"wikidata_id": 'Q3044717',
|
|
"official_api_documentation": 'https://developer.yahoo.com/api/',
|
|
"use_official_api": False,
|
|
"require_api_key": False,
|
|
"results": 'HTML',
|
|
}
|
|
|
|
time_range_support = False
|
|
safesearch = False
|
|
paging = True
|
|
categories = ['news']
|
|
|
|
# search-url
|
|
search_url = (
|
|
# fmt: off
|
|
'https://news.search.yahoo.com/search'
|
|
'?{query}&b={offset}'
|
|
# fmt: on
|
|
)
|
|
|
|
AGO_RE = re.compile(r'([0-9]+)\s*(year|month|week|day|minute|hour)')
|
|
AGO_TIMEDELTA = {
|
|
'minute': timedelta(minutes=1),
|
|
'hour': timedelta(hours=1),
|
|
'day': timedelta(days=1),
|
|
'week': timedelta(days=7),
|
|
'month': timedelta(days=30),
|
|
'year': timedelta(days=365),
|
|
}
|
|
|
|
|
|
def request(query, params):
|
|
offset = (params['pageno'] - 1) * 10 + 1
|
|
|
|
params['url'] = search_url.format(offset=offset, query=urlencode({'p': query}))
|
|
logger.debug("query_url --> %s", params['url'])
|
|
return params
|
|
|
|
|
|
def response(resp):
|
|
results = []
|
|
dom = html.fromstring(resp.text)
|
|
|
|
# parse results
|
|
for result in eval_xpath_list(dom, '//ol[contains(@class,"searchCenterMiddle")]//li'):
|
|
|
|
url = eval_xpath_getindex(result, './/h4/a/@href', 0, None)
|
|
if url is None:
|
|
continue
|
|
url = parse_url(url)
|
|
title = extract_text(result.xpath('.//h4/a'))
|
|
content = extract_text(result.xpath('.//p'))
|
|
img_src = eval_xpath_getindex(result, './/img/@data-src', 0, None)
|
|
|
|
item = {'url': url, 'title': title, 'content': content, 'img_src': img_src}
|
|
|
|
pub_date = extract_text(result.xpath('.//span[contains(@class,"s-time")]'))
|
|
ago = AGO_RE.search(pub_date)
|
|
if ago:
|
|
number = int(ago.group(1))
|
|
delta = AGO_TIMEDELTA[ago.group(2)]
|
|
pub_date = datetime.now() - delta * number
|
|
else:
|
|
try:
|
|
pub_date = parser.parse(pub_date)
|
|
except parser.ParserError:
|
|
pub_date = None
|
|
|
|
if pub_date is not None:
|
|
item['publishedDate'] = pub_date
|
|
results.append(item)
|
|
|
|
for suggestion in eval_xpath_list(dom, '//div[contains(@class,"AlsoTry")]//td'):
|
|
results.append({'suggestion': extract_text(suggestion)})
|
|
|
|
return results
|