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>
156 lines
4.1 KiB
Python
156 lines
4.1 KiB
Python
# SPDX-License-Identifier: AGPL-3.0-or-later
|
|
# lint: pylint
|
|
"""Google (Scholar)
|
|
|
|
For detailed description of the *REST-full* API see: `Query Parameter
|
|
Definitions`_.
|
|
|
|
.. _Query Parameter Definitions:
|
|
https://developers.google.com/custom-search/docs/xml_results#WebSearch_Query_Parameter_Definitions
|
|
"""
|
|
|
|
# pylint: disable=invalid-name
|
|
|
|
from urllib.parse import urlencode
|
|
from datetime import datetime
|
|
from lxml import html
|
|
|
|
from searx.utils import (
|
|
eval_xpath,
|
|
eval_xpath_list,
|
|
extract_text,
|
|
)
|
|
|
|
from searx.engines.google import (
|
|
get_lang_info,
|
|
time_range_dict,
|
|
detect_google_sorry,
|
|
)
|
|
|
|
# pylint: disable=unused-import
|
|
from searx.engines.google import (
|
|
supported_languages_url,
|
|
_fetch_supported_languages,
|
|
)
|
|
|
|
# pylint: enable=unused-import
|
|
|
|
# about
|
|
about = {
|
|
"website": 'https://scholar.google.com',
|
|
"wikidata_id": 'Q494817',
|
|
"official_api_documentation": 'https://developers.google.com/custom-search',
|
|
"use_official_api": False,
|
|
"require_api_key": False,
|
|
"results": 'HTML',
|
|
}
|
|
|
|
# engine dependent config
|
|
categories = ['science']
|
|
paging = True
|
|
use_locale_domain = True
|
|
time_range_support = True
|
|
safesearch = False
|
|
|
|
|
|
def time_range_url(params):
|
|
"""Returns a URL query component for a google-Scholar time range based on
|
|
``params['time_range']``. Google-Scholar does only support ranges in years.
|
|
To have any effect, all the Searx ranges (*day*, *week*, *month*, *year*)
|
|
are mapped to *year*. If no range is set, an empty string is returned.
|
|
Example::
|
|
|
|
&as_ylo=2019
|
|
"""
|
|
# as_ylo=2016&as_yhi=2019
|
|
ret_val = ''
|
|
if params['time_range'] in time_range_dict:
|
|
ret_val = urlencode({'as_ylo': datetime.now().year - 1})
|
|
return '&' + ret_val
|
|
|
|
|
|
def request(query, params):
|
|
"""Google-Scholar search request"""
|
|
|
|
offset = (params['pageno'] - 1) * 10
|
|
lang_info = get_lang_info(params, supported_languages, language_aliases, False)
|
|
logger.debug("HTTP header Accept-Language --> %s", lang_info['headers']['Accept-Language'])
|
|
|
|
# subdomain is: scholar.google.xy
|
|
lang_info['subdomain'] = lang_info['subdomain'].replace("www.", "scholar.")
|
|
|
|
query_url = (
|
|
'https://'
|
|
+ lang_info['subdomain']
|
|
+ '/scholar'
|
|
+ "?"
|
|
+ urlencode(
|
|
{
|
|
'q': query,
|
|
**lang_info['params'],
|
|
'ie': "utf8",
|
|
'oe': "utf8",
|
|
'start': offset,
|
|
}
|
|
)
|
|
)
|
|
|
|
query_url += time_range_url(params)
|
|
params['url'] = query_url
|
|
|
|
params['headers'].update(lang_info['headers'])
|
|
params['headers']['Accept'] = 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8'
|
|
|
|
# params['google_subdomain'] = subdomain
|
|
return params
|
|
|
|
|
|
def response(resp):
|
|
"""Get response from google's search request"""
|
|
results = []
|
|
|
|
detect_google_sorry(resp)
|
|
|
|
# which subdomain ?
|
|
# subdomain = resp.search_params.get('google_subdomain')
|
|
|
|
# convert the text to dom
|
|
dom = html.fromstring(resp.text)
|
|
|
|
# parse results
|
|
for result in eval_xpath_list(dom, '//div[@class="gs_ri"]'):
|
|
|
|
title = extract_text(eval_xpath(result, './h3[1]//a'))
|
|
|
|
if not title:
|
|
# this is a [ZITATION] block
|
|
continue
|
|
|
|
url = eval_xpath(result, './h3[1]//a/@href')[0]
|
|
content = extract_text(eval_xpath(result, './div[@class="gs_rs"]')) or ''
|
|
|
|
pub_info = extract_text(eval_xpath(result, './div[@class="gs_a"]'))
|
|
if pub_info:
|
|
content += "[%s]" % pub_info
|
|
|
|
pub_type = extract_text(eval_xpath(result, './/span[@class="gs_ct1"]'))
|
|
if pub_type:
|
|
title = title + " " + pub_type
|
|
|
|
results.append(
|
|
{
|
|
'url': url,
|
|
'title': title,
|
|
'content': content,
|
|
}
|
|
)
|
|
|
|
# parse suggestion
|
|
for suggestion in eval_xpath(dom, '//div[contains(@class, "gs_qsuggest_wrap")]//li//a'):
|
|
# append suggestion
|
|
results.append({'suggestion': extract_text(suggestion)})
|
|
|
|
for correction in eval_xpath(dom, '//div[@class="gs_r gs_pda"]/a'):
|
|
results.append({'correction': extract_text(correction)})
|
|
|
|
return results
|