[enh] google scholar - python implementation of the engine

The old xpath configuration for google scholar did not work and is replaced by a
python implementation.

Signed-off-by: Markus Heiser <markus.heiser@darmarit.de>
This commit is contained in:
Markus Heiser 2021-03-01 15:02:11 +01:00
parent e2fb500892
commit d48e2e7b0b
4 changed files with 300 additions and 19 deletions

View file

@ -195,7 +195,8 @@ PYLINT_FILES=\
searx/engines/google_videos.py \ searx/engines/google_videos.py \
searx/engines/google_images.py \ searx/engines/google_images.py \
searx/engines/mediathekviewweb.py \ searx/engines/mediathekviewweb.py \
utils/fetch_external_bangs.py utils/fetch_external_bangs.py \
searx/engines/google_scholar.py
test.pylint: pyenvinstall test.pylint: pyenvinstall
$(call cmd,pylint,$(PYLINT_FILES)) $(call cmd,pylint,$(PYLINT_FILES))

View file

@ -25176,6 +25176,146 @@
"name": "\u4e2d\u6587 (\u7e41\u9ad4)" "name": "\u4e2d\u6587 (\u7e41\u9ad4)"
} }
}, },
"google scholar": {
"af": {
"name": "Afrikaans"
},
"ar": {
"name": "\u0627\u0644\u0639\u0631\u0628\u064a\u0629"
},
"be": {
"name": "\u0431\u0435\u043b\u0430\u0440\u0443\u0441\u043a\u0430\u044f"
},
"bg": {
"name": "\u0431\u044a\u043b\u0433\u0430\u0440\u0441\u043a\u0438"
},
"ca": {
"name": "catal\u00e0"
},
"cs": {
"name": "\u010de\u0161tina"
},
"da": {
"name": "dansk"
},
"de": {
"name": "Deutsch"
},
"el": {
"name": "\u0395\u03bb\u03bb\u03b7\u03bd\u03b9\u03ba\u03ac"
},
"en": {
"name": "English"
},
"eo": {
"name": "esperanto"
},
"es": {
"name": "espa\u00f1ol"
},
"et": {
"name": "eesti"
},
"fa": {
"name": "\u0641\u0627\u0631\u0633\u06cc"
},
"fi": {
"name": "suomi"
},
"fr": {
"name": "fran\u00e7ais"
},
"hi": {
"name": "\u0939\u093f\u0928\u094d\u0926\u0940"
},
"hr": {
"name": "hrvatski"
},
"hu": {
"name": "magyar"
},
"hy": {
"name": "\u0570\u0561\u0575\u0565\u0580\u0565\u0576"
},
"id": {
"name": "Indonesia"
},
"is": {
"name": "\u00edslenska"
},
"it": {
"name": "italiano"
},
"iw": {
"name": "\u05e2\u05d1\u05e8\u05d9\u05ea"
},
"ja": {
"name": "\u65e5\u672c\u8a9e"
},
"ko": {
"name": "\ud55c\uad6d\uc5b4"
},
"lt": {
"name": "lietuvi\u0173"
},
"lv": {
"name": "latvie\u0161u"
},
"nl": {
"name": "Nederlands"
},
"no": {
"name": "norsk"
},
"pl": {
"name": "polski"
},
"pt": {
"name": "portugu\u00eas"
},
"ro": {
"name": "rom\u00e2n\u0103"
},
"ru": {
"name": "\u0440\u0443\u0441\u0441\u043a\u0438\u0439"
},
"sk": {
"name": "sloven\u010dina"
},
"sl": {
"name": "sloven\u0161\u010dina"
},
"sr": {
"name": "\u0441\u0440\u043f\u0441\u043a\u0438"
},
"sv": {
"name": "svenska"
},
"sw": {
"name": "Kiswahili"
},
"th": {
"name": "\u0e44\u0e17\u0e22"
},
"tl": {
"name": "Filipino"
},
"tr": {
"name": "T\u00fcrk\u00e7e"
},
"uk": {
"name": "\u0443\u043a\u0440\u0430\u0457\u043d\u0441\u044c\u043a\u0430"
},
"vi": {
"name": "Ti\u1ebfng Vi\u1ec7t"
},
"zh-CN": {
"name": "\u4e2d\u6587 (\u7b80\u4f53)"
},
"zh-TW": {
"name": "\u4e2d\u6587 (\u7e41\u9ad4)"
}
},
"google videos": { "google videos": {
"af": { "af": {
"name": "Afrikaans" "name": "Afrikaans"

View file

@ -0,0 +1,157 @@
# SPDX-License-Identifier: AGPL-3.0-or-later
"""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, missing-function-docstring
from urllib.parse import urlencode
from datetime import datetime
from lxml import html
from searx import logger
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
language_support = True
use_locale_domain = True
time_range_support = True
safesearch = False
logger = logger.getChild('google scholar')
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(
# pylint: disable=undefined-variable
# params, {}, language_aliases
params, supported_languages, language_aliases
)
# subdomain is: scholar.google.xy
lang_info['subdomain'] = lang_info['subdomain'].replace("www.", "scholar.")
query_url = 'https://'+ lang_info['subdomain'] + '/scholar' + "?" + urlencode({
'q': query,
'hl': lang_info['hl'],
'lr': lang_info['lr'],
'ie': "utf8",
'oe': "utf8",
'start' : offset,
})
query_url += time_range_url(params)
logger.debug("query_url --> %s", query_url)
params['url'] = query_url
logger.debug("HTTP header Accept-Language --> %s", lang_info['Accept-Language'])
params['headers']['Accept-Language'] = lang_info['Accept-Language']
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

View file

@ -535,25 +535,8 @@ engines:
# android: *test_android # android: *test_android
- name : google scholar - name : google scholar
engine : xpath engine : google_scholar
paging : True
search_url : https://scholar.google.com/scholar?start={pageno}&q={query}&hl=en&as_sdt=0,5&as_vis=1
results_xpath : //div[contains(@class, "gs_r")]/div[@class="gs_ri"]
url_xpath : .//h3/a/@href
title_xpath : .//h3/a
content_xpath : .//div[@class="gs_rs"]
suggestion_xpath : //div[@id="gs_res_ccl_top"]//a/b
page_size : 10
first_page_num : 0
categories : science
shortcut : gos shortcut : gos
about:
website: https://scholar.google.com/
wikidata_id: Q494817
official_api_documentation:
use_official_api: false
require_api_key: false
results: HTML
- name : google play apps - name : google play apps
engine : xpath engine : xpath