2021-01-13 11:31:25 +01:00
|
|
|
# SPDX-License-Identifier: AGPL-3.0-or-later
|
2021-10-16 13:05:53 +02:00
|
|
|
# lint: pylint
|
|
|
|
"""Yahoo (Web)
|
|
|
|
|
2015-05-02 15:45:17 +02:00
|
|
|
"""
|
2014-01-30 02:33:24 +01:00
|
|
|
|
2020-08-06 17:42:46 +02:00
|
|
|
from urllib.parse import unquote, urlencode
|
2014-01-30 02:33:24 +01:00
|
|
|
from lxml import html
|
2020-10-02 18:13:56 +02:00
|
|
|
from searx.utils import extract_text, extract_url, match_language, eval_xpath
|
2014-01-30 02:33:24 +01:00
|
|
|
|
2021-01-13 11:31:25 +01:00
|
|
|
# about
|
|
|
|
about = {
|
|
|
|
"website": 'https://search.yahoo.com/',
|
|
|
|
"wikidata_id": None,
|
|
|
|
"official_api_documentation": 'https://developer.yahoo.com/api/',
|
|
|
|
"use_official_api": False,
|
|
|
|
"require_api_key": False,
|
|
|
|
"results": 'HTML',
|
|
|
|
}
|
|
|
|
|
2014-09-01 16:17:29 +02:00
|
|
|
# engine dependent config
|
2014-01-30 02:33:24 +01:00
|
|
|
categories = ['general']
|
2014-09-01 16:17:29 +02:00
|
|
|
paging = True
|
2016-07-17 18:42:30 +02:00
|
|
|
time_range_support = True
|
2014-09-01 16:17:29 +02:00
|
|
|
|
|
|
|
# search-url
|
2014-12-16 17:26:16 +01:00
|
|
|
base_url = 'https://search.yahoo.com/'
|
|
|
|
search_url = 'search?{query}&b={offset}&fl=1&vl=lang_{lang}'
|
2016-07-17 18:42:30 +02:00
|
|
|
search_url_with_time = 'search?{query}&b={offset}&fl=1&vl=lang_{lang}&age={age}&btf={btf}&fr2=time'
|
2014-09-01 16:17:29 +02:00
|
|
|
|
2016-11-06 03:51:38 +01:00
|
|
|
supported_languages_url = 'https://search.yahoo.com/web/advanced'
|
|
|
|
|
2014-09-01 16:17:29 +02:00
|
|
|
# specific xpath variables
|
2015-02-20 12:34:13 +01:00
|
|
|
results_xpath = "//div[contains(concat(' ', normalize-space(@class), ' '), ' Sr ')]"
|
2014-01-30 02:33:24 +01:00
|
|
|
url_xpath = './/h3/a/@href'
|
|
|
|
title_xpath = './/h3/a'
|
2020-06-25 21:45:42 +02:00
|
|
|
content_xpath = './/div[contains(@class, "compText")]'
|
2015-02-20 12:34:13 +01:00
|
|
|
suggestion_xpath = "//div[contains(concat(' ', normalize-space(@class), ' '), ' AlsoTry ')]//a"
|
2014-01-30 02:33:24 +01:00
|
|
|
|
2021-10-16 13:05:53 +02:00
|
|
|
time_range_dict = {
|
|
|
|
'day': ['1d', 'd'],
|
|
|
|
'week': ['1w', 'w'],
|
|
|
|
'month': ['1m', 'm']
|
|
|
|
}
|
2018-03-01 05:30:48 +01:00
|
|
|
|
2021-10-16 13:05:53 +02:00
|
|
|
language_aliases = {
|
|
|
|
'zh-CN': 'zh-CHS',
|
|
|
|
'zh-TW': 'zh-CHT',
|
|
|
|
'zh-HK': 'zh-CHT'
|
|
|
|
}
|
2016-07-19 10:14:11 +02:00
|
|
|
|
2014-09-01 16:17:29 +02:00
|
|
|
# remove yahoo-specific tracking-url
|
2014-03-08 19:09:03 +01:00
|
|
|
def parse_url(url_string):
|
2014-03-18 10:06:14 +01:00
|
|
|
endings = ['/RS', '/RK']
|
|
|
|
endpositions = []
|
2015-02-04 20:41:40 +01:00
|
|
|
start = url_string.find('http', url_string.find('/RU=') + 1)
|
2014-09-01 16:17:29 +02:00
|
|
|
|
2014-03-18 10:06:14 +01:00
|
|
|
for ending in endings:
|
|
|
|
endpos = url_string.rfind(ending)
|
|
|
|
if endpos > -1:
|
|
|
|
endpositions.append(endpos)
|
|
|
|
|
2014-12-07 16:37:56 +01:00
|
|
|
if start == 0 or len(endpositions) == 0:
|
|
|
|
return url_string
|
2014-01-30 02:33:24 +01:00
|
|
|
|
2021-10-16 13:05:53 +02:00
|
|
|
end = min(endpositions)
|
|
|
|
return unquote(url_string[start:end])
|
2014-03-10 16:46:11 +01:00
|
|
|
|
2016-07-17 18:42:30 +02:00
|
|
|
def _get_url(query, offset, language, time_range):
|
2016-07-26 00:22:05 +02:00
|
|
|
if time_range in time_range_dict:
|
2021-10-16 13:05:53 +02:00
|
|
|
return base_url + search_url_with_time.format(
|
|
|
|
offset = offset,
|
|
|
|
query = urlencode({'p': query}),
|
|
|
|
lang = language,
|
|
|
|
age = time_range_dict[time_range][0],
|
|
|
|
btf = time_range_dict[time_range][1]
|
|
|
|
)
|
|
|
|
return base_url + search_url.format(
|
|
|
|
offset=offset,
|
|
|
|
query=urlencode({'p': query}),
|
|
|
|
lang=language
|
|
|
|
)
|
2016-07-17 18:42:30 +02:00
|
|
|
|
2019-01-06 15:27:46 +01:00
|
|
|
def _get_language(params):
|
|
|
|
if params['language'] == 'all':
|
|
|
|
return 'en'
|
|
|
|
|
|
|
|
language = match_language(params['language'], supported_languages, language_aliases)
|
|
|
|
if language not in language_aliases.values():
|
|
|
|
language = language.split('-')[0]
|
|
|
|
language = language.replace('-', '_').lower()
|
|
|
|
|
|
|
|
return language
|
|
|
|
|
|
|
|
|
2014-09-01 16:17:29 +02:00
|
|
|
# do search-request
|
2014-01-30 02:33:24 +01:00
|
|
|
def request(query, params):
|
2016-12-11 16:41:14 +01:00
|
|
|
if params['time_range'] and params['time_range'] not in time_range_dict:
|
|
|
|
return params
|
|
|
|
|
2014-01-30 02:33:24 +01:00
|
|
|
offset = (params['pageno'] - 1) * 10 + 1
|
2019-01-06 15:27:46 +01:00
|
|
|
language = _get_language(params)
|
2014-09-01 16:17:29 +02:00
|
|
|
|
2016-07-17 18:42:30 +02:00
|
|
|
params['url'] = _get_url(query, offset, language, params['time_range'])
|
2014-09-01 16:17:29 +02:00
|
|
|
|
2014-01-30 02:33:24 +01:00
|
|
|
return params
|
|
|
|
|
|
|
|
|
2014-09-01 16:17:29 +02:00
|
|
|
# get response from search-request
|
2014-01-30 02:33:24 +01:00
|
|
|
def response(resp):
|
|
|
|
results = []
|
2014-09-01 16:17:29 +02:00
|
|
|
|
2014-01-30 02:33:24 +01:00
|
|
|
dom = html.fromstring(resp.text)
|
|
|
|
|
2016-06-28 00:06:50 +02:00
|
|
|
try:
|
2021-10-16 13:05:53 +02:00
|
|
|
results_num = int(
|
|
|
|
eval_xpath(
|
|
|
|
dom,
|
|
|
|
'//div[@class="compPagination"]/span[last()]/text()'
|
|
|
|
)[0].split()[0].replace(',', '')
|
|
|
|
)
|
2016-06-28 00:06:50 +02:00
|
|
|
results.append({'number_of_results': results_num})
|
2021-10-16 13:05:53 +02:00
|
|
|
except: # pylint: disable=bare-except
|
2016-06-28 00:06:50 +02:00
|
|
|
pass
|
|
|
|
|
2014-09-01 16:17:29 +02:00
|
|
|
# parse results
|
2019-11-15 09:31:37 +01:00
|
|
|
for result in eval_xpath(dom, results_xpath):
|
2014-03-21 16:36:13 +01:00
|
|
|
try:
|
2019-11-15 09:31:37 +01:00
|
|
|
url = parse_url(extract_url(eval_xpath(result, url_xpath), search_url))
|
|
|
|
title = extract_text(eval_xpath(result, title_xpath)[0])
|
2021-10-16 13:05:53 +02:00
|
|
|
|
|
|
|
except: # pylint: disable=bare-except
|
2014-03-21 16:36:13 +01:00
|
|
|
continue
|
2014-09-01 16:17:29 +02:00
|
|
|
|
2019-11-15 09:31:37 +01:00
|
|
|
content = extract_text(eval_xpath(result, content_xpath)[0])
|
2014-01-30 02:33:24 +01:00
|
|
|
|
2014-09-01 16:17:29 +02:00
|
|
|
# append result
|
2021-10-16 13:05:53 +02:00
|
|
|
results.append({
|
|
|
|
'url': url,
|
|
|
|
'title': title,
|
|
|
|
'content': content
|
|
|
|
})
|
2014-09-01 16:17:29 +02:00
|
|
|
|
|
|
|
# if no suggestion found, return results
|
2019-11-15 09:31:37 +01:00
|
|
|
suggestions = eval_xpath(dom, suggestion_xpath)
|
2015-02-20 12:34:13 +01:00
|
|
|
if not suggestions:
|
2014-01-30 02:33:24 +01:00
|
|
|
return results
|
|
|
|
|
2014-09-01 16:17:29 +02:00
|
|
|
# parse suggestion
|
2015-02-20 12:34:13 +01:00
|
|
|
for suggestion in suggestions:
|
2014-09-01 16:17:29 +02:00
|
|
|
# append suggestion
|
2014-01-30 02:33:24 +01:00
|
|
|
results.append({'suggestion': extract_text(suggestion)})
|
|
|
|
|
2014-09-01 16:17:29 +02:00
|
|
|
# return results
|
2014-01-30 02:33:24 +01:00
|
|
|
return results
|
2016-11-06 03:51:38 +01:00
|
|
|
|
|
|
|
|
|
|
|
# get supported languages from their site
|
2016-12-15 07:34:43 +01:00
|
|
|
def _fetch_supported_languages(resp):
|
2016-11-06 03:51:38 +01:00
|
|
|
supported_languages = []
|
2016-12-15 07:34:43 +01:00
|
|
|
dom = html.fromstring(resp.text)
|
2019-11-15 09:31:37 +01:00
|
|
|
options = eval_xpath(dom, '//div[@id="yschlang"]/span/label/input')
|
2016-11-06 03:51:38 +01:00
|
|
|
for option in options:
|
2019-11-15 09:31:37 +01:00
|
|
|
code_parts = eval_xpath(option, './@value')[0][5:].split('_')
|
2018-03-01 05:30:48 +01:00
|
|
|
if len(code_parts) == 2:
|
|
|
|
code = code_parts[0] + '-' + code_parts[1].upper()
|
|
|
|
else:
|
|
|
|
code = code_parts[0]
|
2016-11-06 03:51:38 +01:00
|
|
|
supported_languages.append(code)
|
|
|
|
|
|
|
|
return supported_languages
|