mirror of https://github.com/searxng/searxng.git
Merge branch 'master' of github.com:y0nei/searxng
This commit is contained in:
y0nei
commit
3732b7fef5
2
manage
2
manage
|
|
@ -41,7 +41,7 @@ PATH="${REPO_ROOT}/node_modules/.bin:${PATH}"
|
|||
|
||||
PYOBJECTS="searx"
|
||||
PY_SETUP_EXTRAS='[test]'
|
||||
GECKODRIVER_VERSION="v0.30.0"
|
||||
GECKODRIVER_VERSION="v0.33.0"
|
||||
# SPHINXOPTS=
|
||||
BLACK_OPTIONS=("--target-version" "py311" "--line-length" "120" "--skip-string-normalization")
|
||||
BLACK_TARGETS=("--exclude" "searx/static,searx/languages.py" "--include" 'searxng.msg|\.pyi?$' "searx" "searxng_extra" "tests")
|
||||
|
|
|
|||
|
|
@ -1,7 +1,7 @@
|
|||
{
|
||||
"dependencies": {
|
||||
"eslint": "^8.18.0",
|
||||
"pyright": "^1.1.255"
|
||||
"eslint": "^8.50.0",
|
||||
"pyright": "^1.1.329"
|
||||
},
|
||||
"scripts": {
|
||||
"clean": "rm -Rf node_modules package-lock.json"
|
||||
|
|
|
|||
|
|
@ -51,7 +51,6 @@ from . import (
|
|||
http_accept,
|
||||
http_accept_encoding,
|
||||
http_accept_language,
|
||||
http_connection,
|
||||
http_user_agent,
|
||||
ip_limit,
|
||||
ip_lists,
|
||||
|
|
@ -136,7 +135,6 @@ def filter_request(request: flask.Request) -> werkzeug.Response | None:
|
|||
http_accept,
|
||||
http_accept_encoding,
|
||||
http_accept_language,
|
||||
http_connection,
|
||||
http_user_agent,
|
||||
ip_limit,
|
||||
]:
|
||||
|
|
|
|||
File diff suppressed because it is too large
Load Diff
|
|
@ -8,19 +8,18 @@ implementations are shared by other engines:
|
|||
- :ref:`bing videos engine`
|
||||
|
||||
On the `preference page`_ Bing offers a lot of languages an regions (see section
|
||||
'Search results languages' and 'Country/region'). However, the abundant choice
|
||||
does not correspond to reality, where Bing has a full-text indexer only for a
|
||||
limited number of languages. By example: you can select a language like Māori
|
||||
but you never get a result in this language.
|
||||
LANGUAGE and COUNTRY/REGION). The Language is the language of the UI, we need
|
||||
in SearXNG to get the translations of data such as *"published last week"*.
|
||||
|
||||
What comes a bit closer to the truth are the `search-APIs`_ but they don`t seem
|
||||
to be completely correct either (if you take a closer look you will find some
|
||||
inaccuracies there too):
|
||||
There is a description of the offical search-APIs_, unfortunately this is not
|
||||
the API we can use or that bing itself would use. You can look up some things
|
||||
in the API to get a better picture of bing, but the value specifications like
|
||||
the market codes are usually outdated or at least no longer used by bing itself.
|
||||
|
||||
- :py:obj:`searx.engines.bing.bing_traits_url`
|
||||
- :py:obj:`searx.engines.bing_videos.bing_traits_url`
|
||||
- :py:obj:`searx.engines.bing_images.bing_traits_url`
|
||||
- :py:obj:`searx.engines.bing_news.bing_traits_url`
|
||||
The market codes have been harmonized and are identical for web, video and
|
||||
images. The news area has also been harmonized with the other categories. Only
|
||||
political adjustments still seem to be made -- for example, there is no news
|
||||
category for the Chinese market.
|
||||
|
||||
.. _preference page: https://www.bing.com/account/general
|
||||
.. _search-APIs: https://learn.microsoft.com/en-us/bing/search-apis/
|
||||
|
|
@ -30,9 +29,8 @@ inaccuracies there too):
|
|||
|
||||
from typing import TYPE_CHECKING
|
||||
import base64
|
||||
import datetime
|
||||
import re
|
||||
import uuid
|
||||
import time
|
||||
from urllib.parse import parse_qs, urlencode, urlparse
|
||||
from lxml import html
|
||||
import babel
|
||||
|
|
@ -45,7 +43,7 @@ from searx.enginelib.traits import EngineTraits
|
|||
if TYPE_CHECKING:
|
||||
import logging
|
||||
|
||||
logger: logging.Logger
|
||||
logger = logging.getLogger()
|
||||
|
||||
traits: EngineTraits
|
||||
|
||||
|
|
@ -58,124 +56,63 @@ about = {
|
|||
"results": 'HTML',
|
||||
}
|
||||
|
||||
send_accept_language_header = True
|
||||
"""Bing tries to guess user's language and territory from the HTTP
|
||||
Accept-Language. Optional the user can select a search-language (can be
|
||||
different to the UI language) and a region (market code)."""
|
||||
|
||||
# engine dependent config
|
||||
categories = ['general', 'web']
|
||||
paging = True
|
||||
time_range_support = True
|
||||
safesearch = True
|
||||
safesearch_types = {2: 'STRICT', 1: 'DEMOTE', 0: 'OFF'} # cookie: ADLT=STRICT
|
||||
"""Bing results are always SFW. To get NSFW links from bing some age
|
||||
verification by a cookie is needed / thats not possible in SearXNG.
|
||||
"""
|
||||
|
||||
base_url = 'https://www.bing.com/search'
|
||||
"""Bing (Web) search URL"""
|
||||
|
||||
bing_traits_url = 'https://learn.microsoft.com/en-us/bing/search-apis/bing-web-search/reference/market-codes'
|
||||
"""Bing (Web) search API description"""
|
||||
|
||||
def _page_offset(pageno):
|
||||
return (int(pageno) - 1) * 10 + 1
|
||||
|
||||
|
||||
def _get_offset_from_pageno(pageno):
|
||||
return (pageno - 1) * 10 + 1
|
||||
|
||||
|
||||
def set_bing_cookies(params, engine_language, engine_region, SID):
|
||||
|
||||
# set cookies
|
||||
# -----------
|
||||
|
||||
params['cookies']['_EDGE_V'] = '1'
|
||||
|
||||
# _EDGE_S: F=1&SID=3A5253BD6BCA609509B741876AF961CA&mkt=zh-tw
|
||||
_EDGE_S = [
|
||||
'F=1',
|
||||
'SID=%s' % SID,
|
||||
'mkt=%s' % engine_region.lower(),
|
||||
'ui=%s' % engine_language.lower(),
|
||||
]
|
||||
params['cookies']['_EDGE_S'] = '&'.join(_EDGE_S)
|
||||
logger.debug("cookie _EDGE_S=%s", params['cookies']['_EDGE_S'])
|
||||
|
||||
# "_EDGE_CD": "m=zh-tw",
|
||||
|
||||
_EDGE_CD = [ # pylint: disable=invalid-name
|
||||
'm=%s' % engine_region.lower(), # search region: zh-cn
|
||||
'u=%s' % engine_language.lower(), # UI: en-us
|
||||
]
|
||||
|
||||
params['cookies']['_EDGE_CD'] = '&'.join(_EDGE_CD) + ';'
|
||||
logger.debug("cookie _EDGE_CD=%s", params['cookies']['_EDGE_CD'])
|
||||
|
||||
SRCHHPGUSR = [ # pylint: disable=invalid-name
|
||||
'SRCHLANG=%s' % engine_language,
|
||||
# Trying to set ADLT cookie here seems not to have any effect, I assume
|
||||
# there is some age verification by a cookie (and/or session ID) needed,
|
||||
# to disable the SafeSearch.
|
||||
'ADLT=%s' % safesearch_types.get(params['safesearch'], 'DEMOTE'),
|
||||
]
|
||||
params['cookies']['SRCHHPGUSR'] = '&'.join(SRCHHPGUSR)
|
||||
logger.debug("cookie SRCHHPGUSR=%s", params['cookies']['SRCHHPGUSR'])
|
||||
def set_bing_cookies(params, engine_language, engine_region):
|
||||
params['cookies']['_EDGE_CD'] = f'm={engine_region}&u={engine_language}'
|
||||
params['cookies']['_EDGE_S'] = f'mkt={engine_region}&ui={engine_language}'
|
||||
logger.debug("bing cookies: %s", params['cookies'])
|
||||
|
||||
|
||||
def request(query, params):
|
||||
"""Assemble a Bing-Web request."""
|
||||
|
||||
engine_region = traits.get_region(params['searxng_locale'], 'en-US')
|
||||
engine_language = traits.get_language(params['searxng_locale'], 'en')
|
||||
engine_region = traits.get_region(params['searxng_locale'], traits.all_locale) # type: ignore
|
||||
engine_language = traits.get_language(params['searxng_locale'], 'en') # type: ignore
|
||||
set_bing_cookies(params, engine_language, engine_region)
|
||||
|
||||
SID = uuid.uuid1().hex.upper()
|
||||
CVID = uuid.uuid1().hex.upper()
|
||||
|
||||
set_bing_cookies(params, engine_language, engine_region, SID)
|
||||
|
||||
# build URL query
|
||||
# ---------------
|
||||
|
||||
# query term
|
||||
page = int(params.get('pageno', 1))
|
||||
page = params.get('pageno', 1)
|
||||
query_params = {
|
||||
# fmt: off
|
||||
'q': query,
|
||||
# if arg 'pq' is missed, somtimes on page 4 we get results from page 1,
|
||||
# don't ask why it is only sometimes / its M$ and they have never been
|
||||
# deterministic ;)
|
||||
'pq': query,
|
||||
'cvid': CVID,
|
||||
'qs': 'n',
|
||||
'sp': '-1'
|
||||
# fmt: on
|
||||
}
|
||||
|
||||
# page
|
||||
# To get correct page, arg first and this arg FORM is needed, the value PERE
|
||||
# is on page 2, on page 3 its PERE1 and on page 4 its PERE2 .. and so forth.
|
||||
# The 'first' arg should never send on page 1.
|
||||
|
||||
if page > 1:
|
||||
referer = base_url + '?' + urlencode(query_params)
|
||||
params['headers']['Referer'] = referer
|
||||
logger.debug("headers.Referer --> %s", referer)
|
||||
|
||||
query_params['first'] = _get_offset_from_pageno(page)
|
||||
|
||||
query_params['first'] = _page_offset(page) # see also arg FORM
|
||||
if page == 2:
|
||||
query_params['FORM'] = 'PERE'
|
||||
elif page > 2:
|
||||
query_params['FORM'] = 'PERE%s' % (page - 2)
|
||||
|
||||
filters = ''
|
||||
if params['time_range']:
|
||||
query_params['filt'] = 'custom'
|
||||
params['url'] = f'{base_url}?{urlencode(query_params)}'
|
||||
|
||||
if params['time_range'] == 'day':
|
||||
filters = 'ex1:"ez1"'
|
||||
elif params['time_range'] == 'week':
|
||||
filters = 'ex1:"ez2"'
|
||||
elif params['time_range'] == 'month':
|
||||
filters = 'ex1:"ez3"'
|
||||
elif params['time_range'] == 'year':
|
||||
epoch_1970 = datetime.date(1970, 1, 1)
|
||||
today_no = (datetime.date.today() - epoch_1970).days
|
||||
filters = 'ex1:"ez5_%s_%s"' % (today_no - 365, today_no)
|
||||
if params.get('time_range'):
|
||||
unix_day = int(time.time() / 86400)
|
||||
time_ranges = {'day': '1', 'week': '2', 'month': '3', 'year': f'5_{unix_day-365}_{unix_day}'}
|
||||
params['url'] += f'&filters=ex1:"ez{time_ranges[params["time_range"]]}"'
|
||||
|
||||
params['url'] = base_url + '?' + urlencode(query_params)
|
||||
if filters:
|
||||
params['url'] = params['url'] + '&filters=' + filters
|
||||
return params
|
||||
|
||||
|
||||
|
|
@ -197,10 +134,11 @@ def response(resp):
|
|||
url = link.attrib.get('href')
|
||||
title = extract_text(link)
|
||||
|
||||
content = eval_xpath(result, '(.//p)[1]')
|
||||
content = eval_xpath(result, './/p')
|
||||
for p in content:
|
||||
# Make sure that the element is free of <a href> links
|
||||
for e in p.xpath('.//a'):
|
||||
# Make sure that the element is free of:
|
||||
# <span class="algoSlug_icon" # data-priority="2">Web</span>
|
||||
for e in p.xpath('.//span[@class="algoSlug_icon"]'):
|
||||
e.getparent().remove(e)
|
||||
content = extract_text(content)
|
||||
|
||||
|
|
@ -236,7 +174,7 @@ def response(resp):
|
|||
except Exception as e: # pylint: disable=broad-except
|
||||
logger.debug('result error :\n%s', e)
|
||||
|
||||
if result_len and _get_offset_from_pageno(resp.search_params.get("pageno", 0)) > result_len:
|
||||
if result_len and _page_offset(resp.search_params.get("pageno", 0)) > result_len:
|
||||
# Avoid reading more results than avalaible.
|
||||
# For example, if there is 100 results from some search and we try to get results from 120 to 130,
|
||||
# Bing will send back the results from 0 to 10 and no error.
|
||||
|
|
@ -249,72 +187,76 @@ def response(resp):
|
|||
|
||||
def fetch_traits(engine_traits: EngineTraits):
|
||||
"""Fetch languages and regions from Bing-Web."""
|
||||
|
||||
xpath_market_codes = '//table[1]/tbody/tr/td[3]'
|
||||
# xpath_country_codes = '//table[2]/tbody/tr/td[2]'
|
||||
xpath_language_codes = '//table[3]/tbody/tr/td[2]'
|
||||
|
||||
_fetch_traits(engine_traits, bing_traits_url, xpath_language_codes, xpath_market_codes)
|
||||
|
||||
|
||||
def _fetch_traits(engine_traits: EngineTraits, url: str, xpath_language_codes: str, xpath_market_codes: str):
|
||||
# pylint: disable=too-many-locals,import-outside-toplevel
|
||||
# pylint: disable=import-outside-toplevel
|
||||
|
||||
from searx.network import get # see https://github.com/searxng/searxng/issues/762
|
||||
|
||||
# insert alias to map from a language (zh) to a language + script (zh_Hans)
|
||||
engine_traits.languages['zh'] = 'zh-hans'
|
||||
|
||||
resp = get(url)
|
||||
|
||||
resp = get("https://www.bing.com/account/general")
|
||||
if not resp.ok: # type: ignore
|
||||
print("ERROR: response from peertube is not OK.")
|
||||
print("ERROR: response from bing is not OK.")
|
||||
|
||||
dom = html.fromstring(resp.text) # type: ignore
|
||||
|
||||
map_lang = {'jp': 'ja'}
|
||||
for td in eval_xpath(dom, xpath_language_codes):
|
||||
eng_lang = td.text
|
||||
# languages
|
||||
|
||||
if eng_lang in ('en-gb', 'pt-br'):
|
||||
# language 'en' is already in the list and a language 'en-gb' can't
|
||||
# be handled in SearXNG, same with pt-br which is covered by pt-pt.
|
||||
continue
|
||||
engine_traits.languages['zh'] = 'zh-hans'
|
||||
|
||||
babel_lang = map_lang.get(eng_lang, eng_lang).replace('-', '_')
|
||||
try:
|
||||
sxng_tag = language_tag(babel.Locale.parse(babel_lang))
|
||||
except babel.UnknownLocaleError:
|
||||
print("ERROR: language (%s) is unknown by babel" % (eng_lang))
|
||||
continue
|
||||
conflict = engine_traits.languages.get(sxng_tag)
|
||||
if conflict:
|
||||
if conflict != eng_lang:
|
||||
print("CONFLICT: babel %s --> %s, %s" % (sxng_tag, conflict, eng_lang))
|
||||
continue
|
||||
engine_traits.languages[sxng_tag] = eng_lang
|
||||
|
||||
map_region = {
|
||||
'en-ID': 'id_ID',
|
||||
'no-NO': 'nb_NO',
|
||||
map_lang = {'prs': 'fa-AF', 'en': 'en-us'}
|
||||
bing_ui_lang_map = {
|
||||
# HINT: this list probably needs to be supplemented
|
||||
'en': 'us', # en --> en-us
|
||||
'da': 'dk', # da --> da-dk
|
||||
}
|
||||
|
||||
for td in eval_xpath(dom, xpath_market_codes):
|
||||
eng_region = td.text
|
||||
babel_region = map_region.get(eng_region, eng_region).replace('-', '_')
|
||||
|
||||
if eng_region == 'en-WW':
|
||||
engine_traits.all_locale = eng_region
|
||||
continue
|
||||
|
||||
for href in eval_xpath(dom, '//div[@id="language-section"]//li/a/@href'):
|
||||
eng_lang = parse_qs(urlparse(href).query)['setlang'][0]
|
||||
babel_lang = map_lang.get(eng_lang, eng_lang)
|
||||
try:
|
||||
sxng_tag = region_tag(babel.Locale.parse(babel_region))
|
||||
sxng_tag = language_tag(babel.Locale.parse(babel_lang.replace('-', '_')))
|
||||
except babel.UnknownLocaleError:
|
||||
print("ERROR: region (%s) is unknown by babel" % (eng_region))
|
||||
print("ERROR: language (%s) is unknown by babel" % (babel_lang))
|
||||
continue
|
||||
# Language (e.g. 'en' or 'de') from https://www.bing.com/account/general
|
||||
# is converted by bing to 'en-us' or 'de-de'. But only if there is not
|
||||
# already a '-' delemitter in the language. For instance 'pt-PT' -->
|
||||
# 'pt-pt' and 'pt-br' --> 'pt-br'
|
||||
bing_ui_lang = eng_lang.lower()
|
||||
if '-' not in bing_ui_lang:
|
||||
bing_ui_lang = bing_ui_lang + '-' + bing_ui_lang_map.get(bing_ui_lang, bing_ui_lang)
|
||||
|
||||
conflict = engine_traits.languages.get(sxng_tag)
|
||||
if conflict:
|
||||
if conflict != bing_ui_lang:
|
||||
print(f"CONFLICT: babel {sxng_tag} --> {conflict}, {bing_ui_lang}")
|
||||
continue
|
||||
engine_traits.languages[sxng_tag] = bing_ui_lang
|
||||
|
||||
# regions (aka "market codes")
|
||||
|
||||
engine_traits.regions['zh-CN'] = 'zh-cn'
|
||||
|
||||
map_market_codes = {
|
||||
'zh-hk': 'en-hk', # not sure why, but at M$ this is the market code for Hongkong
|
||||
}
|
||||
for href in eval_xpath(dom, '//div[@id="region-section"]//li/a/@href'):
|
||||
cc_tag = parse_qs(urlparse(href).query)['cc'][0]
|
||||
if cc_tag == 'clear':
|
||||
engine_traits.all_locale = cc_tag
|
||||
continue
|
||||
|
||||
# add market codes from official languages of the country ..
|
||||
for lang_tag in babel.languages.get_official_languages(cc_tag, de_facto=True):
|
||||
if lang_tag not in engine_traits.languages.keys():
|
||||
# print("ignore lang: %s <-- %s" % (cc_tag, lang_tag))
|
||||
continue
|
||||
lang_tag = lang_tag.split('_')[0] # zh_Hant --> zh
|
||||
market_code = f"{lang_tag}-{cc_tag}" # zh-tw
|
||||
|
||||
market_code = map_market_codes.get(market_code, market_code)
|
||||
sxng_tag = region_tag(babel.Locale.parse('%s_%s' % (lang_tag, cc_tag.upper())))
|
||||
conflict = engine_traits.regions.get(sxng_tag)
|
||||
if conflict:
|
||||
if conflict != eng_region:
|
||||
print("CONFLICT: babel %s --> %s, %s" % (sxng_tag, conflict, eng_region))
|
||||
if conflict != market_code:
|
||||
print("CONFLICT: babel %s --> %s, %s" % (sxng_tag, conflict, market_code))
|
||||
continue
|
||||
engine_traits.regions[sxng_tag] = eng_region
|
||||
engine_traits.regions[sxng_tag] = market_code
|
||||
|
|
|
|||
|
|
@ -6,23 +6,20 @@
|
|||
|
||||
|
||||
from typing import TYPE_CHECKING
|
||||
import uuid
|
||||
import json
|
||||
from urllib.parse import urlencode
|
||||
|
||||
from lxml import html
|
||||
|
||||
from searx.enginelib.traits import EngineTraits
|
||||
from searx.engines.bing import (
|
||||
set_bing_cookies,
|
||||
_fetch_traits,
|
||||
)
|
||||
from searx.engines.bing import send_accept_language_header # pylint: disable=unused-import
|
||||
from searx.engines.bing import set_bing_cookies
|
||||
from searx.engines.bing import fetch_traits # pylint: disable=unused-import
|
||||
|
||||
|
||||
if TYPE_CHECKING:
|
||||
import logging
|
||||
|
||||
logger: logging.Logger
|
||||
logger = logging.getLogger()
|
||||
|
||||
traits: EngineTraits
|
||||
|
||||
|
|
@ -45,39 +42,29 @@ time_range_support = True
|
|||
base_url = 'https://www.bing.com/images/async'
|
||||
"""Bing (Images) search URL"""
|
||||
|
||||
bing_traits_url = 'https://learn.microsoft.com/en-us/bing/search-apis/bing-image-search/reference/market-codes'
|
||||
"""Bing (Images) search API description"""
|
||||
|
||||
time_map = {
|
||||
# fmt: off
|
||||
'day': 60 * 24,
|
||||
'week': 60 * 24 * 7,
|
||||
'month': 60 * 24 * 31,
|
||||
'year': 60 * 24 * 365,
|
||||
# fmt: on
|
||||
}
|
||||
|
||||
|
||||
def request(query, params):
|
||||
"""Assemble a Bing-Image request."""
|
||||
|
||||
engine_region = traits.get_region(params['searxng_locale'], 'en-US')
|
||||
engine_language = traits.get_language(params['searxng_locale'], 'en')
|
||||
|
||||
SID = uuid.uuid1().hex.upper()
|
||||
set_bing_cookies(params, engine_language, engine_region, SID)
|
||||
engine_region = traits.get_region(params['searxng_locale'], traits.all_locale) # type: ignore
|
||||
engine_language = traits.get_language(params['searxng_locale'], 'en') # type: ignore
|
||||
set_bing_cookies(params, engine_language, engine_region)
|
||||
|
||||
# build URL query
|
||||
# - example: https://www.bing.com/images/async?q=foo&first=155&count=35
|
||||
|
||||
# - example: https://www.bing.com/images/async?q=foo&async=content&first=1&count=35
|
||||
query_params = {
|
||||
# fmt: off
|
||||
'q': query,
|
||||
'async' : 'content',
|
||||
'async': '1',
|
||||
# to simplify the page count lets use the default of 35 images per page
|
||||
'first' : (int(params.get('pageno', 1)) - 1) * 35 + 1,
|
||||
'count' : 35,
|
||||
# fmt: on
|
||||
'first': (int(params.get('pageno', 1)) - 1) * 35 + 1,
|
||||
'count': 35,
|
||||
}
|
||||
|
||||
# time range
|
||||
|
|
@ -120,13 +107,3 @@ def response(resp):
|
|||
}
|
||||
)
|
||||
return results
|
||||
|
||||
|
||||
def fetch_traits(engine_traits: EngineTraits):
|
||||
"""Fetch languages and regions from Bing-News."""
|
||||
|
||||
xpath_market_codes = '//table[1]/tbody/tr/td[3]'
|
||||
# xpath_country_codes = '//table[2]/tbody/tr/td[2]'
|
||||
xpath_language_codes = '//table[3]/tbody/tr/td[2]'
|
||||
|
||||
_fetch_traits(engine_traits, bing_traits_url, xpath_language_codes, xpath_market_codes)
|
||||
|
|
|
|||
|
|
@ -1,22 +1,23 @@
|
|||
# SPDX-License-Identifier: AGPL-3.0-or-later
|
||||
# lint: pylint
|
||||
"""Bing-News: description see :py:obj:`searx.engines.bing`.
|
||||
|
||||
.. hint::
|
||||
|
||||
Bing News is *different* in some ways!
|
||||
|
||||
"""
|
||||
|
||||
# pylint: disable=invalid-name
|
||||
|
||||
from typing import TYPE_CHECKING
|
||||
import uuid
|
||||
from urllib.parse import urlencode
|
||||
|
||||
from lxml import html
|
||||
|
||||
from searx.utils import eval_xpath, extract_text, eval_xpath_list, eval_xpath_getindex
|
||||
from searx.enginelib.traits import EngineTraits
|
||||
from searx.engines.bing import (
|
||||
set_bing_cookies,
|
||||
_fetch_traits,
|
||||
)
|
||||
from searx.engines.bing import send_accept_language_header # pylint: disable=unused-import
|
||||
from searx.engines.bing import set_bing_cookies
|
||||
|
||||
if TYPE_CHECKING:
|
||||
import logging
|
||||
|
|
@ -39,58 +40,48 @@ about = {
|
|||
# engine dependent config
|
||||
categories = ['news']
|
||||
paging = True
|
||||
"""If go through the pages and there are actually no new results for another
|
||||
page, then bing returns the results from the last page again."""
|
||||
|
||||
time_range_support = True
|
||||
time_map = {
|
||||
'day': '4',
|
||||
'week': '8',
|
||||
'month': '9',
|
||||
'day': 'interval="4"',
|
||||
'week': 'interval="7"',
|
||||
'month': 'interval="9"',
|
||||
}
|
||||
"""A string '4' means *last hour*. We use *last hour* for ``day`` here since the
|
||||
difference of *last day* and *last week* in the result list is just marginally.
|
||||
"""
|
||||
Bing does not have news range ``year`` / we use ``month`` instead."""
|
||||
|
||||
base_url = 'https://www.bing.com/news/infinitescrollajax'
|
||||
"""Bing (News) search URL"""
|
||||
|
||||
bing_traits_url = 'https://learn.microsoft.com/en-us/bing/search-apis/bing-news-search/reference/market-codes'
|
||||
"""Bing (News) search API description"""
|
||||
|
||||
mkt_alias = {
|
||||
'zh': 'en-WW',
|
||||
'zh-CN': 'en-WW',
|
||||
}
|
||||
"""Bing News has an official market code 'zh-CN' but we won't get a result with
|
||||
this market code. For 'zh' and 'zh-CN' we better use the *Worldwide aggregate*
|
||||
market code (en-WW).
|
||||
"""
|
||||
|
||||
|
||||
def request(query, params):
|
||||
"""Assemble a Bing-News request."""
|
||||
|
||||
sxng_locale = params['searxng_locale']
|
||||
engine_region = traits.get_region(mkt_alias.get(sxng_locale, sxng_locale), traits.all_locale)
|
||||
engine_language = traits.get_language(sxng_locale, 'en')
|
||||
|
||||
SID = uuid.uuid1().hex.upper()
|
||||
set_bing_cookies(params, engine_language, engine_region, SID)
|
||||
engine_region = traits.get_region(params['searxng_locale'], traits.all_locale) # type: ignore
|
||||
engine_language = traits.get_language(params['searxng_locale'], 'en') # type: ignore
|
||||
set_bing_cookies(params, engine_language, engine_region)
|
||||
|
||||
# build URL query
|
||||
#
|
||||
# example: https://www.bing.com/news/infinitescrollajax?q=london&first=1
|
||||
|
||||
page = int(params.get('pageno', 1)) - 1
|
||||
query_params = {
|
||||
# fmt: off
|
||||
'q': query,
|
||||
'InfiniteScroll': 1,
|
||||
# to simplify the page count lets use the default of 10 images per page
|
||||
'first' : (int(params.get('pageno', 1)) - 1) * 10 + 1,
|
||||
# fmt: on
|
||||
'first': page * 10 + 1,
|
||||
'SFX': page,
|
||||
'form': 'PTFTNR',
|
||||
'setlang': engine_region.split('-')[0],
|
||||
'cc': engine_region.split('-')[-1],
|
||||
}
|
||||
|
||||
if params['time_range']:
|
||||
# qft=interval:"7"
|
||||
query_params['qft'] = 'qft=interval="%s"' % time_map.get(params['time_range'], '9')
|
||||
query_params['qft'] = time_map.get(params['time_range'], 'interval="9"')
|
||||
|
||||
params['url'] = base_url + '?' + urlencode(query_params)
|
||||
|
||||
|
|
@ -106,18 +97,34 @@ def response(resp):
|
|||
|
||||
dom = html.fromstring(resp.text)
|
||||
|
||||
for newsitem in dom.xpath('//div[contains(@class, "newsitem")]'):
|
||||
for newsitem in eval_xpath_list(dom, '//div[contains(@class, "newsitem")]'):
|
||||
|
||||
link = eval_xpath_getindex(newsitem, './/a[@class="title"]', 0, None)
|
||||
if link is None:
|
||||
continue
|
||||
url = link.attrib.get('href')
|
||||
title = extract_text(link)
|
||||
content = extract_text(eval_xpath(newsitem, './/div[@class="snippet"]'))
|
||||
|
||||
metadata = []
|
||||
source = eval_xpath_getindex(newsitem, './/div[contains(@class, "source")]', 0, None)
|
||||
if source is not None:
|
||||
for item in (
|
||||
eval_xpath_getindex(source, './/span[@aria-label]/@aria-label', 0, None),
|
||||
# eval_xpath_getindex(source, './/a', 0, None),
|
||||
# eval_xpath_getindex(source, './div/span', 3, None),
|
||||
link.attrib.get('data-author'),
|
||||
):
|
||||
if item is not None:
|
||||
t = extract_text(item)
|
||||
if t and t.strip():
|
||||
metadata.append(t.strip())
|
||||
metadata = ' | '.join(metadata)
|
||||
|
||||
url = newsitem.xpath('./@url')[0]
|
||||
title = ' '.join(newsitem.xpath('.//div[@class="caption"]//a[@class="title"]/text()')).strip()
|
||||
content = ' '.join(newsitem.xpath('.//div[@class="snippet"]/text()')).strip()
|
||||
thumbnail = None
|
||||
author = newsitem.xpath('./@data-author')[0]
|
||||
metadata = ' '.join(newsitem.xpath('.//div[@class="source"]/span/text()')).strip()
|
||||
|
||||
img_src = newsitem.xpath('.//a[@class="imagelink"]//img/@src')
|
||||
if img_src:
|
||||
thumbnail = 'https://www.bing.com/' + img_src[0]
|
||||
imagelink = eval_xpath_getindex(newsitem, './/a[@class="imagelink"]//img', 0, None)
|
||||
if imagelink is not None:
|
||||
thumbnail = 'https://www.bing.com/' + imagelink.attrib.get('src')
|
||||
|
||||
results.append(
|
||||
{
|
||||
|
|
@ -125,7 +132,6 @@ def response(resp):
|
|||
'title': title,
|
||||
'content': content,
|
||||
'img_src': thumbnail,
|
||||
'author': author,
|
||||
'metadata': metadata,
|
||||
}
|
||||
)
|
||||
|
|
@ -134,17 +140,20 @@ def response(resp):
|
|||
|
||||
|
||||
def fetch_traits(engine_traits: EngineTraits):
|
||||
"""Fetch languages and regions from Bing-News.
|
||||
"""Fetch languages and regions from Bing-News."""
|
||||
# pylint: disable=import-outside-toplevel
|
||||
|
||||
The :py:obj:`description <searx.engines.bing_news.bing_traits_url>` of the
|
||||
first table says *"query parameter when calling the Video Search API."*
|
||||
.. that's why I use the 4. table "News Category API markets" for the
|
||||
``xpath_market_codes``.
|
||||
from searx.engines.bing import fetch_traits as _f
|
||||
|
||||
"""
|
||||
_f(engine_traits)
|
||||
|
||||
xpath_market_codes = '//table[4]/tbody/tr/td[3]'
|
||||
# xpath_country_codes = '//table[2]/tbody/tr/td[2]'
|
||||
xpath_language_codes = '//table[3]/tbody/tr/td[2]'
|
||||
# fix market codes not known by bing news:
|
||||
|
||||
_fetch_traits(engine_traits, bing_traits_url, xpath_language_codes, xpath_market_codes)
|
||||
# In bing the market code 'zh-cn' exists, but there is no 'news' category in
|
||||
# bing for this market. Alternatively we use the the market code from Honk
|
||||
# Kong. Even if this is not correct, it is better than having no hits at
|
||||
# all, or sending false queries to bing that could raise the suspicion of a
|
||||
# bot.
|
||||
|
||||
# HINT: 'en-hk' is the region code it does not indicate the language en!!
|
||||
engine_traits.regions['zh-CN'] = 'en-hk'
|
||||
|
|
|
|||
|
|
@ -5,18 +5,15 @@
|
|||
# pylint: disable=invalid-name
|
||||
|
||||
from typing import TYPE_CHECKING
|
||||
import uuid
|
||||
import json
|
||||
from urllib.parse import urlencode
|
||||
|
||||
from lxml import html
|
||||
|
||||
from searx.enginelib.traits import EngineTraits
|
||||
from searx.engines.bing import (
|
||||
set_bing_cookies,
|
||||
_fetch_traits,
|
||||
)
|
||||
from searx.engines.bing import send_accept_language_header # pylint: disable=unused-import
|
||||
from searx.engines.bing import set_bing_cookies
|
||||
from searx.engines.bing import fetch_traits # pylint: disable=unused-import
|
||||
from searx.engines.bing_images import time_map
|
||||
|
||||
if TYPE_CHECKING:
|
||||
import logging
|
||||
|
|
@ -44,40 +41,24 @@ time_range_support = True
|
|||
base_url = 'https://www.bing.com/videos/asyncv2'
|
||||
"""Bing (Videos) async search URL."""
|
||||
|
||||
bing_traits_url = 'https://learn.microsoft.com/en-us/bing/search-apis/bing-video-search/reference/market-codes'
|
||||
"""Bing (Video) search API description"""
|
||||
|
||||
time_map = {
|
||||
# fmt: off
|
||||
'day': 60 * 24,
|
||||
'week': 60 * 24 * 7,
|
||||
'month': 60 * 24 * 31,
|
||||
'year': 60 * 24 * 365,
|
||||
# fmt: on
|
||||
}
|
||||
|
||||
|
||||
def request(query, params):
|
||||
"""Assemble a Bing-Video request."""
|
||||
|
||||
engine_region = traits.get_region(params['searxng_locale'], 'en-US')
|
||||
engine_language = traits.get_language(params['searxng_locale'], 'en')
|
||||
|
||||
SID = uuid.uuid1().hex.upper()
|
||||
set_bing_cookies(params, engine_language, engine_region, SID)
|
||||
engine_region = traits.get_region(params['searxng_locale'], traits.all_locale) # type: ignore
|
||||
engine_language = traits.get_language(params['searxng_locale'], 'en') # type: ignore
|
||||
set_bing_cookies(params, engine_language, engine_region)
|
||||
|
||||
# build URL query
|
||||
#
|
||||
# example: https://www.bing.com/videos/asyncv2?q=foo&async=content&first=1&count=35
|
||||
|
||||
query_params = {
|
||||
# fmt: off
|
||||
'q': query,
|
||||
'async' : 'content',
|
||||
'async': 'content',
|
||||
# to simplify the page count lets use the default of 35 images per page
|
||||
'first' : (int(params.get('pageno', 1)) - 1) * 35 + 1,
|
||||
'count' : 35,
|
||||
# fmt: on
|
||||
'first': (int(params.get('pageno', 1)) - 1) * 35 + 1,
|
||||
'count': 35,
|
||||
}
|
||||
|
||||
# time range
|
||||
|
|
@ -116,13 +97,3 @@ def response(resp):
|
|||
)
|
||||
|
||||
return results
|
||||
|
||||
|
||||
def fetch_traits(engine_traits: EngineTraits):
|
||||
"""Fetch languages and regions from Bing-Videos."""
|
||||
|
||||
xpath_market_codes = '//table[1]/tbody/tr/td[3]'
|
||||
# xpath_country_codes = '//table[2]/tbody/tr/td[2]'
|
||||
xpath_language_codes = '//table[3]/tbody/tr/td[2]'
|
||||
|
||||
_fetch_traits(engine_traits, bing_traits_url, xpath_language_codes, xpath_market_codes)
|
||||
|
|
|
|||
|
|
@ -14,7 +14,6 @@ from lxml import html
|
|||
|
||||
from searx.utils import (
|
||||
eval_xpath_list,
|
||||
eval_xpath_getindex,
|
||||
extract_text,
|
||||
)
|
||||
|
||||
|
|
@ -28,11 +27,9 @@ about = {
|
|||
}
|
||||
|
||||
categories = []
|
||||
paging = False
|
||||
time_range_support = False
|
||||
|
||||
base_url = 'https://emojipedia.org'
|
||||
search_url = base_url + '/search/?{query}'
|
||||
search_url = base_url + '/search?{query}'
|
||||
|
||||
|
||||
def request(query, params):
|
||||
|
|
@ -47,20 +44,10 @@ def response(resp):
|
|||
|
||||
dom = html.fromstring(resp.text)
|
||||
|
||||
for result in eval_xpath_list(dom, "//ol[@class='search-results']/li"):
|
||||
for result in eval_xpath_list(dom, '//div[starts-with(@class, "EmojisList")]/a'):
|
||||
|
||||
extracted_desc = extract_text(eval_xpath_getindex(result, './/p', 0))
|
||||
|
||||
if 'No results found.' in extracted_desc:
|
||||
break
|
||||
|
||||
link = eval_xpath_getindex(result, './/h2/a', 0)
|
||||
|
||||
url = base_url + link.attrib.get('href')
|
||||
title = extract_text(link)
|
||||
content = extracted_desc
|
||||
|
||||
res = {'url': url, 'title': title, 'content': content}
|
||||
url = base_url + result.attrib.get('href')
|
||||
res = {'url': url, 'title': extract_text(result), 'content': ''}
|
||||
|
||||
results.append(res)
|
||||
|
||||
|
|
|
|||
|
|
@ -0,0 +1,45 @@
|
|||
# SPDX-License-Identifier: AGPL-3.0-or-later
|
||||
# lint: pylint
|
||||
"""Matrixrooms.info (social media)
|
||||
"""
|
||||
|
||||
from urllib.parse import quote_plus
|
||||
|
||||
about = {
|
||||
"website": 'https://matrixrooms.info',
|
||||
"wikidata_id": 'Q107565255',
|
||||
"official_api_documentation": None,
|
||||
"use_official_api": False,
|
||||
"require_api_key": False,
|
||||
"results": 'JSON',
|
||||
}
|
||||
paging = True
|
||||
categories = ['social media']
|
||||
|
||||
base_url = "https://apicdn.matrixrooms.info"
|
||||
matrix_url = "https://matrix.to"
|
||||
page_size = 20
|
||||
|
||||
|
||||
def request(query, params):
|
||||
params['url'] = f"{base_url}/search/{quote_plus(query)}/{page_size}/{(params['pageno']-1)*page_size}"
|
||||
return params
|
||||
|
||||
|
||||
def response(resp):
|
||||
results = []
|
||||
|
||||
for result in resp.json():
|
||||
results.append(
|
||||
{
|
||||
'url': matrix_url + '/#/' + result['alias'],
|
||||
'title': result['name'],
|
||||
'content': result['topic']
|
||||
+ f" // {result['members']} members"
|
||||
+ f" // {result['alias']}"
|
||||
+ f" // {result['server']}",
|
||||
'thumbnail': result['avatar_url'],
|
||||
}
|
||||
)
|
||||
|
||||
return results
|
||||
|
|
@ -105,11 +105,11 @@ def response(resp):
|
|||
item['metadata'] = html_to_text(result.get('meta_short', ''))
|
||||
|
||||
if result.get('image'):
|
||||
item['thumbnail'] = image_url.format(image_id=result['image'], filename=result['image_filename'])
|
||||
item['img_src'] = image_url.format(image_id=result['image'], filename=result['image_filename'])
|
||||
else:
|
||||
item['url'] = result['url']
|
||||
item['content'] = ', '.join([result['class'], result['info'], result['more']])
|
||||
item['thumbnail'] = result['image']
|
||||
item['img_src'] = result['image']
|
||||
|
||||
results.append(item)
|
||||
|
||||
|
|
|
|||
|
|
@ -0,0 +1,63 @@
|
|||
# SPDX-License-Identifier: AGPL-3.0-or-later
|
||||
# lint: pylint
|
||||
"""Pinterest (images)
|
||||
"""
|
||||
|
||||
from json import dumps
|
||||
|
||||
about = {
|
||||
"website": 'https://www.pinterest.com/',
|
||||
"wikidata_id": 'Q255381',
|
||||
"official_api_documentation": 'https://developers.pinterest.com/docs/api/v5/',
|
||||
"use_official_api": False,
|
||||
"require_api_key": False,
|
||||
"results": 'JSON',
|
||||
}
|
||||
|
||||
categories = ['images']
|
||||
paging = True
|
||||
|
||||
base_url = 'https://www.pinterest.com'
|
||||
|
||||
|
||||
def request(query, params):
|
||||
args = {
|
||||
'options': {
|
||||
'query': query,
|
||||
'bookmarks': [params['engine_data'].get('bookmark', '')],
|
||||
},
|
||||
'context': {},
|
||||
}
|
||||
params['url'] = f"{base_url}/resource/BaseSearchResource/get/?data={dumps(args)}"
|
||||
|
||||
return params
|
||||
|
||||
|
||||
def response(resp):
|
||||
results = []
|
||||
|
||||
json_resp = resp.json()
|
||||
|
||||
results.append(
|
||||
{
|
||||
'engine_data': json_resp['resource_response']['bookmark'],
|
||||
# it's called bookmark by pinterest, but it's rather a nextpage
|
||||
# parameter to get the next results
|
||||
'key': 'bookmark',
|
||||
}
|
||||
)
|
||||
|
||||
for result in json_resp['resource_response']['data']['results']:
|
||||
results.append(
|
||||
{
|
||||
'template': 'images.html',
|
||||
'url': result['link'] or f"{base_url}/pin/{result['id']}/",
|
||||
'title': result.get('title') or result.get('grid_title'),
|
||||
'content': (result.get('rich_summary') or {}).get('display_description') or "",
|
||||
'img_src': result['images']['orig']['url'],
|
||||
'thumbnail_src': result['images']['236x']['url'],
|
||||
'source': (result.get('rich_summary') or {}).get('site_name'),
|
||||
}
|
||||
)
|
||||
|
||||
return results
|
||||
|
|
@ -42,6 +42,17 @@ paging = True
|
|||
results_per_page = 10
|
||||
base_url = "https://www.tagesschau.de"
|
||||
|
||||
use_source_url = True
|
||||
"""When set to false, display URLs from Tagesschau, and not the actual source
|
||||
(e.g. NDR, WDR, SWR, HR, ...)
|
||||
|
||||
.. note::
|
||||
|
||||
The actual source may contain additional content, such as commentary, that is
|
||||
not displayed in the Tagesschau.
|
||||
|
||||
"""
|
||||
|
||||
|
||||
def request(query, params):
|
||||
args = {
|
||||
|
|
@ -78,7 +89,7 @@ def _story(item):
|
|||
'thumbnail': item.get('teaserImage', {}).get('imageVariants', {}).get('16x9-256'),
|
||||
'publishedDate': datetime.strptime(item['date'][:19], '%Y-%m-%dT%H:%M:%S'),
|
||||
'content': item['firstSentence'],
|
||||
'url': item['shareURL'],
|
||||
'url': item['shareURL'] if use_source_url else item['detailsweb'],
|
||||
}
|
||||
|
||||
|
||||
|
|
|
|||
|
|
@ -133,12 +133,7 @@ def response(resp):
|
|||
continue
|
||||
url = parse_url(url)
|
||||
|
||||
title = eval_xpath_getindex(result, './/h3/a', 0, default=None)
|
||||
if title is None:
|
||||
continue
|
||||
offset = len(extract_text(title.xpath('span')))
|
||||
title = extract_text(title)[offset:]
|
||||
|
||||
title = extract_text(result.xpath('.//h3//a/@aria-label'))
|
||||
content = eval_xpath_getindex(result, './/div[contains(@class, "compText")]', 0, default='')
|
||||
content = extract_text(content, allow_none=True)
|
||||
|
||||
|
|
@ -164,7 +159,7 @@ def fetch_traits(engine_traits: EngineTraits):
|
|||
|
||||
resp = network.get('https://search.yahoo.com/preferences/languages')
|
||||
if not resp.ok:
|
||||
print("ERROR: response from peertube is not OK.")
|
||||
print("ERROR: response from yahoo is not OK.")
|
||||
|
||||
dom = html.fromstring(resp.text)
|
||||
offset = len('lang_')
|
||||
|
|
|
|||
|
|
@ -1018,6 +1018,11 @@ engines:
|
|||
require_api_key: false
|
||||
results: HTML
|
||||
|
||||
- name: matrixrooms
|
||||
engine: matrixrooms
|
||||
shortcut: mtrx
|
||||
disabled: true
|
||||
|
||||
- name: metacpan
|
||||
engine: metacpan
|
||||
shortcut: cpan
|
||||
|
|
@ -1201,6 +1206,10 @@ engines:
|
|||
engine: photon
|
||||
shortcut: ph
|
||||
|
||||
- name: pinterest
|
||||
engine: pinterest
|
||||
shortcut: pin
|
||||
|
||||
- name: piped
|
||||
engine: piped
|
||||
shortcut: ppd
|
||||
|
|
@ -1483,6 +1492,9 @@ engines:
|
|||
|
||||
- name: tagesschau
|
||||
engine: tagesschau
|
||||
# when set to false, display URLs from Tagesschau, and not the actual source
|
||||
# (e.g. NDR, WDR, SWR, HR, ...)
|
||||
use_source_url: true
|
||||
shortcut: ts
|
||||
disabled: true
|
||||
|
||||
|
|
|
|||
Loading…
Reference in New Issue