mirror of
https://github.com/searxng/searxng.git
synced 2026-05-07 18:03:51 +02:00
[enh] engines: rework bing engine (#5793)
* [enh] engines: rework bing engine Only Bing-Web has been reworked. Some features now require JavaScript (paging and time-range results). Cookies no longer work, parameters such as `cc`, `ui`, ... alter the results. The engine only appears to use the locale from `Accept-Language` header properly. The rest of Bing's child engines (Bing-Image, Bing-Video, ...) seem to benefit from using `mkt` param in conjunction with the `Accept-Language` header override, although Bing-Web does not (?) * [enh] explicit mkt * [fix] engines: bing_videos.py https://github.com/searxng/searxng/pull/5793#pullrequestreview-3881883250
This commit is contained in:
Ivan Gabaldon
+109
-170
@@ -1,34 +1,20 @@
|
||||
# SPDX-License-Identifier: AGPL-3.0-or-later
|
||||
"""This is the implementation of the Bing-WEB engine. Some of this
|
||||
"""This is the implementation of the Bing-Web engine. Some of this
|
||||
implementations are shared by other engines:
|
||||
|
||||
- :ref:`bing images engine`
|
||||
- :ref:`bing news engine`
|
||||
- :ref:`bing videos engine`
|
||||
|
||||
On the `preference page`_ Bing offers a lot of languages an regions (see section
|
||||
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"*.
|
||||
|
||||
There is a description of the official 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the market codes are usually outdated or at least no longer used by bing itself.
|
||||
|
||||
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/
|
||||
.. note::
|
||||
|
||||
Some functionality (paging and time-range results) are not supported
|
||||
since they depend on JavaScript.
|
||||
"""
|
||||
# pylint: disable=too-many-branches, invalid-name
|
||||
|
||||
import base64
|
||||
import re
|
||||
import time
|
||||
import typing as t
|
||||
from urllib.parse import parse_qs, urlencode, urlparse
|
||||
|
||||
import babel
|
||||
@@ -36,14 +22,17 @@ import babel.languages
|
||||
from lxml import html
|
||||
|
||||
from searx.enginelib.traits import EngineTraits
|
||||
from searx.exceptions import SearxEngineAPIException
|
||||
from searx.locales import language_tag, region_tag
|
||||
from searx.locales import region_tag
|
||||
from searx.utils import eval_xpath, eval_xpath_getindex, eval_xpath_list, extract_text
|
||||
|
||||
about = {
|
||||
if t.TYPE_CHECKING:
|
||||
from searx.extended_types import SXNG_Response
|
||||
from searx.search.processors import OnlineParams
|
||||
|
||||
about: dict[str, t.Any] = {
|
||||
"website": "https://www.bing.com",
|
||||
"wikidata_id": "Q182496",
|
||||
"official_api_documentation": "https://www.microsoft.com/en-us/bing/apis/bing-web-search-api",
|
||||
"official_api_documentation": "https://github.com/MicrosoftDocs/bing-docs",
|
||||
"use_official_api": False,
|
||||
"require_api_key": False,
|
||||
"results": "HTML",
|
||||
@@ -51,69 +40,78 @@ about = {
|
||||
|
||||
# engine dependent config
|
||||
categories = ["general", "web"]
|
||||
paging = True
|
||||
max_page = 200
|
||||
"""200 pages maximum (``&first=1991``)"""
|
||||
|
||||
time_range_support = True
|
||||
safesearch = True
|
||||
"""Bing results are always SFW. To get NSFW links from bing some age
|
||||
verification by a cookie is needed / thats not possible in SearXNG.
|
||||
"""
|
||||
_safesearch_map: dict[int, str] = {
|
||||
0: "off",
|
||||
1: "moderate",
|
||||
2: "strict",
|
||||
}
|
||||
"""Filter results. 0: None, 1: Moderate, 2: Strict"""
|
||||
|
||||
base_url = "https://www.bing.com/search"
|
||||
"""Bing (Web) search URL"""
|
||||
"""Bing-Web search URL"""
|
||||
|
||||
|
||||
def _page_offset(pageno):
|
||||
return (int(pageno) - 1) * 10 + 1
|
||||
def get_locale_params(engine_region: str | None) -> dict[str, str] | None:
|
||||
"""API documentation states the ``mkt`` parameter is *the
|
||||
recommended primary signal* for locale:
|
||||
|
||||
If known, you are encouraged to always specify the market.
|
||||
Specifying the market helps Bing route the request and return an
|
||||
appropriate and optimal response.
|
||||
|
||||
The ``mkt`` parameter takes a full ``<language>-<country>`` code.
|
||||
|
||||
This function is shared with :py:mod:`searx.engines.bing_images`,
|
||||
:py:mod:`searx.engines.bing_news`, and :py:mod:`searx.engines.bing_videos`.
|
||||
"""
|
||||
|
||||
if not engine_region or engine_region == "clear":
|
||||
return None
|
||||
|
||||
return {"mkt": engine_region}
|
||||
|
||||
|
||||
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 override_accept_language(params: "OnlineParams", engine_region: str | None) -> None:
|
||||
"""Override the ``Accept-Language`` header.
|
||||
|
||||
The default header built by :py:class:`~searx.search.processors.online.OnlineProcessor`
|
||||
appends ``en;q=0.3`` as a fallback language::
|
||||
|
||||
Accept-Language: de,de-DE;q=0.7,en;q=0.3
|
||||
|
||||
Bing seems to better select the results locale based on the
|
||||
``Accept-Language`` value header.
|
||||
|
||||
This function is shared with :py:mod:`searx.engines.bing_images`,
|
||||
:py:mod:`searx.engines.bing_news`, and :py:mod:`searx.engines.bing_videos`.
|
||||
"""
|
||||
|
||||
if not engine_region or engine_region == "clear":
|
||||
return
|
||||
|
||||
lang = engine_region.split("-")[0]
|
||||
params["headers"]["Accept-Language"] = f"{engine_region},{lang};q=0.9"
|
||||
|
||||
|
||||
def request(query, params):
|
||||
def request(query: str, params: "OnlineParams") -> "OnlineParams":
|
||||
"""Assemble a Bing-Web request."""
|
||||
|
||||
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)
|
||||
engine_region = traits.get_region(params["searxng_locale"], traits.all_locale)
|
||||
|
||||
page = params.get("pageno", 1)
|
||||
query_params = {
|
||||
override_accept_language(params, engine_region)
|
||||
|
||||
query_params: dict[str, str | int] = {
|
||||
"q": query,
|
||||
# if arg 'pq' is missed, sometimes 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,
|
||||
"adlt": _safesearch_map.get(params.get("safesearch", 0), "off"),
|
||||
}
|
||||
|
||||
# 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:
|
||||
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)
|
||||
locale_params = get_locale_params(engine_region)
|
||||
if locale_params:
|
||||
query_params.update(locale_params)
|
||||
|
||||
params["url"] = f"{base_url}?{urlencode(query_params)}"
|
||||
|
||||
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"]]}"'
|
||||
|
||||
# in some regions where geoblocking is employed (e.g. China),
|
||||
# www.bing.com redirects to the regional version of Bing
|
||||
params["allow_redirects"] = True
|
||||
@@ -121,82 +119,57 @@ def request(query, params):
|
||||
return params
|
||||
|
||||
|
||||
def response(resp):
|
||||
# pylint: disable=too-many-locals
|
||||
def response(resp: "SXNG_Response") -> list[dict[str, t.Any]]:
|
||||
"""Get response from Bing-Web"""
|
||||
|
||||
results = []
|
||||
result_len = 0
|
||||
results: list[dict[str, t.Any]] = []
|
||||
|
||||
dom = html.fromstring(resp.text)
|
||||
|
||||
# parse results again if nothing is found yet
|
||||
|
||||
for result in eval_xpath_list(dom, '//ol[@id="b_results"]/li[contains(@class, "b_algo")]'):
|
||||
link = eval_xpath_getindex(result, ".//h2/a", 0, None)
|
||||
for item in eval_xpath_list(dom, '//ol[@id="b_results"]/li[contains(@class, "b_algo")]'):
|
||||
link = eval_xpath_getindex(item, ".//h2/a", 0, None)
|
||||
if link is None:
|
||||
continue
|
||||
url = link.attrib.get("href")
|
||||
|
||||
href = link.attrib.get("href", "")
|
||||
title = extract_text(link)
|
||||
|
||||
content = eval_xpath(result, ".//p")
|
||||
for p in content:
|
||||
# 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)
|
||||
if not href or not title:
|
||||
continue
|
||||
|
||||
# get the real URL
|
||||
if url.startswith("https://www.bing.com/ck/a?"):
|
||||
# get the first value of u parameter
|
||||
url_query = urlparse(url).query
|
||||
parsed_url_query = parse_qs(url_query)
|
||||
param_u = parsed_url_query["u"][0]
|
||||
# remove "a1" in front
|
||||
encoded_url = param_u[2:]
|
||||
# add padding
|
||||
encoded_url = encoded_url + "=" * (-len(encoded_url) % 4)
|
||||
# decode base64 encoded URL
|
||||
url = base64.urlsafe_b64decode(encoded_url).decode()
|
||||
# what about cn.bing.com, ..?
|
||||
if href.startswith("https://www.bing.com/ck/a?"):
|
||||
qs = parse_qs(urlparse(href).query)
|
||||
u_values = qs.get("u")
|
||||
if u_values:
|
||||
u_val = u_values[0]
|
||||
if u_val.startswith("a1"):
|
||||
encoded = u_val[2:]
|
||||
# base64url without padding
|
||||
encoded += "=" * (-len(encoded) % 4)
|
||||
href = base64.urlsafe_b64decode(encoded).decode("utf-8", errors="replace")
|
||||
|
||||
# append result
|
||||
results.append({"url": url, "title": title, "content": content})
|
||||
# remove decorative icons that Bing injects into <p> elements
|
||||
# (`<span class="algoSlug_icon">`)
|
||||
content_els = eval_xpath(item, ".//p")
|
||||
for p in content_els:
|
||||
for icon in p.xpath('.//span[@class="algoSlug_icon"]'):
|
||||
icon.getparent().remove(icon)
|
||||
content = extract_text(content_els)
|
||||
|
||||
results.append({"url": href, "title": title, "content": content})
|
||||
|
||||
# get number_of_results
|
||||
if results:
|
||||
result_len_container = "".join(eval_xpath(dom, '//span[@class="sb_count"]//text()'))
|
||||
if "-" in result_len_container:
|
||||
start_str, result_len_container = re.split(r"-\d+", result_len_container)
|
||||
start = int(start_str)
|
||||
else:
|
||||
start = 1
|
||||
result_len_container = re.sub(r"[^0-9]", "", result_len_container)
|
||||
if result_len_container:
|
||||
results.append({"number_of_results": int(result_len_container)})
|
||||
|
||||
result_len_container = re.sub("[^0-9]", "", result_len_container)
|
||||
if len(result_len_container) > 0:
|
||||
result_len = int(result_len_container)
|
||||
|
||||
expected_start = _page_offset(resp.search_params.get("pageno", 1))
|
||||
|
||||
if expected_start != start:
|
||||
if expected_start > result_len:
|
||||
# Avoid reading more results than available.
|
||||
# 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.
|
||||
# If we compare results count with the first parameter of the request we can avoid this "invalid"
|
||||
# results.
|
||||
return []
|
||||
|
||||
# Sometimes Bing will send back the first result page instead of the requested page as a rate limiting
|
||||
# measure.
|
||||
msg = f"Expected results to start at {expected_start}, but got results starting at {start}"
|
||||
raise SearxEngineAPIException(msg)
|
||||
|
||||
results.append({"number_of_results": result_len})
|
||||
return results
|
||||
|
||||
|
||||
def fetch_traits(engine_traits: EngineTraits):
|
||||
"""Fetch languages and regions from Bing-Web."""
|
||||
def fetch_traits(engine_traits: EngineTraits) -> None:
|
||||
"""Fetch regions from Bing-Web."""
|
||||
# pylint: disable=import-outside-toplevel
|
||||
|
||||
from searx.network import get # see https://github.com/searxng/searxng/issues/762
|
||||
@@ -219,47 +192,10 @@ def fetch_traits(engine_traits: EngineTraits):
|
||||
|
||||
dom = html.fromstring(resp.text)
|
||||
|
||||
# languages
|
||||
|
||||
engine_traits.languages["zh"] = "zh-hans"
|
||||
|
||||
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
|
||||
map_market_codes: dict[str, str] = {
|
||||
"zh-hk": "en-hk", # not sure why, but at Microslop this is the market code for Hongkong
|
||||
}
|
||||
|
||||
for href in eval_xpath(dom, '//div[@id="language-section-content"]//div[@class="languageItem"]/a/@href'):
|
||||
eng_lang = parse_qs(urlparse(href).query)["setlang"][0]
|
||||
babel_lang = map_lang.get(eng_lang, eng_lang)
|
||||
try:
|
||||
sxng_tag = language_tag(babel.Locale.parse(babel_lang.replace("-", "_")))
|
||||
except babel.UnknownLocaleError:
|
||||
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-content"]//div[@class="regionItem"]/a/@href'):
|
||||
cc_tag = parse_qs(urlparse(href).query)["cc"][0]
|
||||
if cc_tag == "clear":
|
||||
@@ -268,17 +204,20 @@ def fetch_traits(engine_traits: EngineTraits):
|
||||
|
||||
# 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)
|
||||
|
||||
try:
|
||||
sxng_tag = region_tag(babel.Locale.parse("%s_%s" % (lang_tag, cc_tag.upper())))
|
||||
except babel.UnknownLocaleError:
|
||||
# silently ignore unknown languages
|
||||
continue
|
||||
|
||||
conflict = engine_traits.regions.get(sxng_tag)
|
||||
if conflict:
|
||||
if conflict != market_code:
|
||||
print("CONFLICT: babel %s --> %s, %s" % (sxng_tag, conflict, market_code))
|
||||
continue
|
||||
|
||||
engine_traits.regions[sxng_tag] = market_code
|
||||
|
||||
@@ -1,96 +1,101 @@
|
||||
# SPDX-License-Identifier: AGPL-3.0-or-later
|
||||
"""Bing-Images: description see :py:obj:`searx.engines.bing`."""
|
||||
# pylint: disable=invalid-name
|
||||
|
||||
import json
|
||||
from urllib.parse import urlencode
|
||||
|
||||
from lxml import html
|
||||
|
||||
from searx.engines.bing import set_bing_cookies
|
||||
from searx.engines.bing import fetch_traits # pylint: disable=unused-import
|
||||
from searx.engines.bing import ( # pylint: disable=unused-import
|
||||
fetch_traits,
|
||||
get_locale_params,
|
||||
override_accept_language,
|
||||
)
|
||||
|
||||
# about
|
||||
about = {
|
||||
"website": 'https://www.bing.com/images',
|
||||
"wikidata_id": 'Q182496',
|
||||
"official_api_documentation": 'https://www.microsoft.com/en-us/bing/apis/bing-image-search-api',
|
||||
"website": "https://www.bing.com/images",
|
||||
"wikidata_id": "Q182496",
|
||||
"official_api_documentation": "https://github.com/MicrosoftDocs/bing-docs",
|
||||
"use_official_api": False,
|
||||
"require_api_key": False,
|
||||
"results": 'HTML',
|
||||
"results": "HTML",
|
||||
}
|
||||
|
||||
# engine dependent config
|
||||
categories = ['images', 'web']
|
||||
categories = ["images", "web"]
|
||||
paging = True
|
||||
safesearch = True
|
||||
time_range_support = True
|
||||
|
||||
base_url = 'https://www.bing.com/images/async'
|
||||
"""Bing (Images) search URL"""
|
||||
|
||||
time_map = {
|
||||
'day': 60 * 24,
|
||||
'week': 60 * 24 * 7,
|
||||
'month': 60 * 24 * 31,
|
||||
'year': 60 * 24 * 365,
|
||||
"day": 60 * 24,
|
||||
"week": 60 * 24 * 7,
|
||||
"month": 60 * 24 * 31,
|
||||
"year": 60 * 24 * 365,
|
||||
}
|
||||
|
||||
base_url = "https://www.bing.com/images/async"
|
||||
"""Bing-Image search URL"""
|
||||
|
||||
|
||||
def request(query, params):
|
||||
"""Assemble a Bing-Image request."""
|
||||
|
||||
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)
|
||||
engine_region = traits.get_region(params["searxng_locale"], traits.all_locale)
|
||||
|
||||
override_accept_language(params, engine_region)
|
||||
|
||||
# build URL query
|
||||
# - example: https://www.bing.com/images/async?q=foo&async=content&first=1&count=35
|
||||
# - example: https://www.bing.com/images/async?q=foo&async=1&first=1&count=35
|
||||
query_params = {
|
||||
'q': query,
|
||||
'async': '1',
|
||||
"q": query,
|
||||
"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,
|
||||
"first": (int(params.get("pageno", 1)) - 1) * 35 + 1,
|
||||
"count": 35,
|
||||
}
|
||||
|
||||
locale_params = get_locale_params(engine_region)
|
||||
if locale_params:
|
||||
query_params.update(locale_params)
|
||||
|
||||
# time range
|
||||
# - example: one year (525600 minutes) 'qft=+filterui:age-lt525600'
|
||||
# - example: one year (525600 minutes) 'qft=filterui:age-lt525600'
|
||||
if params["time_range"]:
|
||||
query_params["qft"] = "filterui:age-lt%s" % time_map[params["time_range"]]
|
||||
|
||||
if params['time_range']:
|
||||
query_params['qft'] = 'filterui:age-lt%s' % time_map[params['time_range']]
|
||||
|
||||
params['url'] = base_url + '?' + urlencode(query_params)
|
||||
params["url"] = base_url + "?" + urlencode(query_params)
|
||||
|
||||
return params
|
||||
|
||||
|
||||
def response(resp):
|
||||
"""Get response from Bing-Images"""
|
||||
"""Get response from Bing-Image"""
|
||||
|
||||
results = []
|
||||
|
||||
dom = html.fromstring(resp.text)
|
||||
|
||||
for result in dom.xpath('//ul[contains(@class, "dgControl_list")]/li'):
|
||||
|
||||
metadata = result.xpath('.//a[@class="iusc"]/@m')
|
||||
if not metadata:
|
||||
continue
|
||||
|
||||
metadata = json.loads(result.xpath('.//a[@class="iusc"]/@m')[0])
|
||||
title = ' '.join(result.xpath('.//div[@class="infnmpt"]//a/text()')).strip()
|
||||
img_format = ' '.join(result.xpath('.//div[@class="imgpt"]/div/span/text()')).strip().split(" · ")
|
||||
source = ' '.join(result.xpath('.//div[@class="imgpt"]//div[@class="lnkw"]//a/text()')).strip()
|
||||
title = " ".join(result.xpath('.//div[@class="infnmpt"]//a/text()')).strip()
|
||||
img_format = " ".join(result.xpath('.//div[@class="imgpt"]/div/span/text()')).strip().split(" · ")
|
||||
source = " ".join(result.xpath('.//div[@class="imgpt"]//div[@class="lnkw"]//a/text()')).strip()
|
||||
results.append(
|
||||
{
|
||||
'template': 'images.html',
|
||||
'url': metadata['purl'],
|
||||
'thumbnail_src': metadata['turl'],
|
||||
'img_src': metadata['murl'],
|
||||
'content': metadata.get('desc'),
|
||||
'title': title,
|
||||
'source': source,
|
||||
'resolution': img_format[0],
|
||||
'img_format': img_format[1] if len(img_format) >= 2 else None,
|
||||
"template": "images.html",
|
||||
"url": metadata["purl"],
|
||||
"thumbnail_src": metadata["turl"],
|
||||
"img_src": metadata["murl"],
|
||||
"content": metadata.get("desc"),
|
||||
"title": title,
|
||||
"source": source,
|
||||
"resolution": img_format[0],
|
||||
"img_format": img_format[1] if len(img_format) >= 2 else None,
|
||||
}
|
||||
)
|
||||
return results
|
||||
|
||||
+45
-47
@@ -7,92 +7,90 @@
|
||||
|
||||
"""
|
||||
|
||||
# pylint: disable=invalid-name
|
||||
|
||||
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
|
||||
from searx.engines.bing import (
|
||||
get_locale_params,
|
||||
override_accept_language,
|
||||
)
|
||||
from searx.utils import eval_xpath, eval_xpath_getindex, eval_xpath_list, extract_text
|
||||
|
||||
# about
|
||||
about = {
|
||||
"website": 'https://www.bing.com/news',
|
||||
"wikidata_id": 'Q2878637',
|
||||
"official_api_documentation": 'https://www.microsoft.com/en-us/bing/apis/bing-news-search-api',
|
||||
"website": "https://www.bing.com/news",
|
||||
"wikidata_id": "Q2878637",
|
||||
"official_api_documentation": "https://github.com/MicrosoftDocs/bing-docs",
|
||||
"use_official_api": False,
|
||||
"require_api_key": False,
|
||||
"results": 'RSS',
|
||||
"results": "RSS",
|
||||
}
|
||||
|
||||
# engine dependent config
|
||||
categories = ['news']
|
||||
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': 'interval="4"',
|
||||
'week': 'interval="7"',
|
||||
'month': 'interval="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'
|
||||
base_url = "https://www.bing.com/news/infinitescrollajax"
|
||||
"""Bing (News) search URL"""
|
||||
|
||||
|
||||
def request(query, params):
|
||||
"""Assemble a Bing-News request."""
|
||||
|
||||
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)
|
||||
engine_region = traits.get_region(params["searxng_locale"], traits.all_locale)
|
||||
|
||||
override_accept_language(params, engine_region)
|
||||
|
||||
# build URL query
|
||||
#
|
||||
# example: https://www.bing.com/news/infinitescrollajax?q=london&first=1
|
||||
|
||||
page = int(params.get('pageno', 1)) - 1
|
||||
# - example: https://www.bing.com/news/infinitescrollajax?q=london&first=1
|
||||
page = int(params.get("pageno", 1)) - 1
|
||||
query_params = {
|
||||
'q': query,
|
||||
'InfiniteScroll': 1,
|
||||
"q": query,
|
||||
"InfiniteScroll": 1,
|
||||
# to simplify the page count lets use the default of 10 images per page
|
||||
'first': page * 10 + 1,
|
||||
'SFX': page,
|
||||
'form': 'PTFTNR',
|
||||
'setlang': engine_region.split('-')[0],
|
||||
'cc': engine_region.split('-')[-1],
|
||||
"first": page * 10 + 1,
|
||||
"SFX": page,
|
||||
"form": "PTFTNR",
|
||||
}
|
||||
|
||||
if params['time_range']:
|
||||
query_params['qft'] = time_map.get(params['time_range'], 'interval="9"')
|
||||
locale_params = get_locale_params(engine_region)
|
||||
if locale_params:
|
||||
query_params.update(locale_params)
|
||||
|
||||
params['url'] = base_url + '?' + urlencode(query_params)
|
||||
if params["time_range"]:
|
||||
query_params["qft"] = time_map.get(params["time_range"], 'interval="9"')
|
||||
|
||||
params["url"] = base_url + "?" + urlencode(query_params)
|
||||
|
||||
return params
|
||||
|
||||
|
||||
def response(resp):
|
||||
"""Get response from Bing-Video"""
|
||||
results = []
|
||||
"""Parse the Bing-News response."""
|
||||
|
||||
if not resp.ok or not resp.text:
|
||||
return results
|
||||
results = []
|
||||
|
||||
dom = html.fromstring(resp.text)
|
||||
|
||||
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')
|
||||
url = link.attrib.get("href")
|
||||
title = extract_text(link)
|
||||
content = extract_text(eval_xpath(newsitem, './/div[@class="snippet"]'))
|
||||
|
||||
@@ -100,31 +98,31 @@ def response(resp):
|
||||
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, ".//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'),
|
||||
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)
|
||||
metadata = " | ".join(metadata)
|
||||
|
||||
thumbnail = None
|
||||
imagelink = eval_xpath_getindex(newsitem, './/a[@class="imagelink"]//img', 0, None)
|
||||
if imagelink is not None:
|
||||
thumbnail = imagelink.attrib.get('src')
|
||||
thumbnail = imagelink.attrib.get("src")
|
||||
if not thumbnail.startswith("https://www.bing.com"):
|
||||
thumbnail = 'https://www.bing.com/' + thumbnail
|
||||
thumbnail = "https://www.bing.com/" + thumbnail
|
||||
|
||||
results.append(
|
||||
{
|
||||
'url': url,
|
||||
'title': title,
|
||||
'content': content,
|
||||
'thumbnail': thumbnail,
|
||||
'metadata': metadata,
|
||||
"url": url,
|
||||
"title": title,
|
||||
"content": content,
|
||||
"thumbnail": thumbnail,
|
||||
"metadata": metadata,
|
||||
}
|
||||
)
|
||||
|
||||
@@ -148,4 +146,4 @@ def fetch_traits(engine_traits: EngineTraits):
|
||||
# bot.
|
||||
|
||||
# HINT: 'en-hk' is the region code it does not indicate the language en!!
|
||||
engine_traits.regions['zh-CN'] = 'en-hk'
|
||||
engine_traits.regions["zh-CN"] = "en-hk"
|
||||
|
||||
@@ -1,5 +1,4 @@
|
||||
# SPDX-License-Identifier: AGPL-3.0-or-later
|
||||
# pylint: disable=invalid-name
|
||||
"""Bing-Videos: description see :py:obj:`searx.engines.bing`."""
|
||||
|
||||
import json
|
||||
@@ -7,81 +6,90 @@ from urllib.parse import urlencode
|
||||
|
||||
from lxml import html
|
||||
|
||||
from searx.engines.bing import set_bing_cookies
|
||||
from searx.engines.bing import fetch_traits # pylint: disable=unused-import
|
||||
from searx.engines.bing import ( # pylint: disable=unused-import
|
||||
fetch_traits,
|
||||
get_locale_params,
|
||||
override_accept_language,
|
||||
)
|
||||
from searx.engines.bing_images import time_map
|
||||
|
||||
from searx.utils import eval_xpath, eval_xpath_getindex
|
||||
|
||||
about = {
|
||||
"website": 'https://www.bing.com/videos',
|
||||
"wikidata_id": 'Q4914152',
|
||||
"official_api_documentation": 'https://www.microsoft.com/en-us/bing/apis/bing-video-search-api',
|
||||
"website": "https://www.bing.com/videos",
|
||||
"wikidata_id": "Q4914152",
|
||||
"official_api_documentation": "https://github.com/MicrosoftDocs/bing-docs",
|
||||
"use_official_api": False,
|
||||
"require_api_key": False,
|
||||
"results": 'HTML',
|
||||
"results": "HTML",
|
||||
}
|
||||
|
||||
# engine dependent config
|
||||
categories = ['videos', 'web']
|
||||
categories = ["videos", "web"]
|
||||
paging = True
|
||||
safesearch = True
|
||||
time_range_support = True
|
||||
|
||||
base_url = 'https://www.bing.com/videos/asyncv2'
|
||||
"""Bing (Videos) async search URL."""
|
||||
base_url = "https://www.bing.com/videos/asyncv2"
|
||||
"""Bing-Video search URL"""
|
||||
|
||||
|
||||
def request(query, params):
|
||||
"""Assemble a Bing-Video request."""
|
||||
|
||||
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)
|
||||
engine_region = traits.get_region(params["searxng_locale"], traits.all_locale)
|
||||
|
||||
override_accept_language(params, engine_region)
|
||||
|
||||
# build URL query
|
||||
#
|
||||
# example: https://www.bing.com/videos/asyncv2?q=foo&async=content&first=1&count=35
|
||||
|
||||
# - example: https://www.bing.com/videos/asyncv2?q=foo&async=content&first=1&count=35
|
||||
query_params = {
|
||||
'q': query,
|
||||
'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,
|
||||
"q": query,
|
||||
"async": "content",
|
||||
# to simplify the page count lets use the default of 35 videos per page
|
||||
"first": (int(params.get("pageno", 1)) - 1) * 35 + 1,
|
||||
"count": 35,
|
||||
}
|
||||
|
||||
locale_params = get_locale_params(engine_region)
|
||||
if locale_params:
|
||||
query_params.update(locale_params)
|
||||
|
||||
# time range
|
||||
#
|
||||
# example: one week (10080 minutes) '&qft= filterui:videoage-lt10080' '&form=VRFLTR'
|
||||
# - example: one week (10080 minutes) '&qft= filterui:videoage-lt10080' '&form=VRFLTR'
|
||||
if params["time_range"]:
|
||||
query_params["form"] = "VRFLTR"
|
||||
query_params["qft"] = " filterui:videoage-lt%s" % time_map[params["time_range"]]
|
||||
|
||||
if params['time_range']:
|
||||
query_params['form'] = 'VRFLTR'
|
||||
query_params['qft'] = ' filterui:videoage-lt%s' % time_map[params['time_range']]
|
||||
|
||||
params['url'] = base_url + '?' + urlencode(query_params)
|
||||
params["url"] = base_url + "?" + urlencode(query_params)
|
||||
|
||||
return params
|
||||
|
||||
|
||||
def response(resp):
|
||||
"""Get response from Bing-Video"""
|
||||
|
||||
results = []
|
||||
|
||||
dom = html.fromstring(resp.text)
|
||||
|
||||
for result in dom.xpath('//div[@class="dg_u"]//div[contains(@id, "mc_vtvc_video")]'):
|
||||
metadata = json.loads(result.xpath('.//div[@class="vrhdata"]/@vrhm')[0])
|
||||
info = ' - '.join(result.xpath('.//div[@class="mc_vtvc_meta_block"]//span/text()')).strip()
|
||||
content = '{0} - {1}'.format(metadata['du'], info)
|
||||
thumbnail = result.xpath('.//div[contains(@class, "mc_vtvc_th")]//img/@src')[0]
|
||||
for result in dom.xpath('//div[contains(@id, "mc_vtvc_video")]'):
|
||||
metadata = json.loads(eval_xpath_getindex(result, './/div[@class="vrhdata"]/@vrhm', index=0))
|
||||
info = " - ".join(eval_xpath(result, './/div[@class="mc_vtvc_meta_block"]//span/text()')).strip()
|
||||
thumbnail = eval_xpath_getindex(
|
||||
result,
|
||||
'.//img[starts-with(@class, "rms")]/@data-src-hq',
|
||||
index=0,
|
||||
default=None,
|
||||
)
|
||||
|
||||
results.append(
|
||||
{
|
||||
'url': metadata['murl'],
|
||||
'thumbnail': thumbnail,
|
||||
'title': metadata.get('vt', ''),
|
||||
'content': content,
|
||||
'template': 'videos.html',
|
||||
"url": metadata["murl"],
|
||||
"thumbnail": thumbnail,
|
||||
"title": metadata.get("vt", ""),
|
||||
"content": info,
|
||||
"length": metadata["du"],
|
||||
"template": "videos.html",
|
||||
}
|
||||
)
|
||||
|
||||
|
||||
Reference in New Issue
Block a user