mirror of
https://github.com/searxng/searxng.git
synced 2026-06-09 11:27:50 +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
+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"
|
||||
|
||||
Reference in New Issue
Block a user