[mod] bing_images: use async API & upgrade to data_type: traits_v1

Browse Source 
Signed-off-by: Markus Heiser <markus.heiser@darmarit.de>
This commit is contained in:
Markus Heiser 2022-10-22 19:01:51 +02:00
parent bc21d28298
commit ff80e7637e
1 changed files with 68 additions and 55 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

123
searx/engines/bing_images.py
View File

@ -1,16 +1,30 @@
# SPDX-License-Identifier: AGPL-3.0-or-later # SPDX-License-Identifier: AGPL-3.0-or-later
# lint: pylint # lint: pylint
"""Bing (Images) """Bing-Images: description see :py:obj:`searx.engines.bing`.
""" """
# pylint: disable=invalid-name
from json import loads
from typing import TYPE_CHECKING
import uuid
import json
from urllib.parse import urlencode from urllib.parse import urlencode
from lxml import html from lxml import html
from searx.utils import match_language
from searx.enginelib.traits import EngineTraits 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
if TYPE_CHECKING:
import logging
logger: logging.Logger
traits: EngineTraits
# about # about
about = { about = {
@ -27,93 +41,92 @@ categories = ['images', 'web']
paging = True paging = True
safesearch = True safesearch = True
time_range_support = True time_range_support = True
send_accept_language_header = True
supported_languages_url = 'https://www.bing.com/account/general'
number_of_results = 28
# search-url base_url = 'https://www.bing.com/images/async'
base_url = 'https://www.bing.com/' """Bing (Images) search URL"""
search_string = (
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 # fmt: off
'images/search' 'day': 60 * 24,
'?{query}' 'week': 60 * 24 * 7,
'&count={count}' 'month': 60 * 24 * 31,
'&first={first}' 'year': 60 * 24 * 365,
'&tsc=ImageHoverTitle'
# fmt: on # fmt: on
) }
time_range_string = '&qft=+filterui:age-lt{interval}'
time_range_dict = {'day': '1440', 'week': '10080', 'month': '43200', 'year': '525600'}
# safesearch definitions
safesearch_types = {2: 'STRICT', 1: 'DEMOTE', 0: 'OFF'}
# do search-request
def request(query, params): def request(query, params):
offset = ((params['pageno'] - 1) * number_of_results) + 1 """Assemble a Bing-Image request."""
search_path = search_string.format(query=urlencode({'q': query}), count=number_of_results, first=offset) engine_region = traits.get_region(params['searxng_locale'], 'en-US')
engine_language = traits.get_language(params['searxng_locale'], 'en')
language = match_language(params['language'], supported_languages, language_aliases).lower() SID = uuid.uuid1().hex.upper()
set_bing_cookies(params, engine_language, engine_region, SID)
params['cookies']['SRCHHPGUSR'] = 'ADLT=' + safesearch_types.get(params['safesearch'], 'DEMOTE') # build URL query
# - example: https://www.bing.com/images/async?q=foo&first=155&count=35
params['cookies']['_EDGE_S'] = 'mkt=' + language + '&ui=' + language + '&F=1' query_params = {
# fmt: off
'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,
# fmt: on
}
params['url'] = base_url + search_path # time range
if params['time_range'] in time_range_dict: # - example: one year (525600 minutes) 'qft=+filterui:age-lt525600'
params['url'] += time_range_string.format(interval=time_range_dict[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)
return params return params
# get response from search-request
def response(resp): def response(resp):
results = [] """Get response from Bing-Images"""
results = []
dom = html.fromstring(resp.text) dom = html.fromstring(resp.text)
# parse results for result in dom.xpath('//ul[contains(@class, "dgControl_list")]/li'):
for result in dom.xpath('//div[@class="imgpt"]'):
img_format = result.xpath('./div[contains(@class, "img_info")]/span/text()')[0]
# Microsoft seems to experiment with this code so don't make the path too specific,
# just catch the text section for the first anchor in img_info assuming this to be
# the originating site.
source = result.xpath('./div[contains(@class, "img_info")]//a/text()')[0]
m = loads(result.xpath('./a/@m')[0]) metadata = result.xpath('.//a[@class="iusc"]/@m')
if not metadata:
continue
# strip 'Unicode private use area' highlighting, they render to Tux metadata = json.loads(result.xpath('.//a[@class="iusc"]/@m')[0])
# the Linux penguin and a standing diamond on my machine... title = ' '.join(result.xpath('.//div[@class="infnmpt"]//a/text()')).strip()
title = m.get('t', '').replace('\ue000', '').replace('\ue001', '') img_format = ' '.join(result.xpath('.//div[@class="imgpt"]/div/span/text()')).strip()
source = ' '.join(result.xpath('.//div[@class="imgpt"]//div[@class="lnkw"]//a/text()')).strip()
results.append( results.append(
{ {
'template': 'images.html', 'template': 'images.html',
'url': m['purl'], 'url': metadata['purl'],
'thumbnail_src': m['turl'], 'thumbnail_src': metadata['turl'],
'img_src': m['murl'], 'img_src': metadata['murl'],
'content': '', 'content': metadata['desc'],
'title': title, 'title': title,
'source': source, 'source': source,
'img_format': img_format, 'img_format': img_format,
} }
) )
return results return results
def fetch_traits(engine_traits: EngineTraits): 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
from searx.engines.bing import _fetch_traits
url = 'https://learn.microsoft.com/en-us/bing/search-apis/bing-news-search/reference/market-codes'
xpath_market_codes = '//table[1]/tbody/tr/td[3]' xpath_market_codes = '//table[1]/tbody/tr/td[3]'
# xpath_country_codes = '//table[2]/tbody/tr/td[2]' # xpath_country_codes = '//table[2]/tbody/tr/td[2]'
xpath_language_codes = '//table[3]/tbody/tr/td[2]' xpath_language_codes = '//table[3]/tbody/tr/td[2]'
_fetch_traits(engine_traits, url, xpath_language_codes, xpath_market_codes) _fetch_traits(engine_traits, bing_traits_url, xpath_language_codes, xpath_market_codes)