searxng/searx/engines/bing.py

145 lines
4.4 KiB
Python
Raw Normal View History

# SPDX-License-Identifier: AGPL-3.0-or-later
# lint: pylint
"""Bing (Web)
- https://github.com/searx/searx/issues/2019#issuecomment-648227442
"""
2014-09-01 12:38:59 +00:00
import re
from urllib.parse import urlencode
2014-02-05 19:24:31 +00:00
from lxml import html
from searx.utils import eval_xpath, extract_text, match_language
2013-10-24 21:52:57 +00:00
about = {
"website": 'https://www.bing.com',
"wikidata_id": 'Q182496',
"official_api_documentation": 'https://www.microsoft.com/en-us/bing/apis/bing-web-search-api',
"use_official_api": False,
"require_api_key": False,
"results": 'HTML',
}
2014-09-01 12:38:59 +00:00
# engine dependent config
categories = ['general']
2014-01-29 20:14:38 +00:00
paging = True
time_range_support = False
safesearch = False
supported_languages_url = 'https://www.bing.com/account/general'
language_aliases = {'zh-CN': 'zh-CHS', 'zh-TW': 'zh-CHT', 'zh-HK': 'zh-CHT'}
2014-01-29 20:14:38 +00:00
2014-09-01 12:38:59 +00:00
# search-url
base_url = 'https://www.bing.com/'
# initial query: https://www.bing.com/search?q=foo&search=&form=QBLH
inital_query = 'search?{query}&search=&form=QBLH'
# following queries: https://www.bing.com/search?q=foo&search=&first=11&FORM=PERE
page_query = 'search?{query}&search=&first={offset}&FORM=PERE'
2013-10-24 21:52:57 +00:00
def _get_offset_from_pageno(pageno):
return (pageno - 1) * 10 + 1
2013-10-24 21:52:57 +00:00
def request(query, params):
2014-09-01 12:38:59 +00:00
offset = _get_offset_from_pageno(params.get('pageno', 1))
# logger.debug("params['pageno'] --> %s", params.get('pageno'))
# logger.debug(" offset --> %s", offset)
search_string = page_query
if offset == 1:
search_string = inital_query
if params['language'] == 'all':
lang = 'EN'
else:
lang = match_language(params['language'], supported_languages, language_aliases)
query = 'language:{} {}'.format(lang.split('-')[0].upper(), query)
2014-09-01 12:38:59 +00:00
search_path = search_string.format(query=urlencode({'q': query}), offset=offset)
if offset > 1:
referer = base_url + inital_query.format(query=urlencode({'q': query}))
params['headers']['Referer'] = referer
logger.debug("headers.Referer --> %s", referer)
2013-10-24 21:52:57 +00:00
params['url'] = base_url + search_path
params['headers']['Accept-Language'] = "en-US,en;q=0.5"
params['headers']['Accept'] = 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8'
return params
2013-10-24 21:52:57 +00:00
2013-10-24 21:52:57 +00:00
def response(resp):
2013-10-24 21:52:57 +00:00
results = []
result_len = 0
2014-09-01 12:38:59 +00:00
dom = html.fromstring(resp.text)
for result in eval_xpath(dom, '//div[@class="sa_cc"]'):
# IMO //div[@class="sa_cc"] does no longer match
logger.debug('found //div[@class="sa_cc"] --> %s', result)
link = eval_xpath(result, './/h3/a')[0]
2013-10-24 21:52:57 +00:00
url = link.attrib.get('href')
2015-01-25 19:14:37 +00:00
title = extract_text(link)
content = extract_text(eval_xpath(result, './/p'))
2013-10-24 23:37:48 +00:00
2014-09-01 12:38:59 +00:00
# append result
results.append({'url': url, 'title': title, 'content': content})
2014-09-01 12:38:59 +00:00
# parse results again if nothing is found yet
for result in eval_xpath(dom, '//li[@class="b_algo"]'):
link = eval_xpath(result, './/h2/a')[0]
2013-10-24 23:37:48 +00:00
url = link.attrib.get('href')
2015-01-25 19:14:37 +00:00
title = extract_text(link)
content = extract_text(eval_xpath(result, './/p'))
2014-09-01 12:38:59 +00:00
# append result
results.append({'url': url, 'title': title, 'content': content})
2014-09-01 12:38:59 +00:00
try:
2020-01-02 21:28:47 +00:00
result_len_container = "".join(eval_xpath(dom, '//span[@class="sb_count"]//text()'))
if "-" in result_len_container:
# Remove the part "from-to" for paginated request ...
result_len_container = result_len_container[result_len_container.find("-") * 2 + 2 :]
result_len_container = re.sub('[^0-9]', '', result_len_container)
if len(result_len_container) > 0:
result_len = int(result_len_container)
except Exception as e: # pylint: disable=broad-except
logger.debug('result error :\n%s', e)
2020-01-02 21:28:47 +00:00
if result_len and _get_offset_from_pageno(resp.search_params.get("pageno", 0)) > result_len:
return []
results.append({'number_of_results': result_len})
2013-10-24 21:52:57 +00:00
return results
# get supported languages from their site
def _fetch_supported_languages(resp):
lang_tags = set()
setmkt = re.compile('setmkt=([^&]*)')
dom = html.fromstring(resp.text)
lang_links = eval_xpath(dom, "//li/a[contains(@href, 'setmkt')]")
for a in lang_links:
href = eval_xpath(a, './@href')[0]
match = setmkt.search(href)
l_tag = match.groups()[0]
_lang, _nation = l_tag.split('-', 1)
l_tag = _lang.lower() + '-' + _nation.upper()
lang_tags.add(l_tag)
return list(lang_tags)