From b2177e5916c58b817665623ca107bb2467773e97 Mon Sep 17 00:00:00 2001 From: Markus Heiser Date: Sat, 18 Dec 2021 11:40:12 +0100 Subject: [PATCH 1/2] [pylint] Bing (Web) engine Fix remarks from pylint and improved code-style. In preparation for a bug-fix of the Bing (Web) engine I add this engine to the pylint-list. Signed-off-by: Markus Heiser --- searx/engines/bing.py | 52 ++++++++++++++++++++++++++----------------- 1 file changed, 31 insertions(+), 21 deletions(-) diff --git a/searx/engines/bing.py b/searx/engines/bing.py index 9cac3e926..a25f0212d 100644 --- a/searx/engines/bing.py +++ b/searx/engines/bing.py @@ -1,6 +1,6 @@ # SPDX-License-Identifier: AGPL-3.0-or-later -""" - Bing (Web) +# lint: pylint +"""Bing (Web) """ import re @@ -8,7 +8,6 @@ from urllib.parse import urlencode from lxml import html from searx.utils import eval_xpath, extract_text, match_language -# about about = { "website": 'https://www.bing.com', "wikidata_id": 'Q182496', @@ -21,6 +20,8 @@ about = { # engine dependent config categories = ['general'] 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'} @@ -28,71 +29,80 @@ language_aliases = {'zh-CN': 'zh-CHS', 'zh-TW': 'zh-CHT', 'zh-HK': 'zh-CHT'} base_url = 'https://www.bing.com/' search_string = 'search?{query}&first={offset}' - def _get_offset_from_pageno(pageno): return (pageno - 1) * 10 + 1 - -# do search-request def request(query, params): - offset = _get_offset_from_pageno(params.get('pageno', 0)) + offset = _get_offset_from_pageno(params.get('pageno', 0)) if params['language'] == 'all': lang = 'EN' else: - lang = match_language(params['language'], supported_languages, language_aliases) + lang = match_language( + params['language'], supported_languages, language_aliases + ) - query = 'language:{} {}'.format(lang.split('-')[0].upper(), query) + query = 'language:{} {}'.format( + lang.split('-')[0].upper(), query + ) search_path = search_string.format( - query=urlencode({'q': query}), - offset=offset) - + query = urlencode({'q': query}), + offset = offset) params['url'] = base_url + search_path return params -# get response from search-request def response(resp): + results = [] result_len = 0 dom = html.fromstring(resp.text) - # parse results + for result in eval_xpath(dom, '//div[@class="sa_cc"]'): + link = eval_xpath(result, './/h3/a')[0] url = link.attrib.get('href') title = extract_text(link) content = extract_text(eval_xpath(result, './/p')) # append result - results.append({'url': url, - 'title': title, - 'content': content}) + results.append({ + 'url': url, + 'title': title, + 'content': content + }) # 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] url = link.attrib.get('href') title = extract_text(link) content = extract_text(eval_xpath(result, './/p')) # append result - results.append({'url': url, - 'title': title, - 'content': content}) + results.append({ + 'url': url, + 'title': title, + 'content': content + }) try: 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: + + 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: From 6b85607274b7a74cadb4707d430011650a087a5b Mon Sep 17 00:00:00 2001 From: Markus Heiser Date: Sat, 18 Dec 2021 13:41:12 +0100 Subject: [PATCH 2/2] [fix] bing engine: fix paging support, show inital page. Follow up queries for the pages needed to be fixed. - Split search-term in one for initial query and one for following queries. - Set some headers in HTTP requests, bing needs for paging support. - IMO //div[@class="sa_cc"] does no longer match in a bing response. Signed-off-by: Markus Heiser --- searx/engines/bing.py | 34 ++++++++++++++++++++++++++++++---- 1 file changed, 30 insertions(+), 4 deletions(-) diff --git a/searx/engines/bing.py b/searx/engines/bing.py index a25f0212d..3917e54c1 100644 --- a/searx/engines/bing.py +++ b/searx/engines/bing.py @@ -1,6 +1,8 @@ # SPDX-License-Identifier: AGPL-3.0-or-later # lint: pylint """Bing (Web) + +- https://github.com/searx/searx/issues/2019#issuecomment-648227442 """ import re @@ -27,14 +29,27 @@ language_aliases = {'zh-CN': 'zh-CHS', 'zh-TW': 'zh-CHT', 'zh-HK': 'zh-CHT'} # search-url base_url = 'https://www.bing.com/' -search_string = 'search?{query}&first={offset}' + +# 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' def _get_offset_from_pageno(pageno): return (pageno - 1) * 10 + 1 def request(query, params): - offset = _get_offset_from_pageno(params.get('pageno', 0)) + 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: @@ -49,11 +64,19 @@ def request(query, params): 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 ) + 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 - def response(resp): results = [] @@ -63,6 +86,9 @@ def response(resp): 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] url = link.attrib.get('href') title = extract_text(link)