[fix] Revision of the Bing engines

Signed-off-by: Markus Heiser <markus.heiser@darmarit.de>

4 files changed, 181 insertions, 189 deletions

diff --git a/searx/engines/bing.py b/searx/engines/bing.py
index 2a56a7fa6..ae001ffac 100644
--- a/searx/engines/bing.py
+++ b/searx/engines/bing.py
@@ -8,19 +8,18 @@ implementations are shared by other engines:
 - :ref:`bing videos engine`
 
 On the `preference page`_ Bing offers a lot of languages an regions (see section
-'Search results languages' and 'Country/region').  However, the abundant choice
-does not correspond to reality, where Bing has a full-text indexer only for a
-limited number of languages.  By example: you can select a language like Māori
-but you never get a result in this language.
+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"*.
 
-What comes a bit closer to the truth are the `search-APIs`_ but they don`t seem
-to be completely correct either (if you take a closer look you will find some
-inaccuracies there too):
+There is a description of the offical 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+the market codes are usually outdated or at least no longer used by bing itself.
 
-- :py:obj:`searx.engines.bing.bing_traits_url`
-- :py:obj:`searx.engines.bing_videos.bing_traits_url`
-- :py:obj:`searx.engines.bing_images.bing_traits_url`
-- :py:obj:`searx.engines.bing_news.bing_traits_url`
+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/
@@ -44,7 +43,7 @@ from searx.enginelib.traits import EngineTraits
 if TYPE_CHECKING:
     import logging
 
-    logger: logging.Logger
+    logger = logging.getLogger()
 
 traits: EngineTraits
 
@@ -61,35 +60,57 @@ about = {
 categories = ['general', 'web']
 paging = True
 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.
+"""
 
 base_url = 'https://www.bing.com/search'
 """Bing (Web) search URL"""
 
-bing_traits_url = 'https://learn.microsoft.com/en-us/bing/search-apis/bing-web-search/reference/market-codes'
-"""Bing (Web) search API description"""
-
 
 def _page_offset(pageno):
     return (int(pageno) - 1) * 10 + 1
 
 
 def set_bing_cookies(params, engine_language, engine_region):
-    params['cookies']['_EDGE_CD'] = f'm={engine_region.lower()}&u={engine_language.lower()};'
+    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 request(query, params):
     """Assemble a Bing-Web request."""
 
-    engine_region = traits.get_region(params['searxng_locale'], 'en-us')
-    engine_language = traits.get_language(params['searxng_locale'], 'en-us')
+    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)
 
-    query_params = {'q': query, 'first': _page_offset(params.get('pageno', 1))}
+    page = params.get('pageno', 1)
+    query_params = {
+        'q': query,
+        # if arg 'pq' is missed, somtimes 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,
+    }
+
+    # 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)
+
     params['url'] = f'{base_url}?{urlencode(query_params)}'
 
-    unix_day = int(time.time() / 86400)
-    time_ranges = {'day': '1', 'week': '2', 'month': '3', 'year': f'5_{unix_day-365}_{unix_day}'}
-    if params.get('time_range') in time_ranges:
+    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"]]}"'
 
     return params
@@ -113,10 +134,11 @@ def response(resp):
         url = link.attrib.get('href')
         title = extract_text(link)
 
-        content = eval_xpath(result, '(.//p)[1]')
+        content = eval_xpath(result, './/p')
         for p in content:
-            # Make sure that the element is free of <a href> links
-            for e in p.xpath('.//a'):
+            # 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)
 
@@ -165,72 +187,76 @@ def response(resp):
 
 def fetch_traits(engine_traits: EngineTraits):
     """Fetch languages and regions from Bing-Web."""
-
-    xpath_market_codes = '//table[1]/tbody/tr/td[3]'
-    # xpath_country_codes = '//table[2]/tbody/tr/td[2]'
-    xpath_language_codes = '//table[3]/tbody/tr/td[2]'
-
-    _fetch_traits(engine_traits, bing_traits_url, xpath_language_codes, xpath_market_codes)
-
-
-def _fetch_traits(engine_traits: EngineTraits, url: str, xpath_language_codes: str, xpath_market_codes: str):
-    # pylint: disable=too-many-locals,import-outside-toplevel
+    # pylint: disable=import-outside-toplevel
 
     from searx.network import get  # see https://github.com/searxng/searxng/issues/762
 
-    # insert alias to map from a language (zh) to a language + script (zh_Hans)
-    engine_traits.languages['zh'] = 'zh-hans'
-
-    resp = get(url)
-
+    resp = get("https://www.bing.com/account/general")
     if not resp.ok:  # type: ignore
-        print("ERROR: response from peertube is not OK.")
+        print("ERROR: response from bing is not OK.")
 
     dom = html.fromstring(resp.text)  # type: ignore
 
-    map_lang = {'jp': 'ja'}
-    for td in eval_xpath(dom, xpath_language_codes):
-        eng_lang = td.text
+    # languages
 
-        if eng_lang in ('en-gb', 'pt-br'):
-            # language 'en' is already in the list and a language 'en-gb' can't
-            # be handled in SearXNG, same with pt-br which is covered by pt-pt.
-            continue
+    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
+    }
 
-        babel_lang = map_lang.get(eng_lang, eng_lang).replace('-', '_')
+    for href in eval_xpath(dom, '//div[@id="language-section"]//li/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))
+            sxng_tag = language_tag(babel.Locale.parse(babel_lang.replace('-', '_')))
         except babel.UnknownLocaleError:
-            print("ERROR: language (%s) is unknown by babel" % (eng_lang))
+            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 != eng_lang:
-                print("CONFLICT: babel %s --> %s, %s" % (sxng_tag, conflict, eng_lang))
+            if conflict != bing_ui_lang:
+                print(f"CONFLICT: babel {sxng_tag} --> {conflict}, {bing_ui_lang}")
             continue
-        engine_traits.languages[sxng_tag] = eng_lang
+        engine_traits.languages[sxng_tag] = bing_ui_lang
 
-    map_region = {
-        'en-ID': 'id_ID',
-        'no-NO': 'nb_NO',
-    }
+    # regions (aka "market codes")
 
-    for td in eval_xpath(dom, xpath_market_codes):
-        eng_region = td.text
-        babel_region = map_region.get(eng_region, eng_region).replace('-', '_')
+    engine_traits.regions['zh-CN'] = 'zh-cn'
 
-        if eng_region == 'en-WW':
-            engine_traits.all_locale = eng_region
+    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"]//li/a/@href'):
+        cc_tag = parse_qs(urlparse(href).query)['cc'][0]
+        if cc_tag == 'clear':
+            engine_traits.all_locale = cc_tag
             continue
 
-        try:
-            sxng_tag = region_tag(babel.Locale.parse(babel_region))
-        except babel.UnknownLocaleError:
-            print("ERROR: region (%s) is unknown by babel" % (eng_region))
-            continue
-        conflict = engine_traits.regions.get(sxng_tag)
-        if conflict:
-            if conflict != eng_region:
-                print("CONFLICT: babel %s --> %s, %s" % (sxng_tag, conflict, eng_region))
-            continue
-        engine_traits.regions[sxng_tag] = eng_region
+        # 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)
+            sxng_tag = region_tag(babel.Locale.parse('%s_%s' % (lang_tag, cc_tag.upper())))
+            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
diff --git a/searx/engines/bing_images.py b/searx/engines/bing_images.py
index 25b4e4f41..faf0941c8 100644
--- a/searx/engines/bing_images.py
+++ b/searx/engines/bing_images.py
@@ -12,15 +12,14 @@ from urllib.parse import urlencode
 from lxml import html
 
 from searx.enginelib.traits import EngineTraits
-from searx.engines.bing import (
-    set_bing_cookies,
-    _fetch_traits,
-)
+from searx.engines.bing import set_bing_cookies
+from searx.engines.bing import fetch_traits  # pylint: disable=unused-import
+
 
 if TYPE_CHECKING:
     import logging
 
-    logger: logging.Logger
+    logger = logging.getLogger()
 
 traits: EngineTraits
 
@@ -43,38 +42,29 @@ time_range_support = True
 base_url = 'https://www.bing.com/images/async'
 """Bing (Images) search URL"""
 
-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
     'day': 60 * 24,
     'week': 60 * 24 * 7,
     'month': 60 * 24 * 31,
     'year': 60 * 24 * 365,
-    # fmt: on
 }
 
 
 def request(query, params):
     """Assemble a Bing-Image request."""
 
-    engine_region = traits.get_region(params['searxng_locale'], 'en-us')
-    engine_language = traits.get_language(params['searxng_locale'], 'en-us')
-
+    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)
 
     # build URL query
-    # - example: https://www.bing.com/images/async?q=foo&first=155&count=35
-
+    # - example: https://www.bing.com/images/async?q=foo&async=content&first=1&count=35
     query_params = {
-        # fmt: off
         'q': query,
-        'async' : 'content',
+        '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,
-        # fmt: on
+        'first': (int(params.get('pageno', 1)) - 1) * 35 + 1,
+        'count': 35,
     }
 
     # time range
@@ -117,13 +107,3 @@ def response(resp):
             }
         )
     return results
-
-
-def fetch_traits(engine_traits: EngineTraits):
-    """Fetch languages and regions from Bing-News."""
-
-    xpath_market_codes = '//table[1]/tbody/tr/td[3]'
-    # xpath_country_codes = '//table[2]/tbody/tr/td[2]'
-    xpath_language_codes = '//table[3]/tbody/tr/td[2]'
-
-    _fetch_traits(engine_traits, bing_traits_url, xpath_language_codes, xpath_market_codes)
diff --git a/searx/engines/bing_news.py b/searx/engines/bing_news.py
index 81c8df0f3..3585a1cd1 100644
--- a/searx/engines/bing_news.py
+++ b/searx/engines/bing_news.py
@@ -1,6 +1,11 @@
 # SPDX-License-Identifier: AGPL-3.0-or-later
 # lint: pylint
 """Bing-News: description see :py:obj:`searx.engines.bing`.
+
+.. hint::
+
+   Bing News is *different* in some ways!
+
 """
 
 # pylint: disable=invalid-name
@@ -10,11 +15,9 @@ 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,
-    _fetch_traits,
-)
+from searx.engines.bing import set_bing_cookies
 
 if TYPE_CHECKING:
     import logging
@@ -37,57 +40,48 @@ about = {
 # engine dependent config
 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': '4',
-    'week': '8',
-    'month': '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
+"""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'
 """Bing (News) search URL"""
 
-bing_traits_url = 'https://learn.microsoft.com/en-us/bing/search-apis/bing-news-search/reference/market-codes'
-"""Bing (News) search API description"""
-
-mkt_alias = {
-    'zh': 'en-WW',
-    'zh-CN': 'en-WW',
-}
-"""Bing News has an official market code 'zh-CN' but we won't get a result with
-this market code.  For 'zh' and 'zh-CN' we better use the *Worldwide aggregate*
-market code (en-WW).
-"""
-
 
 def request(query, params):
     """Assemble a Bing-News request."""
 
-    sxng_locale = params['searxng_locale']
-    engine_region = traits.get_region(mkt_alias.get(sxng_locale, sxng_locale), traits.all_locale)
-    engine_language = traits.get_language(sxng_locale, 'en-us')
-
+    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)
 
     # build URL query
     #
     # example: https://www.bing.com/news/infinitescrollajax?q=london&first=1
 
+    page = int(params.get('pageno', 1)) - 1
     query_params = {
-        # fmt: off
         'q': query,
         'InfiniteScroll': 1,
         # to simplify the page count lets use the default of 10 images per page
-        'first' : (int(params.get('pageno', 1)) - 1) * 10 + 1,
-        # fmt: on
+        'first': page * 10 + 1,
+        'SFX': page,
+        'form': 'PTFTNR',
+        'setlang': engine_region.split('-')[0],
+        'cc': engine_region.split('-')[-1],
     }
 
     if params['time_range']:
-        # qft=interval:"7"
-        query_params['qft'] = 'qft=interval="%s"' % time_map.get(params['time_range'], '9')
+        query_params['qft'] = time_map.get(params['time_range'], 'interval="9"')
 
     params['url'] = base_url + '?' + urlencode(query_params)
 
@@ -103,18 +97,34 @@ def response(resp):
 
     dom = html.fromstring(resp.text)
 
-    for newsitem in dom.xpath('//div[contains(@class, "newsitem")]'):
+    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')
+        title = extract_text(link)
+        content = extract_text(eval_xpath(newsitem, './/div[@class="snippet"]'))
+
+        metadata = []
+        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, './/a', 0, None),
+                # eval_xpath_getindex(source, './div/span', 3, None),
+                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)
 
-        url = newsitem.xpath('./@url')[0]
-        title = ' '.join(newsitem.xpath('.//div[@class="caption"]//a[@class="title"]/text()')).strip()
-        content = ' '.join(newsitem.xpath('.//div[@class="snippet"]/text()')).strip()
         thumbnail = None
-        author = newsitem.xpath('./@data-author')[0]
-        metadata = ' '.join(newsitem.xpath('.//div[@class="source"]/span/text()')).strip()
-
-        img_src = newsitem.xpath('.//a[@class="imagelink"]//img/@src')
-        if img_src:
-            thumbnail = 'https://www.bing.com/' + img_src[0]
+        imagelink = eval_xpath_getindex(newsitem, './/a[@class="imagelink"]//img', 0, None)
+        if imagelink is not None:
+            thumbnail = 'https://www.bing.com/' + imagelink.attrib.get('src')
 
         results.append(
             {
@@ -122,7 +132,6 @@ def response(resp):
                 'title': title,
                 'content': content,
                 'img_src': thumbnail,
-                'author': author,
                 'metadata': metadata,
             }
         )
@@ -131,17 +140,20 @@ def response(resp):
 
 
 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 as _f
 
-    The :py:obj:`description <searx.engines.bing_news.bing_traits_url>` of the
-    first table says *"query parameter when calling the Video Search API."*
-    .. that's why I use the 4. table "News Category API markets" for the
-    ``xpath_market_codes``.
+    _f(engine_traits)
 
-    """
+    # fix market codes not known by bing news:
 
-    xpath_market_codes = '//table[4]/tbody/tr/td[3]'
-    # xpath_country_codes = '//table[2]/tbody/tr/td[2]'
-    xpath_language_codes = '//table[3]/tbody/tr/td[2]'
+    # In bing the market code 'zh-cn' exists, but there is no 'news' category in
+    # bing for this market.  Alternatively we use the the market code from Honk
+    # Kong.  Even if this is not correct, it is better than having no hits at
+    # all, or sending false queries to bing that could raise the suspicion of a
+    # bot.
 
-    _fetch_traits(engine_traits, bing_traits_url, xpath_language_codes, xpath_market_codes)
+    # HINT: 'en-hk' is the region code it does not indicate the language en!!
+    engine_traits.regions['zh-CN'] = 'en-hk'
diff --git a/searx/engines/bing_videos.py b/searx/engines/bing_videos.py
index d4cb6058b..41bf2d3e1 100644
--- a/searx/engines/bing_videos.py
+++ b/searx/engines/bing_videos.py
@@ -11,10 +11,9 @@ from urllib.parse import urlencode
 from lxml import html
 
 from searx.enginelib.traits import EngineTraits
-from searx.engines.bing import (
-    set_bing_cookies,
-    _fetch_traits,
-)
+from searx.engines.bing import set_bing_cookies
+from searx.engines.bing import fetch_traits  # pylint: disable=unused-import
+from searx.engines.bing_images import time_map
 
 if TYPE_CHECKING:
     import logging
@@ -42,25 +41,12 @@ time_range_support = True
 base_url = 'https://www.bing.com/videos/asyncv2'
 """Bing (Videos) async search URL."""
 
-bing_traits_url = 'https://learn.microsoft.com/en-us/bing/search-apis/bing-video-search/reference/market-codes'
-"""Bing (Video) search API description"""
-
-time_map = {
-    # fmt: off
-    'day': 60 * 24,
-    'week': 60 * 24 * 7,
-    'month': 60 * 24 * 31,
-    'year': 60 * 24 * 365,
-    # fmt: on
-}
-
 
 def request(query, params):
     """Assemble a Bing-Video request."""
 
-    engine_region = traits.get_region(params['searxng_locale'], 'en-us')
-    engine_language = traits.get_language(params['searxng_locale'], 'en-us')
-
+    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)
 
     # build URL query
@@ -68,13 +54,11 @@ def request(query, params):
     # example: https://www.bing.com/videos/asyncv2?q=foo&async=content&first=1&count=35
 
     query_params = {
-        # fmt: off
         'q': query,
-        'async' : 'content',
+        '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
+        'first': (int(params.get('pageno', 1)) - 1) * 35 + 1,
+        'count': 35,
     }
 
     # time range
@@ -113,13 +97,3 @@ def response(resp):
         )
 
     return results
-
-
-def fetch_traits(engine_traits: EngineTraits):
-    """Fetch languages and regions from Bing-Videos."""
-
-    xpath_market_codes = '//table[1]/tbody/tr/td[3]'
-    # xpath_country_codes = '//table[2]/tbody/tr/td[2]'
-    xpath_language_codes = '//table[3]/tbody/tr/td[2]'
-
-    _fetch_traits(engine_traits, bing_traits_url, xpath_language_codes, xpath_market_codes)