1 files changed, 35 insertions, 34 deletions

diff --git a/searx/engines/google_news.py b/searx/engines/google_news.py
index e83b2ba48..b10f77005 100644
--- a/searx/engines/google_news.py
+++ b/searx/engines/google_news.py
@@ -2,13 +2,16 @@
 """Google (News)
 
 For detailed description of the *REST-full* API see: `Query Parameter
-Definitions`_.  Not all parameters can be appied, e.g. num_ (the number of
-search results to return) is ignored.
+Definitions`_.  Not all parameters can be appied:
+
+- num_ : the number of search results is ignored
+- save_ : is ignored / Google-News results are always *SafeSearch*
 
 .. _Query Parameter Definitions:
    https://developers.google.com/custom-search/docs/xml_results#WebSearch_Query_Parameter_Definitions
 
 .. _num: https://developers.google.com/custom-search/docs/xml_results#numsp
+.. _save: https://developers.google.com/custom-search/docs/xml_results#safesp
 
 """
 
@@ -32,20 +35,19 @@ from searx.utils import (
 from searx.engines.google import (
     supported_languages_url,
     _fetch_supported_languages,
-    detect_google_sorry,
 )
 # pylint: enable=unused-import
 
 from searx.engines.google import (
-    get_lang_country,
-    filter_mapping,
+    get_lang_info,
+    detect_google_sorry,
 )
 
 # about
 about = {
     "website": 'https://news.google.com',
     "wikidata_id": 'Q12020',
-    "official_api_documentation": None,
+    "official_api_documentation": 'https://developers.google.com/custom-search',
     "use_official_api": False,
     "require_api_key": False,
     "results": 'HTML',
@@ -69,51 +71,53 @@ paging = False
 language_support = True
 use_locale_domain = True
 time_range_support = True
-safesearch = True # not really, but it is not generated by google
+
+# Google-News results are always *SafeSearch*. Option 'safesearch' is set to
+# False here, otherwise checker will report safesearch-errors::
+#
+#  safesearch : results are identitical for safesearch=0 and safesearch=2
+safesearch = False
 
 def request(query, params):
     """Google-News search request"""
 
-    language, country, lang_country = get_lang_country(
+    lang_info = get_lang_info(
         # pylint: disable=undefined-variable
         params, supported_languages, language_aliases
     )
-    subdomain = 'news.google.com'
 
-    if params['time_range']: # in time_range_dict:
+    # google news has only one domain
+    lang_info['subdomain'] = 'news.google.com'
+
+    ceid = "%s:%s" % (lang_info['country'], lang_info['language'])
+
+    # google news redirects en to en-US
+    if lang_info['hl'] == 'en':
+        lang_info['hl'] = 'en-US'
+
+    # Very special to google-news compared to other google engines, the time
+    # range is included in the search term.
+    if params['time_range']:
         query += ' ' + time_range_dict[params['time_range']]
 
-    query_url = 'https://'+ subdomain + '/search' + "?" + urlencode({
+    query_url = 'https://' + lang_info['subdomain'] + '/search' + "?" + urlencode({
         'q': query,
-        'hl': language,
-        'lr': "lang_" + language,
+        'hl': lang_info['hl'],
+        'lr': lang_info['lr'],
         'ie': "utf8",
         'oe': "utf8",
-        'ceid' : "%s:%s" % (country, language),
-        'gl' : country,
-    })
+        'gl': lang_info['country'],
+    }) + ('&ceid=%s' % ceid)  # ceid includes a ':' character which must not be urlencoded
 
-    if params['safesearch']:
-        query_url += '&' + urlencode({'safe': filter_mapping[params['safesearch']]})
-
-    params['url'] = query_url
     logger.debug("query_url --> %s", query_url)
+    params['url'] = query_url
 
-    # en-US,en;q=0.8,en;q=0.5
-    params['headers']['Accept-Language'] = (
-        lang_country + ',' + language + ';q=0.8,' + language + ';q=0.5'
-        )
-    logger.debug("HTTP header Accept-Language --> %s",
-                 params['headers']['Accept-Language'])
+    logger.debug("HTTP header Accept-Language --> %s", lang_info['Accept-Language'])
+    params['headers']['Accept-Language'] = lang_info['Accept-Language']
     params['headers']['Accept'] = (
         'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8'
         )
 
-    # hl=en redirect to hl=en-US / en-CA ...
-    params['soft_max_redirects'] = 1
-
-    #params['google_subdomain'] = subdomain
-
     return params
 
 
@@ -123,9 +127,6 @@ def response(resp):
 
     detect_google_sorry(resp)
 
-    # which subdomain ?
-    # subdomain = resp.search_params.get('google_subdomain')
-
     # convert the text to dom
     dom = html.fromstring(resp.text)