on master help sign in
[enh] google engine: supports "default language"

Same behaviour behaviour than Whoogle [1]. Only the google engine with the "Default language" choice "(all)"" is changed by this patch. When searching for a locate place, the result are in the expect language, without missing results [2]: > When a language is not specified, the language interpretation is left up to > Google to decide how the search results should be delivered. The query parameters are copied from Whoogle. With the ``all`` language: - add parameter ``source=lnt`` - don't use parameter ``lr`` - don't add a ``Accept-Language`` HTTP header. The new signature of function ``get_lang_info()`` is: lang_info = get_lang_info(params, lang_list, custom_aliases, supported_any_language) Argument ``supported_any_language`` is True for google.py and False for the other google engines. With this patch the function now returns: - query parameters: ``lang_info['params']`` - HTTP headers: ``lang_info['headers']`` - and as before this patch: - ``lang_info['subdomain']`` - ``lang_info['country']`` - ``lang_info['language']`` [1] https://github.com/benbusby/whoogle-search [2] https://github.com/benbusby/whoogle-search/releases/tag/v0.5.4

commit3863f5a83fa3046a90ce2715416363b1e15a445a authorAlexandre Flament <alex@al-f.net> dateSun 6 Jun 2021, 08:18 (5 years ago) parente628d75
5 files changed+46−45
searx/engines/google.py+30−25 searx/engines/google_images.py+4−5 searx/engines/google_news.py+4−5 searx/engines/google_scholar.py+4−5 searx/engines/google_videos.py+4−5
searx/engines/google.py+30−25
@@ -132,11 +132,12 @@ suggestion_xpath = '//div[contains(@class, "card-section")]//a'
132132spelling_suggestion_xpath = '//div[@class="med"]/p/a'
133133
134134
135−def get_lang_info(params, lang_list, custom_aliases):
135+def get_lang_info(params, lang_list, custom_aliases, supported_any_language):
136136 ret_val = {}
137137
138138 _lang = params['language']
139− if _lang.lower() == 'all':
139+ _any_language = _lang.lower() == 'all'
140+ if _any_language:
140141 _lang = 'en-US'
141142
142143 language = match_language(_lang, lang_list, custom_aliases)
@@ -158,31 +159,36 @@ def get_lang_info(params, lang_list, custom_aliases):
158159 # the combination (en-US, en-EN, de-DE, de-AU, fr-FR, fr-FR)
159160 lang_country = '%s-%s' % (language, country)
160161
161− # Accept-Language: fr-CH, fr;q=0.8, en;q=0.6, *;q=0.5
162− ret_val['Accept-Language'] = ','.join([
163− lang_country,
164− language + ';q=0.8,',
165− 'en;q=0.6',
166− '*;q=0.5',
167− ])
168−
169162 # subdomain
170163 ret_val['subdomain'] = 'www.' + google_domains.get(country.upper(), 'google.com')
171164
165+ ret_val['params'] = {}
166+ ret_val['headers'] = {}
167+
168+ if _any_language and supported_any_language:
169+ # based on whoogle
170+ ret_val['params']['source'] = 'lnt'
171+ else:
172+ # Accept-Language: fr-CH, fr;q=0.8, en;q=0.6, *;q=0.5
173+ ret_val['headers']['Accept-Language'] = ','.join([
174+ lang_country,
175+ language + ';q=0.8,',
176+ 'en;q=0.6',
177+ '*;q=0.5',
178+ ])
179+
180+ # lr parameter:
181+ # https://developers.google.com/custom-search/docs/xml_results#lrsp
182+ # Language Collection Values:
183+ # https://developers.google.com/custom-search/docs/xml_results_appendices#languageCollections
184+ ret_val['params']['lr'] = "lang_" + lang_list.get(lang_country, language)
185+
186+ ret_val['params']['hl'] = lang_list.get(lang_country, language)
187+
172188 # hl parameter:
173189 # https://developers.google.com/custom-search/docs/xml_results#hlsp The
174190 # Interface Language:
175191 # https://developers.google.com/custom-search/docs/xml_results_appendices#interfaceLanguages
176−
177− ret_val['hl'] = lang_list.get(lang_country, language)
178−
179− # lr parameter:
180− # https://developers.google.com/custom-search/docs/xml_results#lrsp
181− # Language Collection Values:
182− # https://developers.google.com/custom-search/docs/xml_results_appendices#languageCollections
183−
184− ret_val['lr'] = "lang_" + lang_list.get(lang_country, language)
185−
186192 return ret_val
187193
188194def detect_google_sorry(resp):
@@ -197,14 +203,13 @@ def request(query, params):
197203
198204 lang_info = get_lang_info(
199205 # pylint: disable=undefined-variable
200− params, supported_languages, language_aliases
206+ params, supported_languages, language_aliases, True
201207 )
202208
203209 # https://www.google.de/search?q=corona&hl=de&lr=lang_de&start=0&tbs=qdr%3Ad&safe=medium
204210 query_url = 'https://' + lang_info['subdomain'] + '/search' + "?" + urlencode({
205211 'q': query,
206− 'hl': lang_info['hl'],
207− 'lr': lang_info['lr'],
212+ **lang_info['params'],
208213 'ie': "utf8",
209214 'oe': "utf8",
210215 'start': offset,
@@ -218,8 +223,8 @@ def request(query, params):
218223 logger.debug("query_url --> %s", query_url)
219224 params['url'] = query_url
220225
221− logger.debug("HTTP header Accept-Language --> %s", lang_info['Accept-Language'])
222− params['headers']['Accept-Language'] = lang_info['Accept-Language']
226+ logger.debug("HTTP header Accept-Language --> %s", lang_info.get('Accept-Language'))
227+ params['headers'].update(lang_info['headers'])
223228 params['headers']['Accept'] = (
224229 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8'
225230 )
searx/engines/google_images.py+4−5
@@ -100,14 +100,13 @@ def request(query, params):
100100
101101 lang_info = get_lang_info(
102102 # pylint: disable=undefined-variable
103− params, supported_languages, language_aliases
103+ params, supported_languages, language_aliases, False
104104 )
105105
106106 query_url = 'https://' + lang_info['subdomain'] + '/search' + "?" + urlencode({
107107 'q': query,
108108 'tbm': "isch",
109− 'hl': lang_info['hl'],
110− 'lr': lang_info['lr'],
109+ **lang_info['params'],
111110 'ie': "utf8",
112111 'oe': "utf8",
113112 'num': 30,
@@ -121,8 +120,8 @@ def request(query, params):
121120 logger.debug("query_url --> %s", query_url)
122121 params['url'] = query_url
123122
124− logger.debug("HTTP header Accept-Language --> %s", lang_info['Accept-Language'])
125− params['headers']['Accept-Language'] = lang_info['Accept-Language']
123+ logger.debug("HTTP header Accept-Language --> %s", lang_info.get('Accept-Language'))
124+ params['headers'].update(lang_info['headers'])
126125 params['headers']['Accept'] = (
127126 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8'
128127 )
searx/engines/google_news.py+4−5
@@ -82,7 +82,7 @@ def request(query, params):
8282
8383 lang_info = get_lang_info(
8484 # pylint: disable=undefined-variable
85− params, supported_languages, language_aliases
85+ params, supported_languages, language_aliases, False
8686 )
8787
8888 # google news has only one domain
@@ -101,8 +101,7 @@ def request(query, params):
101101
102102 query_url = 'https://' + lang_info['subdomain'] + '/search' + "?" + urlencode({
103103 'q': query,
104− 'hl': lang_info['hl'],
105− 'lr': lang_info['lr'],
104+ **lang_info['params'],
106105 'ie': "utf8",
107106 'oe': "utf8",
108107 'gl': lang_info['country'],
@@ -111,8 +110,8 @@ def request(query, params):
111110 logger.debug("query_url --> %s", query_url)
112111 params['url'] = query_url
113112
114− logger.debug("HTTP header Accept-Language --> %s", lang_info['Accept-Language'])
115− params['headers']['Accept-Language'] = lang_info['Accept-Language']
113+ logger.debug("HTTP header Accept-Language --> %s", lang_info.get('Accept-Language'))
114+ params['headers'].update(lang_info['headers'])
116115 params['headers']['Accept'] = (
117116 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8'
118117 )
searx/engines/google_scholar.py+4−5
@@ -80,15 +80,14 @@ def request(query, params):
8080
8181 # params, {}, language_aliases
8282
83− params, supported_languages, language_aliases
83+ params, supported_languages, language_aliases, False
8484 )
8585 # subdomain is: scholar.google.xy
8686 lang_info['subdomain'] = lang_info['subdomain'].replace("www.", "scholar.")
8787
8888 query_url = 'https://'+ lang_info['subdomain'] + '/scholar' + "?" + urlencode({
8989 'q': query,
90− 'hl': lang_info['hl'],
91− 'lr': lang_info['lr'],
90+ **lang_info['params'],
9291 'ie': "utf8",
9392 'oe': "utf8",
9493 'start' : offset,
@@ -99,8 +98,8 @@ def request(query, params):
9998 logger.debug("query_url --> %s", query_url)
10099 params['url'] = query_url
101100
102− logger.debug("HTTP header Accept-Language --> %s", lang_info['Accept-Language'])
103− params['headers']['Accept-Language'] = lang_info['Accept-Language']
101+ logger.debug("HTTP header Accept-Language --> %s", lang_info.get('Accept-Language'))
102+ params['headers'].update(lang_info['headers'])
104103 params['headers']['Accept'] = (
105104 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8'
106105 )
searx/engines/google_videos.py+4−5
@@ -118,14 +118,13 @@ def request(query, params):
118118
119119 lang_info = get_lang_info(
120120 # pylint: disable=undefined-variable
121− params, supported_languages, language_aliases
121+ params, supported_languages, language_aliases, False
122122 )
123123
124124 query_url = 'https://' + lang_info['subdomain'] + '/search' + "?" + urlencode({
125125 'q': query,
126126 'tbm': "vid",
127− 'hl': lang_info['hl'],
128− 'lr': lang_info['lr'],
127+ **lang_info['params'],
129128 'ie': "utf8",
130129 'oe': "utf8",
131130 })
@@ -138,8 +137,8 @@ def request(query, params):
138137 logger.debug("query_url --> %s", query_url)
139138 params['url'] = query_url
140139
141− logger.debug("HTTP header Accept-Language --> %s", lang_info['Accept-Language'])
142− params['headers']['Accept-Language'] = lang_info['Accept-Language']
140+ logger.debug("HTTP header Accept-Language --> %s", lang_info.get('Accept-Language'))
141+ params['headers'].update(lang_info['headers'])
143142 params['headers']['Accept'] = (
144143 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8'
145144 )