Archives/searxng
2
0
Fork 1
mirror of https://github.com/searxng/searxng synced 2024-11-05 06:01:05 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #134 from searxng/google-default-language

Browse Source 
[enh] google engine: supports "default language"
This commit is contained in:
Alexandre Flament 2021-06-11 17:00:12 +02:00 committed by GitHub
commit 52db47a1c9
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
5 changed files with 111 additions and 61 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

117
searx/engines/google.py
View File

@ -133,56 +133,121 @@ suggestion_xpath = '//div[contains(@class, "card-section")]//a'
spelling_suggestion_xpath = '//div[@class="med"]/p/a'
def get_lang_info(params, lang_list, custom_aliases):
ret_val = {}
def get_lang_info(params, lang_list, custom_aliases, supported_any_language):
"""Composing various language properties for the google engines.
This function is called by the various google engines (google itself,
google-images, -news, -scholar, -videos).
:param dict param: request parameters of the engine
:param list lang_list: list of supported languages of the engine
:py:obj:`ENGINES_LANGUAGES[engine-name] <searx.data.ENGINES_LANGUAGES>`
:param dict lang_list: custom aliases for non standard language codes
(used when calling :py:func:`searx.utils.match_language)
:param bool supported_any_language: When a language is not specified, the
language interpretation is left up to Google to decide how the search
results should be delivered. This argument is ``True`` for the google
engine and ``False`` for the other engines (google-images, -news,
-scholar, -videos).
:rtype: dict
:returns:
Py-Dictionary with the key/value pairs:
language:
Return value from :py:func:`searx.utils.match_language
country:
The country code (e.g. US, AT, CA, FR, DE ..)
subdomain:
Google subdomain :py:obj:`google_domains` that fits to the country
code.
params:
Py-Dictionary with additional request arguments (can be passed to
:py:func:`urllib.parse.urlencode`).
headers:
Py-Dictionary with additional HTTP headers (can be passed to
request's headers)
"""
ret_val = {
'language' : None,
'country' : None,
'subdomain' : None,
'params' : {},
'headers' : {},
}
# language ...
_lang = params['language']
if _lang.lower() == 'all':
_any_language = _lang.lower() == 'all'
if _any_language:
_lang = 'en-US'
language = match_language(_lang, lang_list, custom_aliases)
ret_val['language'] = language
# the requested language from params (en, en-US, de, de-AT, fr, fr-CA, ...)
_l = _lang.split('-')
# country ...
# the country code (US, AT, CA)
_l = _lang.split('-')
if len(_l) == 2:
country = _l[1]
else:
country = _l[0].upper()
if country == 'EN':
country = 'US'
ret_val['country'] = country
# the combination (en-US, en-EN, de-DE, de-AU, fr-FR, fr-FR)
lang_country = '%s-%s' % (language, country)
# subdomain ...
# Accept-Language: fr-CH, fr;q=0.8, en;q=0.6, *;q=0.5
ret_val['Accept-Language'] = ','.join([
lang_country,
language + ';q=0.8,',
'en;q=0.6',
'*;q=0.5',
])
# subdomain
ret_val['subdomain'] = 'www.' + google_domains.get(country.upper(), 'google.com')
# params & headers
lang_country = '%s-%s' % (language, country) # (en-US, en-EN, de-DE, de-AU, fr-FR ..)
# hl parameter:
# https://developers.google.com/custom-search/docs/xml_results#hlsp The
# Interface Language:
# https://developers.google.com/custom-search/docs/xml_results_appendices#interfaceLanguages
ret_val['hl'] = lang_list.get(lang_country, language)
ret_val['params']['hl'] = lang_list.get(lang_country, language)
# lr parameter:
# The lr (language restrict) parameter restricts search results to
# documents written in a particular language.
# https://developers.google.com/custom-search/docs/xml_results#lrsp
# Language Collection Values:
# https://developers.google.com/custom-search/docs/xml_results_appendices#languageCollections
ret_val['lr'] = "lang_" + lang_list.get(lang_country, language)
if _any_language and supported_any_language:
# interpretation is left up to Google (based on whoogle)
#
# - add parameter ``source=lnt``
# - don't use parameter ``lr``
# - don't add a ``Accept-Language`` HTTP header.
ret_val['params']['source'] = 'lnt'
else:
# restricts search results to documents written in a particular
# language.
ret_val['params']['lr'] = "lang_" + lang_list.get(lang_country, language)
# Accept-Language: fr-CH, fr;q=0.8, en;q=0.6, *;q=0.5
ret_val['headers']['Accept-Language'] = ','.join([
lang_country,
language + ';q=0.8,',
'en;q=0.6',
'*;q=0.5',
])
return ret_val
@ -198,14 +263,13 @@ def request(query, params):
lang_info = get_lang_info(
# pylint: disable=undefined-variable
params, supported_languages, language_aliases
params, supported_languages, language_aliases, True
)
# https://www.google.de/search?q=corona&hl=de&lr=lang_de&start=0&tbs=qdr%3Ad&safe=medium
query_url = 'https://' + lang_info['subdomain'] + '/search' + "?" + urlencode({
'q': query,
'hl': lang_info['hl'],
'lr': lang_info['lr'],
**lang_info['params'],
'ie': "utf8",
'oe': "utf8",
'start': offset,
@ -215,12 +279,9 @@ def request(query, params):
query_url += '&' + urlencode({'tbs': 'qdr:' + time_range_dict[params['time_range']]})
if params['safesearch']:
query_url += '&' + urlencode({'safe': filter_mapping[params['safesearch']]})
logger.debug("query_url --> %s", query_url)
params['url'] = query_url
logger.debug("HTTP header Accept-Language --> %s", lang_info['Accept-Language'])
params['headers']['Accept-Language'] = lang_info['Accept-Language']
params['headers'].update(lang_info['headers'])
params['headers']['Accept'] = (
'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8'
)

12
searx/engines/google_images.py
View File

@ -101,14 +101,15 @@ def request(query, params):
lang_info = get_lang_info(
# pylint: disable=undefined-variable
params, supported_languages, language_aliases
params, supported_languages, language_aliases, False
)
logger.debug(
"HTTP header Accept-Language --> %s", lang_info['headers']['Accept-Language'])
query_url = 'https://' + lang_info['subdomain'] + '/search' + "?" + urlencode({
'q': query,
'tbm': "isch",
'hl': lang_info['hl'],
'lr': lang_info['lr'],
**lang_info['params'],
'ie': "utf8",
'oe': "utf8",
'num': 30,
@ -118,12 +119,9 @@ def request(query, params):
query_url += '&' + urlencode({'tbs': 'qdr:' + time_range_dict[params['time_range']]})
if params['safesearch']:
query_url += '&' + urlencode({'safe': filter_mapping[params['safesearch']]})
logger.debug("query_url --> %s", query_url)
params['url'] = query_url
logger.debug("HTTP header Accept-Language --> %s", lang_info['Accept-Language'])
params['headers']['Accept-Language'] = lang_info['Accept-Language']
params['headers'].update(lang_info['headers'])
params['headers']['Accept'] = (
'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8'
)

12
searx/engines/google_news.py
View File

@ -83,8 +83,10 @@ def request(query, params):
lang_info = get_lang_info(
# pylint: disable=undefined-variable
params, supported_languages, language_aliases
params, supported_languages, language_aliases, False
)
logger.debug(
"HTTP header Accept-Language --> %s", lang_info['headers']['Accept-Language'])
# google news has only one domain
lang_info['subdomain'] = 'news.google.com'
@ -102,18 +104,14 @@ def request(query, params):
query_url = 'https://' + lang_info['subdomain'] + '/search' + "?" + urlencode({
'q': query,
'hl': lang_info['hl'],
'lr': lang_info['lr'],
**lang_info['params'],
'ie': "utf8",
'oe': "utf8",
'gl': lang_info['country'],
}) + ('&ceid=%s' % ceid) # ceid includes a ':' character which must not be urlencoded
logger.debug("query_url --> %s", query_url)
params['url'] = query_url
logger.debug("HTTP header Accept-Language --> %s", lang_info['Accept-Language'])
params['headers']['Accept-Language'] = lang_info['Accept-Language']
params['headers'].update(lang_info['headers'])
params['headers']['Accept'] = (
'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8'
)

17
searx/engines/google_scholar.py
View File

@ -77,31 +77,26 @@ def request(query, params):
offset = (params['pageno'] - 1) * 10
lang_info = get_lang_info(
# pylint: disable=undefined-variable
# params, {}, language_aliases
params, supported_languages, language_aliases
params, supported_languages, language_aliases, False
)
logger.debug(
"HTTP header Accept-Language --> %s", lang_info['headers']['Accept-Language'])
# subdomain is: scholar.google.xy
lang_info['subdomain'] = lang_info['subdomain'].replace("www.", "scholar.")
query_url = 'https://'+ lang_info['subdomain'] + '/scholar' + "?" + urlencode({
'q': query,
'hl': lang_info['hl'],
'lr': lang_info['lr'],
**lang_info['params'],
'ie': "utf8",
'oe': "utf8",
'start' : offset,
})
query_url += time_range_url(params)
logger.debug("query_url --> %s", query_url)
params['url'] = query_url
logger.debug("HTTP header Accept-Language --> %s", lang_info['Accept-Language'])
params['headers']['Accept-Language'] = lang_info['Accept-Language']
params['headers'].update(lang_info['headers'])
params['headers']['Accept'] = (
'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8'
)

12
searx/engines/google_videos.py
View File

@ -119,14 +119,15 @@ def request(query, params):
lang_info = get_lang_info(
# pylint: disable=undefined-variable
params, supported_languages, language_aliases
params, supported_languages, language_aliases, False
)
logger.debug(
"HTTP header Accept-Language --> %s", lang_info['headers']['Accept-Language'])
query_url = 'https://' + lang_info['subdomain'] + '/search' + "?" + urlencode({
'q': query,
'tbm': "vid",
'hl': lang_info['hl'],
'lr': lang_info['lr'],
**lang_info['params'],
'ie': "utf8",
'oe': "utf8",
})
@ -135,12 +136,9 @@ def request(query, params):
query_url += '&' + urlencode({'tbs': 'qdr:' + time_range_dict[params['time_range']]})
if params['safesearch']:
query_url += '&' + urlencode({'safe': filter_mapping[params['safesearch']]})
logger.debug("query_url --> %s", query_url)
params['url'] = query_url
logger.debug("HTTP header Accept-Language --> %s", lang_info['Accept-Language'])
params['headers']['Accept-Language'] = lang_info['Accept-Language']
params['headers'].update(lang_info['headers'])
params['headers']['Accept'] = (
'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8'
)