[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
This commit is contained in:
Alexandre Flament 2021-06-06 08:18:07 +02:00 committed by Markus Heiser
parent 73dbee45a6
commit 1c67b6aece
5 changed files with 46 additions and 45 deletions

View file

@ -133,11 +133,12 @@ suggestion_xpath = '//div[contains(@class, "card-section")]//a'
spelling_suggestion_xpath = '//div[@class="med"]/p/a' spelling_suggestion_xpath = '//div[@class="med"]/p/a'
def get_lang_info(params, lang_list, custom_aliases): def get_lang_info(params, lang_list, custom_aliases, supported_any_language):
ret_val = {} ret_val = {}
_lang = params['language'] _lang = params['language']
if _lang.lower() == 'all': _any_language = _lang.lower() == 'all'
if _any_language:
_lang = 'en-US' _lang = 'en-US'
language = match_language(_lang, lang_list, custom_aliases) language = match_language(_lang, lang_list, custom_aliases)
@ -159,31 +160,36 @@ def get_lang_info(params, lang_list, custom_aliases):
# the combination (en-US, en-EN, de-DE, de-AU, fr-FR, fr-FR) # the combination (en-US, en-EN, de-DE, de-AU, fr-FR, fr-FR)
lang_country = '%s-%s' % (language, country) lang_country = '%s-%s' % (language, country)
# subdomain
ret_val['subdomain'] = 'www.' + google_domains.get(country.upper(), 'google.com')
ret_val['params'] = {}
ret_val['headers'] = {}
if _any_language and supported_any_language:
# based on whoogle
ret_val['params']['source'] = 'lnt'
else:
# Accept-Language: fr-CH, fr;q=0.8, en;q=0.6, *;q=0.5 # Accept-Language: fr-CH, fr;q=0.8, en;q=0.6, *;q=0.5
ret_val['Accept-Language'] = ','.join([ ret_val['headers']['Accept-Language'] = ','.join([
lang_country, lang_country,
language + ';q=0.8,', language + ';q=0.8,',
'en;q=0.6', 'en;q=0.6',
'*;q=0.5', '*;q=0.5',
]) ])
# subdomain # lr parameter:
ret_val['subdomain'] = 'www.' + google_domains.get(country.upper(), 'google.com') # 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['params']['lr'] = "lang_" + lang_list.get(lang_country, language)
ret_val['params']['hl'] = lang_list.get(lang_country, language)
# hl parameter: # hl parameter:
# https://developers.google.com/custom-search/docs/xml_results#hlsp The # https://developers.google.com/custom-search/docs/xml_results#hlsp The
# Interface Language: # Interface Language:
# https://developers.google.com/custom-search/docs/xml_results_appendices#interfaceLanguages # https://developers.google.com/custom-search/docs/xml_results_appendices#interfaceLanguages
ret_val['hl'] = lang_list.get(lang_country, language)
# lr parameter:
# 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)
return ret_val return ret_val
def detect_google_sorry(resp): def detect_google_sorry(resp):
@ -198,14 +204,13 @@ def request(query, params):
lang_info = get_lang_info( lang_info = get_lang_info(
# pylint: disable=undefined-variable # 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 # 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({ query_url = 'https://' + lang_info['subdomain'] + '/search' + "?" + urlencode({
'q': query, 'q': query,
'hl': lang_info['hl'], **lang_info['params'],
'lr': lang_info['lr'],
'ie': "utf8", 'ie': "utf8",
'oe': "utf8", 'oe': "utf8",
'start': offset, 'start': offset,
@ -219,8 +224,8 @@ def request(query, params):
logger.debug("query_url --> %s", query_url) logger.debug("query_url --> %s", query_url)
params['url'] = query_url params['url'] = query_url
logger.debug("HTTP header Accept-Language --> %s", lang_info['Accept-Language']) logger.debug("HTTP header Accept-Language --> %s", lang_info.get('Accept-Language'))
params['headers']['Accept-Language'] = lang_info['Accept-Language'] params['headers'].update(lang_info['headers'])
params['headers']['Accept'] = ( params['headers']['Accept'] = (
'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8' 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8'
) )

View file

@ -101,14 +101,13 @@ def request(query, params):
lang_info = get_lang_info( lang_info = get_lang_info(
# pylint: disable=undefined-variable # pylint: disable=undefined-variable
params, supported_languages, language_aliases params, supported_languages, language_aliases, False
) )
query_url = 'https://' + lang_info['subdomain'] + '/search' + "?" + urlencode({ query_url = 'https://' + lang_info['subdomain'] + '/search' + "?" + urlencode({
'q': query, 'q': query,
'tbm': "isch", 'tbm': "isch",
'hl': lang_info['hl'], **lang_info['params'],
'lr': lang_info['lr'],
'ie': "utf8", 'ie': "utf8",
'oe': "utf8", 'oe': "utf8",
'num': 30, 'num': 30,
@ -122,8 +121,8 @@ def request(query, params):
logger.debug("query_url --> %s", query_url) logger.debug("query_url --> %s", query_url)
params['url'] = query_url params['url'] = query_url
logger.debug("HTTP header Accept-Language --> %s", lang_info['Accept-Language']) logger.debug("HTTP header Accept-Language --> %s", lang_info.get('Accept-Language'))
params['headers']['Accept-Language'] = lang_info['Accept-Language'] params['headers'].update(lang_info['headers'])
params['headers']['Accept'] = ( params['headers']['Accept'] = (
'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8' 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8'
) )

View file

@ -83,7 +83,7 @@ def request(query, params):
lang_info = get_lang_info( lang_info = get_lang_info(
# pylint: disable=undefined-variable # pylint: disable=undefined-variable
params, supported_languages, language_aliases params, supported_languages, language_aliases, False
) )
# google news has only one domain # google news has only one domain
@ -102,8 +102,7 @@ def request(query, params):
query_url = 'https://' + lang_info['subdomain'] + '/search' + "?" + urlencode({ query_url = 'https://' + lang_info['subdomain'] + '/search' + "?" + urlencode({
'q': query, 'q': query,
'hl': lang_info['hl'], **lang_info['params'],
'lr': lang_info['lr'],
'ie': "utf8", 'ie': "utf8",
'oe': "utf8", 'oe': "utf8",
'gl': lang_info['country'], 'gl': lang_info['country'],
@ -112,8 +111,8 @@ def request(query, params):
logger.debug("query_url --> %s", query_url) logger.debug("query_url --> %s", query_url)
params['url'] = query_url params['url'] = query_url
logger.debug("HTTP header Accept-Language --> %s", lang_info['Accept-Language']) logger.debug("HTTP header Accept-Language --> %s", lang_info.get('Accept-Language'))
params['headers']['Accept-Language'] = lang_info['Accept-Language'] params['headers'].update(lang_info['headers'])
params['headers']['Accept'] = ( params['headers']['Accept'] = (
'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8' 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8'
) )

View file

@ -81,15 +81,14 @@ def request(query, params):
# params, {}, language_aliases # params, {}, language_aliases
params, supported_languages, language_aliases params, supported_languages, language_aliases, False
) )
# subdomain is: scholar.google.xy # subdomain is: scholar.google.xy
lang_info['subdomain'] = lang_info['subdomain'].replace("www.", "scholar.") lang_info['subdomain'] = lang_info['subdomain'].replace("www.", "scholar.")
query_url = 'https://'+ lang_info['subdomain'] + '/scholar' + "?" + urlencode({ query_url = 'https://'+ lang_info['subdomain'] + '/scholar' + "?" + urlencode({
'q': query, 'q': query,
'hl': lang_info['hl'], **lang_info['params'],
'lr': lang_info['lr'],
'ie': "utf8", 'ie': "utf8",
'oe': "utf8", 'oe': "utf8",
'start' : offset, 'start' : offset,
@ -100,8 +99,8 @@ def request(query, params):
logger.debug("query_url --> %s", query_url) logger.debug("query_url --> %s", query_url)
params['url'] = query_url params['url'] = query_url
logger.debug("HTTP header Accept-Language --> %s", lang_info['Accept-Language']) logger.debug("HTTP header Accept-Language --> %s", lang_info.get('Accept-Language'))
params['headers']['Accept-Language'] = lang_info['Accept-Language'] params['headers'].update(lang_info['headers'])
params['headers']['Accept'] = ( params['headers']['Accept'] = (
'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8' 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8'
) )

View file

@ -119,14 +119,13 @@ def request(query, params):
lang_info = get_lang_info( lang_info = get_lang_info(
# pylint: disable=undefined-variable # pylint: disable=undefined-variable
params, supported_languages, language_aliases params, supported_languages, language_aliases, False
) )
query_url = 'https://' + lang_info['subdomain'] + '/search' + "?" + urlencode({ query_url = 'https://' + lang_info['subdomain'] + '/search' + "?" + urlencode({
'q': query, 'q': query,
'tbm': "vid", 'tbm': "vid",
'hl': lang_info['hl'], **lang_info['params'],
'lr': lang_info['lr'],
'ie': "utf8", 'ie': "utf8",
'oe': "utf8", 'oe': "utf8",
}) })
@ -139,8 +138,8 @@ def request(query, params):
logger.debug("query_url --> %s", query_url) logger.debug("query_url --> %s", query_url)
params['url'] = query_url params['url'] = query_url
logger.debug("HTTP header Accept-Language --> %s", lang_info['Accept-Language']) logger.debug("HTTP header Accept-Language --> %s", lang_info.get('Accept-Language'))
params['headers']['Accept-Language'] = lang_info['Accept-Language'] params['headers'].update(lang_info['headers'])
params['headers']['Accept'] = ( params['headers']['Accept'] = (
'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8' 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8'
) )