|
@@ -34,6 +34,7 @@ categories = ['general']
|
|
paging = True
|
|
paging = True
|
|
time_range_support = True
|
|
time_range_support = True
|
|
safesearch = True
|
|
safesearch = True
|
|
|
|
+use_mobile_ui = False
|
|
supported_languages_url = 'https://www.google.com/preferences?#languages'
|
|
supported_languages_url = 'https://www.google.com/preferences?#languages'
|
|
|
|
|
|
# based on https://en.wikipedia.org/wiki/List_of_Google_domains and tests
|
|
# based on https://en.wikipedia.org/wiki/List_of_Google_domains and tests
|
|
@@ -266,6 +267,13 @@ def request(query, params):
|
|
params, supported_languages, language_aliases, True
|
|
params, supported_languages, language_aliases, True
|
|
)
|
|
)
|
|
|
|
|
|
|
|
+ additional_parameters = {}
|
|
|
|
+ if use_mobile_ui:
|
|
|
|
+ additional_parameters = {
|
|
|
|
+ 'asearch': "arc",
|
|
|
|
+ 'async': 'arc_id:srp_510,ffilt:all,ve_name:MoreResultsContainer,next_id:srp_5,use_ac:true,_id:arc-srp_510,_pms:qs,_fmt:pc' # pylint: disable=line-too-long
|
|
|
|
+ }
|
|
|
|
+
|
|
# 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,
|
|
@@ -273,6 +281,7 @@ def request(query, params):
|
|
'ie': "utf8",
|
|
'ie': "utf8",
|
|
'oe': "utf8",
|
|
'oe': "utf8",
|
|
'start': offset,
|
|
'start': offset,
|
|
|
|
+ **additional_parameters,
|
|
})
|
|
})
|
|
|
|
|
|
if params['time_range'] in time_range_dict:
|
|
if params['time_range'] in time_range_dict:
|
|
@@ -282,9 +291,12 @@ def request(query, params):
|
|
params['url'] = query_url
|
|
params['url'] = query_url
|
|
|
|
|
|
params['headers'].update(lang_info['headers'])
|
|
params['headers'].update(lang_info['headers'])
|
|
- params['headers']['Accept'] = (
|
|
|
|
- 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8'
|
|
|
|
- )
|
|
|
|
|
|
+ if use_mobile_ui:
|
|
|
|
+ params['headers']['Accept'] = '*/*'
|
|
|
|
+ else:
|
|
|
|
+ params['headers']['Accept'] = (
|
|
|
|
+ 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8'
|
|
|
|
+ )
|
|
|
|
|
|
return params
|
|
return params
|
|
|
|
|
|
@@ -307,14 +319,15 @@ def response(resp):
|
|
logger.debug("did not find 'answer'")
|
|
logger.debug("did not find 'answer'")
|
|
|
|
|
|
# results --> number_of_results
|
|
# results --> number_of_results
|
|
- try:
|
|
|
|
- _txt = eval_xpath_getindex(dom, '//div[@id="result-stats"]//text()', 0)
|
|
|
|
- _digit = ''.join([n for n in _txt if n.isdigit()])
|
|
|
|
- number_of_results = int(_digit)
|
|
|
|
- results.append({'number_of_results': number_of_results})
|
|
|
|
- except Exception as e: # pylint: disable=broad-except
|
|
|
|
- logger.debug("did not 'number_of_results'")
|
|
|
|
- logger.error(e, exc_info=True)
|
|
|
|
|
|
+ if not use_mobile_ui:
|
|
|
|
+ try:
|
|
|
|
+ _txt = eval_xpath_getindex(dom, '//div[@id="result-stats"]//text()', 0)
|
|
|
|
+ _digit = ''.join([n for n in _txt if n.isdigit()])
|
|
|
|
+ number_of_results = int(_digit)
|
|
|
|
+ results.append({'number_of_results': number_of_results})
|
|
|
|
+ except Exception as e: # pylint: disable=broad-except
|
|
|
|
+ logger.debug("did not 'number_of_results'")
|
|
|
|
+ logger.error(e, exc_info=True)
|
|
|
|
|
|
# parse results
|
|
# parse results
|
|
for result in eval_xpath_list(dom, results_xpath):
|
|
for result in eval_xpath_list(dom, results_xpath):
|