diff options
| -rw-r--r-- | .dir-locals.el | 201 | ||||
| -rwxr-xr-x | manage | 2 | ||||
| -rw-r--r-- | searx/engines/google.py | 119 | ||||
| -rw-r--r-- | searx/engines/google_images.py | 12 | ||||
| -rw-r--r-- | searx/engines/google_news.py | 12 | ||||
| -rw-r--r-- | searx/engines/google_scholar.py | 17 | ||||
| -rw-r--r-- | searx/engines/google_videos.py | 12 | ||||
| -rw-r--r-- | utils/templates/etc/searx/use_default_settings.yml | 43 |
8 files changed, 236 insertions, 182 deletions
diff --git a/.dir-locals.el b/.dir-locals.el index 23609b4d2..d0e62208e 100644 --- a/.dir-locals.el +++ b/.dir-locals.el @@ -1,13 +1,22 @@ ;;; .dir-locals.el ;; -;; If you get ``*** EPC Error ***`` (even after a jedi:install-server) in your -;; emacs session, mostly you have jedi-mode enabled but the python enviroment is -;; missed. The python environment has to be next to the -;; ``<repo>/.dir-locals.el`` in:: +;; Per-Directory Local Variables: +;; https://www.gnu.org/software/emacs/manual/html_node/emacs/Directory-Variables.html ;; -;; ./local/py3 +;; .. hint:: ;; -;; In Emacs, some buffer locals are referencing the project environment: +;; If you get ``*** EPC Error ***`` (even after a jedi:install-server) in +;; your emacs session, mostly you have jedi-mode enabled but the python +;; enviroment is missed. The python environment has to be next to the +;; ``<repo>/.dir-locals.el`` in:: +;; +;; ./local/py3 +;; +;; To setup such an environment, build target:: +;; +;; $ make pyenv.install +;; +;; Some buffer locals are referencing the project environment: ;; ;; - prj-root --> <repo>/ ;; - python-environment-directory --> <repo>/local @@ -17,22 +26,12 @@ ;; `process-environment' and `exec-path' get proper values in order to run ;; shells inside the specified virtualenv, example:: ;; (setq python-shell-virtualenv-root "/path/to/env/") +;; - python-shell-interpreter --> <repo>/local/py3/bin/python ;; -;; To setup such an environment build target 'pyenv' or 'pyenvinstall':: -;; -;; $ make pyenvinstall -;; -;; Alternatively create the virtualenv, source it and install jedi + epc -;; (required by `emacs-jedi <https://tkf.github.io/emacs-jedi>`_):: +;; Jedi, flycheck & other python stuff should use the 'python-shell-interpreter' +;; from the local py3 environment. ;; -;; $ python -m venv ./local/py3 -;; ... -;; $ source ./local/py3/bin/activate -;; (py3)$ # now install into the activated 'py3' environment .. -;; (py3)$ pip install jedi epc -;; ... -;; -;; Here is what also I found useful to add to my .emacs:: +;; Other useful jedi stuff you might add to your ~/.emacs:: ;; ;; (global-set-key [f6] 'flycheck-mode) ;; (add-hook 'python-mode-hook 'my:python-mode-hook) @@ -45,97 +44,91 @@ ;; (define-key python-mode-map (kbd "M-.") 'jedi:goto-definition) ;; (define-key python-mode-map (kbd "M-,") 'jedi:goto-definition-pop-marker) ;; ) -;; ((nil . ((fill-column . 80) (indent-tabs-mode . nil) - ;; project root folder is where the `.dir-locals.el' is located - (eval . (setq-local - prj-root (locate-dominating-file default-directory ".dir-locals.el"))) - (eval . (setq-local - python-environment-directory (expand-file-name "./local" prj-root))) - ;; use 'py3' enviroment as default - (eval . (setq-local - python-environment-default-root-name "py3")) - (eval . (setq-local - python-shell-virtualenv-root - (expand-file-name python-environment-default-root-name python-environment-directory) - )) - (eval . (setq-local - python-shell-interpreter - (expand-file-name "bin/python" python-shell-virtualenv-root))) - )) + (eval . (progn + + ;; project root folder is where the `.dir-locals.el' is located + (setq-local prj-root + (locate-dominating-file default-directory ".dir-locals.el")) + + (setq-local python-environment-directory + (expand-file-name "./local" prj-root)) + + ;; use 'py3' enviroment as default + (setq-local python-environment-default-root-name + "py3") + (setq-local python-shell-virtualenv-root + (expand-file-name + python-environment-default-root-name python-environment-directory)) + + (setq-local python-shell-interpreter + (expand-file-name + "bin/python" python-shell-virtualenv-root)))))) (makefile-gmake-mode - . ((indent-tabs-mode . t) - )) + . ((indent-tabs-mode . t))) (yaml-mode - . ( - ;; flycheck should use the local py3 environment - (eval . (setq-local - flycheck-yaml-yamllint-executable - (expand-file-name "bin/yamllint" python-shell-virtualenv-root))) - (eval . (setq-local - flycheck-yamllintrc - (expand-file-name ".yamllint.yml" prj-root))) - (flycheck-checker . yaml-yamllint) - )) + . ((eval . (progn + + ;; flycheck should use the local py3 environment + (setq-local flycheck-yaml-yamllint-executable + (expand-file-name "bin/yamllint" python-shell-virtualenv-root)) + + (setq-local flycheck-yamllintrc + (expand-file-name ".yamllint.yml" prj-root)) + + (flycheck-checker . yaml-yamllint))))) (python-mode - . ((indent-tabs-mode . nil) - - (eval . (setq-local - python-environment-virtualenv - (list (expand-file-name "bin/virtualenv" python-shell-virtualenv-root) - ;;"--system-site-packages" - "--quiet"))) - - (eval . (setq-local - pylint-command - (expand-file-name "bin/pylint" python-shell-virtualenv-root))) - - ;; pylint will find the '.pylintrc' file next to the CWD - ;; https://pylint.readthedocs.io/en/latest/user_guide/run.html#command-line-options - (eval . (setq-local - flycheck-pylintrc ".pylintrc")) - - ;; flycheck & other python stuff should use the local py3 environment - (eval . (setq-local - flycheck-python-pylint-executable python-shell-interpreter)) - - ;; use 'M-x jedi:show-setup-info' and 'M-x epc:controller' to inspect jedi server - - ;; https://tkf.github.io/emacs-jedi/latest/#jedi:environment-root -- You - ;; can specify a full path instead of a name (relative path). In that case, - ;; python-environment-directory is ignored and Python virtual environment - ;; is created at the specified path. - (eval . (setq-local jedi:environment-root python-shell-virtualenv-root)) - - ;; https://tkf.github.io/emacs-jedi/latest/#jedi:server-command - (eval .(setq-local - jedi:server-command - (list python-shell-interpreter - jedi:server-script) - )) - - ;; jedi:environment-virtualenv --> see above 'python-environment-virtualenv' - ;; is set buffer local! No need to setup jedi:environment-virtualenv: - ;; - ;; Virtualenv command to use. A list of string. If it is nil, - ;; python-environment-virtualenv is used instead. You must set non-nil - ;; value to jedi:environment-root in order to make this setting work. - ;; - ;; https://tkf.github.io/emacs-jedi/latest/#jedi:environment-virtualenv - ;; - ;; (eval . (setq-local - ;; jedi:environment-virtualenv - ;; (list (expand-file-name "bin/virtualenv" python-shell-virtualenv-root) - ;; ;;"--python" - ;; ;;"/usr/bin/python3.4" - ;; ))) - - ;; jedi:server-args - - ))) + . ((eval . (progn + + (setq-local python-environment-virtualenv + (list (expand-file-name "bin/virtualenv" python-shell-virtualenv-root) + ;;"--system-site-packages" + "--quiet")) + + (setq-local pylint-command + (expand-file-name "bin/pylint" python-shell-virtualenv-root)) + + ;; pylint will find the '.pylintrc' file next to the CWD + ;; https://pylint.readthedocs.io/en/latest/user_guide/run.html#command-line-options + (setq-local flycheck-pylintrc + ".pylintrc") + + ;; flycheck & other python stuff should use the local py3 environment + (setq-local flycheck-python-pylint-executable + python-shell-interpreter) + + ;; use 'M-x jedi:show-setup-info' and 'M-x epc:controller' to inspect jedi server + ;; https://tkf.github.io/emacs-jedi/latest/#jedi:environment-root -- You + ;; can specify a full path instead of a name (relative path). In that case, + ;; python-environment-directory is ignored and Python virtual environment + ;; is created at the specified path. + (setq-local jedi:environment-root + python-shell-virtualenv-root) + + ;; https://tkf.github.io/emacs-jedi/latest/#jedi:server-command + (setq-local jedi:server-command + (list python-shell-interpreter + jedi:server-script)) + + ;; jedi:environment-virtualenv --> see above 'python-environment-virtualenv' + ;; is set buffer local! No need to setup jedi:environment-virtualenv: + ;; + ;; Virtualenv command to use. A list of string. If it is nil, + ;; python-environment-virtualenv is used instead. You must set non-nil + ;; value to jedi:environment-root in order to make this setting work. + ;; + ;; https://tkf.github.io/emacs-jedi/latest/#jedi:environment-virtualenv + ;; + ;; (setq-local jedi:environment-virtualenv + ;; (list (expand-file-name "bin/virtualenv" python-shell-virtualenv-root) + ;; "--python" + ;; "/usr/bin/python3.4" + ;; )) + )))) + ) @@ -32,7 +32,7 @@ pylint.FILES() { YAMLLINT_FILES=() while IFS= read -r line; do YAMLLINT_FILES+=("$line") -done <<< "$(git ls-files './tests/*.yml' './searx/*.yml')" +done <<< "$(git ls-files './tests/*.yml' './searx/*.yml' './utils/templates/etc/searx/*.yml')" PYLINT_SEARX_DISABLE_OPTION="\ I,C,R,\ diff --git a/searx/engines/google.py b/searx/engines/google.py index 92c9e1399..841212e09 100644 --- a/searx/engines/google.py +++ b/searx/engines/google.py @@ -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) - - # 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 ... - # 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: + # 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' ) diff --git a/searx/engines/google_images.py b/searx/engines/google_images.py index 919c99c63..e7382a6fe 100644 --- a/searx/engines/google_images.py +++ b/searx/engines/google_images.py @@ -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' ) diff --git a/searx/engines/google_news.py b/searx/engines/google_news.py index 355155de8..485d602bc 100644 --- a/searx/engines/google_news.py +++ b/searx/engines/google_news.py @@ -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' ) diff --git a/searx/engines/google_scholar.py b/searx/engines/google_scholar.py index a0ca70e53..8442a7bfa 100644 --- a/searx/engines/google_scholar.py +++ b/searx/engines/google_scholar.py @@ -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' ) diff --git a/searx/engines/google_videos.py b/searx/engines/google_videos.py index 3e3f5d6f1..c57db4e63 100644 --- a/searx/engines/google_videos.py +++ b/searx/engines/google_videos.py @@ -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' ) diff --git a/utils/templates/etc/searx/use_default_settings.yml b/utils/templates/etc/searx/use_default_settings.yml index 845e3139f..f805373fe 100644 --- a/utils/templates/etc/searx/use_default_settings.yml +++ b/utils/templates/etc/searx/use_default_settings.yml @@ -1,23 +1,34 @@ -use_default_settings: True +use_default_settings: true general: - debug : False # Debug mode, only for development - instance_name : "searx" # displayed name + debug: false # Debug mode, only for development + instance_name: "searxng" # displayed name + contact_url: false # mailto:contact@example.com search: - safe_search : 0 # Filter results. 0: None, 1: Moderate, 2: Strict - autocomplete : "" # Existing autocomplete backends: "dbpedia", "duckduckgo", "google", "startpage", "swisscows", "qwant", "wikipedia" - leave blank to turn it off by default - default_lang : "" # Default search language - leave blank to detect from browser information or use codes from 'languages.py' - formats: [html, csv, json, rss] + # Filter results. 0: None, 1: Moderate, 2: Strict + safe_search: 0 + # Existing autocomplete backends: "dbpedia", "duckduckgo", "google", + # "startpage", "swisscows", "qwant", "wikipedia" - leave blank to turn it off + # by default. + autocomplete: "" + # Default search language - leave blank to detect from browser information or + # use codes from 'languages.py' + default_lang: "" + # remove format to deny access, use lower case. + formats: [html, csv, json, rss] server: - port : 8888 - bind_address : "127.0.0.1" # address to listen on - secret_key : "ultrasecretkey" # change this! - base_url : False # Set custom base_url. Possible values: False or "https://your.custom.host/location/" - image_proxy : False # Proxying image results through searx + port: 8888 + # address to listen on + bind_address: "127.0.0.1" + secret_key: "ultrasecretkey" # change this! + # Set custom base_url. Possible values: + # false or "https://your.custom.host/location/" + base_url: https://darmarit.org/searx + # Proxying image results through searx + image_proxy: false -# uncomment below section if you have running morty proxy -#result_proxy: -# url : http://127.0.0.1:3000/ -# key : !!binary "your_morty_proxy_key" +# result_proxy: +# url: http://127.0.0.1:3000/ +# key: !!binary "your_morty_proxy_key" |