Merge branch 'dev/fix-google-engine' into 'master'

# SPDX-License-Identifier: AGPL-3.0-or-later

# SPDX-License-Identifier: AGPL-3.0-or-later

"""Google (Web)

# lint: pylint

For detailed description of the *REST-full* API see: `Query Parameter

"""This is the implementation of the google WEB engine.  Some of this

Definitions`_.

implementations are shared by other engines:

.. _Query Parameter Definitions:

   https://developers.google.com/custom-search/docs/xml_results#WebSearch_Query_Parameter_Definitions

- :ref:`google images engine`

"""

- :ref:`google news engine`

- :ref:`google videos engine`

The google WEB engine itself has a special setup option:

.. code:: yaml

# pylint: disable=invalid-name, missing-function-docstring, too-many-branches

  - name: google

    ...

    use_mobile_ui: false

from urllib.parse import urlencode, urlparse

``use_mobile_ui``: (default: ``false``)

from random import random

  Enables to use *mobile endpoint* to bypass the google blocking (see

  :issue:`159`).  On the mobile UI of Google Search, the button :guilabel:`More

  results` is not affected by Google rate limiting and we can still do requests

  while actively blocked by the original Google search.  By activate

  ``use_mobile_ui`` this behavior is simulated by adding the parameter

  ``async=use_ac:true,_fmt:pc`` to the :py:func:`request`.

"""

from urllib.parse import urlencode

from lxml import html

from lxml import html

from searx import logger

from searx import logger

from searx.utils import match_language, extract_text, eval_xpath, eval_xpath_list, eval_xpath_getindex

from searx.utils import match_language, extract_text, eval_xpath, eval_xpath_list, eval_xpath_getindex

}

}

# engine dependent config

# engine dependent config

categories = ['general']

categories = ['general', 'web']

paging = True

paging = True

time_range_support = True

time_range_support = True

safesearch = True

safesearch = True

send_accept_language_header = True

use_mobile_ui = False

use_mobile_ui = False

supported_languages_url = 'https://www.google.com/preferences?#languages'

supported_languages_url = 'https://www.google.com/preferences?#languages'

    'UA': 'google.com.ua',  # Ukraine

    'UA': 'google.com.ua',  # Ukraine

    'CN': 'google.com.hk',  # There is no google.cn, we use .com.hk for zh-CN

    'CN': 'google.com.hk',  # There is no google.cn, we use .com.hk for zh-CN

    'HK': 'google.com.hk',  # Hong Kong

    'HK': 'google.com.hk',  # Hong Kong

    'TW': 'google.com.tw'   # Taiwan

    'TW': 'google.com.tw',  # Taiwan

}

}

time_range_dict = {

time_range_dict = {'day': 'd', 'week': 'w', 'month': 'm', 'year': 'y'}

    'day': 'd',

    'week': 'w',

    'month': 'm',

    'year': 'y'

}

# Filter results. 0: None, 1: Moderate, 2: Strict

# Filter results. 0: None, 1: Moderate, 2: Strict

filter_mapping = {

filter_mapping = {0: 'off', 1: 'medium', 2: 'high'}

    0: 'off',

    1: 'medium',

    2: 'high'

}

# specific xpath variables

# specific xpath variables

# ------------------------

# ------------------------

# google results are grouped into <div class="jtfYYd ..." ../>

results_xpath = './/div[@data-sokoban-container]'

results_xpath = '//div[contains(@class, "jtfYYd")]'

title_xpath = './/a/h3[1]'

results_xpath_mobile_ui = '//div[contains(@class, "g ")]'

href_xpath = './/a[h3]/@href'

content_xpath = './/div[@data-content-feature=1]'

# google *sections* are no usual *results*, we ignore them

# google *sections* are no usual *results*, we ignore them

g_section_with_header = './g-section-with-header'

g_section_with_header = './g-section-with-header'

# the title is a h3 tag relative to the result group

title_xpath = './/h3[1]'

# in the result group there is <div class="yuRUbf" ../> it's first child is a <a

# href=...>

href_xpath = './/div[@class="yuRUbf"]//a/@href'

# in the result group there is <div class="VwiC3b ..." ../> containing the *content*

content_xpath = './/div[contains(@class, "VwiC3b")]'

# Suggestions are links placed in a *card-section*, we extract only the text

# Suggestions are links placed in a *card-section*, we extract only the text

# from the links not the links itself.

# from the links not the links itself.

suggestion_xpath = '//div[contains(@class, "card-section")]//a'

suggestion_xpath = '//div[contains(@class, "EIaa9b")]//a'

# Since google does *auto-correction* on the first query these are not really

# *spelling suggestions*, we use them anyway.

spelling_suggestion_xpath = '//div[@class="med"]/p/a'

def get_lang_info(params, lang_list, custom_aliases, supported_any_language):

def get_lang_info(params, lang_list, custom_aliases, supported_any_language):

    ret_val = {}

    """Composing various language properties for the google engines.

    This function is called by the various google engines (:ref:`google web

    engine`, :ref:`google images engine`, :ref:`google news engine` and

    :ref:`google videos engine`).

    :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']

    _lang = params['language']

    _any_language = _lang.lower() == 'all'

    _any_language = _lang.lower() == 'all'

    if _any_language:

    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)

    ret_val['language'] = language

    ret_val['language'] = language

    # the requested language from params (en, en-US, de, de-AT, fr, fr-CA, ...)

    # country ...

    _l = _lang.split('-')

    # the country code (US, AT, CA)

    _l = _lang.split('-')

    if len(_l) == 2:

    if len(_l) == 2:

        country = _l[1]

        country = _l[1]

    else:

    else:

        country = _l[0].upper()

        country = _l[0].upper()

        if country == 'EN':

        if country == 'EN':

            country = 'US'

            country = 'US'

    ret_val['country'] = country

    ret_val['country'] = country

    # the combination (en-US, en-EN, de-DE, de-AU, fr-FR, fr-FR)

    # subdomain ...

    lang_country = '%s-%s' % (language, country)

    # subdomain

    ret_val['subdomain'] = 'www.' + google_domains.get(country.upper(), 'google.com')

    ret_val['subdomain'] = 'www.' + google_domains.get(country.upper(), 'google.com')

    ret_val['params'] = {}

    # params & headers

    ret_val['headers'] = {}

    if _any_language and supported_any_language:

    lang_country = '%s-%s' % (language, country)  # (en-US, en-EN, de-DE, de-AU, fr-FR ..)

        # based on whoogle

        ret_val['params']['source'] = 'lnt'

    # hl parameter:

    else:

    #   https://developers.google.com/custom-search/docs/xml_results#hlsp The

        # Accept-Language: fr-CH, fr;q=0.8, en;q=0.6, *;q=0.5

    # Interface Language:

        ret_val['headers']['Accept-Language'] = ','.join([

    #   https://developers.google.com/custom-search/docs/xml_results_appendices#interfaceLanguages

            lang_country,

            language + ';q=0.8,',

    ret_val['params']['hl'] = lang_list.get(lang_country, language)

            'en;q=0.6',

            '*;q=0.5',

        ])

    # lr parameter:

    # 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

    #   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

    #   https://developers.google.com/custom-search/docs/xml_results_appendices#languageCollections

        if lang_country in lang_list:

            ret_val['params']['lr'] = "lang_" + lang_country

    if _any_language and supported_any_language:

        elif language in lang_country:

            ret_val['params']['lr'] = "lang_" + 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:

    else:

            ret_val['params']['lr'] = language

    ret_val['params']['hl'] = lang_country if lang_country in lang_list else language

        # restricts search results to documents written in a particular

        # language.

        ret_val['params']['lr'] = "lang_" + lang_list.get(lang_country, language)

    # 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

    return ret_val

    return ret_val

def detect_google_sorry(resp):

def detect_google_sorry(resp):

    resp_url = urlparse(resp.url)

    """Detect when ratelimited"""

    if resp_url.netloc == 'sorry.google.com' or resp_url.path.startswith('/sorry'):

    if resp.url == 'sorry.google.com' or resp.url.startswith('/sorry'):

        raise SearxEngineCaptchaException()

        raise SearxEngineCaptchaException()

    offset = (params['pageno'] - 1) * 10

    offset = (params['pageno'] - 1) * 10

    lang_info = get_lang_info(

    # pylint: disable=undefined-variable

    # pylint: disable=undefined-variable

        params, supported_languages, language_aliases, True

    lang_info = get_lang_info(params, supported_languages, language_aliases, True)

    )

    additional_parameters = {}

    additional_parameters = {}

    if use_mobile_ui:

    if use_mobile_ui:

        additional_parameters = {

        additional_parameters = {

            'async': 'use_ac:true,_fmt:pc',

            'asearch': 'arc',

            'async': 'use_ac:true,_fmt:prog',

        }

        }

    # 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,

                **lang_info['params'],

                **lang_info['params'],

                'ie': "utf8",

                'ie': "utf8",

                'oe': "utf8",

                'oe': "utf8",

                'start': offset,

                'start': offset,

                'filter': '0',

                'filter': '0',

        'ucbcb': 1,

                **additional_parameters,

                **additional_parameters,

    })

            }

        )

    )

    if params['time_range'] in time_range_dict:

    if params['time_range'] in time_range_dict:

        query_url += '&' + urlencode({'tbs': 'qdr:' + time_range_dict[params['time_range']]})

        query_url += '&' + urlencode({'tbs': 'qdr:' + time_range_dict[params['time_range']]})

    if params['safesearch']:

    if params['safesearch']:

        query_url += '&' + urlencode({'safe': filter_mapping[params['safesearch']]})

        query_url += '&' + urlencode({'safe': filter_mapping[params['safesearch']]})

    logger.debug("query_url --> %s", query_url)

    params['url'] = query_url

    params['url'] = query_url

    logger.debug("HTTP header Accept-Language --> %s", lang_info.get('Accept-Language'))

    params['cookies']['CONSENT'] = "YES+"

    params['cookies']['CONSENT'] = "PENDING+" + str(random()*100)

    params['headers'].update(lang_info['headers'])

    params['headers'].update(lang_info['headers'])

    if use_mobile_ui:

    if use_mobile_ui:

        params['headers']['Accept'] = '*/*'

        params['headers']['Accept'] = '*/*'

    else:

    else:

        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'

        )

    return params

    return params

    # convert the text to dom

    # convert the text to dom

    dom = html.fromstring(resp.text)

    dom = html.fromstring(resp.text)

    # results --> answer

    # results --> answer

    answer_list = eval_xpath(dom, '//div[contains(@class, "LGOjhe")]')

    answer_list = eval_xpath(dom, '//div[contains(@class, "LGOjhe")]')

    if answer_list:

    if answer_list:

    # parse results

    # parse results

    _results_xpath = results_xpath

    for result in eval_xpath_list(dom, results_xpath):

    if use_mobile_ui:

        _results_xpath = results_xpath_mobile_ui

    for result in eval_xpath_list(dom, _results_xpath):

        # google *sections*

        # google *sections*

        if extract_text(eval_xpath(result, g_section_with_header)):

        if extract_text(eval_xpath(result, g_section_with_header)):

            logger.debug("ingoring <g-section-with-header>")

            logger.debug("ignoring <g-section-with-header>")

            continue

            continue

        try:

        try:

            title_tag = eval_xpath_getindex(result, title_xpath, 0, default=None)

            title_tag = eval_xpath_getindex(result, title_xpath, 0, default=None)

            if title_tag is None:

            if title_tag is None:

                # this not one of the common google results *section*

                # this not one of the common google results *section*

                logger.debug('ingoring item from the result_xpath list: missing title')

                logger.debug('ignoring item from the result_xpath list: missing title')

                continue

                continue

            title = extract_text(title_tag)

            title = extract_text(title_tag)

            url = eval_xpath_getindex(result, href_xpath, 0, None)

            url = eval_xpath_getindex(result, href_xpath, 0, None)

                continue

                continue

            content = extract_text(eval_xpath_getindex(result, content_xpath, 0, default=None), allow_none=True)

            content = extract_text(eval_xpath_getindex(result, content_xpath, 0, default=None), allow_none=True)

            if content is None:

            if content is None:

                logger.debug('ingoring item from the result_xpath list: missing content of title "%s"', title)

                logger.debug('ignoring item from the result_xpath list: missing content of title "%s"', title)

                continue

                continue

            logger.debug('add link to results: %s', title)

            logger.debug('add link to results: %s', title)

            results.append({'url': url, 'title': title, 'content': content})

            results.append({

                'url': url,

                'title': title,

                'content': content

            })

        except Exception as e:  # pylint: disable=broad-except

        except Exception as e:  # pylint: disable=broad-except

            logger.error(e, exc_info=True)

            logger.error(e, exc_info=True)

        # append suggestion

        # append suggestion

        results.append({'suggestion': extract_text(suggestion)})

        results.append({'suggestion': extract_text(suggestion)})

    for correction in eval_xpath_list(dom, spelling_suggestion_xpath):

        results.append({'correction': extract_text(correction)})

    # return results

    # return results

    return results

    return results