searx.engines.yahoo Namespace Reference

Functions
	request (query, params)
	parse_url (url_string)
	response (resp)
	fetch_traits (EngineTraits engine_traits)

Variables
dict	about
list	categories = ['general', 'web']
bool	paging = True
bool	time_range_support = True
dict	time_range_dict
dict	lang2domain
dict	locale_aliases

Detailed Description

Yahoo Search (Web)

Languages are supported by mapping the language to a domain.  If domain is not
found in :py:obj:`lang2domain` URL ``<lang>.search.yahoo.com`` is used.

Function Documentation

fetch_traits()

searx.engines.yahoo.fetch_traits

(

EngineTraits

engine_traits

)

Fetch languages from yahoo

Definition at line 159 of file yahoo.py.

def fetch_traits(engine_traits: EngineTraits):
    """Fetch languages from yahoo"""
 
    # pylint: disable=import-outside-toplevel
    import babel
    from searx import network
    from searx.locales import language_tag
 
    engine_traits.all_locale = 'any'
 
    resp = network.get('https://search.yahoo.com/preferences/languages')
    if not resp.ok:
        print("ERROR: response from yahoo is not OK.")
 
    dom = html.fromstring(resp.text)
    offset = len('lang_')
 
    eng2sxng = {'zh_chs': 'zh_Hans', 'zh_cht': 'zh_Hant'}
 
    for val in eval_xpath_list(dom, '//div[contains(@class, "lang-item")]/input/@value'):
        eng_tag = val[offset:]
 
        try:
            sxng_tag = language_tag(babel.Locale.parse(eng2sxng.get(eng_tag, eng_tag)))
        except babel.UnknownLocaleError:
            print('ERROR: unknown language --> %s' % eng_tag)
            continue
 
        conflict = engine_traits.languages.get(sxng_tag)
        if conflict:
            if conflict != eng_tag:
                print("CONFLICT: babel %s --> %s, %s" % (sxng_tag, conflict, eng_tag))
            continue
        engine_traits.languages[sxng_tag] = eng_tag

parse_url()

searx.engines.yahoo.parse_url

(

url_string

)

remove yahoo-specific tracking-url

Definition at line 104 of file yahoo.py.

def parse_url(url_string):
    """remove yahoo-specific tracking-url"""
 
    endings = ['/RS', '/RK']
    endpositions = []
    start = url_string.find('http', url_string.find('/RU=') + 1)
 
    for ending in endings:
        endpos = url_string.rfind(ending)
        if endpos > -1:
            endpositions.append(endpos)
 
    if start == 0 or len(endpositions) == 0:
        return url_string
 
    end = min(endpositions)
    return unquote(url_string[start:end])
 
 

request()

searx.engines.yahoo.request	(		query,
			params )

build request

Definition at line 74 of file yahoo.py.

def request(query, params):
    """build request"""
 
    lang = locale_aliases.get(params['language'], None)
    if not lang:
        lang = params['language'].split('-')[0]
    lang = traits.get_language(lang, traits.all_locale)
 
    offset = (params['pageno'] - 1) * 7 + 1
    age, btf = time_range_dict.get(params['time_range'], ('', ''))
 
    args = urlencode(
        {
            'p': query,
            'ei': 'UTF-8',
            'fl': 1,
            'vl': 'lang_' + lang,
            'btf': btf,
            'fr2': 'time',
            'age': age,
            'b': offset,
            'xargs': 0,
        }
    )
 
    domain = lang2domain.get(lang, '%s.search.yahoo.com' % lang)
    params['url'] = 'https://%s/search?%s' % (domain, args)
    return params
 
 

response()

searx.engines.yahoo.response

(

resp

)

parse response

Definition at line 123 of file yahoo.py.

def response(resp):
    """parse response"""
 
    results = []
    dom = html.fromstring(resp.text)
 
    # parse results
    for result in eval_xpath_list(dom, '//div[contains(@class,"algo-sr")]'):
        url = eval_xpath_getindex(result, './/h3/a/@href', 0, default=None)
        if url is None:
            continue
        url = parse_url(url)
 
        title = eval_xpath_getindex(result, './/h3//a/@aria-label', 0, default='')
        title: str = extract_text(title)
        content = eval_xpath_getindex(result, './/div[contains(@class, "compText")]', 0, default='')
        content: str = extract_text(content, allow_none=True)
 
        # append result
        results.append(
            {
                'url': url,
                # title sometimes contains HTML tags / see
                # https://github.com/searxng/searxng/issues/3790
                'title': " ".join(html_to_text(title).strip().split()),
                'content': " ".join(html_to_text(content).strip().split()),
            }
        )
 
    for suggestion in eval_xpath_list(dom, '//div[contains(@class, "AlsoTry")]//table//a'):
        # append suggestion
        results.append({'suggestion': extract_text(suggestion)})
 
    return results
 
 

Variable Documentation

about

dict searx.engines.yahoo.about

Initial value:

=  {
    "website": 'https://search.yahoo.com/',
    "wikidata_id": None,
    "official_api_documentation": 'https://developer.yahoo.com/api/',
    "use_official_api": False,
    "require_api_key": False,
    "results": 'HTML',
}

Definition at line 26 of file yahoo.py.

categories

list searx.engines.yahoo.categories = ['general', 'web']

Definition at line 36 of file yahoo.py.

lang2domain

dict searx.engines.yahoo.lang2domain

Initial value:

=  {
    'zh_chs': 'hk.search.yahoo.com',
    'zh_cht': 'tw.search.yahoo.com',
    'any': 'search.yahoo.com',
    'en': 'search.yahoo.com',
    'bg': 'search.yahoo.com',
    'cs': 'search.yahoo.com',
    'da': 'search.yahoo.com',
    'el': 'search.yahoo.com',
    'et': 'search.yahoo.com',
    'he': 'search.yahoo.com',
    'hr': 'search.yahoo.com',
    'ja': 'search.yahoo.com',
    'ko': 'search.yahoo.com',
    'sk': 'search.yahoo.com',
    'sl': 'search.yahoo.com',
}

Definition at line 47 of file yahoo.py.

locale_aliases

dict searx.engines.yahoo.locale_aliases

Initial value:

=  {
    'zh': 'zh_Hans',
    'zh-HK': 'zh_Hans',
    'zh-CN': 'zh_Hans',  # dead since 2015 / routed to hk.search.yahoo.com
    'zh-TW': 'zh_Hant',
}

Definition at line 66 of file yahoo.py.

paging

bool searx.engines.yahoo.paging = True

Definition at line 37 of file yahoo.py.

time_range_dict

dict searx.engines.yahoo.time_range_dict

Initial value:

=  {
    'day': ('1d', 'd'),
    'week': ('1w', 'w'),
    'month': ('1m', 'm'),
}

Definition at line 41 of file yahoo.py.

time_range_support

bool searx.engines.yahoo.time_range_support = True

Definition at line 38 of file yahoo.py.