Functions
	init (_)
	request (query, params)
EngineResults	response (resp)
	parse_general (data)
	parse_images (data)
	parse_news (data)
	parse_videos (data)

Variables
dict	about
list	categories = []
bool	paging = True
bool	time_range_support = True
dict	time_range_dict = {"day": "1d", "week": "1w", "month": "1m", "year": "1y"}
str	base_url = "https://search.naver.com"
str	naver_category = "general"
dict	naver_category_dict

Detailed Description

Naver for SearXNG

Function Documentation

◆ init()

searx.engines.naver.init ( _ )

Definition at line 70 of file naver.py.

def init(_):
    if naver_category not in ('general', 'images', 'news', 'videos'):
        raise SearxEngineAPIException(f"Unsupported category: {naver_category}")
 
 

◆ parse_general()

searx.engines.naver.parse_general ( data )

Definition at line 97 of file naver.py.

def parse_general(data):
    results = EngineResults()
 
    dom = html.fromstring(data)
 
    for item in eval_xpath_list(dom, "//ul[contains(@class, 'lst_total')]/li[contains(@class, 'bx')]"):
        thumbnail = None
        try:
            thumbnail = eval_xpath_getindex(item, ".//div[contains(@class, 'thumb_single')]//img/@data-lazysrc", 0)
        except (ValueError, TypeError, SearxEngineXPathException):
            pass
 
        results.add(
            MainResult(
                title=extract_text(eval_xpath(item, ".//a[contains(@class, 'link_tit')]")),
                url=eval_xpath_getindex(item, ".//a[contains(@class, 'link_tit')]/@href", 0),
                content=extract_text(
                    eval_xpath(item, ".//div[contains(@class, 'total_dsc_wrap')]//a[contains(@class, 'api_txt_lines')]")
                ),
                thumbnail=thumbnail,
            )
        )
 
    return results
 
 

◆ parse_images()

searx.engines.naver.parse_images ( data )

Definition at line 123 of file naver.py.

def parse_images(data):
    results = []
 
    match = extr(data, '<script>var imageSearchTabData=', '</script>')
    if match:
        json = js_variable_to_python(match.strip())
        items = json.get('content', {}).get('items', [])
 
        for item in items:
            results.append(
                {
                    "template": "images.html",
                    "url": item.get('link'),
                    "thumbnail_src": item.get('thumb'),
                    "img_src": item.get('originalUrl'),
                    "title": html_to_text(item.get('title')),
                    "source": item.get('source'),
                    "resolution": f"{item.get('orgWidth')} x {item.get('orgHeight')}",
                }
            )
 
    return results
 
 

◆ parse_news()

searx.engines.naver.parse_news ( data )

Definition at line 147 of file naver.py.

def parse_news(data):
    results = EngineResults()
    dom = html.fromstring(data)
 
    for item in eval_xpath_list(
        dom, "//div[contains(@class, 'sds-comps-base-layout') and contains(@class, 'sds-comps-full-layout')]"
    ):
        title = extract_text(eval_xpath(item, ".//span[contains(@class, 'sds-comps-text-type-headline1')]/text()"))
 
        url = eval_xpath_getindex(item, ".//a[@href and @nocr='1']/@href", 0)
 
        content = extract_text(eval_xpath(item, ".//span[contains(@class, 'sds-comps-text-type-body1')]"))
 
        thumbnail = None
        try:
            thumbnail = eval_xpath_getindex(
                item,
                ".//div[contains(@class, 'sds-comps-image') and contains(@class, 'sds-rego-thumb-overlay')]//img[@src]/@src",
                0,
            )
        except (ValueError, TypeError, SearxEngineXPathException):
            pass
 
        if title and content and url:
            results.add(
                MainResult(
                    title=title,
                    url=url,
                    content=content,
                    thumbnail=thumbnail,
                )
            )
 
    return results
 
 

◆ parse_videos()

searx.engines.naver.parse_videos ( data )

Definition at line 183 of file naver.py.

def parse_videos(data):
    results = []
 
    dom = html.fromstring(data)
 
    for item in eval_xpath_list(dom, "//li[contains(@class, 'video_item')]"):
        url = eval_xpath_getindex(item, ".//a[contains(@class, 'info_title')]/@href", 0)
 
        thumbnail = None
        try:
            thumbnail = eval_xpath_getindex(item, ".//img[contains(@class, 'thumb')]/@src", 0)
        except (ValueError, TypeError, SearxEngineXPathException):
            pass
 
        length = None
        try:
            length = parse_duration_string(extract_text(eval_xpath(item, ".//span[contains(@class, 'time')]")))
        except (ValueError, TypeError):
            pass
 
        results.append(
            {
                "template": "videos.html",
                "title": extract_text(eval_xpath(item, ".//a[contains(@class, 'info_title')]")),
                "url": url,
                "thumbnail": thumbnail,
                "length": length,
                "iframe_src": get_embeded_stream_url(url),
            }
        )
 
    return results

◆ request()

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

Definition at line 75 of file naver.py.

def request(query, params):
    query_params = {
        "query": query,
    }
 
    if naver_category in naver_category_dict:
        query_params["start"] = (params["pageno"] - 1) * naver_category_dict[naver_category]["start"] + 1
        query_params["where"] = naver_category_dict[naver_category]["where"]
 
    if params["time_range"] in time_range_dict:
        query_params["nso"] = f"p:{time_range_dict[params['time_range']]}"
 
    params["url"] = f"{base_url}/search.naver?{urlencode(query_params)}"
    return params
 
 

◆ response()

EngineResults searx.engines.naver.response ( resp )

Definition at line 91 of file naver.py.

def response(resp) -> EngineResults:
    parsers = {'general': parse_general, 'images': parse_images, 'news': parse_news, 'videos': parse_videos}
 
    return parsers[naver_category](resp.text)

Variable Documentation

◆ about

dict searx.engines.naver.about

Initial value:

=  {
    "website": "https://search.naver.com",
    "wikidata_id": "Q485639",
    "use_official_api": False,
    "require_api_key": False,
    "results": "HTML",
    "language": "ko",
}

Definition at line 23 of file naver.py.

◆ base_url

str searx.engines.naver.base_url = "https://search.naver.com"

Definition at line 38 of file naver.py.

◆ categories

list searx.engines.naver.categories = []

Definition at line 32 of file naver.py.

◆ naver_category

str searx.engines.naver.naver_category = "general"

Definition at line 40 of file naver.py.

◆ naver_category_dict

dict searx.engines.naver.naver_category_dict

Initial value:

=  {
    "general": {
        "start": 15,
        "where": "web",
    },
    "images": {
        "start": 50,
        "where": "image",
    },
    "news": {
        "start": 10,
        "where": "news",
    },
    "videos": {
        "start": 48,
        "where": "video",
    },
}

Definition at line 50 of file naver.py.

◆ paging

bool searx.engines.naver.paging = True

Definition at line 33 of file naver.py.

◆ time_range_dict

dict searx.engines.naver.time_range_dict = {"day": "1d", "week": "1w", "month": "1m", "year": "1y"}

Definition at line 36 of file naver.py.

◆ time_range_support

bool searx.engines.naver.time_range_support = True

Definition at line 35 of file naver.py.

Functions

Variables