15 Commits

Author SHA1 Message Date
Sisyphus
28d3885764 [fix] naver: update HTML parsing for redesigned Naver search results page
Naver redesigned their search results page, replacing the old CSS classes
(lst_total, link_tit, total_dsc_wrap, api_txt_lines) with a new layout
using fds-web-doc-root containers and sds-comps design system.

Updated parse_general():
- Result container: fds-web-doc-root + fds-web-normal-doc-root
- Title: sds-comps-text-type-headline1 span
- URL: first external http link (with try/except guard)
- Content: sds-comps-text-type-body1 span
- Thumbnail: profile-thumbnail img src
- Added guard: skip results without title or URL
2026-06-29 20:25:23 +02:00
Hu Butui
b084194c09 [fix] engine baidu: fix image search blocked by antiFlag
Baidu image search returns antiFlag=1 when the acjson API is called
without session cookies from image.baidu.com.

Warm up cookies with a GET to the image homepage, cache them for one
hour via EngineCache, and pass them to image search requests. Raise
SearxEngineAccessDeniedException when antiFlag is still returned.

Signed-off-by: Hu Butui <hot123tea123@gmail.com>
2026-06-29 19:54:10 +02:00
Hu Butui
8c4df4cf3f [feat] bilibili engine: add time range support
Signed-off-by: Hu Butui <hot123tea123@gmail.com>
2026-06-29 19:53:20 +02:00
Bnyro
a0e594e16e [fix] neosearch: crashes when result has no url 2026-06-29 18:54:01 +02:00
Bnyro
cb4bfbe129 [chore] data.traits: update traits for neosearch 2026-06-29 13:05:01 +02:00
Bnyro
a5660bcc4f [feat] engines: add support for neosearch.org (general) 2026-06-29 13:05:01 +02:00
Bnyro
1396265774 [feat] engines: add magnific images engine 2026-06-29 10:19:19 +02:00
Bnyro
0fd40d5f29 [feat] engines: add shopify stock images engine 2026-06-29 10:02:16 +02:00
Bnyro
13a5ace8b5 [feat] engines: add stocksnap images engine 2026-06-29 10:02:04 +02:00
Bnyro
a6831797ba [feat] engines: add support for picjumbo.com 2026-06-29 10:01:43 +02:00
github-actions[bot]
0e990f78a3 [data] update searx.data - update_gsa_useragents.py (#6329) 2026-06-29 08:03:21 +02:00
github-actions[bot]
990c63b709 [data] update searx.data - update_currencies.py (#6333) 2026-06-29 07:09:12 +02:00
github-actions[bot]
e535e4c61a [data] update searx.data - update_firefox_version.py (#6332) 2026-06-29 07:08:32 +02:00
github-actions[bot]
79506441c5 [data] update searx.data - update_wikidata_units.py (#6330) 2026-06-29 07:08:02 +02:00
github-actions[bot]
6cb1c077e9 [data] update searx.data - update_ahmia_blacklist.py (#6331) 2026-06-29 07:07:28 +02:00
16 changed files with 6931 additions and 4535 deletions

File diff suppressed because it is too large Load Diff

View File

@@ -773,7 +773,7 @@
"nl": "Boliviaanse boliviano",
"oc": "Boliviano",
"pa": "ਬੋਲੀਵੀਆਨੋ",
"pl": "boliviano",
"pl": "boliwiano",
"pt": "Boliviano",
"ro": "boliviano",
"ru": "боливиано",
@@ -1107,7 +1107,7 @@
"fi": "Kongon frangi",
"fr": "franc congolais",
"ga": "franc an Chongó",
"gl": "Franco congolés",
"gl": "franco congolés",
"he": "פרנק קונגולזי",
"hr": "Kongoanski franak",
"hu": "kongói frank",
@@ -1636,7 +1636,7 @@
"fi": "Algerian dinaari",
"fr": "dinar algérien",
"ga": "dinar na hAilgéire",
"gl": "Dinar alxeriano",
"gl": "dinar alxeriano",
"he": "דינר אלג'ירי",
"hr": "Alžirski dinar",
"hu": "algériai dinár",
@@ -1651,7 +1651,7 @@
"pap": "dinar argelino",
"pl": "dinar algierski",
"pt": "dinar argelino",
"ro": "Dinar algerian",
"ro": "dinar algerian",
"ru": "алжирский динар",
"sk": "Alžírský dinár",
"sl": "alžirski dinar",
@@ -1786,7 +1786,7 @@
"cy": "Ewro",
"da": "Euro",
"de": "Euro",
"en": "Euro",
"en": "euro",
"eo": "eŭro",
"es": "Euro",
"et": "Euro",
@@ -1803,7 +1803,7 @@
"it": "Euro",
"ja": "ユーロ",
"ko": "유로",
"lt": "Euras",
"lt": "euras",
"lv": "eiro",
"ml": "യൂറോ",
"ms": "Euro",
@@ -2759,7 +2759,7 @@
"pa": "ਜਪਾਨੀ ਯੈੱਨ",
"pl": "jen",
"pt": "iene",
"ro": "yeni",
"ro": "yen",
"ru": "японская иена",
"sk": "jen",
"sl": "japonski jen",
@@ -3337,6 +3337,7 @@
"fi": "Libyan dinaari",
"fr": "dinar libyen",
"ga": "dinar na Libia",
"gl": "dinar libio",
"he": "דינר לובי ",
"hr": "Libijski dinar",
"hu": "líbiai dinár",
@@ -3539,6 +3540,7 @@
"ja": "チャット",
"ko": "미얀마 짯",
"lt": "Kijatas",
"lv": "Kjats",
"ml": "ബർമ്മീസ് ക്യാറ്റ്",
"nl": "Myanmarese kyat",
"oc": "Kyat",
@@ -4310,7 +4312,7 @@
"ar": "بيسو فلبيني",
"bg": "Филипинско песо",
"ca": "peso filipí",
"cs": "Filipínské peso",
"cs": "filipínské peso",
"de": "philippinischer Peso",
"en": "Philippine peso",
"eo": "filipina peso",
@@ -4614,7 +4616,7 @@
"fi": "Serbian dinaari",
"fr": "dinar serbe",
"ga": "Dinar na Seirbia",
"gl": "Dinar serbio",
"gl": "dinar serbio",
"he": "דינר סרבי",
"hr": "srpski dinar",
"hu": "szerb dinár",
@@ -5331,7 +5333,7 @@
"pa": "ਤਾਜਿਕਿਸਤਾਨੀ ਸੋਮੋਨੀ",
"pl": "Somoni",
"pt": "Somoni",
"ro": "Somoni tadjic",
"ro": "somoni tadjic",
"ru": "таджикский сомони",
"sk": "tadžický som",
"sl": "tadžikistanski somoni",
@@ -5394,6 +5396,7 @@
"fi": "Tunisian dinaari",
"fr": "dinar tunisien",
"ga": "dinar na Túinéise",
"gl": "dinar tunisiano",
"he": "דינר תוניסאי",
"hr": "tuniski dinar",
"hu": "tunéziai dinár",
@@ -5766,7 +5769,7 @@
"fi": "Uruguayn peso",
"fr": "peso uruguayen",
"ga": "peso Uragua",
"gl": "Peso uruguaio",
"gl": "peso uruguaio",
"he": "פסו של אורוגוואי",
"hr": "Urugvajski pezo",
"hu": "uruguayi peso",
@@ -6147,7 +6150,7 @@
"oc": "Drechs de tiratge Especials",
"pl": "specjalne prawa ciągnienia",
"pt": "direitos especiais de saque",
"ro": "Drepturi speciale de tragere",
"ro": "drepturi speciale de tragere",
"ru": "специальные права заимствования",
"sk": "Zvláštne práva čerpania",
"sl": "posebne pravice črpanja",
@@ -6225,6 +6228,7 @@
"ja": "CFPフラン",
"ko": "CFP 프랑",
"lt": "CFP frankas",
"lv": "Klusā okeāna franks",
"ms": "Franc CFP",
"nl": "CFP-frank",
"oc": "Franc CFP",
@@ -7055,6 +7059,7 @@
"bolivjano": "BOB",
"bolivya bolivianosu": "BOB",
"bolivya bolivyanosu": "BOB",
"boliwiano": "BOB",
"bolívar digital": "VED",
"bolívar soberano": "VES",
"bolívar sobirà": "VES",
@@ -8425,6 +8430,7 @@
"drame arménio": "AMD",
"dramm": "AMD",
"drechs de tiratge especials": "XDR",
"drept special de tragere": "XDR",
"drepturi speciale de tragere": "XDR",
"drets especials de gir": "XDR",
"droits de tirage speciaux": "XDR",
@@ -9518,6 +9524,8 @@
"kíp lào": "LAK",
"kīp": "LAK",
"kjat": "MMK",
"kjats": "MMK",
"klusā okeāna franks": "XPF",
"km": "BAM",
"kmf": "KMF",
"koeweitse dinar": "KWD",
@@ -10023,6 +10031,7 @@
"lire sterline": "GBP",
"lire turque": "TRY",
"lisente": "LSL",
"list of syrian coins": "SYP",
"liura de gibartar": "GIP",
"liura egipciana": "EGP",
"liura esterlina": "GBP",
@@ -11313,7 +11322,6 @@
"riel camboxano": "KHR",
"riel camboyano": "KHR",
"riel campuchia": "KHR",
"riel kambodżański": "KHR",
"riel kamboja": "KHR",
"riel na cambóide": "KHR",
"rietumāfrikas franks": "XOF",
@@ -12257,6 +12265,7 @@
"thaise baht": "THB",
"thajský baht": "THB",
"thb": "THB",
"the australian dollar": "AUD",
"thebe": "BWP",
"third belarusian ruble": "BYN",
"tical": "THB",
@@ -12740,6 +12749,7 @@
"yen": "JPY",
"yen giapponese": "JPY",
"yen japones": "JPY",
"yen japonez": "JPY",
"yen japonés": "JPY",
"yeni": "JPY",
"yeni i̇srail şekeli": "ILS",
@@ -12806,7 +12816,6 @@
"zimbabwe zig": "ZWG",
"zimbabwean dollar": "ZWL",
"zimbabwean gold": "ZWG",
"zimbabwean zig": "ZWG",
"zimbabwen kulta": "ZWG",
"zimbabwiansky zlatý": "ZWG",
"zimbabwský dolar": "ZWL",
@@ -12965,6 +12974,7 @@
"FKP",
"EGP"
],
"£S": "SYP",
"£e": "EGP",
"£s": "SYP",
"¥": [
@@ -14959,6 +14969,8 @@
"فورنت مجري": "HUF",
"فورينت مجري": "HUF",
"فِرَنْكٌ رُوَنْدِيٌّ": "RWF",
"قائمة النقود المعدنية السورية": "SYP",
"قائمة عملات سوريا المعدنية": "SYP",
"ك": "KWD",
"كتزال غواتيمالي": "GTQ",
"كرونة آيسلندية": "ISK",

View File

@@ -6544,6 +6544,103 @@
"to-TO": "to"
}
},
"neosearch": {
"all_locale": null,
"custom": {
"countrycodes": [
"AE",
"AM",
"AR",
"AT",
"AU",
"AZ",
"BE",
"BG",
"BH",
"BO",
"BR",
"BY",
"CA",
"CH",
"CL",
"CN",
"CO",
"CY",
"CZ",
"DE",
"DK",
"DZ",
"EC",
"EE",
"EG",
"ES",
"FI",
"FR",
"GB",
"GE",
"GH",
"GR",
"HK",
"HR",
"HU",
"ID",
"IE",
"IL",
"IN",
"IT",
"JO",
"JP",
"KE",
"KG",
"KR",
"KW",
"KZ",
"LB",
"LT",
"LU",
"LV",
"MA",
"MD",
"MT",
"MX",
"MY",
"NG",
"NL",
"NO",
"NZ",
"OM",
"PE",
"PH",
"PL",
"PT",
"PY",
"QA",
"RO",
"RU",
"SA",
"SE",
"SG",
"SI",
"SK",
"TH",
"TJ",
"TM",
"TN",
"TR",
"TW",
"UA",
"US",
"UY",
"UZ",
"VE",
"VN",
"ZA"
]
},
"data_type": "traits_v1",
"languages": {},
"regions": {}
},
"odysee": {
"all_locale": null,
"custom": {},
@@ -9585,4 +9682,4 @@
},
"regions": {}
}
}
}

File diff suppressed because it is too large Load Diff

View File

@@ -5,7 +5,7 @@
],
"ua": "Mozilla/5.0 ({os}; rv:{version}) Gecko/20100101 Firefox/{version}",
"versions": [
"151.0",
"150.0"
"152.0",
"151.0"
]
}

View File

@@ -3272,7 +3272,7 @@
"Q128822": {
"si_name": "Q182429",
"symbol": "kn",
"to_si_factor": 0.5144444444444445
"to_si_factor": 0.514
},
"Q12912288": {
"si_name": null,

View File

@@ -7,13 +7,17 @@
# There exits a https://github.com/ohblue/baidu-serp-api/
# but we don't use it here (may we can learn from).
import typing as t
from urllib.parse import urlencode
from datetime import datetime
from html import unescape
import time
import json
from searx.exceptions import SearxEngineAPIException, SearxEngineCaptchaException
from searx.exceptions import SearxEngineAPIException, SearxEngineCaptchaException, SearxEngineAccessDeniedException
from searx.enginelib import EngineCache
from searx.network import get as http_get
from searx.utils import html_to_text
about = {
@@ -35,6 +39,31 @@ baidu_category = 'general'
time_range_support = True
time_range_dict = {"day": 86400, "week": 604800, "month": 2592000, "year": 31536000}
image_base_url = "https://image.baidu.com/"
COOKIE_CACHE_KEY = "cookie"
COOKIE_CACHE_EXPIRATION_SECONDS = 3600
CACHE: EngineCache
"""Stores cookies from Baidu image search warmup."""
def setup(engine_settings: dict[str, t.Any]) -> bool:
global CACHE # pylint: disable=global-statement
CACHE = EngineCache(engine_settings["name"])
return True
def get_image_cookies(headers: dict[str, str]) -> dict[str, str]:
cookies: dict[str, str] | None = CACHE.get(COOKIE_CACHE_KEY)
if cookies:
return cookies
warmup = http_get(image_base_url, headers=headers, timeout=10)
cookies = dict(warmup.cookies.items())
CACHE.set(key=COOKIE_CACHE_KEY, value=cookies, expire=COOKIE_CACHE_EXPIRATION_SECONDS)
return cookies
def init(_):
if baidu_category not in ('general', 'images', 'it'):
@@ -88,6 +117,9 @@ def request(query, params):
if baidu_category == 'it':
query_params["paramList"] += f",timestamp_range={past}-{now}"
if baidu_category == 'images':
params["cookies"] = get_image_cookies(params["headers"])
params["url"] = f"{query_url}?{urlencode(query_params)}"
params["allow_redirects"] = False
return params
@@ -103,6 +135,8 @@ def response(resp):
# baidu's JSON encoder wrongly quotes / and ' characters by \\ and \'
text = text.replace(r"\/", "/").replace(r"\'", "'")
data = json.loads(text, strict=False)
if data.get("antiFlag") == 1:
raise SearxEngineAccessDeniedException(data.get("message", "Forbid spider access"))
parsers = {'general': parse_general, 'images': parse_images, 'it': parse_it}
return parsers[baidu_category](data)

View File

@@ -8,6 +8,7 @@ import random
import string
from urllib.parse import urlencode
from datetime import datetime, timedelta
from zoneinfo import ZoneInfo
from searx import utils
@@ -39,6 +40,32 @@ cookie = {
"home_feed_column": "4",
}
_CN_TZ = ZoneInfo("Asia/Shanghai")
# Calendar-day time filter (Asia/Shanghai); dict values are days to subtract from today.
time_range_support = True
time_range_dict = {"day": 0, "week": 6, "month": 29, "year": 364}
def _pubtime_range(time_range: str) -> tuple[int, int]:
"""Return ``(pubtime_begin_s, pubtime_end_s)`` for Bilibili's search API.
Time ranges follow Bilibili's website semantics: they are counted in
**calendar days** in China Standard Time (``Asia/Shanghai``), not as
sliding 24-hour windows. For example, ``day`` means from 00:00:00 to
23:59:59 of the current local day; ``week`` spans from 00:00:00 on the
calendar day six days ago through the end of today, and so on.
The returned Unix timestamps (seconds) map to Bilibili's
``pubtime_begin_s`` and ``pubtime_end_s`` query parameters.
"""
now = datetime.now(_CN_TZ)
pubtime_end_s = int(now.replace(hour=23, minute=59, second=59, microsecond=0).timestamp())
begin_day = now - timedelta(days=time_range_dict[time_range])
pubtime_begin_s = int(begin_day.replace(hour=0, minute=0, second=0, microsecond=0).timestamp())
return pubtime_begin_s, pubtime_end_s
def request(query, params):
query_params = {
@@ -50,6 +77,11 @@ def request(query, params):
"search_type": "video",
}
if params.get("time_range") in time_range_dict:
pubtime_begin_s, pubtime_end_s = _pubtime_range(params["time_range"])
query_params["pubtime_begin_s"] = pubtime_begin_s
query_params["pubtime_end_s"] = pubtime_end_s
params["url"] = f"{base_url}?{urlencode(query_params)}"
params["headers"]["Referer"] = "https://www.bilibili.com/"
params["headers"]["Accept"] = "application/json, text/javascript, */*; q=0.01"

62
searx/engines/magnific.py Normal file
View File

@@ -0,0 +1,62 @@
# SPDX-License-Identifier: AGPL-3.0-or-later
"""Magnific_ is a database for images.
.. _Magnific: https://www.magnific.com
"""
from urllib.parse import urlencode
import typing as t
from searx.result_types import EngineResults
if t.TYPE_CHECKING:
from searx.extended_types import SXNG_Response
from searx.search.processors import OnlineParams
about = {
"website": "https://www.magnific.com",
"wikidata_id": "Q104211654",
"official_api_documentation": None,
"use_official_api": False,
"require_api_key": False,
"results": "JSON",
}
base_url = "https://www.magnific.com"
categories = ["images"]
paging = True
free_images_only = True
"""
Whether to only load images that may be used for free, without a Magnific account.
"""
def request(query: str, params: "OnlineParams") -> None:
args = {"term": query, "filters[ai-generated][excluded]": 1, "page": params["pageno"], "locale": "en"}
if free_images_only:
args["filters[license]"] = "free"
params["headers"]["Referer"] = f"{base_url}/search"
params["url"] = f"{base_url}/api/regular/search?{urlencode(args)}"
def response(resp: "SXNG_Response"):
res = EngineResults()
result: dict[str, t.Any] # TBH: dict[str, t.Any]
for result in resp.json()["items"]:
res.add(
res.types.Image(
title=result["name"],
url=result["url"],
thumbnail_src=result["preview"]["url"],
img_src=result["preview"]["url"],
resolution=f"{result['preview']['width']}x{result['preview']['height']}",
)
)
return res

View File

@@ -99,23 +99,35 @@ def parse_general(data):
dom = html.fromstring(data)
for item in eval_xpath_list(dom, "//ul[contains(@class, 'lst_total')]/li[contains(@class, 'bx')]"):
thumbnail = None
for item in eval_xpath_list(dom, "//div[contains(@class, 'fds-web-normal-doc-root')]"):
thumbnail = extract_text(
eval_xpath(
item,
".//div[contains(@class, 'sds-comps-image') and not(contains(@class, 'sds-comps-image-circle'))]/img/@src",
)
)
title = extract_text(eval_xpath(item, ".//span[contains(@class, 'sds-comps-text-type-headline1')]"))
url = None
try:
thumbnail = eval_xpath_getindex(item, ".//div[contains(@class, 'thumb_single')]//img/@data-lazysrc", 0)
url = eval_xpath_getindex(
item, ".//a[starts-with(@href, 'http') and not(contains(@href, 'keep.naver.com'))]/@href", 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,
content = extract_text(eval_xpath(item, ".//span[contains(@class, 'sds-comps-text-type-body1')]"))
if title and url:
results.add(
MainResult(
title=title,
url=url,
content=content or "",
thumbnail=thumbnail or "",
)
)
)
return results
@@ -173,7 +185,7 @@ def parse_news(data):
title=title,
url=url,
content=content,
thumbnail=thumbnail,
thumbnail=thumbnail or "",
)
)
@@ -196,7 +208,7 @@ def parse_videos(data):
length = None
try:
length = parse_duration_string(extract_text(eval_xpath(item, ".//span[contains(@class, 'time')]")))
length = parse_duration_string(extract_text(eval_xpath(item, ".//span[contains(@class, 'time')]")) or "")
except (ValueError, TypeError):
pass

View File

@@ -0,0 +1,92 @@
# SPDX-License-Identifier: AGPL-3.0-or-later
"""Neosearch_ aims to be a privacy-first alternative to Google.
.. _Neosearch: https://neosearch.org/About
"""
from json import loads
import typing as t
from urllib.parse import urlencode
from searx.extended_types import SXNG_Response
from searx.result_types import EngineResults
if t.TYPE_CHECKING:
from searx.enginelib.traits import EngineTraits
from searx.search.processors import OnlineParams
traits: EngineTraits
about = {
"website": "https://neosearch.org",
"official_api_documentation": None,
"use_official_api": False,
"require_api_key": False,
"results": "JSON",
}
base_url = "https://neosearch.org"
categories = ["general"]
paging = False
def request(query: str, params: "OnlineParams"):
args = {"q": query, "generate": "auto"}
countrycode = params["searxng_locale"].split("-")[-1].upper()
if countrycode in traits.custom["countrycodes"]:
args["loc"] = countrycode
params["url"] = f"{base_url}/search?{urlencode(args)}"
def response(resp: "SXNG_Response") -> EngineResults:
res = EngineResults()
# first line contains something like `{"location": "de"}`
# second line contains the actual results
json_resp = loads(resp.text.splitlines()[-1])
for lens in json_resp["lenses"]:
for category in lens["categories"]:
for result in category["links"]:
if not result["url"]:
continue
res.add(
res.types.MainResult(
url=result["url"],
title=result["title"],
content=result["snippet"] or result["description"],
)
)
for suggestion in json_resp.get("suggestions", []):
res.add(res.types.LegacyResult(suggestion=suggestion))
return res
def fetch_traits(engine_traits: "EngineTraits") -> None:
# pylint: disable=import-outside-toplevel
from searx.network import get
from searx.utils import extr, js_obj_str_to_python
from babel.core import get_global
resp = get(base_url)
locations_js_raw = extr(resp.text, "const LOCATIONS = ", ";")
if not locations_js_raw:
raise RuntimeError("failed to find locations in neosearch HTML response")
locations: list[dict[str, str]] = js_obj_str_to_python(locations_js_raw)
babel_reg_list = get_global("territory_languages").keys()
countrycodes: list[str] = []
for loc in locations:
_reg = loc["code"].upper()
if _reg not in babel_reg_list:
print(f"ERROR: region tag {_reg} is unknown by babel")
continue
countrycodes.append(_reg)
countrycodes.sort()
engine_traits.custom["countrycodes"] = countrycodes

63
searx/engines/picjumbo.py Normal file
View File

@@ -0,0 +1,63 @@
# SPDX-License-Identifier: AGPL-3.0-or-later
"""Picjumbo_ provides free stock photos.
.. _Picjumbo: https://picjumbo.com
"""
from urllib.parse import urlparse, urlunparse
import typing as t
from lxml import html
from searx.result_types import EngineResults
from searx.utils import eval_xpath, eval_xpath_list, extract_text
if t.TYPE_CHECKING:
from searx.extended_types import SXNG_Response
from searx.search.processors import OnlineParams
about = {
"website": "https://picjumbo.com",
"wikidata_id": None,
"official_api_documentation": None,
"use_official_api": False,
"require_api_key": False,
"results": "HTML",
}
base_url = "https://picjumbo.com"
categories = ["images"]
paging = True
def request(query: str, params: "OnlineParams") -> None:
params["url"] = f"{base_url}/search/{query}/page/{params['pageno']}"
def _get_max_res_url(url: str) -> str:
"""Get the maximum resolution of the image based on the thumbnail URL."""
parsed_url = urlparse(url)
max_res_url = parsed_url._replace(query="w=10000&quality=100")
return urlunparse(max_res_url)
def response(resp: "SXNG_Response"):
res = EngineResults()
doc = html.fromstring(resp.text)
for result in eval_xpath_list(doc, "//div[contains(@class, 'photo_query')]/div[contains(@class, 'photo_item')]"):
thumbnail = extract_text(eval_xpath(result, ".//img[contains(@class, 'image')]/@src")) or ""
res.add(
res.types.Image(
url=extract_text(eval_xpath(result, ".//a[contains(@class, 'image')]/@href")) or "",
title=extract_text(eval_xpath(result, ".//h3")) or "",
content=extract_text(eval_xpath(result, ".//meta[@itemprop='keywords']/@content")) or "",
thumbnail_src=thumbnail,
img_src=_get_max_res_url(thumbnail),
)
)
return res

View File

@@ -0,0 +1,62 @@
# SPDX-License-Identifier: AGPL-3.0-or-later
"""Shopify stock photos provides royalty-free images, intended for use with
Shopify.
"""
import typing as t
from urllib.parse import urlencode
from lxml import html
from searx.result_types import EngineResults
from searx.utils import eval_xpath, eval_xpath_list, extract_text
if t.TYPE_CHECKING:
from searx.extended_types import SXNG_Response
from searx.search.processors import OnlineParams
about = {
"website": "https://www.shopify.com/stock-photos",
"wikidata_id": None,
"official_api_documentation": None,
"use_official_api": False,
"require_api_key": False,
"results": "HTML",
}
base_url = "https://www.shopify.com"
categories = ["images"]
paging = True
def request(query: str, params: "OnlineParams") -> None:
args = {"q": query, "page": params["pageno"]}
params["url"] = f"{base_url}/stock-photos/photos/search?{urlencode(args)}"
def _get_download_url(url: str) -> str:
"""Get the link to the full quality image."""
query_start = url.find("?")
return url[:query_start] + "/download?quality=premium"
def response(resp: "SXNG_Response"):
res = EngineResults()
doc = html.fromstring(resp.text)
for result in eval_xpath_list(doc, "//div[contains(@class, 'js-masonry-grid')]/div"):
url = base_url + (extract_text(eval_xpath(result, ".//a[contains(@class, 'photo-tile')]/@href")) or "")
res.add(
res.types.Image(
url=url,
title=extract_text(eval_xpath(result, ".//p[contains(@class, 'photo-tile__title')]")) or "",
thumbnail_src=extract_text(eval_xpath(result, ".//img[contains(@class, 'photo-card__image')]/@src"))
or "",
img_src=_get_download_url(url),
)
)
return res

View File

@@ -0,0 +1,55 @@
# SPDX-License-Identifier: AGPL-3.0-or-later
"""Stocksnap_ is a search engine for CC0-licensed images.
.. _Stocksnap: https://stocksnap.io
"""
import typing as t
from searx.result_types import EngineResults
if t.TYPE_CHECKING:
from searx.extended_types import SXNG_Response
from searx.search.processors import OnlineParams
about = {
"website": "https://stocksnap.io",
"wikidata_id": None,
"official_api_documentation": None,
"use_official_api": False,
"require_api_key": False,
"results": "JSON",
}
# otherwise all requests get blocked, probably HTTP2 fingerprinting
enable_http2 = False
base_url = "https://stocksnap.io"
cdn_url = "https://cdn.stocksnap.io"
categories = ["images"]
paging = True
def request(query: str, params: "OnlineParams") -> None:
params["url"] = f"{base_url}/api/search-photos/{query}/relevance/desc/{params['pageno']}"
def response(resp: "SXNG_Response"):
res = EngineResults()
result: dict[str, str] # TBH: dict[str, t.Any]
for result in resp.json()["results"]:
slug = "-".join(result['keywords'][:1]) + "-" + result["img_id"]
res.add(
res.types.Image(
title=result["tags"],
url=f"{base_url}/photo/{slug}",
thumbnail_src=f"{cdn_url}/img-thumbs/280h/{result['img_id']}.jpg",
img_src=f"{cdn_url}/img-thumbs/960w/{result['img_id']}.jpg",
img_format="JPEG",
resolution=f"{result['img_width']}x{result['img_height']}",
)
)
return res

View File

@@ -1585,6 +1585,11 @@ engines:
disabled: true
inactive: true
- name: magnific
engine: magnific
shortcut: mag
disabled: true
- name: marginalia
engine: marginalia
shortcut: mar
@@ -1857,6 +1862,11 @@ engines:
engine: photon
shortcut: ph
- name: picjumbo
engine: picjumbo
shortcut: pj
disabled: true
- name: pinterest
engine: pinterest
shortcut: pin
@@ -2165,6 +2175,11 @@ engines:
engine: sepiasearch
shortcut: sep
- name: shopify stock
engine: shopify_stock
shortcut: shs
disabled: true
- name: sogou
engine: sogou
shortcut: sogou
@@ -2195,6 +2210,11 @@ engines:
api_site: 'stackoverflow'
categories: [it, q&a]
- name: stocksnap
engine: stocksnap
shortcut: sto
disabled: true
- name: askubuntu
engine: stackexchange
shortcut: ubuntu
@@ -2834,6 +2854,12 @@ engines:
shortcut: nvrv
disabled: true
- name: neosearch
engine: neosearch
shortcut: neo
disabled: true
inactive: true
- name: rubygems
shortcut: rbg
engine: xpath

View File

@@ -74,6 +74,8 @@ sxng_locales = (
('ja-JP', '日本語', '日本', 'Japanese', '\U0001f1ef\U0001f1f5'),
('ko', '한국어', '', 'Korean', '\U0001f310'),
('ko-KR', '한국어', '대한민국', 'Korean', '\U0001f1f0\U0001f1f7'),
('mi', 'Māori', '', 'Māori', '\U0001f310'),
('mi-NZ', 'Māori', 'Aotearoa', 'Māori', '\U0001f1f3\U0001f1ff'),
('nb', 'Norsk Bokmål', '', 'Norwegian Bokmål', '\U0001f310'),
('nb-NO', 'Norsk Bokmål', 'Norge', 'Norwegian Bokmål', '\U0001f1f3\U0001f1f4'),
('nl', 'Nederlands', '', 'Dutch', '\U0001f310'),