Merge f49d1a9b90 into 10d3af84b8

The query string send to DDG must not be qouted.

The query string was URL-qouted in #4011, but the URL-qouted query string result
in unexpected *URL decoded* and other garbish results as reported in #4019
and #4020.  To test compare the results of a query like::

    !ddg Häuser und Straßen :de
    !ddg Häuser und Straßen :all
    !ddg 房屋和街道 :all
    !ddg 房屋和街道 :zh

Closed:

- [#4019] https://github.com/searxng/searxng/issues/4019
- [#4020] https://github.com/searxng/searxng/issues/4020

Related:

- [#4011] https://github.com/searxng/searxng/pull/4011

Signed-off-by: Markus Heiser <markus.heiser@darmarit.de>

requirements.txt

@@ -1,7 +1,7 @@
 certifi==2024.8.30
 babel==2.16.0
 flask-babel==4.0.0
-flask==3.0.3
+flask==3.1.0
 jinja2==3.1.4
 lxml==5.3.0
 pygments==2.18.0

searx/engines/duckduckgo.py

@@ -245,10 +245,12 @@ def request(query, params):
 
     # Advanced search syntax ends in CAPTCHA
     # https://duckduckgo.com/duckduckgo-help-pages/results/syntax/
-    query = [
+    query = " ".join(
+        [
             x.removeprefix("site:").removeprefix("intitle:").removeprefix("inurl:").removeprefix("filetype:")
             for x in query.split()
         ]
+    )
     eng_region = traits.get_region(params['searxng_locale'], traits.all_locale)
     if eng_region == "wt-wt":
         # https://html.duckduckgo.com/html sets an empty value for "all".
@@ -379,7 +381,11 @@ def response(resp):
     zero_click_info_xpath = '//div[@id="zero_click_abstract"]'
     zero_click = extract_text(eval_xpath(doc, zero_click_info_xpath)).strip()
 
-    if zero_click and "Your IP address is" not in zero_click and "Your user agent:" not in zero_click:
+    if zero_click and (
+        "Your IP address is" not in zero_click
+        and "Your user agent:" not in zero_click
+        and "URL Decoded:" not in zero_click
+    ):
         current_query = resp.search_params["data"].get("q")
 
         results.append(

searx/search/checker/impl.py

@@ -2,11 +2,11 @@
 # pylint: disable=missing-module-docstring, invalid-name
 
 import gc
+import time
 import typing
 import types
 import functools
 import itertools
-from time import time
 from timeit import default_timer
 from urllib.parse import urlparse
 
@@ -66,15 +66,15 @@ def _download_and_check_if_image(image_url: str) -> bool:
     This function should not be called directly: use _is_url_image
     otherwise the cache of functools.lru_cache contains data: URL which might be huge.
     """
-    retry = 2
+    retry = 3
 
     while retry > 0:
-        a = time()
+        a = default_timer()
         try:
             # use "image_proxy" (avoid HTTP/2)
+            network.set_timeout_for_thread(2)
             network.set_context_network_name('image_proxy')
-            r, stream = network.stream(
-                'GET',
+            r = network.get(
                 image_url,
                 timeout=10.0,
                 allow_redirects=True,
@@ -90,19 +90,20 @@ def _download_and_check_if_image(image_url: str) -> bool:
                     'Cache-Control': 'max-age=0',
                 },
             )
-            r.close()
             if r.status_code == 200:
                 is_image = r.headers.get('content-type', '').startswith('image/')
             else:
                 is_image = False
             del r
-            del stream
             return is_image
         except httpx.TimeoutException:
-            logger.error('Timeout for %s: %i', image_url, int(time() - a))
+            logger.error('Timeout for %s: %i', image_url, int(default_timer() - a))
+            time.sleep(1)
             retry -= 1
-        except httpx.HTTPError:
-            logger.exception('Exception for %s', image_url)
+        except httpx.HTTPStatusError as e:
+            logger.error('Exception for %s: HTTP status=%i', image_url, e.response.status_code)
+        except httpx.HTTPError as e:
+            logger.error('Exception for %s: %s, %s', image_url, e.__class__.__name__, ",".join(e.args))
             return False
     return False
 

searx/translations/es/LC_MESSAGES/messages.po

@@ -39,7 +39,7 @@ msgstr ""
 "Project-Id-Version: searx\n"
 "Report-Msgid-Bugs-To: EMAIL@ADDRESS\n"
 "POT-Creation-Date: 2024-10-05 06:24+0000\n"
-"PO-Revision-Date: 2024-11-03 09:08+0000\n"
+"PO-Revision-Date: 2024-11-14 14:07+0000\n"
 "Last-Translator: return42 <return42@users.noreply.translate.codeberg.org>\n"
 "Language-Team: Spanish <https://translate.codeberg.org/projects/searxng/"
 "searxng/es/>\n"
@@ -1249,7 +1249,7 @@ msgstr "Buscador de favicon"
 
 #: searx/templates/simple/preferences/favicon.html:15
 msgid "Display favicons near search results"
-msgstr ""
+msgstr "Mostrar los favicons al lado de los resultados de búsqueda"
 
 #: searx/templates/simple/preferences/footer.html:2
 msgid ""

searx/translations/it/LC_MESSAGES/messages.po

@@ -28,13 +28,14 @@
 # unoyoa <unoyoa@users.noreply.translate.codeberg.org>, 2024.
 # tiziodcaio <tiziodcaio@users.noreply.translate.codeberg.org>, 2024.
 # Fabio_Perri <Fabio_Perri@users.noreply.translate.codeberg.org>, 2024.
+# lrnz2 <lrnz2@users.noreply.translate.codeberg.org>, 2024.
 msgid ""
 msgstr ""
 "Project-Id-Version: searx\n"
 "Report-Msgid-Bugs-To: EMAIL@ADDRESS\n"
 "POT-Creation-Date: 2024-10-05 06:24+0000\n"
-"PO-Revision-Date: 2024-10-08 13:41+0000\n"
-"Last-Translator: return42 <return42@users.noreply.translate.codeberg.org>\n"
+"PO-Revision-Date: 2024-11-14 02:16+0000\n"
+"Last-Translator: lrnz2 <lrnz2@users.noreply.translate.codeberg.org>\n"
 "Language-Team: Italian <https://translate.codeberg.org/projects/searxng/"
 "searxng/it/>\n"
 "Language: it\n"
@@ -42,13 +43,13 @@ msgstr ""
 "Content-Type: text/plain; charset=utf-8\n"
 "Content-Transfer-Encoding: 8bit\n"
 "Plural-Forms: nplurals=2; plural=n != 1;\n"
-"X-Generator: Weblate 5.7.2\n"
+"X-Generator: Weblate 5.8.1\n"
 "Generated-By: Babel 2.16.0\n"
 
 #. CONSTANT_NAMES['NO_SUBGROUPING']
 #: searx/searxng.msg
 msgid "without further subgrouping"
-msgstr "senza altri sottogruppi"
+msgstr "senza altri sottogruppamenti"
 
 #. CONSTANT_NAMES['DEFAULT_CATEGORY']
 #: searx/searxng.msg
@@ -73,7 +74,7 @@ msgstr "musica"
 #. CATEGORY_NAMES['SOCIAL_MEDIA']
 #: searx/searxng.msg
 msgid "social media"
-msgstr "social"
+msgstr "social media"
 
 #. CATEGORY_NAMES['IMAGES']
 #: searx/searxng.msg
@@ -113,7 +114,7 @@ msgstr "mappa"
 #. CATEGORY_NAMES['ONIONS']
 #: searx/searxng.msg
 msgid "onions"
-msgstr "onion"
+msgstr "cipolle"
 
 #. CATEGORY_NAMES['SCIENCE']
 #: searx/searxng.msg
@@ -133,7 +134,7 @@ msgstr "dizionari"
 #. CATEGORY_GROUPS['LYRICS']
 #: searx/searxng.msg
 msgid "lyrics"
-msgstr "testi musicali"
+msgstr "testo musicale"
 
 #. CATEGORY_GROUPS['PACKAGES']
 #: searx/searxng.msg
@@ -148,12 +149,12 @@ msgstr "d&r"
 #. CATEGORY_GROUPS['REPOS']
 #: searx/searxng.msg
 msgid "repos"
-msgstr "ripostigli"
+msgstr "repos"
 
 #. CATEGORY_GROUPS['SOFTWARE_WIKIS']
 #: searx/searxng.msg
 msgid "software wikis"
-msgstr "wiki software"
+msgstr "wiki del software"
 
 #. CATEGORY_GROUPS['WEB']
 #: searx/searxng.msg
@@ -193,7 +194,7 @@ msgstr "Tempo di attività"
 #. BRAND_CUSTOM_LINKS['ABOUT']
 #: searx/searxng.msg searx/templates/simple/base.html:50
 msgid "About"
-msgstr "A proposito"
+msgstr "Al riguardo"
 
 #. WEATHER_TERMS['AVERAGE TEMP.']
 #: searx/engines/wttr.py:32 searx/searxng.msg

searx/translations/nb_NO/LC_MESSAGES/messages.po

@@ -11,13 +11,14 @@
 # omfj <omfj@users.noreply.translate.codeberg.org>, 2024.
 # combwizard <combwizard@users.noreply.translate.codeberg.org>, 2024.
 # laaknor <laaknor@users.noreply.translate.codeberg.org>, 2024.
+# Aadniz <Aadniz@users.noreply.translate.codeberg.org>, 2024.
 msgid ""
 msgstr ""
 "Project-Id-Version: PROJECT VERSION\n"
 "Report-Msgid-Bugs-To: EMAIL@ADDRESS\n"
 "POT-Creation-Date: 2024-10-05 06:24+0000\n"
-"PO-Revision-Date: 2024-11-03 09:08+0000\n"
-"Last-Translator: laaknor <laaknor@users.noreply.translate.codeberg.org>\n"
+"PO-Revision-Date: 2024-11-09 12:07+0000\n"
+"Last-Translator: Aadniz <Aadniz@users.noreply.translate.codeberg.org>\n"
 "Language-Team: Norwegian Bokmål <https://translate.codeberg.org/projects/"
 "searxng/searxng/nb_NO/>\n"
 "Language: nb_NO\n"
@@ -192,13 +193,13 @@ msgstr "Skydekke"
 #: searx/engines/duckduckgo_weather.py:45 searx/engines/wttr.py:51
 #: searx/searxng.msg
 msgid "Condition"
-msgstr ""
+msgstr "Betingelse"
 
 #. WEATHER_TERMS['CURRENT CONDITION']
 #: searx/engines/duckduckgo_weather.py:118 searx/engines/wttr.py:104
 #: searx/searxng.msg
 msgid "Current condition"
-msgstr ""
+msgstr "Nåværende betingelse"
 
 #. WEATHER_TERMS['EVENING']
 #: searx/engines/wttr.py:100 searx/searxng.msg
@@ -221,13 +222,13 @@ msgstr "Luftfuktighet"
 #: searx/engines/duckduckgo_weather.py:77 searx/engines/wttr.py:34
 #: searx/searxng.msg
 msgid "Max temp."
-msgstr ""
+msgstr "Maks temp."
 
 #. WEATHER_TERMS['MIN TEMP.']
 #: searx/engines/duckduckgo_weather.py:73 searx/engines/wttr.py:33
 #: searx/searxng.msg
 msgid "Min temp."
-msgstr ""
+msgstr "Min temp."
 
 #. WEATHER_TERMS['MORNING']
 #: searx/engines/wttr.py:100 searx/searxng.msg
@@ -334,17 +335,17 @@ msgstr "opphavsmann"
 #. SOCIAL_MEDIA_TERMS['THREAD OPEN']
 #: searx/engines/discourse.py:149 searx/searxng.msg
 msgid "open"
-msgstr ""
+msgstr "åpen"
 
 #. SOCIAL_MEDIA_TERMS['THREAD CLOSED']
 #: searx/engines/discourse.py:149 searx/searxng.msg
 msgid "closed"
-msgstr ""
+msgstr "lukket"
 
 #. SOCIAL_MEDIA_TERMS['THREAD ANSWERED']
 #: searx/engines/discourse.py:160 searx/searxng.msg
 msgid "answered"
-msgstr ""
+msgstr "svart på"
 
 #: searx/webapp.py:332
 msgid "No item found"
@@ -421,7 +422,7 @@ msgstr "tilgang nektet"
 
 #: searx/webutils.py:60
 msgid "server API error"
-msgstr "Tjener-API-feil"
+msgstr "server API feil"
 
 #: searx/webutils.py:79
 msgid "Suspended"
@@ -453,7 +454,7 @@ msgstr "Regn ut {functions} av parameterne"
 
 #: searx/engines/mozhi.py:57
 msgid "Synonyms"
-msgstr ""
+msgstr "Synonymer"
 
 #: searx/engines/openstreetmap.py:159
 msgid "Get directions"
@@ -528,7 +529,7 @@ msgstr "Filkvalitet"
 
 #: searx/plugins/calculator.py:14
 msgid "Calculate mathematical expressions via the search bar"
-msgstr ""
+msgstr "Kalkuler matematiske uttrykk via søkebaren"
 
 #: searx/plugins/hash_plugin.py:10
 msgid "Converts strings to different hash digests."
@@ -572,7 +573,7 @@ msgstr ""
 
 #: searx/plugins/self_info.py:28
 msgid "Your IP is: "
-msgstr ""
+msgstr "Din IP er "
 
 #: searx/plugins/self_info.py:31
 msgid "Your user-agent is: "
@@ -580,16 +581,16 @@ msgstr ""
 
 #: searx/plugins/tor_check.py:24
 msgid "Tor check plugin"
-msgstr "Tor sjekk pluggin"
+msgstr "Tor sjekking plugin"
 
 #: searx/plugins/tor_check.py:27
 msgid ""
 "This plugin checks if the address of the request is a Tor exit-node, and "
 "informs the user if it is; like check.torproject.org, but from SearXNG."
 msgstr ""
-"Denne plugin sjekker om adressen til forespørselen er en Tor utgangsnode,"
-" og informerer brukeren om den er det; som check.torproject.org, men fra "
-"SearXNG."
+"Denne plugin-en sjekker om adressen til forespørselen er en Tor utgangsnode, "
+"og informerer brukeren om den er det; slik som check.torproject.org gjør, "
+"men fra SearXNG."
 
 #: searx/plugins/tor_check.py:61
 msgid ""
@@ -621,7 +622,7 @@ msgstr "Fjern sporer-argumenter fra returnert nettadresse"
 
 #: searx/plugins/unit_converter.py:29
 msgid "Convert between units"
-msgstr ""
+msgstr "Konverter mellom forskjellige enheter"
 
 #: searx/templates/simple/404.html:4
 msgid "Page not found"
@@ -688,7 +689,7 @@ msgstr "Lengde"
 
 #: searx/templates/simple/macros.html:41
 msgid "Views"
-msgstr ""
+msgstr "Visninger"
 
 #: searx/templates/simple/macros.html:42
 #: searx/templates/simple/result_templates/files.html:34
@@ -946,7 +947,7 @@ msgstr "Meldinger fra søkemotorene"
 
 #: searx/templates/simple/elements/engines_msg.html:7
 msgid "seconds"
-msgstr ""
+msgstr "sekunder"
 
 #: searx/templates/simple/elements/search_url.html:3
 msgid "Search URL"
@@ -1068,7 +1069,7 @@ msgstr "Bytt til en annen instans:"
 
 #: searx/templates/simple/messages/no_results.html:24
 msgid "Search for another query or select another category."
-msgstr ""
+msgstr "Oppgi et annet søkeord eller velg en annen kategori."
 
 #: searx/templates/simple/messages/no_results.html:25
 msgid "Go back to the previous page using the previous page button."
@@ -1194,11 +1195,11 @@ msgstr ""
 
 #: searx/templates/simple/preferences/engines.html:15
 msgid "Enable all"
-msgstr ""
+msgstr "Aktiver alle"
 
 #: searx/templates/simple/preferences/engines.html:16
 msgid "Disable all"
-msgstr ""
+msgstr "Deaktiver alle"
 
 #: searx/templates/simple/preferences/engines.html:25
 msgid "!bang"

searx/translations/vi/LC_MESSAGES/messages.po

@@ -10,13 +10,14 @@
 # return42 <return42@users.noreply.translate.codeberg.org>, 2024.
 # vducong <vducong@users.noreply.translate.codeberg.org>, 2024.
 # tvminh19 <tvminh19@users.noreply.translate.codeberg.org>, 2024.
+# KhietVo <KhietVo@users.noreply.translate.codeberg.org>, 2024.
 msgid ""
 msgstr ""
 "Project-Id-Version: searx\n"
 "Report-Msgid-Bugs-To: EMAIL@ADDRESS\n"
 "POT-Creation-Date: 2024-10-05 06:24+0000\n"
-"PO-Revision-Date: 2024-10-26 21:13+0000\n"
-"Last-Translator: return42 <return42@users.noreply.translate.codeberg.org>\n"
+"PO-Revision-Date: 2024-11-14 14:07+0000\n"
+"Last-Translator: KhietVo <KhietVo@users.noreply.translate.codeberg.org>\n"
 "Language-Team: Vietnamese <https://translate.codeberg.org/projects/searxng/"
 "searxng/vi/>\n"
 "Language: vi\n"
@@ -166,7 +167,7 @@ msgstr "Tối"
 #. STYLE_NAMES['BLACK']
 #: searx/searxng.msg
 msgid "black"
-msgstr ""
+msgstr "màu đen"
 
 #. BRAND_CUSTOM_LINKS['UPTIME']
 #: searx/searxng.msg
@@ -198,7 +199,7 @@ msgstr "Điều kiện"
 #: searx/engines/duckduckgo_weather.py:118 searx/engines/wttr.py:104
 #: searx/searxng.msg
 msgid "Current condition"
-msgstr ""
+msgstr "tình hình hiện tại"
 
 #. WEATHER_TERMS['EVENING']
 #: searx/engines/wttr.py:100 searx/searxng.msg
@@ -209,25 +210,25 @@ msgstr "Buổi chiều"
 #: searx/engines/duckduckgo_weather.py:53 searx/engines/open_meteo.py:81
 #: searx/engines/wttr.py:59 searx/searxng.msg
 msgid "Feels like"
-msgstr ""
+msgstr "Cảm thấy"
 
 #. WEATHER_TERMS['HUMIDITY']
 #: searx/engines/duckduckgo_weather.py:64 searx/engines/open_meteo.py:93
 #: searx/engines/wttr.py:68 searx/searxng.msg
 msgid "Humidity"
-msgstr ""
+msgstr "Độ ẩm"
 
 #. WEATHER_TERMS['MAX TEMP.']
 #: searx/engines/duckduckgo_weather.py:77 searx/engines/wttr.py:34
 #: searx/searxng.msg
 msgid "Max temp."
-msgstr ""
+msgstr "Nhiệt độ tối đa"
 
 #. WEATHER_TERMS['MIN TEMP.']
 #: searx/engines/duckduckgo_weather.py:73 searx/engines/wttr.py:33
 #: searx/searxng.msg
 msgid "Min temp."
-msgstr ""
+msgstr "Nhiệt độ thấp nhất"
 
 #. WEATHER_TERMS['MORNING']
 #: searx/engines/wttr.py:100 searx/searxng.msg
@@ -247,37 +248,37 @@ msgstr "Buổi trưa"
 #. WEATHER_TERMS['PRESSURE']
 #: searx/engines/open_meteo.py:95 searx/searxng.msg
 msgid "Pressure"
-msgstr ""
+msgstr "Áp suất"
 
 #. WEATHER_TERMS['SUNRISE']
 #: searx/engines/duckduckgo_weather.py:81 searx/engines/wttr.py:36
 #: searx/searxng.msg
 msgid "Sunrise"
-msgstr ""
+msgstr "Mặt trời mọc"
 
 #. WEATHER_TERMS['SUNSET']
 #: searx/engines/duckduckgo_weather.py:82 searx/engines/wttr.py:37
 #: searx/searxng.msg
 msgid "Sunset"
-msgstr ""
+msgstr "mặt trời lặn"
 
 #. WEATHER_TERMS['TEMPERATURE']
 #: searx/engines/duckduckgo_weather.py:48 searx/engines/open_meteo.py:76
 #: searx/engines/wttr.py:55 searx/searxng.msg
 msgid "Temperature"
-msgstr ""
+msgstr "Nhiệt độ"
 
 #. WEATHER_TERMS['UV INDEX']
 #: searx/engines/duckduckgo_weather.py:80 searx/engines/wttr.py:35
 #: searx/searxng.msg
 msgid "UV index"
-msgstr ""
+msgstr "Chỉ số UV"
 
 #. WEATHER_TERMS['VISIBILITY']
 #: searx/engines/duckduckgo_weather.py:62 searx/engines/wttr.py:66
 #: searx/searxng.msg
 msgid "Visibility"
-msgstr ""
+msgstr "Tầm nhìn"
 
 #. WEATHER_TERMS['WIND']
 #: searx/engines/duckduckgo_weather.py:58 searx/engines/open_meteo.py:86
@@ -288,12 +289,12 @@ msgstr "Gió"
 #. SOCIAL_MEDIA_TERMS['SUBSCRIBERS']
 #: searx/engines/lemmy.py:85 searx/searxng.msg
 msgid "subscribers"
-msgstr ""
+msgstr "người đăng ký"
 
 #. SOCIAL_MEDIA_TERMS['POSTS']
 #: searx/engines/lemmy.py:86 searx/searxng.msg
 msgid "posts"
-msgstr ""
+msgstr "những bài đăng"
 
 #. SOCIAL_MEDIA_TERMS['ACTIVE USERS']
 #: searx/engines/lemmy.py:87 searx/searxng.msg
@@ -309,42 +310,42 @@ msgstr ""
 #. SOCIAL_MEDIA_TERMS['USER']
 #: searx/engines/lemmy.py:129 searx/engines/lemmy.py:164 searx/searxng.msg
 msgid "user"
-msgstr ""
+msgstr "người dùng"
 
 #. SOCIAL_MEDIA_TERMS['COMMUNITY']
 #: searx/engines/lemmy.py:131 searx/engines/lemmy.py:165 searx/searxng.msg
 msgid "community"
-msgstr ""
+msgstr "cộng đồng"
 
 #. SOCIAL_MEDIA_TERMS['POINTS']
 #: searx/engines/hackernews.py:78 searx/searxng.msg
 msgid "points"
-msgstr ""
+msgstr "điểm"
 
 #. SOCIAL_MEDIA_TERMS['TITLE']
 #: searx/searxng.msg
 msgid "title"
-msgstr ""
+msgstr "tiêu đề"
 
 #. SOCIAL_MEDIA_TERMS['AUTHOR']
 #: searx/engines/hackernews.py:81 searx/searxng.msg
 msgid "author"
-msgstr ""
+msgstr "tác giả"
 
 #. SOCIAL_MEDIA_TERMS['THREAD OPEN']
 #: searx/engines/discourse.py:149 searx/searxng.msg
 msgid "open"
-msgstr ""
+msgstr "mở"
 
 #. SOCIAL_MEDIA_TERMS['THREAD CLOSED']
 #: searx/engines/discourse.py:149 searx/searxng.msg
 msgid "closed"
-msgstr ""
+msgstr "đóng"
 
 #. SOCIAL_MEDIA_TERMS['THREAD ANSWERED']
 #: searx/engines/discourse.py:160 searx/searxng.msg
 msgid "answered"
-msgstr ""
+msgstr "đã trả lời"
 
 #: searx/webapp.py:332
 msgid "No item found"
@@ -529,7 +530,7 @@ msgstr "Chất lượng tệp"
 
 #: searx/plugins/calculator.py:14
 msgid "Calculate mathematical expressions via the search bar"
-msgstr ""
+msgstr "Tính toán bằng thanh tìm kiếm"
 
 #: searx/plugins/hash_plugin.py:10
 msgid "Converts strings to different hash digests."
@@ -540,12 +541,14 @@ msgid "hash digest"
 msgstr "hash băm"
 
 #: searx/plugins/hostnames.py:103
+#, fuzzy
 msgid "Hostnames plugin"
-msgstr ""
+msgstr "Mấy chủ bổ trợ"
 
 #: searx/plugins/hostnames.py:104
 msgid "Rewrite hostnames, remove results or prioritize them based on the hostname"
 msgstr ""
+"Viết lại máy chủ, xoá các kểt quả tìm kiếm hoặc sắp xếp dựa trên máy chủ"
 
 #: searx/plugins/oa_doi_rewrite.py:12
 msgid "Open Access DOI rewrite"
@@ -571,7 +574,7 @@ msgstr "Hiện IP của bạn khi gõ \"ip\" và hiện user agent khi gõ \"use
 
 #: searx/plugins/self_info.py:28
 msgid "Your IP is: "
-msgstr ""
+msgstr "Địa chỉ IP của bạn: "
 
 #: searx/plugins/self_info.py:31
 msgid "Your user-agent is: "