From 20a5220199c9c146dc1bdd7f410018014f052317 Mon Sep 17 00:00:00 2001 From: AngeD Date: Sun, 17 Sep 2023 22:11:34 +0200 Subject: [PATCH] feat(searXNG): updated settings.yml --- searxng/settings.yml | 434 +++++++++++++++++++++++++++---------------- 1 file changed, 273 insertions(+), 161 deletions(-) diff --git a/searxng/settings.yml b/searxng/settings.yml index e84bb01..4da154a 100644 --- a/searxng/settings.yml +++ b/searxng/settings.yml @@ -7,7 +7,7 @@ general: privacypolicy_url: false # use true to use your own donation page written in searx/info/en/donate.md # use false to disable the donation link - donation_url: https://docs.searxng.org/donate.html + donation_url: false # mailto:contact@example.com contact_url: false # record stats @@ -23,7 +23,7 @@ brand: search: # Filter results. 0: None, 1: Moderate, 2: Strict safe_search: 0 - # Existing autocomplete backends: "dbpedia", "duckduckgo", "google", "yandex", + # Existing autocomplete backends: "dbpedia", "duckduckgo", "google", "yandex", "mwmbl", # "seznam", "startpage", "swisscows", "qwant", "wikipedia" - leave blank to turn it off # by default. autocomplete: "duckduckgo" @@ -113,7 +113,7 @@ ui: default_theme: simple # center the results ? center_alignment: false - # URL prefix of the internet archive, don't forgett trailing slash (if needed). + # URL prefix of the internet archive, don't forget trailing slash (if needed). # cache_url: "https://webcache.googleusercontent.com/search?q=cache:" # Default interface locale - leave blank to detect from browser information or # use codes from the 'locales' config section @@ -292,6 +292,19 @@ engines: shortcut: 9g disabled: true + - name: annas archive + engine: annas_archive + disabled: true + shortcut: aa + + # - name: annas articles + # engine: annas_archive + # shortcut: aaa + # # https://docs.searxng.org/dev/engines/online/annas_archive.html + # aa_content: 'journal_article' # book_any .. magazine, standards_document + # aa_ext: 'pdf' # pdf, epub, .. + # aa_sort: 'newest' # newest, oldest, largest, smallest + - name: apk mirror engine: apkmirror timeout: 4.0 @@ -310,29 +323,24 @@ engines: enable_http: true shortcut: ah + - name: anaconda + engine: xpath + paging: true + first_page_num: 0 + search_url: https://anaconda.org/search?q={query}&page={pageno} + results_xpath: //tbody/tr + url_xpath: ./td/h5/a[last()]/@href + title_xpath: ./td/h5 + content_xpath: ./td[h5]/text() + categories: it + timeout: 6.0 + shortcut: conda + disabled: true + - name: arch linux wiki engine: archlinux shortcut: al - - name: archive is - engine: xpath - search_url: https://archive.is/search/?q={query} - url_xpath: (//div[@class="TEXT-BLOCK"]/a)/@href - title_xpath: (//div[@class="TEXT-BLOCK"]/a) - content_xpath: //div[@class="TEXT-BLOCK"]/ul/li - categories: general - timeout: 7.0 - disabled: true - shortcut: ai - soft_max_redirects: 1 - about: - website: https://archive.is/ - wikidata_id: Q13515725 - official_api_documentation: https://mementoweb.org/depot/native/archiveis/ - use_official_api: false - require_api_key: false - results: HTML - - name: artic engine: artic shortcut: arc @@ -358,6 +366,11 @@ engines: shortcut: wp base_url: 'https://{language}.wikipedia.org/' + - name: bilibili + engine: bilibili + shortcut: bil + disabled: true + - name: bing engine: bing shortcut: bi @@ -400,6 +413,7 @@ engines: - name: btdigg engine: btdigg shortcut: bt + disabled: true - name: ccc-tv engine: xpath @@ -440,6 +454,20 @@ engines: timeout: 30 disabled: true + - name: crowdview + engine: json_engine + shortcut: cv + categories: general + paging: false + search_url: https://crowdview-next-js.onrender.com/api/search-v3?query={query} + results_query: results + url_query: link + title_query: title + content_query: snippet + disabled: true + about: + website: https://crowdview.ai/ + - name: yep engine: json_engine shortcut: yep @@ -640,11 +668,6 @@ engines: shortcut: fsd categories: [it, software wikis] base_url: https://directory.fsf.org/ - number_of_results: 5 - # what part of a page matches the query string: title, text, nearmatch - # * title - query matches title - # * text - query matches the text of page - # * nearmatch - nearmatch in title search_type: title timeout: 5.0 disabled: true @@ -790,10 +813,11 @@ engines: - name: habrahabr engine: xpath paging: true - search_url: https://habrahabr.ru/search/page{pageno}/?q={query} - url_xpath: //article[contains(@class, "post")]//a[@class="post__title_link"]/@href - title_xpath: //article[contains(@class, "post")]//a[@class="post__title_link"] - content_xpath: //article[contains(@class, "post")]//div[contains(@class, "post__text")] + search_url: https://habr.com/en/search/page{pageno}/?q={query} + results_xpath: //article[contains(@class, "tm-articles-list__item")] + url_xpath: .//a[@class="tm-title__link"]/@href + title_xpath: .//a[@class="tm-title__link"] + content_xpath: .//div[contains(@class, "article-formatted-body")] categories: it timeout: 4.0 disabled: true @@ -842,11 +866,14 @@ engines: # Instanes will be selected randomly, see https://api.invidious.io/ for # instances that are stable (good uptime) and close to you. base_url: - - https://invidious.snopyta.org + - https://invidious.io.lol + - https://invidious.fdn.fr + - https://yt.artemislena.eu + - https://invidious.tiekoetter.com + - https://invidious.flokinet.to - https://vid.puffyan.us - # - https://invidious.kavin.rocks # Error 1020 // Access denied by Cloudflare - - https://invidio.xamh.de - - https://inv.riverside.rocks + - https://invidious.privacydev.net + - https://inv.tux.pizza shortcut: iv timeout: 3.0 disabled: true @@ -863,6 +890,29 @@ engines: timeout: 4.0 disabled: true + - name: lemmy communities + engine: lemmy + lemmy_type: Communities + shortcut: leco + + - name: lemmy users + engine: lemmy + network: lemmy communities + lemmy_type: Users + shortcut: leus + + - name: lemmy posts + engine: lemmy + network: lemmy communities + lemmy_type: Posts + shortcut: lepo + + - name: lemmy comments + engine: lemmy + network: lemmy communities + lemmy_type: Comments + shortcut: lecom + - name: library genesis engine: xpath search_url: https://libgen.fun/search.php?req={query} @@ -881,19 +931,11 @@ engines: require_api_key: false results: HTML - # Disabling zlibrary due to z-lib.org domain seizure - # https://github.com/searxng/searxng/pull/1937 - # - # - name: z-library - # engine: zlibrary - # shortcut: zlib - # categories: files - # timeout: 3.0 - # # choose base_url, otherwise engine will do it at initialization time - # # base_url: https://b-ok.cc - # # base_url: https://de1lib.org - # # base_url: https://booksc.eu # does not have cover preview - # # base_url: https://booksc.org # does not have cover preview + - name: z-library + engine: zlibrary + shortcut: zlib + categories: files + timeout: 7.0 - name: library of congress engine: loc @@ -975,6 +1017,12 @@ engines: # collection: 'reviews' # name of the db collection # key: 'name' # key in the collection to search for + - name: mwmbl + engine: mwmbl + # api_url: https://api.mwmbl.org + shortcut: mwm + disabled: true + - name: npm engine: json_engine paging: true @@ -1018,6 +1066,11 @@ engines: require_api_key: false results: JSON + - name: odysee + engine: odysee + shortcut: od + disabled: true + - name: openairedatasets engine: json_engine paging: true @@ -1116,6 +1169,29 @@ engines: engine: photon shortcut: ph + - name: piped + engine: piped + shortcut: ppd + categories: videos + piped_filter: videos + timeout: 3.0 + + # URL to use as link and for embeds + frontend_url: https://srv.piped.video + # Instance will be selected randomly, for more see https://piped-instances.kavin.rocks/ + backend_url: + - https://pipedapi.kavin.rocks + - https://pipedapi-libre.kavin.rocks + - https://pipedapi.adminforge.de + + - name: piped.music + engine: piped + network: piped + shortcut: ppdm + categories: music + piped_filter: music_songs + timeout: 3.0 + - name: piratebay engine: piratebay shortcut: tpb @@ -1139,10 +1215,10 @@ engines: shortcut: pd search_url: https://pub.dev/packages?q={query}&page={pageno} paging: true - results_xpath: /html/body/main/div/div[@class="search-results"]/div[@class="packages"]/div + results_xpath: //div[contains(@class,"packages-item")] url_xpath: ./div/h3/a/@href title_xpath: ./div/h3/a - content_xpath: ./p[@class="packages-description"] + content_xpath: ./div/div/div[contains(@class,"packages-description")]/span categories: [packages, it] timeout: 3.0 disabled: true @@ -1163,7 +1239,7 @@ engines: shortcut: pypi engine: xpath paging: true - search_url: https://pypi.org/search?q={query}&page={pageno} + search_url: https://pypi.org/search/?q={query}&page={pageno} results_xpath: /html/body/main/div/div/div/form/div/ul/li/a[@class="package-snippet"] url_xpath: ./@href title_xpath: ./h3/span[@class="package-snippet__name"] @@ -1180,11 +1256,10 @@ engines: results: HTML - name: qwant - qwant_categ: web + qwant_categ: web-lite engine: qwant shortcut: qw categories: [general, web] - disabled: false additional_tests: rosebud: *test_rosebud @@ -1193,7 +1268,6 @@ engines: engine: qwant shortcut: qwn categories: news - disabled: false network: qwant - name: qwant images @@ -1349,10 +1423,7 @@ engines: engine: solidtorrents shortcut: solid timeout: 4.0 - disabled: false base_url: - - https://solidtorrents.net - - https://solidtorrents.eu - https://solidtorrents.to - https://bitsearch.to @@ -1374,7 +1445,23 @@ engines: # FROM film # WHERE title LIKE :wildcard OR description LIKE :wildcard # ORDER BY duration DESC - # disabled: false + + - name: tagesschau + engine: tagesschau + shortcut: ts + disabled: true + + - name: tmdb + engine: xpath + paging: true + search_url: https://www.themoviedb.org/search?page={pageno}&query={query} + results_xpath: //div[contains(@class,"movie") or contains(@class,"tv")]//div[contains(@class,"card")] + url_xpath: .//div[contains(@class,"poster")]/a/@href + thumbnail_xpath: .//img/@src + title_xpath: .//div[contains(@class,"title")]//h2 + content_xpath: .//div[contains(@class,"overview")] + shortcut: tm + disabled: true # Requires Tor - name: torch @@ -1391,15 +1478,18 @@ engines: shortcut: tch # torznab engine lets you query any torznab compatible indexer. Using this - # engine in combination with Jackett (https://github.com/Jackett/Jackett) - # opens the possibility to query a lot of public and private indexers directly - # from SearXNG. - # - name: torznab + # engine in combination with Jackett opens the possibility to query a lot of + # public and private indexers directly from SearXNG. More details at: + # https://docs.searxng.org/dev/engines/online/torznab.html + # + # - name: Torznab EZTV # engine: torznab - # shortcut: trz - # base_url: http://localhost:9117/api/v2.0/indexers/all/results/torznab + # shortcut: eztv + # base_url: http://localhost:9117/api/v2.0/indexers/eztv/results/torznab # enable_http: true # if using localhost # api_key: xxxxxxxxxxxxxxx + # show_magnet_links: true + # show_torrent_files: false # # https://github.com/Jackett/Jackett/wiki/Jackett-Categories # torznab_categories: # optional # - 2000 @@ -1410,13 +1500,6 @@ engines: engine: twitter disabled: true - # maybe in a fun category - # - name: uncyclopedia - # engine: mediawiki - # shortcut: unc - # base_url: https://uncyclopedia.wikia.com/ - # number_of_results: 5 - # tmp suspended - too slow, too many errors # - name: urbandictionary # engine : xpath @@ -1471,27 +1554,6 @@ engines: about: website: https://wiby.me/ - - name: marginalia - engine: json_engine - shortcut: mar - categories: general - paging: false - # index: {"0": "popular", "1": "blogs", "2": "big_sites", - # "3": "default", "4": experimental"} - search_url: https://api.marginalia.nu/public/search/{query}?index=4&count=20 - results_query: results - url_query: url - title_query: title - content_query: description - timeout: 1.5 - disabled: true - about: - website: https://www.marginalia.nu/ - official_api_documentation: https://api.marginalia.nu/ - use_official_api: true - require_api_key: true - results: JSON - - name: alexandria engine: json_engine shortcut: alx @@ -1513,10 +1575,10 @@ engines: - name: wikibooks engine: mediawiki + weight: 0.5 shortcut: wb - categories: general + categories: [general, wikimedia] base_url: "https://{language}.wikibooks.org/" - number_of_results: 5 search_type: text disabled: true about: @@ -1526,21 +1588,20 @@ engines: - name: wikinews engine: mediawiki shortcut: wn - categories: news + categories: [news, wikimedia] base_url: "https://{language}.wikinews.org/" - number_of_results: 5 search_type: text - disabled: true + srsort: create_timestamp_desc about: website: https://www.wikinews.org/ wikidata_id: Q964 - name: wikiquote engine: mediawiki + weight: 0.5 shortcut: wq - categories: general + categories: [general, wikimedia] base_url: "https://{language}.wikiquote.org/" - number_of_results: 5 search_type: text disabled: true additional_tests: @@ -1551,34 +1612,42 @@ engines: - name: wikisource engine: mediawiki + weight: 0.5 shortcut: ws - categories: general + categories: [general, wikimedia] base_url: "https://{language}.wikisource.org/" - number_of_results: 5 search_type: text - disabled: true about: website: https://www.wikisource.org/ wikidata_id: Q263 + - name: wikispecies + engine: mediawiki + shortcut: wsp + categories: [general, science, wikimedia] + base_url: "https://species.wikimedia.org/" + search_type: text + disabled: true + about: + website: https://species.wikimedia.org/ + wikidata_id: Q13679 + - name: wiktionary engine: mediawiki shortcut: wt - categories: [dictionaries] + categories: [dictionaries, wikimedia] base_url: "https://{language}.wiktionary.org/" - number_of_results: 5 search_type: text - disabled: false about: website: https://www.wiktionary.org/ wikidata_id: Q151 - name: wikiversity engine: mediawiki + weight: 0.5 shortcut: wv - categories: general + categories: [general, wikimedia] base_url: "https://{language}.wikiversity.org/" - number_of_results: 5 search_type: text disabled: true about: @@ -1587,16 +1656,22 @@ engines: - name: wikivoyage engine: mediawiki + weight: 0.5 shortcut: wy - categories: general + categories: [general, wikimedia] base_url: "https://{language}.wikivoyage.org/" - number_of_results: 5 search_type: text disabled: true about: website: https://www.wikivoyage.org/ wikidata_id: Q373 + - name: wikicommons.images + engine: wikicommons + shortcut: wc + categories: images + number_of_results: 10 + - name: wolframalpha shortcut: wa # You can use the engine using the official stable API, but you need an API @@ -1608,7 +1683,8 @@ engines: # Or you can use the html non-stable engine, activated by default engine: wolframalpha_noapi timeout: 6.0 - categories: [] + categories: general + disabled: true - name: dictzone engine: dictzone @@ -1618,7 +1694,6 @@ engines: engine: translated shortcut: tl timeout: 5.0 - disabled: false # You can use without an API key, but you are limited to 1000 words/day # See: https://mymemory.translated.net/doc/usagelimits.php # api_key: '' @@ -1679,6 +1754,11 @@ engines: require_api_key: false results: HTML + - name: moviepilot + engine: moviepilot + shortcut: mp + disabled: true + - name: naver shortcut: nvr categories: [general, web] @@ -1740,10 +1820,11 @@ engines: # engine: yacy # shortcut: ya # base_url: http://localhost:8090 - # required if you aren't using HTTPS for your local yacy instance' + # # required if you aren't using HTTPS for your local yacy instance' # enable_http: true - # number_of_results: 5 # timeout: 3.0 + # # Yacy search mode. 'global' or 'local'. + # search_mode: 'global' - name: rumble engine: rumble @@ -1759,7 +1840,6 @@ engines: base_url: https://www.wordnik.com/ categories: [dictionaries] timeout: 5.0 - disabled: false - name: woxikon.de synonyme engine: xpath @@ -1780,6 +1860,29 @@ engines: results: HTML language: de + - name: seekr news + engine: seekr + shortcut: senews + categories: news + seekr_category: news + disabled: true + + - name: seekr images + engine: seekr + network: seekr news + shortcut: seimg + categories: images + seekr_category: images + disabled: true + + - name: seekr videos + engine: seekr + network: seekr news + shortcut: sevid + categories: videos + seekr_category: videos + disabled: true + - name: sjp.pwn engine: sjp shortcut: sjp @@ -1787,6 +1890,12 @@ engines: timeout: 5.0 disabled: true + - name: svgrepo + engine: svgrepo + shortcut: svg + timeout: 10.0 + disabled: true + # wikimini: online encyclopedia for children # The fulltext and title parameter is necessary for Wikimini because # sometimes it will not show the results and redirect instead @@ -1812,60 +1921,42 @@ engines: shortcut: wttr timeout: 9.0 + - name: yummly + engine: yummly + shortcut: yum + disabled: true + - name: brave - shortcut: brave - engine: xpath - paging: true + engine: brave + shortcut: br time_range_support: true - first_page_num: 0 - time_range_url: "&tf={time_range_val}" - search_url: https://search.brave.com/search?q={query}&offset={pageno}&spellcheck=1{time_range} - url_xpath: //a[@class="result-header"]/@href - title_xpath: //span[@class="snippet-title"] - content_xpath: //p[1][@class="snippet-description"] - suggestion_xpath: //div[@class="text-gray h6"]/a - time_range_map: - day: 'pd' - week: 'pw' - month: 'pm' - year: 'py' + paging: true categories: [general, web] disabled: true - headers: - Accept-Encoding: gzip, deflate - about: - website: https://brave.com/search/ - wikidata_id: Q107355971 - use_official_api: false - require_api_key: false - results: HTML + brave_category: search + # brave_spellcheck: true - - name: petalsearch - shortcut: pts - engine: xpath - paging: true - search_url: https://petalsearch.com/search?query={query}&pn={pageno} - url_xpath: //div[@class='card-source'] - title_xpath: //div[@class='title-name'] - content_xpath: //div[@class='webpage-text'] - first_page_num: 1 + - name: brave.images + engine: brave + network: brave + shortcut: brimg + categories: [images, web] + brave_category: images disabled: true - headers: - User-Agent: Mozilla/5.0 (Linux; Android 7.0;) \ - AppleWebKit/537.36 (KHTML, like Gecko) \ - Mobile Safari/537.36 (compatible; PetalBot;+https://webmaster.petalsearch.com/site/petalbot) - about: - website: https://petalsearch.com/ - wikidata_id: Q104399280 - use_official_api: false - require_api_key: false - results: HTML - - name: petalsearch images - engine: petal_images - shortcut: ptsi - disabled: true - timeout: 3.0 + - name: brave.videos + engine: brave + network: brave + shortcut: brvid + categories: [videos, web] + brave_category: videos + + - name: brave.news + engine: brave + network: brave + shortcut: brnews + categories: news + brave_category: news - name: lib.rs shortcut: lrs @@ -1924,6 +2015,27 @@ engines: results: HTML language: ja + - name: bt4g + engine: bt4g + shortcut: bt4g + + - name: pkg.go.dev + engine: xpath + shortcut: pgo + search_url: https://pkg.go.dev/search?limit=100&m=package&q={query} + results_xpath: /html/body/main/div[contains(@class,"SearchResults")]/div[not(@class)]/div[@class="SearchSnippet"] + url_xpath: ./div[@class="SearchSnippet-headerContainer"]/h2/a/@href + title_xpath: ./div[@class="SearchSnippet-headerContainer"]/h2/a + content_xpath: ./p[@class="SearchSnippet-synopsis"] + categories: [packages, it] + timeout: 3.0 + disabled: true + about: + website: https://pkg.go.dev/ + use_official_api: false + require_api_key: false + results: HTML + # Doku engine lets you access to any Doku wiki instance: # A public one or a privete/corporate one. # - name: ubuntuwiki