SearXNG: updated settings.yml

README.md

@@ -16,8 +16,6 @@ They are deployed with [Compose files](templates/compose) and load balanced acco
 
 Our caddy server blocks IP ranges that have been involved in mass spams. The [block range file](https://github.com/ProjectSegfault/ansible/blob/master/privfrontends/blocked-ranges.yaml) is created by [ProjectSegfault](https://projectsegfau.lt/). Thanks to their team.
 
-Our SearXNG instance uses a custom [settings.yml](templates/conf/settings.yml.j2). It is updated by hand with reference to [Pussthecat.org's configuration](https://github.com/PussTheCat-org/PussTheCat.org-Configs/tree/master/Services/SearXNG). Thanks to [TheFrenchGhosty](https://github.com/PussTheCat-org).
-
 Data of our Privatebin, Etherpad, and Gitea instances are backed up periodically.
 
 Passwords and other sensitive data are kept locally as encrypted variables in [secrets.yaml](vars/secrets.example.yaml). We host an Authelia and Firefox stack that is restricted to specific users only. Their related files are also kept locally.

templates/conf/settings.yml.j2

@@ -73,16 +73,14 @@ search:
     - html
 
 server:
-  # If you change port, bind_address or base_url don't forget to rebuild
+  # Is overwritten by ${SEARXNG_PORT} and ${SEARXNG_BIND_ADDRESS}
-  # instance's environment (make buildenv). Is overwritten by ${SEARXNG_PORT}
-  # and ${SEARXNG_BIND_ADDRESS}
   port: 8080
   bind_address: "0.0.0.0"
   # public URL of the instance, to ensure correct inbound links. Is overwritten
   # by ${SEARXNG_URL}.
   base_url: "https://opnxng.com"
   limiter: true  # rate limit the number of request on the instance, block some bots
-  public_instance: true
+  public_instance: true # enable features designed only for public instances
 
   # If your instance owns a /etc/searxng/settings.yml file, then set the following
   # values there.
@@ -95,7 +93,10 @@ server:
   # problems when using Firefox containers
   method: "POST"
   default_http_headers:
+  #  X-Content-Type-Options: nosniff
     X-Download-Options: noopen
+  #  X-Robots-Tag: noindex, nofollow
+  #  Referrer-Policy: no-referrer
 
 redis:
   # URL to connect redis database. Is overwritten by ${SEARXNG_REDIS_URL}.
@@ -190,6 +191,19 @@ outgoing:
       - socks5://{{ oracle4_private_ip }}:8870
       - socks5h://{{ oracle4_private_ip }}:8870
 
+  #  using_tor_proxy: true
+  #
+  # Extra seconds to add in order to account for the time taken by the proxy
+  #
+  #  extra_proxy_timeout: 10
+  #
+  # uncomment below section only if you have more than one network interface
+  # which can be the source of outgoing search requests
+  #
+  #  source_ips:
+  #    - 1.1.1.1
+  #    - 1.1.1.2
+  #    - fe80::/126
 
 # External plugin configuration, for more details see
 #   https://docs.searxng.org/dev/plugins.html
@@ -249,7 +263,6 @@ hostnames:
     '(.*\.)?stackapps\.com$': 'code.whatever.social/exchange/stackapps.com'
     '(.*\.)?askubuntu\.com$': 'code.whatever.social/exchange/askubuntu.com'
   remove:
-    - '(.*\.)?facebook.com$'
     - 'com\.de'
     - '(.*\.)?codegrepper\.com'
     - '(.*\.)?w3schools\.com'
@@ -461,7 +474,6 @@ hostnames:
 #  high_priority:
 #    - '(.*\.)?wikipedia.org$'
 
-
 checker:
   # disable checker when in debug mode
   off_when_debug: true
@@ -671,33 +683,20 @@ engines:
     shortcut: bt
     disabled: true
 
-  - name: ccc-tv
-    engine: xpath
-    paging: false
-    search_url: https://media.ccc.de/search/?q={query}
-    url_xpath: //div[@class="caption"]/h3/a/@href
-    title_xpath: //div[@class="caption"]/h3/a/text()
-    content_xpath: //div[@class="caption"]/h4/@title
-    categories: videos
-    disabled: true
-    shortcut: c3tv
-    about:
-      website: https://media.ccc.de/
-      wikidata_id: Q80729951
-      official_api_documentation: https://github.com/voc/voctoweb
-      use_official_api: false
-      require_api_key: false
-      results: HTML
-      # We don't set language: de here because media.ccc.de is not just
-      # for a German audience. It contains many English videos and many
-      # German videos have English subtitles.
-
   - name: openverse
     engine: openverse
     categories: images
     shortcut: opv
     disabled: true
 
+  - name: media.ccc.de
+    engine: ccc_media
+    shortcut: c3tv
+    # We don't set language: de here because media.ccc.de is not just
+    # for a German audience. It contains many English videos and many
+    # German videos have English subtitles.
+    disabled: true
+
   - name: chefkoch
     engine: chefkoch
     shortcut: chef
@@ -743,6 +742,7 @@ engines:
     shortcut: yep
     categories: general
     search_type: web
+    timeout: 5
     disabled: true
 
   - name: yep images
@@ -812,7 +812,6 @@ engines:
         test:
           - unique_results
 
-
   - name: deezer
     engine: deezer
     shortcut: dz
@@ -979,6 +978,11 @@ engines:
     shortcut: fd
     disabled: true
 
+  - name: findthatmeme
+    engine: findthatmeme
+    shortcut: ftm
+    disabled: true
+
   - name: flickr
     categories: images
     shortcut: fl
@@ -1024,7 +1028,7 @@ engines:
   - name: genius
     engine: genius
     shortcut: gen
-    disabled: true
+    categories: music
 
   - name: gentoo
     engine: gentoo
@@ -1057,26 +1061,18 @@ engines:
     shortcut: gh
     categories: [it, q&a]
 
-    # This a Gitea service. If you would like to use a different instance,
-    # change codeberg.org to URL of the desired Gitea host. Or you can create a
-    # new engine by copying this and changing the name, shortcut and search_url.
-
   - name: codeberg
-    engine: json_engine
+    # https://docs.searxng.org/dev/engines/online/gitea.html
-    search_url: https://codeberg.org/api/v1/repos/search?q={query}&limit=10
+    engine: gitea
-    url_query: html_url
+    base_url: https://codeberg.org
-    title_query: name
-    content_query: description
-    categories: [it, repos]
     shortcut: cb
     disabled: true
-    about:
+
-      website: https://codeberg.org/
+  - name: gitea.com
-      wikidata_id:
+    engine: gitea
-      official_api_documentation: https://try.gitea.io/api/swagger
+    base_url: https://gitea.com
-      use_official_api: false
+    shortcut: gitea
-      require_api_key: false
+    disabled: true
-      results: JSON
 
 {% endraw %}
 
@@ -1191,6 +1187,20 @@ engines:
     shortcut: hn
     disabled: true
 
+  - name: hex
+    engine: hex
+    shortcut: hex
+    disabled: true
+    # Valid values: name inserted_at updated_at total_downloads recent_downloads
+    sort_criteria: "recent_downloads"
+    page_size: 10
+
+  - name: crates.io
+    engine: crates
+    shortcut: crates
+    disabled: true
+    timeout: 6.0
+
   - name: hoogle
     engine: xpath
     search_url: https://hoogle.haskell.org/?hoogle={query}
@@ -1319,6 +1329,16 @@ engines:
     categories: images
     disabled: true
 
+  - name: libretranslate
+    engine: libretranslate
+    # https://github.com/LibreTranslate/LibreTranslate?tab=readme-ov-file#mirrors
+    base_url:
+      - https://translate.terraprint.co
+      - https://trans.zillyhuhn.com
+    # api_key: abc123
+    shortcut: lt
+    disabled: true
+
   - name: lingva
     engine: lingva
     shortcut: lv
@@ -1345,25 +1365,6 @@ engines:
       require_api_key: false
       results: HTML
 
-  - name: azlyrics
-    shortcut: lyrics
-    engine: xpath
-    timeout: 4.0
-    disabled: true
-    categories: [music, lyrics]
-    paging: true
-    search_url: https://search.azlyrics.com/search.php?q={query}&w=lyrics&p={pageno}
-    url_xpath: //td[@class="text-left visitedlyr"]/a/@href
-    title_xpath: //span/b/text()
-    content_xpath: //td[@class="text-left visitedlyr"]/a/small
-    about:
-      website: https://azlyrics.com
-      wikidata_id: Q66372542
-      official_api_documentation:
-      use_official_api: false
-      require_api_key: false
-      results: HTML
-
   - name: mastodon users
     engine: mastodon
     mastodon_type: accounts
@@ -1836,6 +1837,20 @@ engines:
   #    engine: scanr_structures
   #    disabled: true
 
+  - name: searchmysite
+    engine: xpath
+    shortcut: sms
+    categories: general
+    paging: true
+    search_url: https://searchmysite.net/search/?q={query}&page={pageno}
+    results_xpath: //div[contains(@class,'search-result')]
+    url_xpath: .//a[contains(@class,'result-link')]/@href
+    title_xpath: .//span[contains(@class,'result-title-txt')]/text()
+    content_xpath: ./p[@id='result-hightlight']
+    disabled: true
+    about:
+      website: https://searchmysite.net
+
   - name: sepiasearch
     engine: sepiasearch
     shortcut: sep
@@ -1861,7 +1876,7 @@ engines:
   - name: internetarchivescholar
     engine: internet_archive_scholar
     shortcut: ias
-    timeout: 5.0
+    timeout: 15.0
     disabled: true
 
   - name: superuser
@@ -1870,6 +1885,27 @@ engines:
     api_site: 'superuser'
     categories: [it, q&a]
 
+  - name: discuss.python
+    engine: discourse
+    shortcut: dpy
+    base_url: 'https://discuss.python.org'
+    categories: [it, q&a]
+    disabled: true
+
+  - name: caddy.community
+    engine: discourse
+    shortcut: caddy
+    base_url: 'https://caddy.community'
+    categories: [it, q&a]
+    disabled: true
+
+  - name: pi-hole.community
+    engine: discourse
+    shortcut: pi
+    categories: [it, q&a]
+    base_url: 'https://discourse.pi-hole.net'
+    disabled: true
+
   - name: searchcode code
     engine: searchcode_code
     shortcut: scc
@@ -2204,6 +2240,28 @@ engines:
     engine: wikicommons
     shortcut: wc
     categories: images
+    search_type: images
+    number_of_results: 10
+
+  - name: wikicommons.videos
+    engine: wikicommons
+    shortcut: wcv
+    categories: videos
+    search_type: videos
+    number_of_results: 10
+
+  - name: wikicommons.audio
+    engine: wikicommons
+    shortcut: wca
+    categories: music
+    search_type: audio
+    number_of_results: 10
+
+  - name: wikicommons.files
+    engine: wikicommons
+    shortcut: wcf
+    categories: files
+    search_type: files
     number_of_results: 10
 
   - name: wolframalpha
@@ -2270,26 +2328,25 @@ engines:
 
   - name: mojeek
     shortcut: mjk
-    engine: xpath
+    engine: mojeek
-    paging: true
     categories: [general, web]
-    search_url: https://www.mojeek.com/search?q={query}&s={pageno}&lang={lang}&lb={lang}
-    results_xpath: //ul[@class="results-standard"]/li/a[@class="ob"]
-    url_xpath: ./@href
-    title_xpath: ../h2/a
-    content_xpath: ..//p[@class="s"]
-    suggestion_xpath: //div[@class="top-info"]/p[@class="top-info spell"]/em/a
-    first_page_num: 0
-    page_size: 10
-    max_page: 100
     disabled: true
-    about:
+
-      website: https://www.mojeek.com/
+  - name: mojeek images
-      wikidata_id: Q60747299
+    shortcut: mjkimg
-      official_api_documentation: https://www.mojeek.com/services/api.html/
+    engine: mojeek
-      use_official_api: false
+    categories: [images, web]
-      require_api_key: false
+    search_type: images
-      results: HTML
+    paging: false
+    disabled: true
+
+  - name: mojeek news
+    shortcut: mjknews
+    engine: mojeek
+    categories: [news, web]
+    search_type: news
+    paging: false
+    disabled: true
 
   - name: moviepilot
     engine: moviepilot
@@ -2357,7 +2414,11 @@ engines:
     engine: yacy
     categories: general
     search_type: text
-    base_url: https://yacy.searchlab.eu
+    base_url:
+      - https://yacy.searchlab.eu
+      - https://search.lomig.me
+      - https://yacy.ecosys.eu
+      - https://search.webproject.link
     shortcut: ya
     disabled: true
     # required if you aren't using HTTPS for your local yacy instance
@@ -2370,7 +2431,6 @@ engines:
     engine: yacy
     categories: images
     search_type: image
-    base_url: https://yacy.searchlab.eu
     shortcut: yai
     disabled: true