Add option to limit archived entries

2023-12-08 11:32:01 +00:00 · 2023-12-08 11:32:01 +00:00 · 7c928fea25
commit 7c928fea25
parent 1e55dba759
97 changed files with 476 additions and 92 deletions
--- a/datasets/activity/bot.csv
+++ b/datasets/activity/bot.csv
@ -0,0 +1,3 @@
 name, url, language, country
 Feed of "poezio/biboumi", https://codeberg.org/poezio/biboumi.atom, en-US, France
 maubot activity, https://mau.dev/maubot.atom, en-US, Worldwide
--- a/datasets/activity/game.csv
+++ b/datasets/activity/game.csv
@ -1,2 +1,8 @@
 name, url, language, country
 Feed of "MintApps Team", https://codeberg.org/MintApps.rss, en-US, Germany
 Activity for TORCS - The Open Racing Car Simulator, https://sourceforge.net/p/torcs/activity/feed, en-US, Switzerland
 Activity for Speed Dreams : an Open Motorsport Sim, https://sourceforge.net/p/speed-dreams/activity/feed, en-US, Worldwide
 Activity for Ultimate Stunts, https://sourceforge.net/p/ultimatestunts/activity/feed, en-US, Worldwide
 Activity for SuperTuxKart, https://sourceforge.net/p/supertuxkart/activity/feed, en-US, Worldwide
 Recent changes to wiki, https://sourceforge.net/p/speed-dreams/wiki/feed.atom, en-US, Worldwide
 Activity for TROPHY, https://sourceforge.net/p/trophy/activity/feed, en-US, France
--- a/datasets/activity/internet.csv
+++ b/datasets/activity/internet.csv
@ -1,18 +1,22 @@
 name, url, language, country
 DokuWiki, https://www.dokuwiki.org/feed.php, en-US, Worldwide
-Feed of "MarvinsMastodonTools/tootbot", https://codeberg.org/MarvinsMastodonTools/tootbot.atom, en-US, Worldwide
+Feed of "tootbot", https://codeberg.org/MarvinsMastodonTools/tootbot.atom, en-US, Worldwide
-Feed of "MarvinsMastodonTools/feed2fedi", https://codeberg.org/MarvinsMastodonTools/feed2fedi.atom, en-US, Worldwide
+Feed of "feed2fedi", https://codeberg.org/MarvinsMastodonTools/feed2fedi.atom, en-US, Worldwide
 slidge activity, https://sr.ht/~nicoco/slidge/feed.rss, en-US, France
 Feed of "RightToPrivacy/wipri", http://gg6zxtreajiijztyy5g6bt5o6l3qu32nrg7eulyemlhxwwl6enk6ghad.onion/RightToPrivacy/wipri.atom, en-US, Worldwide
 Feed of "RightToPrivacy", http://gg6zxtreajiijztyy5g6bt5o6l3qu32nrg7eulyemlhxwwl6enk6ghad.onion/RightToPrivacy.atom, en-US, Worldwide
 firefish activity, https://git.joinfirefish.org/firefish/firefish.atom, en-US, Worldwide
 funkwhale activity, https://dev.funkwhale.audio/funkwhale/funkwhale.atom, en-US, Worldwide
 Howler activity, https://gitlab.com/awoo.fyi/howler.atom, en-US, Worldwide
 firefish activity, https://git.joinfirefish.org/firefish/firefish.atom, en-US, Worldwide
-Feed of "calckey/calckey", https://codeberg.org/calckey/calckey.atom, en-US, Worldwide
+Feed of "calckey", https://codeberg.org/calckey/calckey.atom, en-US, Worldwide
 gajim activity, https://dev.gajim.org/gajim/gajim.atom, en-US, France
 Bugs in qutim, http://feeds.launchpad.net/qutim/latest-bugs.atom, en-US, Russia
-Feed of "poezio/slixmpp", https://codeberg.org/poezio/slixmpp.atom, en-US, France
+Feed of "slixmpp", https://codeberg.org/poezio/slixmpp.atom, en-US, France
 Feed of "JoinJabber", https://codeberg.org/joinjabber.rss, en-US, Worldwide
-Feed of "poezio/poezio", https://codeberg.org/poezio/poezio.atom, en-US, France
+Feed of "poezio", https://codeberg.org/poezio/poezio.atom, en-US, France
-Feed of "poezio/biboumi", https://codeberg.org/poezio/biboumi.atom, en-US, France
+Feed of "biboumi", https://codeberg.org/poezio/biboumi.atom, en-US, France
 OpenTalk activity, https://gitlab.opencode.de/opentalk.atom, en-US, Worldwide
 Activity for I Hear U, https://sourceforge.net/p/ihu/activity/feed, en-US, Worldwide
 maubot activity, https://mau.dev/maubot.atom, en-US, Worldwide
 briar activity, https://code.briarproject.org/briar.atom, en-US, Worldwide
--- a/datasets/activity/linux.csv
+++ b/datasets/activity/linux.csv
@ -0,0 +1,3 @@
 name, url, language, country
 Activity for salix, https://sourceforge.net/p/salix/activity/feed, en-US, Europe
 Wiki ubuntu-fr, https://doc.ubuntu-fr.org/feed.php, fr-FR, France
--- a/datasets/activity/operating_system.csv
+++ b/datasets/activity/operating_system.csv
@ -2,3 +2,4 @@ name, url, language, country
 Replicant: Issues, https://redmine.replicant.us/projects/replicant/issues.atom, en-US, Worldwide
 Activity for AROS Research Operating System, https://sourceforge.net/p/aros/activity/feed, en-US, Worldwide
 Activity for salix, https://sourceforge.net/p/salix/activity/feed, en-US, Europe
 Wiki ubuntu-fr, https://doc.ubuntu-fr.org/feed.php, fr-FR, France
--- a/datasets/activity/voip.csv
+++ b/datasets/activity/voip.csv
@ -1,3 +1,4 @@
 name, url, language, country
 OpenTalk activity, https://gitlab.opencode.de/opentalk.atom, en-US, Worldwide
 gajim activity, https://dev.gajim.org/gajim.atom, en-US, France
 Activity for I Hear U, https://sourceforge.net/p/ihu/activity/feed, en-US, Worldwide
--- a/datasets/activity/xmpp.csv
+++ b/datasets/activity/xmpp.csv
@ -5,3 +5,5 @@ Feed of "poezio/slixmpp", https://codeberg.org/poezio/slixmpp.atom, en-US, Franc
 Feed of "JoinJabber", https://codeberg.org/joinjabber.rss, en-US, Worldwide
 Feed of "poezio/poezio", https://codeberg.org/poezio/poezio.atom, en-US, France
 Feed of "poezio/biboumi", https://codeberg.org/poezio/biboumi.atom, en-US, France
 slidge activity, https://sr.ht/~nicoco/slidge/feed.rss, en-US, France
 ~singpolyma/cheogram-muc-bridge log, https://git.singpolyma.net/cheogram-muc-bridge/log/master/rss.xml, en-US, Worldwide
--- a/datasets/catalogues/game.csv
+++ b/datasets/catalogues/game.csv
@ -1,2 +1,3 @@
 name, url, language, country
 Open Source Game Clones: New/Updated Games, https://osgameclones.com/feed.xml, en-US, Worldwide
 Speed Dreams Maps, https://commut3r.wordpress.com/feed/, en-US, Worldwide
--- a/datasets/catalogues/software.csv
+++ b/datasets/catalogues/software.csv
@ -19,3 +19,4 @@ Newest Python PEPs, https://peps.python.org/peps.rss/, en-US, Worldwide
 Joomla! Extensions, https://extensions.joomla.org/browse/new/?format=feed&type=rss, en-US, Worldwide
 cblgh.org (wikis), https://cblgh.org/wikis.xml, en-US, Worldwide
 cblgh.org (projects), https://cblgh.org/projects.xml, en-US, Worldwide
 Recent files - The AROS Archives @ aros-exec.org, http://archives.aros-exec.org/modules/rssfeed.php, en-US, Worldwide
--- a/datasets/corporations/communication.csv
+++ b/datasets/corporations/communication.csv
@ -1,3 +1,6 @@
 name, url, language, country
 Ignite Realtime, https://discourse.igniterealtime.org/c/blogs/ignite-realtime-blogs/5.rss, en-US, Worldwide
 Twilio, https://www.twilio.com/blog/feed?locale=en, en-US, United States
 Andrews & Arnold Ltd (AAISP), https://social.aa.net.uk/@aaisp.rss, en-UK, United Kingdom
 The Tutanota Blog, https://tuta.com/blog/feed.xml, en-US, Worldwide
 Fastmail, https://www.fastmail.com/feed/, en-US, Worldwide
--- a/datasets/corporations/computing.csv
+++ b/datasets/corporations/computing.csv
@ -13,3 +13,4 @@ Debian Long Term Support on Freexian, https://www.freexian.com/lts/debian/index.
 BairesDev, https://www.bairesdev.com/feed/, en-US, United States
 Twilio, https://www.twilio.com/blog/feed?locale=en, en-US, United States
 PythonAnywhere, https://blog.pythonanywhere.com/index.xml, en-US, Texas
 SourceForge, https://fosstodon.org/@sourceforge.rss, en-US, California
--- a/datasets/corporations/hardware.csv
+++ b/datasets/corporations/hardware.csv
@ -1,3 +1,4 @@
 name, url, language, country
 Linaro - Arm-based solutions, https://www.linaro.org/feed.xml, en-US, United States
 MIPS, https://mips.com/feed/, en-US, California
 Altispeed Technologies, https://www.altispeed.com/rss.xml, en-US, Columbia
--- a/datasets/corporations/hosting.csv
+++ b/datasets/corporations/hosting.csv
@ -0,0 +1,5 @@
 name, url, language, country
 Altispeed Technologies, https://www.altispeed.com/rss.xml, en-US, Columbia
 Kyun, https://blog.kyun.host/atom, en-US, Romania
 Fastmail, https://www.fastmail.com/feed/, en-US, Worldwide
 The Tutanota Blog, https://tuta.com/blog/feed.xml, en-US, Worldwide
--- a/datasets/corporations/music.csv
+++ b/datasets/corporations/music.csv
@ -1,2 +1,3 @@
 name, url, language, country
 DopeSONIX VSTi VST AU Hip Hop Beatmaking Production Software, https://www.dopesonix.com/feed/, en-UK, England
 33 & West, https://www.33andwest.com/blog-feed.xml, en-US, United States
--- a/datasets/events/blockchain.csv
+++ b/datasets/events/blockchain.csv
@ -0,0 +1,2 @@
 name, url, language, country
 Monero Observer, https://monero.observer/feed-calendar.xml, en-US, Worldwide
--- a/datasets/events/internet.csv
+++ b/datasets/events/internet.csv
@ -4,3 +4,4 @@ FSFE Events (FR), https://fsfe.org/events/events.fr.rss, fr-FR, Germany
 FSFE Events (DE), https://fsfe.org/events/events.de.rss, de-DE, Germany
 cblgh.org - events, https://cblgh.org/events.xml, en-US, Worldwide
 IndieWeb Events, https://events.indieweb.org/feed, en-US, Germany
 Monero Observer, https://monero.observer/feed-calendar.xml, en-US, Worldwide
--- a/datasets/forums/computer.csv
+++ b/datasets/forums/computer.csv
@ -4,3 +4,4 @@ Arch Linux ARM, https://archlinuxarm.org/forum/feed.php, en-US, Worldwide
 Arch Linux, https://bbs.archlinux.org/extern.php?action=feed&type=atom, en-US, Worldwide
 Replicant: Messages, https://redmine.replicant.us/projects/replicant/activity.atom?show_messages=1, en-US, Worldwide
 Cacti, http://forums.cacti.net/app.php/feed, en-US, Worldwide
 Artix Linux Forum, https://forum.artixlinux.org/index.php?action=.xml;type=atom;limit=30, en-US, Worldwide
--- a/datasets/forums/game.csv
+++ b/datasets/forums/game.csv
@ -0,0 +1,5 @@
 name, url, language, country
 Speed Dreams Community, http://community.speed-dreams.org/feed.php, en-US, Worldwide
 Speed Dreams Community - New Topics, http://community.speed-dreams.org/feed.php?mode=topics, en-US, Worldwide
 VDrift Forums, https://vdrift.net/Forum/syndication.php?type=atom1.0, en-US, Worldwide
 GamingOnLinux, https://www.gamingonlinux.com/forum_rss.php, en-US, Worldwide
--- a/datasets/forums/linux.csv
+++ b/datasets/forums/linux.csv
@ -1,3 +1,5 @@
 name, url, language, country
 Arch Linux ARM, https://archlinuxarm.org/forum/feed.php, en-US, Worldwide
 Arch Linux, https://bbs.archlinux.org/extern.php?action=feed&type=atom, en-US, Worldwide
 nixCraft Linux/Unix Forum, https://www.nixcraft.com/posts.rss, en-US, Worldwide
 Artix Linux Forum, https://forum.artixlinux.org/index.php?action=.xml;type=atom;limit=30, en-US, Worldwide
--- a/datasets/forums/telecom.csv
+++ b/datasets/forums/telecom.csv
@ -0,0 +1,2 @@
 name, url, language, country
 SimpleX, https://lemmy.ml/feeds/c/simplex.xml?sort=Active, en-US, Worldwide
--- a/datasets/fronts/human_trafficking.csv
+++ b/datasets/fronts/human_trafficking.csv
@ -0,0 +1,5 @@
 name, url, language, country
 Polaris (Human Trafficking), https://polarisproject.org/feed/, en-US, United States
 Thorn (Human Trafficking), https://www.thorn.org/feed/, en-US, United States
 CATW (Human Trafficking), https://catwinternational.org/feed/, en-US, United States
 Freedom Light (Human Trafficking), https://www.freedomlight.org/feed/, en-US, United States
--- a/datasets/fronts/united_states.csv
+++ b/datasets/fronts/united_states.csv
@ -0,0 +1,5 @@
 name, url, language, country
 Polaris, https://polarisproject.org/feed/, en-US, United States
 Thorn, https://www.thorn.org/feed/, en-US, United States
 CATW, https://catwinternational.org/feed/, en-US, United States
 Freedom Light, https://www.freedomlight.org/feed/, en-US, United States
--- a/datasets/games/building.csv
+++ b/datasets/games/building.csv
@ -0,0 +1,2 @@
 name, url, language, country
 Minetest, https://blog.minetest.net/feed.rss, en-US, Worldwide
--- a/datasets/games/card.csv
+++ b/datasets/games/card.csv
@ -0,0 +1,2 @@
 name, url, language, country
 Pirate Solitaire Devlog - itch.io, https://victor-pernet.itch.io/pirate-solitaire/devlog.rss, en-US, Worldwide
--- a/datasets/games/fps.csv
+++ b/datasets/games/fps.csv
@ -0,0 +1,2 @@
 name, url, language, country
 Xonotic: The Free and Fast Arena Shooter, https://xonotic.org/index.xml, en-US, Worldwide
--- a/datasets/games/race.csv
+++ b/datasets/games/race.csv
@ -0,0 +1,7 @@
 name, url, language, country
 Speed Dreams, https://www.speed-dreams.net/en/feed/, en-US, Worldwide
 Speed Dreams, https://www.speed-dreams.net/fr/feed/, fr-FR, Worldwide
 SuperTuxKart, https://blog.supertuxkart.net/feeds/posts/default, en-US, Worldwide
 Recent posts to TORCS, https://sourceforge.net/p/torcs/news/feed.atom, en-US, Switzerland
 Recent posts to Speed Dreams, https://sourceforge.net/p/speed-dreams/news/feed.atom, en-US, Worldwide
 TROPHY, https://sourceforge.net/projects/trophy/rss, en-US, France
--- a/datasets/news/blockchain.csv
+++ b/datasets/news/blockchain.csv
@ -1,6 +1,11 @@
 name, url, language, country
 CryptoSlate, https://cryptoslate.com/feed/, en-US, United States
 CryptoPotato, https://cryptopotato.com/feed/, en-US, United States
-Decrypt, https://decrypt.co/feed, , en-US, United States
+Decrypt, https://decrypt.co/feed, en-US, United States
-
+Monero Observer, https://monero.observer/feed-mini.xml, en-US, Worldwide
 Ctrl blog: Crypto-currencies, https://feed.ctrl.blog/topic/crypto-currencies.atom, en-US, United States
 Monero Observer (stories), https://monero.observer/feed-stories-mini.xml, en-US, Worldwide
 Monero Observer (summaries), https://monero.observer/feed-summaries.xml, en-US, Worldwide
 Monero, https://www.getmonero.org/feed.xml, en-US, Worldwide
 Cryptocurrency – Simplified Privacy, https://simplifiedprivacy.com/category/cryptocurrency/feed/, en-US, Cambodia
 Particl News, https://particl.news/rss, en-US, Worldwide
--- a/datasets/news/business.csv
+++ b/datasets/news/business.csv
@ -14,9 +14,12 @@ ynet - כלכלה, https://www.ynet.co.il/Integration/StoryRss6.xml, he-IL, Isra
 דה מרקר - פרשנויות היום, https://www.themarker.com/srv/tm-opinions, he-IL, Israel
 שוק ההון והשקעות, https://www.globes.co.il/webservice/rss/rssfeeder.asmx/FeederNode?iID=585, he-IL, Israel
 StockNews, https://stocknews.com/feed/, en-US, United States
 Network World, https://www.networkworld.com/feed/, en-US, Worldwide
 Phoronix, https://www.phoronix.com/rss.php, en-US, United States
 Business Writing Info Blog, https://www.instructionalsolutions.com/blog/rss.xml, en-US, United States
 Fastmail, https://www.fastmail.com/feed/, en-US, Worldwide
 BairesDev, https://www.bairesdev.com/feed/, en-US, United States
 Educate 360 Professional Training Partners, https://educate360.com/feed/, en-US, Worldwide
 Simplex Group, https://simplexgroup.net/feed/, en-US, Illinois
--- a/datasets/news/canada.csv
+++ b/datasets/news/canada.csv
@ -1,2 +1,6 @@
 name, url, language, country
 blogTO, http://www.blogto.com/rss/articles.xml, en-US, Canada
 Kirksville Today, https://www.kirksvilletoday.com/feed/, en-US, United States
 Mami's Shit, http://grizzom.blogspot.com/feeds/posts/default, en-US, United States
 Vanguard News Network, http://www.vanguardnewsnetwork.com/feed/, en-US, United States
 National Vanguard, https://nationalvanguard.org/feed/, en-US, United States
--- a/datasets/news/censorship.csv
+++ b/datasets/news/censorship.csv
@ -0,0 +1,3 @@
 name, url, language, country
 Reclaim The Net, https://reclaimthenet.org/feed, en-US, United States
 Propaganda & Censorship – Simplified Privacy, https://simplifiedprivacy.com/category/censorship/feed/, en-US, Cambodia
--- a/datasets/news/code.csv
+++ b/datasets/news/code.csv
@ -15,3 +15,4 @@ Lainblog, https://blog.soykaf.com/index.xml, en-US, Worldwide
 PythonAnywhere, https://blog.pythonanywhere.com/index.xml, en-US, Texas
 Mario Alberto Chávez Cárdenas, https://mariochavez.io/feed.xml, en-US, Worldwide
 metajack.im, https://metajack.im/atom.xml, en-US, Worldwide
 njanakiev, https://janakiev.com/feed.xml, en-US, Austria
--- a/datasets/news/computer.csv
+++ b/datasets/news/computer.csv
@ -1,26 +1,39 @@
 name, url, language, country
 Blog de Stéphane Bortzmeyer, https://www.bortzmeyer.org/feed.atom, fr-FR, France
 Simon Willison's Weblog, https://simonwillison.net/atom/everything/, en-US, Worldwide
 The Tutanota Blog, https://tuta.com/blog/feed.xml, en-US, Worldwide
 Read the Tea Leaves, https://nolanlawson.com/feed/, en-US, Worldwide
 Big Tech is Evil – Simplified Privacy, https://simplifiedprivacy.com/category/big-tech-is-evil/feed/, en-US, Cambodia
 Farooq's, https://far.chickenkiller.com/index.xml, en-US, Iran
 Posts on deuill.org, https://deuill.org/post/index.xml, en-US, Worldwide
 Encryption & File Tools – Simplified Privacy, https://simplifiedprivacy.com/category/encryption-files/feed/, en-US, Cambodia
 Gadgets To Use, https://gadgetstouse.com/feed/, en-US, Worldwide
 njanakiev, https://janakiev.com/feed.xml, en-US, Austria
 کرم‌های کامپیوتر, https://pcworms.ir/feed/, ir-IR, Iran
 Phones & Service – Simplified Privacy, https://simplifiedprivacy.com/category/phones-service-2fa/feed/, en-US, Cambodia
 Agate Blue, https://agate.blue/feed.xml, fr-FR, France
 HotHardware, https://hothardware.com/rss/news.aspx, en-US, Worldwide
 News You Can Bruise, https://www.crummy.com/atom.xml, en-US, Worldwide
 Michael W Lucas, https://mwl.io/feed, en-US, United States
 Andriy Utkin, http://autkin.net/feed.xml, en-US, United States
 Jan Wagemakers, https://www.janwagemakers.be/jekyll/feed.xml, en-US, Belgium
 Remko Tronçon (mko.re), https://el-tramo.be/feed.xml, en-US, Germany
 Martins Schmierzettel, https://blog.mdosch.de/index.xml, de-DE, Germany
 Fastmail, https://www.fastmail.com/feed/, en-US, Worldwide
 Network World, https://www.networkworld.com/feed/, en-US, Worldwide
 Hacking around oppressions, https://bouah.net/index.xml, en-US, France
 Virtual Machines – Simplified Privacy, https://simplifiedprivacy.com/category/virtual-machines/feed/, en-US, Cambodia
 Tatsumoto Ren, https://tatsumoto.neocities.org/blog/feed.rss, en-US, Japan
 metajack.im, https://metajack.im/atom.xml, en-US, Worldwide
 Hugo Barrera, https://whynothugo.nl/posts.xml, en-US, Netherlands
 Truthstream Media, https://truthstreammedia.com/feed/, en-US, United States
 Liliputing, https://liliputing.com/feed/, en-US, Worldwide
 Mario Sabatino Gemini capsule, https://gemini.sabatino.cloud/rss.xml, it-IT, Italy
 Lainblog, https://blog.soykaf.com/index.xml, en-US, Worldwide
 camen design, https://camendesign.com/rss, en-US, United States
 computers are bad, https://computer.rip/rss.xml, en-US, Worldwide
 Machina Speculatrix, https://mansfield-devine.com/speculatrix/feed/, en-US, Worldwide
-Rabin.IO, https://blog.rabin.io/feed, en-US, Worldwide
+/home/rabin.io/notes, https://blog.rabin.io/feed, en-US, Worldwide
 Jacob McCormick, https://mccor.xyz/rss.xml, en-US, United States
 Alle Neuigkeiten von jotwewe.de, http://www.jotwewe.de/alles_de.xml, en-US, Germany
 Alle Neuigkeiten von jotwewe.de, http://www.jotwewe.de/alles_de.xml, de-DE, Germany
--- a/datasets/news/culture.csv
+++ b/datasets/news/culture.csv
@ -7,11 +7,14 @@ ynet - Culture, https://www.ynet.co.il/Integration/StoryRss3086.xml, en-IL, Isra
 ynet - חדר משלך, https://www.ynet.co.il/Integration/StoryRss4111.xml, he-IL, Israel
 Tampa Free Press, https://www.tampafp.com/feed/, en-US, United States
 Deutsche Welle: DW.com KULTUR & LEBEN, http://rss.dw.com/atom/rss-de-cul, de-DE, Germany
 Kirksville Today, https://www.kirksvilletoday.com/feed/, en-US, United States
 Deutsche Welle: DW.com KULTUR & LEBEN: BÜCHER, http://rss.dw.com/atom/rss-de-cul-buch, de-DE, Germany
 Fakeologist, https://fakeologist.com/feed/, en-US, Canada
 Deutsche Welle: DW.com KULTUR & LEBEN: FILM, http://rss.dw.com/atom/rss-de-cul-film, de-DE, Germany
 Mami's Shit, http://grizzom.blogspot.com/feeds/posts/default, en-US, United States
 Deutsche Welle: DW.com KULTUR & LEBEN: MUSIK, http://rss.dw.com/atom/rss-de-cul-musik, de-DE, Germany
 Deutsche Welle: DW.com DEUTSCHLAND ENTDECKEN, http://rss.dw.com/atom/rss-de-deutschlandentdecken, de-DE, Germany
 Truthstream Media, https://truthstreammedia.com/feed/, en-US, United States
 Kopimi, https://kopimi.com/feed/, en-US, Sweden
 Mashable, https://mashable.com/feeds/rss/all, en-US, United States
 За вашу и нашу Свободу!, https://lev-sharansky2.livejournal.com/data/atom, ru-RU, Russia
--- a/datasets/news/cybersecurity.csv
+++ b/datasets/news/cybersecurity.csv
@ -1,11 +1,14 @@
 name, url, language, country
 Blog de Stéphane Bortzmeyer, https://www.bortzmeyer.org/feed.atom, fr-FR, France
 Hacking around oppressions, https://bouah.net/index.xml, en-US, France
 Michael W Lucas, https://mwl.io/feed, en-US, United States
 Necuno Solutions, https://necunos.com/feed.xml, en-US, Finland
 Flipper Blog, https://blog.flipper.net/rss/, en-US, United States
 ollieparanoid, https://ollieparanoid.github.io/feed.xml, en-US, United States
 FSFE News, https://fsfe.org/news/news.en.rss, en-US, Germany
 Encryption & File Tools – Simplified Privacy, https://simplifiedprivacy.com/category/encryption-files/feed/, en-US, Cambodia
 FSFE News (DE), https://fsfe.org/news/news.de.rss, de-DE, Germany
 FSFE News (FR), https://fsfe.org/news/news.fr.rss, fr-FR, Germany
 Schneier on Security, https://www.schneier.com/feed/atom/, en-US, United States
 Kuketz IT-Security » Blog + Microblog, https://www.kuketz-blog.de/feed/, de-DE, Germany
 Security & 2FA – Simplified Privacy, https://simplifiedprivacy.com/category/security/feed/, en-US, Cambodia
--- a/datasets/news/electronics.csv
+++ b/datasets/news/electronics.csv
@ -7,6 +7,7 @@ FSFE News, https://fsfe.org/news/news.en.rss, en-US, Germany
 FSFE News (DE), https://fsfe.org/news/news.de.rss, de-DE, Germany
 FSFE News (FR), https://fsfe.org/news/news.fr.rss, fr-FR, Germany
 heise online News, https://www.heise.de/rss/heise-atom.xml, de-DE, Germany
 Truthstream Media, https://truthstreammedia.com/feed/, en-US, United States
 c't Magazin, https://social.heise.de/@ct_Magazin.rss, de-DE, Germany
 electro·pizza, https://electro.pizza/feed.xml, en-US, United States
 IdleBlog, http://blog.idleman.fr/feed/, fr-FR, France
--- a/datasets/news/europe.csv
+++ b/datasets/news/europe.csv
@ -7,11 +7,14 @@ Deutsche Welle: DW.com DEUTSCHLAND ENTDECKEN, http://rss.dw.com/atom/rss-de-deut
 Deutsche Welle: DW.com PRESSE, http://rss.dw.com/atom/presse, de-DE, Germany
 "ZEIT ONLINE | Nachrichten, News, Hintergründe und Debatten", https://newsfeed.zeit.de/index, de-DE, Germany
 strukturart.com latest articles,https://strukturart.com/feed, de-DE, Germany
 Kirksville Today, https://www.kirksvilletoday.com/feed/, en-US, United States
 classless Kulla, https://www.classless.org/feed/atom/, de-DE, Germany
 classless Kulla, https://www.classless.org/feed/atom/, en-US, Germany
 ZDFheute, https://www.zdf.de/rss/zdf/nachrichten, de-DE, Germany
 Kasparov, https://www.kasparov.com/feed/, en-US, United States
 РЖЕВСКАЯ ПРАВДА, https://presska.ru/feed/, ru-RU, Russia
 Mami's Shit, http://grizzom.blogspot.com/feeds/posts/default, en-US, United States
 За вашу и нашу Свободу!, https://lev-sharansky2.livejournal.com/data/atom, ru-RU, Russia
 Meduza.io, https://meduza.io/rss/en/all, en-US, United States
-
+Vanguard News Network, http://www.vanguardnewsnetwork.com/feed/, en-US, United States
 National Vanguard, https://nationalvanguard.org/feed/, en-US, United States
--- a/datasets/news/gaming.csv
+++ b/datasets/news/gaming.csv
@ -1,3 +1,8 @@
 name, url, language, country
 DESIGNER NOTES, http://www.designer-notes.com/feed/, en-US, United States
 Kitsune Games, http://kitsunegames.com/feed.xml, en-US, Worldwide
 Speed Dreams, https://mastodon.social/@speed_dreams_official.rss, en-US, Worldwide
 Le Bottin des Jeux Linux, https://floss.social/@Le_bottin_des_jeux_linux.rss, fr-FR, France
 GamingOnLinux, https://www.gamingonlinux.com/article_rss.php, en-US, Worldwide
 Le Bottin des Jeux Linux / The Linux Games Book, http://www.lebottindesjeuxlinux.tuxfamily.org/en/feed/, fr-FR, France
 Minetest, https://fosstodon.org/@Minetest.rss, en-US, Worldwide
--- a/datasets/news/general.csv
+++ b/datasets/news/general.csv
@ -8,8 +8,11 @@ Courageous Discourse™ with Dr. Peter McCullough & John Leake, https://petermcc
 DER SPIEGEL - International, https://www.spiegel.de/international/index.rss, en-US, Germany
 nobulart - Exploring the Great Reset, https://nobulart.com/feed/, en-US, United States
 Jerm Warfare, https://jermwarfare.com/feed, en-US, United States
 Mami's Shit, http://grizzom.blogspot.com/feeds/posts/default, en-US, United States
 Daily Stormer, https://dailystormer.in/feed/, en-US, United States
 Associated Press News, https://apnews.com/index.rss, en-US, United States
 Deutsche Welle: DW.com NACHRICHTEN, http://rss.dw.com/atom/rss-de-news, de-DE, Germany
 Real Liberty Media, https://www.reallibertymedia.com/feed/, en-US, United States
 PetaPixel, https://petapixel.com/feed/, en-US, Worldwide
 Vanguard News Network, http://www.vanguardnewsnetwork.com/feed/, en-US, United States
 National Vanguard, https://nationalvanguard.org/feed/, en-US, United States
--- a/datasets/news/geography.csv
+++ b/datasets/news/geography.csv
@ -0,0 +1,3 @@
 name, url, language, country
 NACIS, https://nacis.org/feed/, en-US, United States
 Natural Earth, https://www.naturalearthdata.com/feed/, en-US, United States
--- a/datasets/news/germany.csv
+++ b/datasets/news/germany.csv
@ -10,3 +10,5 @@ strukturart.com latest articles,https://strukturart.com/feed, de-DE, Germany
 classless Kulla, https://www.classless.org/feed/atom/, de-DE, Germany
 classless Kulla, https://www.classless.org/feed/atom/, en-US, Germany
 ZDFheute, https://www.zdf.de/rss/zdf/nachrichten, de-DE, Germany
 Vanguard News Network, http://www.vanguardnewsnetwork.com/feed/, en-US, United States
 National Vanguard, https://nationalvanguard.org/feed/, en-US, United States
--- a/datasets/news/government.csv
+++ b/datasets/news/government.csv
@ -3,13 +3,16 @@ Fakeologist, https://fakeologist.com/feed/, en-US, Canada
 The Corbett Report, https://www.corbettreport.com/feed/, en-US, Japan
 ZeroGov, https://zerogov.com/feed/, en-US, United States
 Daily Stormer, https://dailystormer.in/feed/, en-US, United States
 Truthstream Media, https://truthstreammedia.com/feed/, en-US, United States
 The Organic Prepper, https://www.theorganicprepper.com/feed/, en-US, United States
 The Hill News, https://thehill.com/feed/?feed=partnerfeed-news-feed&format=rss, en-US, United States
 Jerm Warfare, https://jermwarfare.com/feed, en-US, United States
 Kirksville Today, https://www.kirksvilletoday.com/feed/, en-US, United States
 nobulart - Exploring the Great Reset, https://nobulart.com/feed/, en-US, United States
 John W. Whitehead, Constitutional Attorney, https://agovernmentofwolves.com/feed/, en-US, United States
 BlackListed News, https://www.blacklistednews.com/rss.php, en-US, United States
 Tampa Free Press, https://www.tampafp.com/feed/, en-US, United States
 Mami's Shit, http://grizzom.blogspot.com/feeds/posts/default, en-US, United States
 Deutsche Welle: DW.com POLITIK, http://rss.dw.com/atom/rss_de_politik, de-DE, Germany
 Real Liberty Media, https://www.reallibertymedia.com/feed/, en-US, United States
 Robert Reich, https://robertreich.substack.com/feed, en-US, United States
@ -19,3 +22,6 @@ ZDFheute, https://www.zdf.de/rss/zdf/nachrichten, de-DE, Germany
 Sam Bent aka DoingFedTime, https://www.doingfedtime.com/feed/, en-US, United States
 (RTP) Privacy & Tech Tips, https://fosstodon.org/@RTP.rss, en-US, Worldwide
 the OpenAustralia Foundation, https://www.oaf.org.au/feed/, en-AU, Australia
 Vanguard News Network, http://www.vanguardnewsnetwork.com/feed/, en-US, United States
 National Vanguard, https://nationalvanguard.org/feed/, en-US, United States
 Voice of America, https://www.voanews.com/api/, en-US, United States
--- a/datasets/news/hardware.csv
+++ b/datasets/news/hardware.csv
@ -1,2 +1,4 @@
 name, url, language, country
 Phoronix, https://www.phoronix.com/rss.php, en-US, United States
 Truthstream Media, https://truthstreammedia.com/feed/, en-US, United States
 HotHardware, https://hothardware.com/rss/news.aspx, en-US, Worldwide
--- a/datasets/news/history.csv
+++ b/datasets/news/history.csv
@ -1,4 +1,9 @@
 name, url, language, country
 Historic.ly, https://www.historicly.net/feed, en-US, United States
 Mami's Shit, http://grizzom.blogspot.com/feeds/posts/default, en-US, United States
 classless Kulla, https://www.classless.org/feed/atom/, de-DE, Germany
 classless Kulla, https://www.classless.org/feed/atom/, en-US, Germany
 Kirksville Today, https://www.kirksvilletoday.com/feed/, en-US, United States
 Truthstream Media, https://truthstreammedia.com/feed/, en-US, United States
 Vanguard News Network, http://www.vanguardnewsnetwork.com/feed/, en-US, United States
 National Vanguard, https://nationalvanguard.org/feed/, en-US, United States
--- a/datasets/news/internet.csv
+++ b/datasets/news/internet.csv
@ -1,10 +1,23 @@
 name, url, language, country
 Blog de Stéphane Bortzmeyer, https://www.bortzmeyer.org/feed.atom, fr-FR, France
 Read the Tea Leaves, https://nolanlawson.com/feed/, en-US, Worldwide
 Phones & Service – Simplified Privacy, https://simplifiedprivacy.com/category/phones-service-2fa/feed/, en-US, Cambodia
 jezebel cheblik, gopher://triapul.cz/0/rss.xml, en-US, United States
 triapul.cz gopher, https://triapul.cz/feed/gopher.xml, en-US, Czech
 soeren-hentzschel.at - Aktuelles zu Mozilla, https://www.soeren-hentzschel.at/feed/, de-DE, Germany
 The Tutanota Blog, https://tuta.com/blog/feed.xml, en-US, Worldwide
 Tor – Simplified Privacy, https://simplifiedprivacy.com/category/tor/feed/, en-US, Cambodia
 GNU social, http://www.gnusocial.rocks/feed.rss, en-US, Worldwide
 Private Messengers & Apps – Simplified Privacy, https://simplifiedprivacy.com/category/private-messengers-apps/feed/, en-US, Cambodia
 Truthstream Media, https://truthstreammedia.com/feed/, en-US, United States
 IndieWeb, https://indieweb.org/wiki/index.php?title=Special:RecentChanges&feed=atom, en-US, Worldwide
 VPNs & Browsers – Simplified Privacy, https://simplifiedprivacy.com/category/vpns-browsers/feed/, en-US, Cambodia
 Fastmail, https://www.fastmail.com/feed/, en-US, Worldwide
 Security & 2FA – Simplified Privacy, https://simplifiedprivacy.com/category/security/feed/, en-US, Cambodia
 Email – Simplified Privacy, https://simplifiedprivacy.com/category/email/feed/, en-US, Cambodia
 Network World, https://www.networkworld.com/feed/, en-US, Worldwide
 Simplified Privacy, https://simplifiedprivacy.com/feed/, en-US, Cambodia
 SimpleX Chat, https://mastodon.social/@simplex.rss, en-US, Worldwide
 Fediverse.Party - explore federated networks, https://fediverse.party/atom.xml, en-US, Worldwide
 Takahē Project, https://takahe.social/@takahe@jointakahe.org/rss/, en-US, Worldwide
 404 Media, https://www.404media.co/rss/, en-US, United States
--- a/datasets/news/lifestyle.csv
+++ b/datasets/news/lifestyle.csv
@ -4,3 +4,5 @@ The Organic Prepper, https://www.theorganicprepper.com/feed/, en-US, United Stat
 XXIIVV, https://wiki.xxiivv.com/links/rss.xml, en-US, Canada
 Divine Lifestyle, https://divinelifestyle.com/feed/, en-US, United States
 lectronice :: now, https://now.lectronice.com/feed.xml, en-US, United States
 Truthstream Media, https://truthstreammedia.com/feed/, en-US, United States
 Simplified Privacy, https://simplifiedprivacy.com/feed/, en-US, Cambodia
--- a/datasets/news/linux.csv
+++ b/datasets/news/linux.csv
@ -1,16 +1,20 @@
 name, url, language, country
 Breaking updates in postmarketOS edge, https://postmarketos.org/edge/feed.atom, en-US, Germany
 Arch Linux: Recent news updates, https://archlinux.org/feeds/news/, en-US, Worldwide
 Michael W Lucas, https://mwl.io/feed, en-US, United States
 Jan Wagemakers, https://www.janwagemakers.be/jekyll/feed.xml, en-US, Belgium
 code monk | hacking habits, https://drj11.wordpress.com/feed/, en-US, United States
 Remko Tronçon (mko.re), https://el-tramo.be/feed.xml, en-US, Germany
 Linux Professional Institute (LPI), https://www.lpi.org/feed/, en-US, Canada
 LinuxConfig, https://linuxconfig.org/feed, en-US, Worldwide
 Virtual Machines – Simplified Privacy, https://simplifiedprivacy.com/category/virtual-machines/feed/, en-US, Cambodia
 The Logs, https://www.flu0r1ne.net/logs/rss.xml, en-US, United States
 Hugo Barrera, https://whynothugo.nl/posts.xml, en-US, Netherlands
 Ctrl blog: Fedora Linux, https://feed.ctrl.blog/topic/fedora-linux.atom, en-US, United States
 Ctrl blog: Linux, https://feed.ctrl.blog/topic/linux.atom, en-US, United States
 Anjan Momi, https://momi.ca/feed.xml, en-US, United States
 This Week in GNOME, https://thisweek.gnome.org/index.xml, en-US, Worldwide
 Linux – Simplified Privacy, https://simplifiedprivacy.com/category/linux/feed/, en-US, Cambodia
 Phoronix, https://www.phoronix.com/rss.php, en-US, United States
 Kuketz IT-Security » Blog + Microblog, https://www.kuketz-blog.de/feed/, de-DE, Germany
 postmarketOS, https://postmarketos.org/blog/feed.atom, en-US, United States
@ -34,3 +38,4 @@ Collabora Office and Collabora Online, https://www.collaboraoffice.com/feed/, en
 LGUG2Z, https://lgug2z.com/index.xml, en-US, United States
 Hugo Barrera's site, https://whynothugo.nl/posts.xml, en-US, United States
 ShadowKat Studios, https://shadowkat.net/rss.xml, en-US, Worldwide
 GTK, https://floss.social/@GTK.rss, en-US, United States
--- a/datasets/news/literature.csv
+++ b/datasets/news/literature.csv
@ -8,3 +8,4 @@ Michael W Lucas, https://mwl.io/feed, en-US, United States
 classless Kulla, https://www.classless.org/feed/atom/, de-DE, Germany
 classless Kulla, https://www.classless.org/feed/atom/, en-US, Germany
 National Novel Writing Month, https://blog.nanowrimo.org/rss, en-US, California
 thecozy.cat, https://thecozy.cat/feed/, en-US, Worldwide
--- a/datasets/news/misc.csv
+++ b/datasets/news/misc.csv
@ -5,3 +5,4 @@ Ctrl blog: Metadata, https://feed.ctrl.blog/topic/metadata.atom, en-US, United S
 Ctrl blog: Compression, https://feed.ctrl.blog/topic/compression.atom, en-US, United States
 Ctrl blog: Backup, https://feed.ctrl.blog/topic/backup.atom, en-US, United States
 Kopimi, https://kopimi.com/feed/, en-US, Sweden
 thecozy.cat, https://thecozy.cat/feed/, en-US, Worldwide
--- a/datasets/news/music.csv
+++ b/datasets/news/music.csv
@ -1,3 +1,6 @@
 name, url, language, country
 Funkwhale, https://blog.funkwhale.audio/feeds/all.atom.xml, en-US, Worldwide
 Agate Blue, https://agate.blue/feed.xml, fr-FR, France
 incompetech, https://incompetech.com/wordpress/feed/, en-US, Worldwide
 Immortal Guardian, https://www.immortalguardian.net/blog-feed.xml, en-US, United States
 33 & West, https://www.33andwest.com/blog-feed.xml, en-US, United States
--- a/datasets/news/opinion.csv
+++ b/datasets/news/opinion.csv
@ -1,9 +1,9 @@
 name, url, language, country
 Farooq's, https://far.chickenkiller.com/index.xml, en-US, Iran
 کرم‌های کامپیوتر, https://pcworms.ir/feed/, ir-IR, Iran
-National Vanguard, https://nationalvanguard.org/feed/, en-US, USA
+National Vanguard, https://nationalvanguard.org/feed/, en-US, United States
-Vanguard News Network, http://www.vanguardnewsnetwork.com/feed/, en-US, USA
+Vanguard News Network, http://www.vanguardnewsnetwork.com/feed/, en-US, United States
 דה מרקר - פרשנויות היום, https://www.themarker.com/srv/tm-opinions, he-IL, Israel
-Richard Stallman's Political Notes, https://stallman.org/rss/rss.xml, en-US, USA
+Richard Stallman's Political Notes, https://stallman.org/rss/rss.xml, en-US, United States
 ynet - דעות, https://www.ynet.co.il/Integration/StoryRss194.xml, he-IL, Israel
--- a/datasets/news/people.csv
+++ b/datasets/news/people.csv
@ -1,6 +1,9 @@
 name, url, language, country
 Stéphane Bortzmeyer, https://mastodon.gougere.fr/@bortzmeyer.rss, fr-FR, France
 Blog de Stéphane Bortzmeyer, https://www.bortzmeyer.org/feed.atom, fr-FR, France
 Simon Willison's Weblog, https://simonwillison.net/atom/everything/, en-US, Worldwide
 Read the Tea Leaves, https://nolanlawson.com/feed/, en-US, Worldwide
-hollie butler, https://eilloh.net/feed.xml en-US, Worldwide
+hollie butler, https://eilloh.net/feed.xml, en-US, Worldwide
 Farooq Karimi Zadeh (@farooqkz@qoto.org), https://qoto.org/@farooqkz.rss, en-US, Iran
 کرم‌های کامپیوتر, https://pcworms.ir/feed/, ir-IR, Iran
 Farooq's, https://far.chickenkiller.com/index.xml, en-US, Iran
@ -12,8 +15,11 @@ Hugo Barrera, https://whynothugo.nl/posts.xml, en-US, Netherlands
 Remko Tronçon (mko.re), https://el-tramo.be/feed.xml, en-US, Germany
 Hacking around oppressions, https://bouah.net/index.xml, en-US, France
 Jerm Warfare, https://jermwarfare.com/feed, en-US, United States
 Dan d'Auge, https://mamot.fr/@dandauge.rss, fr-FR, France
 iMOM, https://www.imom.com/feed/, en-US, United States
 Mario Sabatino Gemini capsule, https://gemini.sabatino.cloud/rss.xml, it-IT, Italy
 Mami's Shit, http://grizzom.blogspot.com/feeds/posts/default, en-US, United States
 nicoco's blog, https://www.nicoco.fr/feed/blog.xml, en-US, France
 Mom on a Mission, https://www.mom-on-a-mission.blog/all-posts?format=rss, en-US, United States
 Michael W Lucas, https://mwl.io/feed, en-US, United States
 Martins Schmierzettel, https://blog.mdosch.de/index.xml, de-DE, Germany
@ -21,7 +27,6 @@ Alixander Court, https://alixandercourt.com/feed/, en-US, United States
 Anjan Momi, https://momi.ca/feed.xml, en-US, United States
 Amethyst Reese, https://noswap.com/feed.xml, en-US, United States
 Dan d'Auge, https://fedi.thechangebook.org/feed/dandauge, fr-FR, France
 Dan d'Auge, https://mamot.fr/@dandauge.rss, fr-FR, France
 Christof Meerwald, https://cmeerw.org/blog.atom, en-US, Austria
 Christof Meerwald, http://cmeerw.org/blog.rdf, en-US, Austria
 PureTryOut, https://mastodon.fam-ribbers.com/@bart.rss, en-US, Netherlands
@ -61,3 +66,4 @@ alexander cobleigh (updates), https://cblgh.org/updates.xml, en-US, United State
 Daniel Aleksandersen, https://mastodon.daniel.priv.no/@da.rss, en-US, United States
 Laslo Hunhold, https://laslo.hunhold.de/index.xml, en-US, Germany
 Kitty Cat, https://kitty.social/@Kitty.rss, en-US, Worldwide
 Kirksville Today, https://www.kirksvilletoday.com/feed/, en-US, United States
--- a/datasets/news/pharma.csv
+++ b/datasets/news/pharma.csv
@ -1,2 +1,3 @@
 name, url, language, country
-STAT, https://www.statnews.com/feed/, en-US, USA
+STAT, https://www.statnews.com/feed/, en-US, United States
 Truthstream Media, https://truthstreammedia.com/feed/, en-US, United States
--- a/datasets/news/privacy.csv
+++ b/datasets/news/privacy.csv
@ -2,9 +2,15 @@ name, url, language, country
 Hacking around oppressions, https://bouah.net/index.xml, en-US, France
 The Logs, https://www.flu0r1ne.net/logs/rss.xml, en-US, United States
 Necuno Solutions, https://necunos.com/feed.xml, en-US, Finland
 Why Privacy – Simplified Privacy, https://simplifiedprivacy.com/category/why-privacy/feed/, en-US, Cambodia
 Phones & Service – Simplified Privacy, https://simplifiedprivacy.com/category/phones-service-2fa/feed/, en-US, Cambodia
 ollieparanoid, https://ollieparanoid.github.io/feed.xml, en-US, United States
 FSFE News, https://fsfe.org/news/news.en.rss, en-US, Germany
 Encryption & File Tools – Simplified Privacy, https://simplifiedprivacy.com/category/encryption-files/feed/, en-US, Cambodia
 OpenNews.opennet.ru: Общая лента новостей, https://www.opennet.ru/opennews/opennews_all_utf.rss, ru-RU, Russia
 Private Messengers & Apps – Simplified Privacy, https://simplifiedprivacy.com/category/private-messengers-apps/feed/, en-US, Cambodia
 The Tutanota Blog, https://tuta.com/blog/feed.xml, en-US, Worldwide
 SimpleX Chat, https://mastodon.social/@simplex.rss, en-US, Worldwide
 FSFE News (DE), https://fsfe.org/news/news.de.rss, de-DE, Germany
 FSFE News (FR), https://fsfe.org/news/news.fr.rss, fr-FR, Germany
 EFF Action Center, https://act.eff.org/action.atom, en-US, United States
@ -15,3 +21,9 @@ Reclaim The Net, https://reclaimthenet.org/feed, en-US, United States
 404 Media, https://www.404media.co/rss/, en-US, United States
 (RTP) Privacy & Tech Tips, https://fosstodon.org/@RTP.rss, en-US, Worldwide
 Sam Bent aka DoingFedTime, https://www.doingfedtime.com/feed/, en-US, United States
 Truthstream Media, https://truthstreammedia.com/feed/, en-US, United States
 Big Tech is Evil – Simplified Privacy, https://simplifiedprivacy.com/category/big-tech-is-evil/feed/, en-US, Cambodia
 Simplified Privacy, https://simplifiedprivacy.com/feed/, en-US, Cambodia
 Virtual Machines – Simplified Privacy, https://simplifiedprivacy.com/category/virtual-machines/feed/, en-US, Cambodia
 VPNs & Browsers – Simplified Privacy, https://simplifiedprivacy.com/category/vpns-browsers/feed/, en-US, Cambodia
 Tor – Simplified Privacy, https://simplifiedprivacy.com/category/tor/feed/, en-US, Cambodia
--- a/datasets/news/propaganda.csv
+++ b/datasets/news/propaganda.csv
@ -1,4 +1,6 @@
 name, url, language, country
-Daily Stormer, https://dailystormer.in/feed/, en-US, USA
+Daily Stormer, https://dailystormer.in/feed/, en-US, United States
 Truthstream Media, https://truthstreammedia.com/feed/, en-US, United States
 Fakeologist, https://fakeologist.com/feed/, en-US, Canada
 העין השביעית, https://www.the7eye.org.il/feed, he-IL, Israel
 Propaganda & Censorship – Simplified Privacy, https://simplifiedprivacy.com/category/censorship/feed/, en-US, Cambodia
--- a/datasets/news/surveillance.csv
+++ b/datasets/news/surveillance.csv
@ -1,6 +1,10 @@
 name, url, language, country
 Why Privacy – Simplified Privacy, https://simplifiedprivacy.com/category/why-privacy/feed/, en-US, Cambodia
 Necuno Solutions, https://necunos.com/feed.xml, en-US, Finland
 Reclaim The Net, https://reclaimthenet.org/feed, en-US, United States
 404 Media, https://www.404media.co/rss/, en-US, United States
 (RTP) Privacy & Tech Tips, https://fosstodon.org/@RTP.rss, en-US, Worldwide
 Sam Bent aka DoingFedTime, https://www.doingfedtime.com/feed/, en-US, United States
 Truthstream Media, https://truthstreammedia.com/feed/, en-US, United States
 The Tutanota Blog, https://tuta.com/blog/feed.xml, en-US, Worldwide
 Big Tech is Evil – Simplified Privacy, https://simplifiedprivacy.com/category/big-tech-is-evil/feed/, en-US, Cambodia
--- a/datasets/news/survival.csv
+++ b/datasets/news/survival.csv
@ -1,4 +1,6 @@
 name, url, language, country
 The Organic Prepper, https://www.theorganicprepper.com/feed/, en-US, United States
 nobulart - Exploring the Great Reset, https://nobulart.com/feed/, en-US, United States
-
+Vanguard News Network, http://www.vanguardnewsnetwork.com/feed/, en-US, United States
 National Vanguard, https://nationalvanguard.org/feed/, en-US, United States
 Encryption & File Tools – Simplified Privacy, https://simplifiedprivacy.com/category/encryption-files/feed/, en-US, Cambodia
--- a/datasets/news/technology.csv
+++ b/datasets/news/technology.csv
@ -1,17 +1,23 @@
 name, url, language, country
 Read the Tea Leaves, https://nolanlawson.com/feed/, en-US, Worldwide
 Farooq's, https://far.chickenkiller.com/index.xml, en-US, Iran
 Posts on deuill.org, https://deuill.org/post/index.xml, en-US, Worldwide
 Gadgets To Use, https://gadgetstouse.com/feed/, en-US, Worldwide
 کرم‌های کامپیوتر, https://pcworms.ir/feed/, ir-IR, Iran
 Hacking around oppressions, https://bouah.net/index.xml, en-US, France
 404 Media, https://www.404media.co/rss/, en-US, United States
 Simplified Privacy, https://simplifiedprivacy.com/feed/, en-US, Cambodia
 Truthstream Media, https://truthstreammedia.com/feed/, en-US, United States
 SimpleX Chat, https://mastodon.social/@simplex.rss, en-US, Worldwide
 Redecentralize Blog, https://redecentralize.org/blog/feed.rss, en-US, United States
 Developpez, https://www.developpez.com/index/atom, fr-FR, France
 North Korea Tech – 노스코리아테크, https://www.northkoreatech.org/feed/, en-US, South Korea
 The Logs, https://www.flu0r1ne.net/logs/rss.xml, en-US, United States
 CryptoSlate, https://cryptoslate.com/feed/, en-US, United States
 HotHardware, https://hothardware.com/rss/news.aspx, en-US, Worldwide
 Codemadness, https://codemadness.org/atom.xml, en-US, United States
 Chiportal, https://chiportal.co.il/feed/, he-IL, Israel
 Network World, https://www.networkworld.com/feed/, en-US, Worldwide
 Daily Stormer, https://dailystormer.in/feed/, en-US, United States
 ShadowKat Studios, https://shadowkat.net/rss.xml, en-US, Worldwide
 Futurism, https://futurism.com/feed, en-US, United States
--- a/datasets/news/telecom.csv
+++ b/datasets/news/telecom.csv
@ -3,4 +3,8 @@ The XMPP Blog on XMPP, https://xmpp.org/feeds/all.atom.xml, en-US, Worldwide
 Redecentralize Blog, https://redecentralize.org/blog/feed.rss, en-US, United States
 ollieparanoid, https://ollieparanoid.github.io/feed.xml, en-US, United States
 ShadowKat Studios, https://shadowkat.net/rss.xml, en-US, Worldwide
 The Tutanota Blog, https://tuta.com/blog/feed.xml, en-US, Worldwide
 Reclaim The Net, https://reclaimthenet.org/feed, en-US, United States
 Phones & Service – Simplified Privacy, https://simplifiedprivacy.com/category/phones-service-2fa/feed/, en-US, Cambodia
 SimpleX Chat, https://mastodon.social/@simplex.rss, en-US, Worldwide
 Session Blog, https://getsession.org/feed, en-US, United States
--- a/datasets/news/united_states.csv
+++ b/datasets/news/united_states.csv
@ -1,14 +1,21 @@
 name, url, language, country
 ZeroGov, https://zerogov.com/feed/, en-US, United States
 The Organic Prepper, https://www.theorganicprepper.com/feed/, en-US, United States
 Kirksville Today, https://www.kirksvilletoday.com/feed/, en-US, United States
 The Hill News, https://thehill.com/feed/?feed=partnerfeed-news-feed&format=rss, en-US, United States
 John W. Whitehead, Constitutional Attorney, https://agovernmentofwolves.com/feed/, en-US, United States
 Fakeologist, https://fakeologist.com/feed/, en-US, Canada
 BlackListed News, https://www.blacklistednews.com/rss.php, en-US, United States
 Tampa Free Press, https://www.tampafp.com/feed/, en-US, United States
 Truthstream Media, https://truthstreammedia.com/feed/, en-US, United States
 Real Liberty Media, https://www.reallibertymedia.com/feed/, en-US, United States
 Robert Reich, https://robertreich.substack.com/feed, en-US, United States
 Network World, https://www.networkworld.com/feed/, en-US, Worldwide
 North Carolina Lawyers Weekly, https://nclawyersweekly.com/feed/, en-US, United States
 The Good Men Project, https://goodmenproject.com/feed/, en-US, United States
 Mami's Shit, http://grizzom.blogspot.com/feeds/posts/default, en-US, United States
 Sam Bent aka DoingFedTime, https://www.doingfedtime.com/feed/, en-US, United States
 Jerm Warfare, https://jermwarfare.com/feed, en-US, United States
 Vanguard News Network, http://www.vanguardnewsnetwork.com/feed/, en-US, United States
 National Vanguard, https://nationalvanguard.org/feed/, en-US, United States
 Voice of America, https://www.voanews.com/api/, en-US, United States
--- a/datasets/news/war.csv
+++ b/datasets/news/war.csv
@ -3,4 +3,6 @@ Jerm Warfare, https://jermwarfare.com/feed, en-US, United States
 Daily Stormer, https://dailystormer.in/feed/, en-US, United States
 classless Kulla, https://www.classless.org/feed/atom/, de-DE, Germany
 classless Kulla, https://www.classless.org/feed/atom/, en-US, Germany
 Truthstream Media, https://truthstreammedia.com/feed/, en-US, United States
 Justice for Germans, https://justice4germans.wordpress.com/feed/, en-US, United States
 Voice of America, https://www.voanews.com/api/, en-US, United States
--- a/datasets/podcasts/business.csv
+++ b/datasets/podcasts/business.csv
@ -0,0 +1,2 @@
 name, url, language, country
 Getting Things Done, https://gettingthingsdone.com/feed/, en-US, United States
--- a/datasets/podcasts/culture.csv
+++ b/datasets/podcasts/culture.csv
@ -3,4 +3,5 @@ American Dissident Voices, https://nationalvanguard.org/category/american-dissid
 Radio 3Fourteen, https://redice.tv/rss/radio-3fourteen, en-US, United States
 The National Archives - Podcast Series, https://www.nationalarchives.gov.uk/rss/podcasts.xml, en-UK, United Kingdom
 Oracle Broadcasting Recent Shows, http://www.oraclebroadcasting.com/rss_recent.php, en-US, United States
 Mami's Shit, http://grizzom.blogspot.com/feeds/posts/default, en-US, United States
 Speak Free Radio, https://speakfreeradio.com/feed/, en-US, United States
--- a/datasets/podcasts/government.csv
+++ b/datasets/podcasts/government.csv
@ -4,7 +4,8 @@ The Corbett Report, https://www.corbettreport.com/feed/, en-US, Japan
 Radio 3Fourteen, https://redice.tv/rss/radio-3fourteen, en-US, United States
 Oracle Broadcasting Recent Shows, http://www.oraclebroadcasting.com/rss_recent.php, en-US, United States
 Speak Free Radio, https://speakfreeradio.com/feed/, en-US, United States
-Podcasts | Real Liberty Media, https://www.reallibertymedia.com/category/podcasts/feed/?redirect=no, en-US, United States
+Mami's Shit, http://grizzom.blogspot.com/feeds/posts/default, en-US, United States
 Real Liberty Media, https://www.reallibertymedia.com/category/podcasts/feed/?redirect=no, en-US, United States
 Behind The Woodshed with Hal Anthony, https://www.reallibertymedia.com/feed/behind-the-woodshed/, en-US, United States
--- a/datasets/podcasts/law.csv
+++ b/datasets/podcasts/law.csv
@ -1,2 +1,3 @@
 name, url, language, country
 LPG Flash!, https://anchor.fm/s/430dae74/podcast/rss, it-IT, Italy
 Mami's Shit, http://grizzom.blogspot.com/feeds/posts/default, en-US, United States
--- a/datasets/podcasts/united_states.csv
+++ b/datasets/podcasts/united_states.csv
@ -3,3 +3,4 @@ American Dissident Voices, https://nationalvanguard.org/category/american-dissid
 Radio 3Fourteen, https://redice.tv/rss/radio-3fourteen, en-US, United States
 Oracle Broadcasting Recent Shows, http://www.oraclebroadcasting.com/rss_recent.php, en-US, United States
 Speak Free Radio, https://speakfreeradio.com/feed/, en-US, United States
 Mami's Shit, http://grizzom.blogspot.com/feeds/posts/default, en-US, United States
--- a/datasets/projects/blockchain.csv
+++ b/datasets/projects/blockchain.csv
@ -0,0 +1,4 @@
 name, url, language, country
 Monero, https://www.getmonero.org/feed.xml, en-US, Worldwide
 Session, https://getsession.org/feed, en-US, United States
 Particl News, https://particl.news/rss, en-US, Worldwide
--- a/datasets/projects/chat.csv
+++ b/datasets/projects/chat.csv
@ -15,3 +15,6 @@ Cabal, https://mastodon.social/@cabal.rss, en-US, Worldwide
 CoyIM, https://coy.im/feed.xml, en-US, Worldwide
 Nextcloud, https://nextcloud.com/feed/, en-US, Worldwide
 profanity, https://profanity-im.github.io/blog/index.xml, en-US, Worldwide
 SimpleX Chat, https://simplex.chat/feed.rss, en-US, Worldwide
 Briar, https://briarproject.org/news/index.xml, en-US, Worldwide
 Session, https://getsession.org/feed, en-US, United States
--- a/datasets/projects/cloud.csv
+++ b/datasets/projects/cloud.csv
@ -1,3 +1,4 @@
 name, url, language, country
 Nextcloud, https://nextcloud.com/feed/, en-US, Worldwide
 MicroBin, https://microbin.eu/blog/atom.xml, en-US, Worldwide
 rclone - rsync for cloud storage, https://rclone.org/index.xml, en-US, United States
--- a/datasets/projects/fediverse.csv
+++ b/datasets/projects/fediverse.csv
@ -6,3 +6,4 @@ Immers Space, https://web.immers.space/feed/, en-US, Worldwide
 Firefish, https://joinfirefish.org/rss.xml, en-US, Worldwide
 Funkwhale, https://blog.funkwhale.audio/feeds/all.atom.xml, en-US, Worldwide
 Fediverse.Party - explore federated networks, https://fediverse.party/atom.xml, en-US, Worldwide
 Feditext, https://fedi.software/@Feditext.rss, en-US, Worldwide
--- a/datasets/projects/game.csv
+++ b/datasets/projects/game.csv
@ -1,2 +1,7 @@
 name, url, language, country
 Pirate Solitaire Devlog - itch.io, https://victor-pernet.itch.io/pirate-solitaire/devlog.rss, en-US, Worldwide
 Xonotic: The Free and Fast Arena Shooter, https://xonotic.org/index.xml, en-US, Worldwide
 Speed Dreams, https://www.speed-dreams.net/en/feed/, en-US, Worldwide
 Speed Dreams, https://www.speed-dreams.net/fr/feed/, fr-FR, Worldwide
 SuperTuxKart, https://blog.supertuxkart.net/feeds/posts/default, en-US, Worldwide
 Minetest, https://blog.minetest.net/feed.rss, en-US, Worldwide
--- a/datasets/projects/internet.csv
+++ b/datasets/projects/internet.csv
@ -5,6 +5,7 @@ Pale Moon, https://forum.palemoon.org/app.php/feed/forum/1, en-US, Worldwide
 Falkon - KDE web browser, https://www.falkon.org/atom.xml, en-US, Czech
 Otter Browser, https://otter-browser.org/feed/, en-US, Worldwide
 What's Up, Fraidycat?, https://fraidyc.at/blog/feed.xml, en-US, Worldwide
 Session, https://getsession.org/feed, en-US, United States
 QOTO, https://qoto.org/@QOTO.rss, en-US, Worldwide
 Funkwhale, https://blog.funkwhale.audio/feeds/all.atom.xml, en-US, Worldwide
 geomyidae, branch HEAD, gopher://bitreich.org:70/0/scm/geomyidae/atom.xml, en-US, United States
@ -13,8 +14,11 @@ Feedbin, https://feedbin.com/blog/atom.xml, en-US, United States
 profanity, https://profanity-im.github.io/blog/index.xml, en-US, Worldwide
 Silvio Rizzi (reederapp.com), https://gloria.social/@rizzi.rss, en-US, Worldwide
 lighty, https://redmine.lighttpd.net/news.atom, en-US, Worldwide
 Blogo, https://blogo.site/atom, en-US, Worldwide
 lighttpd, https://www.lighttpd.net/feed/atom.xml, en-US, Worldwide
 Nextcloud, https://nextcloud.com/feed/, en-US, Worldwide
 Briar, https://briarproject.org/news/index.xml, en-US, Worldwide
 I Hear U, https://sourceforge.net/projects/ihu/rss, en-US, Worldwide
 Cabal, https://mastodon.social/@cabal.rss, en-US, Worldwide
 JSON Feed, https://www.jsonfeed.org/feed.xml, en-US, Worldwide
 Liferea, https://lzone.de/feed/liferea.xml, en-US, Germany
@ -29,6 +33,7 @@ CoyIM, https://coy.im/feed.xml, en-US, Worldwide
 Tor Project blog, https://blog.torproject.org/feed.xml, en-US, Worldwide
 blabber.im, https://kanoa.de/@blabber.rss, en-US, Worldwide
 monocles, https://monocles.social/@monocles.rss, en-US, Germany
 Briar, https://briarproject.org/news/index.xml, en-US, Worldwide
 NetworkManager, https://networkmanager.dev/blog/index.xml, en-US, Worldwide
 Jekyll, https://jekyllrb.com/feed.xml, en-US, Worldwide
 Hugo, https://gohugo.io/index.xml, en-US, Worldwide
@ -44,6 +49,7 @@ Textpattern CMS, https://textpattern.com/rss, en-US, Worldwide
 TYPO3, https://typo3.org/rss, en-US, Worldwide
 WordPress, https://wordpress.org/news/feed/, en-US, Worldwide
 Foswiki, https://foswiki.org/Home/WebRss, en-US, Worldwide
 Feditext, https://fedi.software/@Feditext.rss, en-US, Worldwide
 Foswiki, https://blog.foswiki.org/Blog/WebAtom?contenttype=text/xml, en-US, Worldwide
 Extensions - Foswiki, https://foswiki.org/Extensions/ExtensionNews?template=ExtensionNewsRssView&contenttype=text/xml, en-US, Worldwide
 Eleventy, https://www.11ty.dev/blog/feed.xml, en-US, Worldwide
--- a/datasets/projects/operating_system.csv
+++ b/datasets/projects/operating_system.csv
@ -6,3 +6,4 @@ postmarketOS, https://postmarketos.org/blog/feed.atom, en-US, Germany
 cynix, https://git.2f30.org/cynix/atom.xml, en-US, Worldwide
 Replicant, https://blog.replicant.us/feed/, en-US, United States
 Sailfish OS, https://sailfishos.org/feed/, en-US, Finland
 Artix Linux, https://artixlinux.org/feed.php, en-US, Worldwide
--- a/datasets/projects/p2p.csv
+++ b/datasets/projects/p2p.csv
@ -1,2 +1,5 @@
 name, url, language, country
 Cabal, https://mastodon.social/@cabal.rss, en-US, Worldwide
 Session, https://getsession.org/feed, en-US, United States
 Briar, https://briarproject.org/news/index.xml, en-US, Worldwide
 I Hear U, https://sourceforge.net/projects/ihu/rss, en-US, Worldwide
--- a/datasets/projects/publishing.csv
+++ b/datasets/projects/publishing.csv
@ -16,6 +16,7 @@ Publii, https://getpublii.com/feed.xml, en-US, Worldwide
 Textpattern CMS, https://textpattern.com/rss, en-US, Worldwide
 TYPO3, https://typo3.org/rss, en-US, Worldwide
 WordPress, https://wordpress.org/news/feed/, en-US, Worldwide
 Blogo, https://blogo.site/atom, en-US, Worldwide
 Foswiki, https://foswiki.org/Home/WebRss, en-US, Worldwide
 Foswiki, https://blog.foswiki.org/Blog/WebAtom?contenttype=text/xml, en-US, Worldwide
 Extensions - Foswiki, https://foswiki.org/Extensions/ExtensionNews?template=ExtensionNewsRssView&contenttype=text/xml, en-US, Worldwide
@ -23,3 +24,4 @@ Eleventy, https://www.11ty.dev/blog/feed.xml, en-US, Worldwide
 bliper, https://git.2f30.org/bliper/atom.xml, en-US, Worldwide
 LinkStack, https://linkstack.org/feed/, en-US, Worldwide
 Firefish, https://joinfirefish.org/rss.xml, en-US, Worldwide
 Feditext, https://fedi.software/@Feditext.rss, en-US, Worldwide
--- a/datasets/projects/toolkit.csv
+++ b/datasets/projects/toolkit.csv
@ -0,0 +1,2 @@
 name, url, language, country
 GTK Development Blog, https://blog.gtk.org/feed/, en-US, United States
--- a/datasets/projects/voip.csv
+++ b/datasets/projects/voip.csv
@ -4,3 +4,5 @@ Jitsi, https://jitsi.org/feed/, en-US, Worldwide
 Kaidan, https://www.kaidan.im/atom.xml, en-US, Worldwide
 Dino, https://dino.im/index.xml, en-US, Worldwide
 Gajim, https://gajim.org/index.xml, en-US, France
 Briar, https://briarproject.org/news/index.xml, en-US, Worldwide
 I Hear U, https://sourceforge.net/projects/ihu/rss, en-US, Worldwide
--- a/datasets/projects/website.csv
+++ b/datasets/projects/website.csv
@ -18,3 +18,4 @@ Extensions - Foswiki, https://foswiki.org/Extensions/ExtensionNews?template=Exte
 Eleventy, https://www.11ty.dev/blog/feed.xml, en-US, Worldwide
 bliper, https://git.2f30.org/bliper/atom.xml, en-US, Worldwide
 LinkStack, https://linkstack.org/feed/, en-US, Worldwide
 Blogo, https://blogo.site/atom, en-US, Worldwide
--- a/datasets/projects/xmpp.csv
+++ b/datasets/projects/xmpp.csv
@ -10,3 +10,5 @@ profanity, https://profanity-im.github.io/blog/index.xml, en-US, Worldwide
 Ignite Realtime, https://discourse.igniterealtime.org/c/blogs/ignite-realtime-blogs/5.rss, en-US, Worldwide
 Gajim, https://gajim.org/index.xml, en-US, France
 Prosody IM, https://fosstodon.org/@prosodyim.rss, en-US, Worldwide
 Slidge, https://www.nicoco.fr/feed/blog.xml, en-US, France
 cheogram-muc-bridge, https://git.singpolyma.net/cheogram-muc-bridge/log/master/rss.xml, en-US, Worldwide
--- a/datasets/tutorials/code.csv
+++ b/datasets/tutorials/code.csv
@ -1,3 +1,5 @@
 name, url, language, country
 Karl Bartel's Website, https://www.karl.berlin/atom.xml, en-US, Germany
 freeCodeCamp, https://www.freecodecamp.org/news/rss/, en-US, Worldwide
 learn by example, https://learnbyexample.github.io/atom.xml, en-US, Worldwide
 njanakiev, https://janakiev.com/feed.xml, en-US, Austria
--- a/datasets/tutorials/computer.csv
+++ b/datasets/tutorials/computer.csv
@ -1,2 +1,3 @@
 name, url, language, country
 Wiki de sebsauvage.net, https://sebsauvage.net/wiki/feed.php, fr-FR, France
 njanakiev, https://janakiev.com/feed.xml, en-US, Austria
--- a/datasets/tutorials/data.csv
+++ b/datasets/tutorials/data.csv
@ -2,3 +2,4 @@ name, url, language, country
 Data Science Parichay, https://datascienceparichay.com/feed/, en-US, Worldwide
 ScraperWiki, https://scraperwiki.com/feed/, en-US, Worldwide
 Pierian Training, https://pieriantraining.com/feed/, en-US, Worldwide
 njanakiev, https://janakiev.com/feed.xml, en-US, Austria
--- a/datasets/tutorials/javascript.csv
+++ b/datasets/tutorials/javascript.csv
@ -0,0 +1,2 @@
 name, url, language, country
 learn by example, https://learnbyexample.github.io/atom.xml, en-US, Worldwide
--- a/datasets/tutorials/linux.csv
+++ b/datasets/tutorials/linux.csv
@ -2,3 +2,7 @@ name, url, language, country
 Home on Freexian, https://www.freexian.com/index.xml, en-US, France
 Fedora Magazine, https://fedoramagazine.org/feed/, en-US, Worldwide
 LinuxConfig, https://linuxconfig.org/feed, en-US, Worldwide
 Linux Made Simple, https://www.linuxmadesimple.info/feeds/posts/default, en-US, Worldwide
 FOSS Linux, https://www.fosslinux.com/feed/atom, en-US, Worldwide
 nixCraft, https://www.cyberciti.com/faq/feed/, en-US, Worldwide
 LinuxLinks, https://www.linuxlinks.com/feed/, en-US, Worldwide
--- a/datasets/tutorials/perl.csv
+++ b/datasets/tutorials/perl.csv
@ -0,0 +1,2 @@
 name, url, language, country
 learn by example, https://learnbyexample.github.io/atom.xml, en-US, Worldwide
--- a/datasets/tutorials/python.csv
+++ b/datasets/tutorials/python.csv
@ -12,4 +12,6 @@ Deep Thoughts by Raymond Hettinger, https://rhettinger.wordpress.com/feed/, en-U
 Victor Stinner blog 3, https://vstinner.github.io/feeds/all.atom.xml, en-US, Worldwide
 Victor Stinner 🐍, https://mamot.fr/@vstinner.rss, en-US, Worldwide
 Dan Bader, https://dbader.org/rss, en-US, Worldwide
 njanakiev, https://janakiev.com/feed.xml, en-US, Austria
 Pierian Training, https://pieriantraining.com/feed/, en-US, Worldwide
 learn by example, https://learnbyexample.github.io/atom.xml, en-US, Worldwide
--- a/datasets/tutorials/regex.csv
+++ b/datasets/tutorials/regex.csv
@ -0,0 +1,2 @@
 name, url, language, country
 learn by example, https://learnbyexample.github.io/atom.xml, en-US, Worldwide
--- a/datasets/videos/game.csv
+++ b/datasets/videos/game.csv
@ -0,0 +1,2 @@
 name, url, language, country
 Speed Dreams Open Motorsport Simulator, https://peertube.linuxrocks.online/feeds/podcast/videos.xml?videoChannelId=4665, en-US, Worldwide
--- a/datasets/videos/general.csv
+++ b/datasets/videos/general.csv
@ -7,3 +7,4 @@ sp-codes PeerTube, https://tube.sp-codes.de/feeds/videos.xml, de-DE, Germany
 TILvids, https://tilvids.com/feeds/videos.xml, en-US, Worldwide
 tchncs, https://tube.tchncs.de/feeds/videos.xml, en-US, Germany
 Bastyon Video Server, https://peertube35.pocketnet.app/feeds/videos.xml, en-US, Worldwide
 LinuxRocks PeerTube, https://peertube.linuxrocks.online/feeds/videos.xml, en-US, Worldwide
--- a/datasets/videos/lifestyle.csv
+++ b/datasets/videos/lifestyle.csv
@ -2,3 +2,4 @@ name, url, language, country
 denshi.live, https://denshi.live/feeds/videos.xml, en-US, USA
 Luke's Videos, https://videos.lukesmith.xyz/feeds/videos.xml, en-US, USA
 RTP TECH TIPS, https://tilvids.com/feeds/videos.xml?accountId=178762, en-US, Worldwide
 Simplified Privacy, https://video.simplifiedprivacy.com/feed/, en-US, Cambodia
--- a/datasets/videos/privacy.csv
+++ b/datasets/videos/privacy.csv
@ -1,3 +1,4 @@
 name, url, language, country
 RTP TECH TIPS, https://tilvids.com/feeds/videos.xml?accountId=178762, en-US, Worldwide
 (RTP) Privacy & Tech Tips, https://tube.tchncs.de/feeds/videos.xml?videoChannelId=2263, en-US, Worldwide
 Simplified Privacy, https://video.simplifiedprivacy.com/feed/, en-US, Cambodia
--- a/datasets/videos/software.csv
+++ b/datasets/videos/software.csv
@ -0,0 +1,3 @@
 name, url, language, country
 FSFE, https://media.fsfe.org/feeds/videos.xml?accountId=4, en-US, Germany
 FSFE-Tube, https://media.fsfe.org/feeds/videos.xml, en-US, Germany
--- a/datasets/videos/technology.csv
+++ b/datasets/videos/technology.csv
@ -1,11 +1,13 @@
 name, url, language, country
-denshi.live, https://denshi.live/feeds/videos.xml, en-US, USA
+FSFE, https://media.fsfe.org/feeds/videos.xml?accountId=4, de-DE, Germany
-Luke's Videos, https://videos.lukesmith.xyz/feeds/videos.xml, en-US, USA
+denshi.live, https://denshi.live/feeds/videos.xml, en-US, United States
-Films By Kris, https://filmsbykris.com/rss.xml, en-US, USA
+FSFE, https://media.fsfe.org/feeds/videos.xml?accountId=4, en-US, Germany
 Luke's Videos, https://videos.lukesmith.xyz/feeds/videos.xml, en-US, United States
 Framasoft, https://framatube.org/feeds/videos.xml?accountId=3&sort=-publishedAt, fr-FR, France
 Films By Kris, https://filmsbykris.com/rss.xml, en-US, United States
 Simplified Privacy, https://video.simplifiedprivacy.com/feed/, en-US, Cambodia
 Blender Video, https://video.blender.org/feeds/videos.xml, en-US, United States
 Framatube, https://framatube.org/feeds/videos.xml, fr-FR, France
 Framasoft, https://framatube.org/feeds/videos.xml?accountId=3&sort=-publishedAt, fr-FR, France
 Redecentralize Blog, https://redecentralize.org/blog/feed.rss, en-US, United States
 FSFE, https://media.fsfe.org/feeds/videos.xml?accountId=4, de-DE, Germany
 RTP TECH TIPS, https://tilvids.com/feeds/videos.xml?accountId=178762, en-US, Worldwide
 (RTP) Privacy & Tech Tips, https://tube.tchncs.de/feeds/videos.xml?videoChannelId=2263, en-US, Worldwide
 Redecentralize Blog, https://redecentralize.org/blog/feed.rss, en-US, United States
--- a/slixfeed/confighandler.py
+++ b/slixfeed/confighandler.py
@ -32,6 +32,8 @@ async def get_value_default(key):
        Value.
    """
    match key:
        case "archive":
            result = 50
        case "enabled":
            result = 1
        case "filter-allow":
--- a/slixfeed/datahandler.py
+++ b/slixfeed/datahandler.py
@ -18,6 +18,7 @@ from aiohttp import ClientError, ClientSession, ClientTimeout
 from asyncio import TimeoutError
 from asyncio.exceptions import IncompleteReadError
 from bs4 import BeautifulSoup
 from email.utils import parseaddr
 from feedparser import parse
 from http.client import IncompleteRead
 from lxml import html
@ -1016,7 +1017,7 @@ async def feed_mode_auto_discovery(url, tree):
 async def feed_to_http(url):
    """
-    Replace scheme feed by http.
+    Replace scheme FEED by HTTP.
    Parameters
    ----------
@ -1039,9 +1040,10 @@ async def feed_to_http(url):
    return new_url
 """TODO"""
 async def activitypub_to_http(namespace):
    """
-    Replace ActivityPub namespace by http.
+    Replace ActivityPub namespace by HTTP.
    Parameters
    ----------
@ -1062,3 +1064,23 @@ async def activitypub_to_http(namespace):
        par_url.fragment
        ])
    return new_url
 async def check_xmpp_uri(uri):
    """
    Check validity of XMPP URI.
    Parameters
    ----------
    uri : str
        URI.
    Returns
    -------
    jid : str
        JID or None.
    """
    jid = urlsplit(uri).path
    if parseaddr(jid)[1] != jid:
        jid = False
    return jid
--- a/slixfeed/sqlitehandler.py
+++ b/slixfeed/sqlitehandler.py
@ -607,13 +607,19 @@ async def statistics(db_file):
    feeds = await get_number_of_items(db_file, 'feeds')
    active_feeds = await get_number_of_feeds_active(db_file)
    entries = await get_number_of_items(db_file, 'entries')
    archive = await get_number_of_items(db_file, 'archive')
    unread_entries = await get_number_of_entries_unread(db_file)
    # msg = """You have {} unread news items out of {} from {} news sources.
    #       """.format(unread_entries, entries, feeds)
    with create_connection(db_file) as conn:
        cur = conn.cursor()
        keys = []
-        for key in ["enabled", "interval", "quantum"]:
+        for key in [
                "archive",
                "interval",
                "quantum",
                "enabled"
                ]:
            sql = (
            "SELECT value "
            "FROM settings "
@ -621,19 +627,23 @@ async def statistics(db_file):
            )
            keys.extend([cur.execute(sql, (key,)).fetchone()[0]])
        msg = (
-            "```\n"
+            "```"
-            "News items       : {} ({})\n"
+            "\nSTATISTICS\n"
-            "News sources     : {} ({})\n"
+            "News items   : {} / {}\n"
            "News sources : {} / {}\n"
            "\nOPTIONS\n"
            "Items to archive : {}\n"
            "Update interval  : {}\n"
            "Items per update : {}\n"
            "Operation status : {}\n"
            "```"
            ).format(
-                unread_entries, entries,
+                unread_entries, entries + archive,
                active_feeds, feeds,
                keys[0],
                keys[1],
                keys[2],
-                keys[0]
+                keys[3]
                )
    return msg
@ -770,7 +780,7 @@ async def set_date(cur, url):
 async def add_entry_and_set_date(db_file, source, entry):
    """
-    Add entry to table entries and set date of source in table feeds.
+    Add an entry to table entries and set date of source in table feeds.
    Parameters
    ----------
@ -887,53 +897,33 @@ async def add_entry(cur, entry):
        # breakpoint()
-# NOTE See remove_nonexistent_entries
+async def maintain_archive(cur, limit):
 # NOTE This function doesn't work as expected with bbs and docuwiki feeds
 async def remove_entry(db_file, source, length):
    """
-    Maintain list of entries equal to feed.
+    Maintain list of archived entries equal to specified number of items.
    Check the number returned by feed and delete
    existing entries up to the same returned amount.
    Parameters
    ----------
    db_file : str
        Path to database file.
    source : str
        Feed URL.
    length : str
        Number.
    """
-    # FIXED
+    sql = (
-    # Dino empty titles are not counted https://dino.im/index.xml
+        "SELECT count(id) "
-    # SOLVED
+        "FROM archive"
-    # Add text if is empty
+        )
-    # title = '*** No title ***' if not entry.title else entry.title
+    count = cur.execute(sql).fetchone()[0]
-    async with DBLOCK:
+    reduc = count - limit
-        with create_connection(db_file) as conn:
+    if reduc > 0:
-            cur = conn.cursor()
+        sql = (
-            sql = (
+            "DELETE FROM archive "
-                "SELECT count(id) "
+            "WHERE id "
-                "FROM entries "
+            "IN (SELECT id "
-                "WHERE source = ?"
+            "FROM archive "
-                )
+            "ORDER BY timestamp ASC "
-            count = cur.execute(sql, (source,)).fetchone()[0]
+            "LIMIT :reduc)"
-            limit = count - length
+            )
-            if limit:
+        cur.execute(sql, {
-                limit = limit;
+            "reduc": reduc
-                sql = (
+            })
                    "DELETE FROM entries "
                    "WHERE id "
                    "IN (SELECT id "
                    "FROM entries "
                    "WHERE source = :source "
                    "ORDER BY id "
                    "ASC LIMIT :limit)"
                    )
                cur.execute(sql, {
                    "source": source,
                    "limit": limit
                    })
 # TODO Move entries that don't exist into table archive.
@ -1068,9 +1058,12 @@ async def remove_nonexistent_entries(db_file, feed, source):
                            cur.execute(sql, (ix,))
                        except:
                            print(
-                                "ERROR DB deleting entries "
+                                "ERROR DB deleting items from "
-                                "from entries at index", ix
+                                "table entries at index", ix
                                )
        async with DBLOCK:
            limit = await get_settings_value(db_file, "archive")
            await maintain_archive(cur, limit)
 async def get_feeds(db_file):
@ -1207,6 +1200,10 @@ async def last_entries(db_file, num):
        "SELECT title, link "
        "FROM entries "
        "WHERE read = 0 "
        "UNION ALL "
        "SELECT title, link "
        "FROM archive "
        "WHERE read = 0 "
        "ORDER BY timestamp DESC "
        "LIMIT :num "
        )
--- a/slixfeed/taskhandler.py
+++ b/slixfeed/taskhandler.py
@ -393,10 +393,9 @@ async def check_updates(jid):
 """
 NOTE
 This is an older system, utilizing local storage instead of XMPP presence.
-This function is good for use with protocols that don't have presence.
+This function is good for use with protocols that might not have presence.
-IRC, LXMF, Matrix, SMTP, Tox.
+ActivityPub, IRC, LXMF, Matrix, SMTP, Tox.
 """
 async def select_file(self):
    """
--- a/slixfeed/xmpphandler.py
+++ b/slixfeed/xmpphandler.py
@ -60,6 +60,7 @@ from random import randrange
 from datahandler import (
    add_feed,
    add_feed_no_check,
    check_xmpp_uri,
    feed_to_http,
    view_entry,
    view_feed
@ -244,6 +245,12 @@ class Slixfeed(slixmpp.ClientXMPP):
        await self.join_muc(inviter, muc_jid)
    """
    TODO
    1) Send message to inviter that bot has joined to groupchat.
    2) If groupchat requires captcha, send the consequent message.
    3) If groupchat error is received, send that error message to inviter.
    """
    async def join_muc(self, inviter, muc_jid):
        # token = await initdb(
        #     muc_jid,
@ -275,13 +282,13 @@ class Slixfeed(slixmpp.ClientXMPP):
        result = await self.plugin['xep_0048'].get_bookmarks()
        bookmarks = result["private"]["bookmarks"]
        conferences = bookmarks["conferences"]
-        print("result")
+        print("RESULT")
        print(result)
-        print("bookmarks")
+        print("BOOKMARKS")
        print(bookmarks)
-        print("conferences")
+        print("CONFERENCES")
        print(conferences)
-        breakpoint()
+        # breakpoint()
        mucs = []
        for conference in conferences:
            jid = conference["jid"]
@ -669,6 +676,8 @@ class Slixfeed(slixmpp.ClientXMPP):
            print(await current_time(), "COMMAND:", message)
            match message_lowercase:
                case "commands":
                    action = print_cmd()
                case "help":
                    action = print_help()
                case "info":
@ -798,6 +807,23 @@ class Slixfeed(slixmpp.ClientXMPP):
                                ).format(val)
                        else:
                            action = "Missing keywords."
                case _ if message_lowercase.startswith("archive"):
                    key = message[:7]
                    val = message[8:]
                    if val:
                        if int(val) > 500:
                            action = "Value may not be greater than 500."
                        else:
                            await initdb(
                                jid,
                                set_settings_value,
                                [key, val]
                                )
                            action = (
                                "Maximum archived items has been set to {}."
                                ).format(val)
                    else:
                        action = "Missing value."
                case _ if message_lowercase.startswith("deny +"):
                        key = "filter-" + message[:4]
                        val = message[6:]
@ -959,8 +985,17 @@ class Slixfeed(slixmpp.ClientXMPP):
                    else:
                        action = "Missing value."
                case _ if message_lowercase.startswith("join"):
-                    muc = message[5:]
+                    muc = await check_xmpp_uri(message[5:])
-                    await self.join_muc(jid, muc)
+                    if muc:
                        "TODO probe JID and confirm it's a groupchat"
                        await self.join_muc(jid, muc)
                        action = (
                            "Joined groupchat {}"
                                  ).format(message)
                    else:
                        action = (
                            "> {}\nXMPP URI is not valid."
                                  ).format(message)
                case _ if message_lowercase.startswith("length"):
                        key = message[:6]
                        val = message[7:]
@ -976,7 +1011,8 @@ class Slixfeed(slixmpp.ClientXMPP):
                                    )
                            else:
                                action = (
-                                    "Summary maximum length is set to {} characters."
+                                    "Summary maximum length "
                                    "is set to {} characters."
                                    ).format(val)
                        else:
                            action = "Missing value."
@ -1011,7 +1047,7 @@ class Slixfeed(slixmpp.ClientXMPP):
                        ["old", 0]
                        )
                    action = (
-                        "Only new items of added feeds will be sent."
+                        "Only new items of newly added feeds will be sent."
                        )
                case _ if message_lowercase.startswith("next"):
                    num = message[5:]
@ -1046,7 +1082,7 @@ class Slixfeed(slixmpp.ClientXMPP):
                        ["old", 1]
                        )
                    action = (
-                        "All items of added feeds will be sent."
+                        "All items of newly added feeds will be sent."
                        )
                case _ if message_lowercase.startswith("quantum"):
                    key = message[:7]
@ -1227,6 +1263,18 @@ class Slixfeed(slixmpp.ClientXMPP):
                case "support":
                    # TODO Send an invitation.
                    action = "Join xmpp:slixmpp@muc.poez.io?join"
                case _ if message_lowercase.startswith("xmpp:"):
                    muc = await check_xmpp_uri(message)
                    if muc:
                        "TODO probe JID and confirm it's a groupchat"
                        await self.join_muc(jid, muc)
                        action = (
                            "Joined groupchat {}"
                                  ).format(message)
                    else:
                        action = (
                            "> {}\nXMPP URI is not valid."
                                  ).format(message)
                case _:
                    action = (
                        "Unknown command. "
@ -1256,7 +1304,8 @@ def print_info():
        Message.
    """
    msg = (
-        "```\n"
+        "```"
        "\n"
        "ABOUT\n"
        " Slixfeed aims to be an easy to use and fully-featured news\n"
        " aggregator bot for XMPP. It provides a convenient access to Blogs,\n"
@ -1346,7 +1395,8 @@ def print_help():
        Message.
    """
    msg = (
-        "```\n"
+        "```"
        "\n"
        "NAME\n"
        "Slixfeed - News syndication bot for Jabber/XMPP\n"
        "\n"
@ -1373,11 +1423,11 @@ def print_help():
        " length\n"
        "   Set maximum length of news item description. (0 for no limit)\n"
        " new\n"
-        "   Send only new items of added feeds.\n"
+        "   Send only new items of newly added feeds.\n"
        " next N\n"
        "   Send N next updates.\n"
        " old\n"
-        "   Send all items of added feeds.\n"
+        "   Send all items of newly added feeds.\n"
        " quantum N\n"
        "   Set N amount of updates per interval.\n"
        " start\n"
@ -1446,6 +1496,8 @@ def print_help():
        # "   Send a Plain Text file of your news items.\n"
        # "\n"
        "SUPPORT\n"
        " commands\n"
        "   Print list of commands.\n"
        " help\n"
        "   Print this help manual.\n"
        " info\n"
@ -1460,3 +1512,45 @@ def print_help():
        "```"
        )
    return msg
 def print_cmd():
    """
    Print list of commands.
    Returns
    -------
    msg : str
        Message.
    """
    msg = (
        "```"
        "\n"
        "!                 : Use exclamation mark to initiate an actionable command (groupchats only).\n"
        "<MUC>             : Join specified groupchat.\n"
        "<URL>             : Add URL to subscription list.\n"
        "add <URL> <TITLE> : Add URL to subscription list (without validity check).\n"
        "allow +           : Add keywords to allow (comma separates).\n"
        "allow -           : Delete keywords from allow list (comma separates).\n"
        "deny +            : Keywords to block (comma separates).\n"
        "deny -            : Delete keywords from deny list (comma separates).\n"
        "feeds             : List all subscriptions.\n"
        "feeds <TEXT>      : Search subscriptions by given keywords.\n"
        "interval N        : Set interval update to every N minutes.\n"
        "join <MUC>        : Join specified groupchat.\n"
        "length            : Set maximum length of news item description. (0 for no limit)\n"
        "new               : Send only new items of newly added feeds.\n"
        "next N            : Send N next updates.\n"
        "old               : Send all items of newly added feeds.\n"
        "quantum N         : Set N amount of updates per interval.\n"
        "read <URL>        : Display most recent 20 titles of given URL.\n"
        "read URL N        : Display specified entry number from given URL.\n"
        "recent N          : List recent N news items (up to 50 items).\n"
        "remove <ID>       : Remove feed from subscription list.\n"
        "search <TEXT>     : Search news items by given keywords.\n"
        "start             : Enable bot and send updates.\n"
        "status <ID>       : Toggle update status of feed.\n"
        "stop              : Disable bot and stop updates.\n"
        "```"
        )
    return msg
		`@ -0,0 +1,2 @@`
							`name, url, language, country`
							`Monero Observer, https://monero.observer/feed-calendar.xml, en-US, Worldwide`
		`@ -0,0 +1,2 @@`
							`name, url, language, country`
							`SimpleX, https://lemmy.ml/feeds/c/simplex.xml?sort=Active, en-US, Worldwide`
		`@ -0,0 +1,2 @@`
							`name, url, language, country`
							`Minetest, https://blog.minetest.net/feed.rss, en-US, Worldwide`
		`@ -0,0 +1,2 @@`
							`name, url, language, country`
							`Pirate Solitaire Devlog - itch.io, https://victor-pernet.itch.io/pirate-solitaire/devlog.rss, en-US, Worldwide`
		`@ -0,0 +1,2 @@`
							`name, url, language, country`
							`Xonotic: The Free and Fast Arena Shooter, https://xonotic.org/index.xml, en-US, Worldwide`
		`@ -0,0 +1,2 @@`
							`name, url, language, country`
							`Getting Things Done, https://gettingthingsdone.com/feed/, en-US, United States`
		`@ -0,0 +1,2 @@`
							`name, url, language, country`
							`GTK Development Blog, https://blog.gtk.org/feed/, en-US, United States`
		`@ -0,0 +1,2 @@`
							`name, url, language, country`
							`learn by example, https://learnbyexample.github.io/atom.xml, en-US, Worldwide`
		`@ -0,0 +1,2 @@`
							`name, url, language, country`
							`Speed Dreams Open Motorsport Simulator, https://peertube.linuxrocks.online/feeds/podcast/videos.xml?videoChannelId=4665, en-US, Worldwide`