Various of modifications

datasets/activity/game.csv

@@ -0,0 +1,2 @@
+name, url, language, country
+Feed of "MintApps Team", https://codeberg.org/MintApps.rss, en-US, Germany

datasets/activity/internet.csv

@@ -0,0 +1,2 @@
+name, url, language, country
+DokuWiki, https://www.dokuwiki.org/feed.php, en-US, Worldwide

datasets/activity/operating_system.csv

@@ -0,0 +1,2 @@
+name, url, language, country
+Replicant: Issues, https://redmine.replicant.us/projects/replicant/issues.atom, en-US, Worldwide

datasets/activity/xmpp.csv

@@ -0,0 +1,4 @@
+name, url, language, country
+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.rss, en-US, France

datasets/catalogues/book.csv

@@ -1,2 +1,2 @@
 name, url, language, country
-New Online Books, https://onlinebooks.library.upenn.edu/newrss.xml, en-US, USA
+New Online Books, https://onlinebooks.library.upenn.edu/newrss.xml, en-US, United States

datasets/catalogues/computer.csv

@@ -0,0 +1,2 @@
+name, url, language, country
+Vikings Shop, https://shop.vikings.net/feed/, en-US, Germany

datasets/catalogues/electronics.csv

@@ -0,0 +1,2 @@
+name, url, language, country
+BaoFeng Radios, https://baofengtech.com/feed/, en-US, South Dakota

datasets/catalogues/film.csv

@@ -0,0 +1,2 @@
+name, url, language, country
+Movies Subtitle, https://qsubtitles.com/feed/atom/, en-US, Worldwide

datasets/catalogues/game.csv

@@ -0,0 +1,2 @@
+name, url, language, country
+Open Source Game Clones: New/Updated Games, https://osgameclones.com/feed.xml, en-US, Worldwide

datasets/catalogues/music.csv

@@ -1,3 +1,4 @@
 name, url, language, country
 MetaBrainz Blog, https://blog.metabrainz.org/feed/, en-US, Worldwide
 MP3 NFO Database, https://nfodb.ru/rss.php, en-US, Worldwide
+Tubesonix – The Future of Royalty Free Licensed Music, https://www.tubesonix.com/feed/, en-US, Worldwide

datasets/catalogues/radio.csv

@@ -0,0 +1,2 @@
+name, url, language, country
+BaoFeng Radios, https://baofengtech.com/feed/, en-US, South Dakota

datasets/catalogues/travel.csv

@@ -1,2 +1,3 @@
 name, url, language, country
 Trip101, https://trip101.com/feed, en-US, United States
+Travdo Hotels, https://travdo-hotels.de/feed/, de-DE, Germany

datasets/corporations/automotive.csv

@@ -0,0 +1,2 @@
+name, url, language, country
+Seafarix, https://seafarix.com/feed/, en-US, Finland

datasets/corporations/computing.csv

@@ -2,3 +2,7 @@ name, url, language, country
 Panic Blog, https://www.panic.com/blog/feed/, en-US, United States
 Necuno Solutions, https://necunos.com/feed.xml, en-US, Finland
 Debricked, https://debricked.com/blog/feed/, en-US, Europe
+Linaro - Arm-based solutions, https://www.linaro.org/feed.xml, en-US, United States
+Jolla, https://jolla.com/feed/, en-US, Finland
+Seafarix, https://seafarix.com/feed/, en-US, Finland
+Weingärtner IT Services, https://weingaertner-it.de/index.php/feed/, de-DE, Germany

datasets/corporations/hardware.csv

@@ -0,0 +1,2 @@
+name, url, language, country
+Linaro - Arm-based solutions, https://www.linaro.org/feed.xml, en-US, United States

datasets/corporations/music.csv

@@ -0,0 +1,2 @@
+name, url, language, country
+DopeSONIX VSTi VST AU Hip Hop Beatmaking Production Software, https://www.dopesonix.com/feed/, en-UK, England

datasets/forums/computer.csv

@@ -1,2 +1,5 @@
 name, url, language, country
 eGPU.io, https://egpu.io/feed/, en-US, Worldwide
+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

datasets/forums/hacking.csv

@@ -1,3 +1,3 @@
 name, url, language, country
 Leak Zone - Leaking & Cracking Forum, https://leakzone.net/syndication.php?type=atom1.0, en-US, Worldwide
-Pale Moon, https://forum.palemoon.org/app.php/feed/forum/1, en-US, Worldwide
+

datasets/forums/intrenet.csv

@@ -1,3 +1,4 @@
 name, url, language, country
 Pale Moon, https://forum.palemoon.org/app.php/feed, en-US, Worldwide
 Transmission BT, https://forum.transmissionbt.com/app.php/feed, en-US, Worldwide
+ikiwiki, http://ikiwiki.info/forum/index.rss, en-US, Worldwide

datasets/forums/linux.csv

@@ -0,0 +1,3 @@
+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

datasets/news/art.csv

@@ -4,3 +4,4 @@ třiapůl česky, https://triapul.cz/feed/cesky.xml, cz-CZ, Czech
 triapul.cz, http://triapul.cz/feed/english.xml, en-US, Czech
 techno-mage in:, https://bsd.network/@prahou.rss, en-US, United States
 Behance Featured Projects, https://www.behance.net/feeds/projects, en-US, United States
+Mansfield-Devine, https://mansfield-devine.com/feed/, en-US, Worldwide

datasets/news/bsd.csv

@@ -3,3 +3,4 @@ drkhsh, https://drkhsh.at/atom.xml, en-US, Austria
 OpenBSD Webzine, https://webzine.puffy.cafe/atom.xml, en-US, United States
 Solene'%, https://dataswamp.org/~solene/rss.xml, en-US, United States
 Solene'%, https://dataswamp.org/~solene/rss-html.xml, en-US, United States
+Michael W Lucas, https://mwl.io/feed, en-US, United States

datasets/news/business.csv

@@ -14,3 +14,5 @@ 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
+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

datasets/news/christianity.csv

@@ -3,3 +3,5 @@ Evangelical Endtimemachine, https://www.evangelicalendtimemachine.com/feed/, ce-
 Orthodox Christianity, https://orthochristian.com/xml/rss.xml, en-US, USA
 Legio Christi, https://legiochristi.com/rss/, en-US, USA
 Jerm Warfare, https://jermwarfare.com/feed, en-US, USA
+Mom on a Mission, https://www.mom-on-a-mission.blog/all-posts?format=rss, en-US, United States
+iMOM, https://www.imom.com/feed/, en-US, United States

datasets/news/code.csv

@@ -5,5 +5,9 @@ Newest Python PEPs, https://peps.python.org/peps.rss/, en-US, Worldwide
 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
 camen design, https://camendesign.com/rss, en-US, United States
+Hugo Barrera, https://whynothugo.nl/posts.xml, en-US, Netherlands
 LZone | Devops, https://lzone.de/feed/devops.xml, en-US, Germany
 Leonora Tindall on Nora Codes, https://nora.codes/index.xml, en-US, United States
+code monk | hacking habits, https://drj11.wordpress.com/feed/, en-US, United States
+Machina Speculatrix, https://mansfield-devine.com/speculatrix/feed/, en-US, Worldwide
+Lainblog, https://blog.soykaf.com/index.xml, en-US, Worldwide

datasets/news/computer.csv

@@ -1,12 +1,26 @@
 name, url, language, country
+Michael W Lucas, https://mwl.io/feed, 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
+Hacking around oppressions, https://bouah.net/index.xml, en-US, France
+Tatsumoto Ren, https://tatsumoto.neocities.org/blog/feed.rss, en-US, Japan
+Hugo Barrera, https://whynothugo.nl/posts.xml, en-US, Netherlands
 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
 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
 OpenNews.opennet.ru: Общая лента новостей, https://www.opennet.ru/opennews/opennews_all_utf.rss, ru-RU, Russia
 ju_hnny5, https://blog.jbriault.fr/rss/, fr-FR, France
+This Week in GNOME, https://thisweek.gnome.org/index.xml, en-US, Worldwide
 Lazy Reading | The Cyber Vanguard, https://cyber.dabamos.de/blog/feed.rss, en-US, United States
+Christof Meerwald, https://cmeerw.org/blog.atom, en-US, Austria
 XXIIVV, https://wiki.xxiivv.com/links/rss.xml, en-US, Canada
+Phoronix, https://www.phoronix.com/rss.php, en-US, United States
 drkhsh, https://drkhsh.at/atom.xml, en-US, Austria
 Codemadness, https://codemadness.org/atom.xml, en-US, United States
 Leonora Tindall on Nora Codes, https://nora.codes/index.xml, en-US, United States
@@ -17,6 +31,7 @@ schollz, https://schollz.com/index.xml, en-US, United States
 LZone | Devops, https://lzone.de/feed/devops.xml, en-US, Germany
 The Logs, https://www.flu0r1ne.net/logs/rss.xml, en-US, United States
 Newest Python PEPs, https://peps.python.org/peps.rss/, en-US, Worldwide
+monocles, https://monocles.social/@monocles.rss, en-US, Germany
 Ctrl blog: Mobile Apps, https://feed.ctrl.blog/topic/mobile-apps.atom, en-US, United States
 Chiportal, https://chiportal.co.il/feed/, he-IL, Israel
 Hackaday, https://hackaday.com/feed/, en-US, United States
@@ -45,6 +60,7 @@ TuxPhones, https://tuxphones.com/rss/, en-US, United States
 OpenSource.net, https://opensource.net/feed/, en-US, United States
 Collabora Office and Collabora Online, https://www.collaboraoffice.com/feed/, en-US, United States
 LGUG2Z, https://lgug2z.com/index.xml, en-US, United States
+code monk | hacking habits, https://drj11.wordpress.com/feed/, en-US, United States
 Karl Bartel's Website, https://www.karl.berlin/atom.xml, en-US, Germany
 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
@@ -67,3 +83,4 @@ Enterprise Storage, http://feeds.fosketts.net/StephenFoskettPackRat_EnterpriseSt
 Personal, http://feeds.fosketts.net/StephenFoskettPackRat_Personal, en-US, United States
 Terabyte Home, http://feeds.fosketts.net/StephenFoskettPackRat_TerabyteHome, en-US, United States
 Virtual Storage, http://feeds.fosketts.net/StephenFoskettPackRat_VirtualStorage, en-US, United States
+Jolla, https://jolla.com/feed/, en-US, Finland

datasets/news/culture.csv

@@ -1,13 +1,17 @@
 name, url, language, country
-Jerm Warfare, https://jermwarfare.com/feed, en-US, USA
+Jerm Warfare, https://jermwarfare.com/feed, en-US, United States
-The Organic Prepper, https://www.theorganicprepper.com/feed/, en-US, USA
+The Organic Prepper, https://www.theorganicprepper.com/feed/, en-US, United States
-The Public Domain Review, https://publicdomainreview.org/rss.xml, en-US, USA
+The Public Domain Review, https://publicdomainreview.org/rss.xml, en-US, United States
 ynet - תרבות, https://www.ynet.co.il/Integration/StoryRss538.xml, he-IL, Israel
 ynet - Culture, https://www.ynet.co.il/Integration/StoryRss3086.xml, en-IL, Israel
 ynet - חדר משלך, https://www.ynet.co.il/Integration/StoryRss4111.xml, he-IL, Israel
-Tampa Free Press, https://www.tampafp.com/feed/, en-US, USA
+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
 Deutsche Welle: DW.com KULTUR & LEBEN: BÜCHER, http://rss.dw.com/atom/rss-de-cul-buch, de-DE, Germany
 Deutsche Welle: DW.com KULTUR & LEBEN: FILM, http://rss.dw.com/atom/rss-de-cul-film, de-DE, Germany
 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
+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
+

datasets/news/cybersecurity.csv

@@ -1,4 +1,5 @@
 name, url, language, country
+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

datasets/news/data.csv

@@ -1,2 +1,3 @@
 name, url, language, country
 Postgres Professional, https://postgrespro.ru/rss, ru-RU, Russia
+Datenschutz, https://www.datenschutz.org/feed/, de-DE, Germany

datasets/news/design.csv

@@ -1,3 +1,5 @@
 name, url, language, country
 Crumina, https://crumina.net/feed/, en-US, Ukraine
 Behance Featured Projects, https://www.behance.net/feeds/projects, en-US, United States
+Dezeen, https://www.dezeen.com/feed/, en-US, Worldwide
+designboom | architecture & design magazine, https://www.designboom.com/feed/, en-US, Worldwide

datasets/news/electronics.csv

@@ -1,4 +1,5 @@
 name, url, language, country
+Jan Wagemakers, https://www.janwagemakers.be/jekyll/feed.xml, en-US, Belgium
 The Logs, https://www.flu0r1ne.net/logs/rss.xml, en-US, United States
 Flipper Blog, https://blog.flipper.net/rss/, en-US, United States
 ollieparanoid, https://ollieparanoid.github.io/feed.xml, en-US, United States
@@ -10,3 +11,4 @@ c't Magazin, https://social.heise.de/@ct_Magazin.rss, de-DE, Germany
 electro·pizza, https://electro.pizza/feed.xml, en-US, United States
 Ηρακλής Παπαθεοδώρου • heracl.es, https://heracl.es/el/feed.xml, el-GR, Greece
 Heracles Papatheodorou • heracl.es, https://heracl.es/feed.xml, en-US, Greece
+Machina Speculatrix, https://mansfield-devine.com/speculatrix/feed/, en-US, Worldwide

datasets/news/english.csv

@@ -0,0 +1,2 @@
+name, url, language, country
+Business Writing Info Blog, https://www.instructionalsolutions.com/blog/rss.xml, en-US, United States

datasets/news/family.csv

@@ -1,3 +1,5 @@
 name, url, language, country
 Mom on a Mission, https://www.mom-on-a-mission.blog/all-posts?format=rss, en-US, United States
 ynet - הורים, https://www.ynet.co.il/Integration/StoryRss3052.xml, he-IL, Israel
+iMOM, https://www.imom.com/feed/, en-US, United States
+Mom on a Mission, https://momonamission.me/feed/, en-US, United States

datasets/news/germany.csv

@@ -6,4 +6,6 @@ Deutsche Welle: DW.com WISSENSCHAFT, http://rss.dw.com/atom/rss-de-wissenschaft,
 Deutsche Welle: DW.com DEUTSCHLAND ENTDECKEN, http://rss.dw.com/atom/rss-de-deutschlandentdecken, de-DE, Germany
 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 
+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

datasets/news/government.csv

@@ -11,3 +11,5 @@ Tampa Free Press, https://www.tampafp.com/feed/, 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
+Historic.ly, https://www.historicly.net/feed, en-US, United States
+Reclaim The Net, https://reclaimthenet.org/feed, en-US, United States

datasets/news/grammar.csv

@@ -0,0 +1,2 @@
+name, url, language, country
+Business Writing Info Blog, https://www.instructionalsolutions.com/blog/rss.xml, en-US, United States

datasets/news/hacking.csv

@@ -1,2 +1,3 @@
 name, url, language, country
 Flipper Blog, https://blog.flipper.net/rss/, en-US, United States
+code monk | hacking habits, https://drj11.wordpress.com/feed/, en-US, United States

datasets/news/hardware.csv

@@ -0,0 +1,2 @@
+name, url, language, country
+Phoronix, https://www.phoronix.com/rss.php, en-US, United States

datasets/news/history.csv

@@ -0,0 +1,4 @@
+name, url, language, country
+Historic.ly, https://www.historicly.net/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

datasets/news/internet.csv

@@ -6,6 +6,7 @@ WordPress.com News, https://wordpress.com/blog/feed/, en-US, United States
 Micro.blog News, https://news.micro.blog/feed.xml, en-US, United States
 EFF Action Center, https://act.eff.org/action.atom, en-US, United States
 Leonora Tindall on Nora Codes, https://nora.codes/index.xml, en-US, United States
+Reclaim The Net, https://reclaimthenet.org/feed, en-US, United States
 Melon's Thoughts - Guidebooks, https://thoughts.melonking.net/atom/?section=guides, en-US, United States
 thecozy.cat, https://thecozy.cat/feed/, en-US, United States
 OpenNews.opennet.ru: Общая лента новостей, https://www.opennet.ru/opennews/opennews_all_utf.rss, ru-RU, Russia

datasets/news/law.csv

@@ -1,2 +1,4 @@
 name, url, language, country
 North Carolina Lawyers Weekly, https://nclawyersweekly.com/feed/, en-US, United States
+Avvocato a Roma | Studio Legale Sabatino | Famiglia e civile, https://www.studiosabatino.it/feed/, it-IT, Italy
+La Pagina Giuridica, https://www.lapaginagiuridica.it/?feed=rss2, it-IT, Italy

datasets/news/linux.csv

@@ -1,13 +1,21 @@
 name, url, language, country
+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
 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
+Phoronix, https://www.phoronix.com/rss.php, en-US, United States
 postmarketOS, https://postmarketos.org/blog/feed.atom, en-US, United States
 PureTryOut (Alpine Linux, postmarketOS), https://mastodon.fam-ribbers.com/@bart.rss, en-US, Netherlands
 Blog on Bart Ribbers - PureTryOut (Alpine Linux, postmarketOS), https://fam-ribbers.com/blog/index.xml, en-US, Netherlands
+Christof Meerwald, https://cmeerw.org/blog.atom, en-US, Austria
 LZone | Devops, https://lzone.de/feed/devops.xml, en-US, Germany
 Necuno Solutions, https://necunos.com/feed.xml, en-US, Finland
 Laslo Hunhold, https://laslo.hunhold.de/index.xml, en-US, Germany

datasets/news/literature.csv

@@ -3,3 +3,7 @@ Stories by Williams, https://storiesbywilliams.com/feed/, en-US, United States
 Lili Saintcrow, https://www.lilithsaintcrow.com/feed/, en-US, United States
 Shannon Kay, https://blog.shannonkay.me/feed.xml, en-US, United States
 V.K. Dixon, https://vkdixon.substack.com/feed, en-US, United States
+Business Writing Info Blog, https://www.instructionalsolutions.com/blog/rss.xml, en-US, United States
+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

datasets/news/misc.csv

@@ -4,3 +4,4 @@ Kasparov, https://www.kasparov.com/feed/, en-US, United States
 Ctrl blog: Metadata, https://feed.ctrl.blog/topic/metadata.atom, en-US, United States
 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

datasets/news/people.csv

@@ -1,10 +1,22 @@
 name, url, language, country
+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
+Jan Wagemakers, https://www.janwagemakers.be/jekyll/feed.xml, en-US, Belgium
+immanuel60, https://immanuel60.hu/feed/, hu-HU, Hungary
+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
+iMOM, https://www.imom.com/feed/, en-US, United States
+Mario Sabatino Gemini capsule, https://gemini.sabatino.cloud/rss.xml, it-IT, Italy
+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
 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
 Tristan B. Velloza Kildaire, https://gleasonator.com/@deavmi, en-ZA, South Africa
 Blog on Bart Ribbers - PureTryOut, https://fam-ribbers.com/blog/index.xml, en-US, Netherlands

datasets/news/privacy.csv

@@ -1,4 +1,5 @@
 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
 ollieparanoid, https://ollieparanoid.github.io/feed.xml, en-US, United States
@@ -9,3 +10,4 @@ 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
 Spread Privacy, https://spreadprivacy.com/rss/, en-US, United States
 Ctrl blog: Privacy, https://feed.ctrl.blog/topic/privacy.atom, en-US, United States
+Reclaim The Net, https://reclaimthenet.org/feed, en-US, United States

datasets/news/russia.csv

@@ -1,3 +1,4 @@
 name, url, language, country
 Kasparov, https://www.kasparov.com/feed/, en-US, United States
 РЖЕВСКАЯ ПРАВДА, https://presska.ru/feed/, ru-RU, Russia
+За вашу и нашу Свободу!, https://lev-sharansky2.livejournal.com/data/atom, ru-RU, Russia

datasets/news/surveillance.csv

@@ -1,2 +1,3 @@
 name, url, language, country
 Necuno Solutions, https://necunos.com/feed.xml, en-US, Finland
+Reclaim The Net, https://reclaimthenet.org/feed, en-US, United States

datasets/news/technology.csv

@@ -1,4 +1,5 @@
 name, url, language, country
+Hacking around oppressions, https://bouah.net/index.xml, en-US, France
 Redecentralize Blog, https://redecentralize.org/blog/feed.rss, en-US, United States
 Developpez, https://www.developpez.com/index/atom, fr-FR, France
 The Logs, https://www.flu0r1ne.net/logs/rss.xml, en-US, United States
@@ -10,6 +11,9 @@ Futurism, https://futurism.com/feed, en-US, United States
 drkhsh, https://drkhsh.at/atom.xml, en-US, Austria
 Automation Rhapsody, https://automationrhapsody.com/feed/, en-US, United States
 Deep Thoughts by Raymond Hettinger, https://rhettinger.wordpress.com/feed/, en-US, United States
+Lainblog, https://blog.soykaf.com/index.xml, en-US, Worldwide
+code monk | hacking habits, https://drj11.wordpress.com/feed/, en-US, United States
+Reclaim The Net, https://reclaimthenet.org/feed, en-US, United States
 Chiportal, https://chiportal.co.il/feed/, he-IL, Israel
 Hackaday, https://hackaday.com/feed/, en-US, United States
 LZone | Devops, https://lzone.de/feed/devops.xml, en-US, Germany
@@ -30,3 +34,5 @@ Heracles Papatheodorou • heracl.es, https://heracl.es/feed.xml, en-US, Greece
 lectronice :: now, https://now.lectronice.com/feed.xml, en-US, United States
 Ctrl blog: Advertisement Technology, https://feed.ctrl.blog/topic/advertisement-technology.atom, en-US, United States
 OpenNews.opennet.ru: Общая лента новостей, https://www.opennet.ru/opennews/opennews_all_utf.rss, ru-RU, Russia
+ExtremeTech, https://www.extremetech.com/feed, en-US, Worldwide
+Slashdot, http://rss.slashdot.org/Slashdot/slashdot/to, en-US, Worldwide

datasets/news/telecom.csv

@@ -3,3 +3,4 @@ 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
+Reclaim The Net, https://reclaimthenet.org/feed, en-US, United States

datasets/news/united_states.csv

@@ -8,3 +8,4 @@ Tampa Free Press, https://www.tampafp.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
 North Carolina Lawyers Weekly, https://nclawyersweekly.com/feed/, en-US, United States
+The Good Men Project, https://goodmenproject.com/feed/, en-US, United States

datasets/news/unix.csv

@@ -1,15 +1,18 @@
 name, url, language, country
+Michael W Lucas, https://mwl.io/feed, en-US, United States
 Linux Professional Institute (LPI), https://www.lpi.org/feed/, en-US, Canada
 LinuxConfig, https://linuxconfig.org/feed, en-US, Worldwide
 The Logs, https://www.flu0r1ne.net/logs/rss.xml, en-US, United States
 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
+This Week in GNOME, https://thisweek.gnome.org/index.xml, en-US, Worldwide
 Anjan Momi, https://momi.ca/feed.xml, en-US, United States
 postmarketOS, https://postmarketos.org/blog/feed.atom, en-US, United States
 PureTryOut (Alpine Linux, postmarketOS), https://mastodon.fam-ribbers.com/@bart.rss, en-US, Netherlands
 Blog on Bart Ribbers - PureTryOut (Alpine Linux, postmarketOS), https://fam-ribbers.com/blog/index.xml, en-US, Netherlands
 LZone | Devops, https://lzone.de/feed/devops.xml, en-US, Germany
 Necuno Solutions, https://necunos.com/feed.xml, en-US, Finland
+Phoronix, https://www.phoronix.com/rss.php, en-US, United States
 Laslo Hunhold, https://laslo.hunhold.de/index.xml, en-US, Germany
 Alpine Linux, https://fosstodon.org/@alpinelinux.rss, en-US, United States
 ollieparanoid, https://ollieparanoid.github.io/feed.xml, en-US, United States

datasets/news/war.csv

@@ -1,3 +1,5 @@
 name, url, language, country
 Jerm Warfare, https://jermwarfare.com/feed, en-US, USA
 Daily Stormer, https://dailystormer.in/feed/, en-US, USA
+classless Kulla, https://www.classless.org/feed/atom/, de-DE, Germany
+classless Kulla, https://www.classless.org/feed/atom/, en-US, Germany

datasets/news/xmpp.csv

@@ -1,5 +1,17 @@
 name, url, language, country
+Hacking around oppressions, https://bouah.net/index.xml, en-US, France
 The XMPP Blog on XMPP, https://xmpp.org/feeds/all.atom.xml, en-US, Worldwide
 Swift IM, https://swift.im/wordpress/index.php/feed/, en-US, Worldwide
 Berlin XMPP Meetup, https://mov.im/feed/pubsub.movim.eu/berlin-xmpp-meetup, en-US, Germany
 Хомяк diSabler'а, https://dsy.name/feed/, ru-RU, Russia
+JabberES.org, https://www.jabberes.org/index.xml, es-ES, Spain
+Hot-Chilli, https://www.hot-chilli.net/feed/, de-DE, Germany
+Jabber.de, https://www.jabber.de/?feed=rss2, de-DE, Germany
+blabber.im, https://kanoa.de/@blabber.rss, en-US, Worldwide
+monocles, https://monocles.social/@monocles.rss, en-US, Germany
+Alle Neuigkeiten von jotwewe.de, http://www.jotwewe.de/alles_de.xml, de-DE, Germany
+Martins Schmierzettel, https://blog.mdosch.de/index.xml, de-DE, Germany
+Christof Meerwald, https://cmeerw.org/blog.atom, en-US, Austria
+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
+Mario Sabatino Gemini capsule, https://gemini.sabatino.cloud/rss.xml, it-IT, Italy

datasets/organizations/germany.csv

@@ -2,3 +2,5 @@ name, url, language, country
 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
+Sovereign Tech Fund, https://www.sovereigntechfund.de/feed.rss, en-US, Germany
+Sovereign Tech Fund, https://www.sovereigntechfund.de/de/feed.rss, de-DE, Germany

datasets/organizations/united_states.csv

@@ -1,3 +1,7 @@
 name, url, language, country
 National Alliance, https://www.natall.com/feed/, en-US, USA
 EFF Action Center, https://act.eff.org/action.atom, en-US, United States
+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

datasets/podcasts/computer.csv

@@ -2,5 +2,8 @@ name, url, language, country
 Hacker Public Radio, http://hackerpublicradio.org/hpr_spx_rss.php, en-US, United States
 postmarketOS, https://cast.postmarketos.org/feed.rss, en-US, Germany
 0d - Zeroday, https://zeroday-podcast.de/feed/mp3/, de-DE, Germany
+0d - Zeroday, https://0x0d.de/feed/mp3/, de-DE, Germany
 Software Freedom Podcast (OPUS), http://fsfe.org/news/podcast-opus.en.rss, en-US, Germany
 Software Freedom Podcast (MP3), http://fsfe.org/news/podcast.en.rss, en-US, Germany
+Zeroday Podcast (stefan), https://podcasts.social/@zeroday.rss, de-DE, Germany
+LPG Flash!, https://anchor.fm/s/430dae74/podcast/rss, it-IT, Italy

datasets/podcasts/law.csv

@@ -0,0 +1,2 @@
+name, url, language, country
+LPG Flash!, https://anchor.fm/s/430dae74/podcast/rss, it-IT, Italy

datasets/podcasts/technology.csv

@@ -5,3 +5,4 @@ Software Freedom Podcast, http://fsfe.org/news/podcast-opus.en.rss, en-US, Germa
 Software Freedom Podcast, http://fsfe.org/news/podcast-opus.en.rss, en-US, Germany
 Redecentralize Blog, https://redecentralize.org/blog/feed.rss, en-US, United States
 // aNONradio //, https://anonradio.net/feed/, en-US, Worldwide
+LPG Flash!, https://anchor.fm/s/430dae74/podcast/rss, it-IT, Italy

datasets/projects/chat.csv

@@ -6,3 +6,9 @@ Dino, https://dino.im/index.xml, en-US, Worldwide
 ratox, https://git.2f30.org/ratox/atom.xml, en-US, Worldwide
 buzz, https://git.2f30.org/buzz/atom.xml, en-US, Worldwide
 mIRC, https://www.mirc.com/feed/, en-US, Worldwide
+blabber.im, https://kanoa.de/@blabber.rss, en-US, Worldwide
+monocles, https://monocles.social/@monocles.rss, en-US, Germany
+Gajim, https://gajim.org/index.xml, en-US, France
+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

datasets/projects/cloud.csv

@@ -0,0 +1,2 @@
+name, url, language, country
+Nextcloud, https://nextcloud.com/feed/, en-US, Worldwide

datasets/projects/desktop.csv

@@ -0,0 +1,3 @@
+name, url, language, country
+"fluxbox.git, branch master", http://git.fluxbox.org/fluxbox.git/atom/?h=master, en-US, Worldwide
+This Week in GNOME, https://thisweek.gnome.org/index.xml, en-US, Worldwide

datasets/projects/email.csv

@@ -0,0 +1,3 @@
+name, url, language, country
+Nextcloud, https://nextcloud.com/feed/, en-US, Worldwide
+Roundcube, https://roundcube.net/feeds/atom.xml, en-US, Worldwide

datasets/projects/fediverse.csv

@@ -0,0 +1,2 @@
+name, url, language, country
+GNU social, http://www.gnusocial.rocks/feed.rss, en-US, Worldwide

datasets/projects/internet.csv

@@ -2,6 +2,7 @@ name, url, language, country
 DownThemAll!, https://www.downthemall.org/feed, en-US, Worldwide
 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
 geomyidae, branch HEAD, gopher://bitreich.org:70/0/scm/geomyidae/atom.xml, en-US, United States
 rclone - rsync for cloud storage, https://rclone.org/index.xml, en-US, Worldwide
@@ -9,6 +10,7 @@ Feedbin, https://feedbin.com/blog/atom.xml, en-US, United States
 Silvio Rizzi (reederapp.com), https://gloria.social/@rizzi.rss, en-US, Worldwide
 lighty, https://redmine.lighttpd.net/news.atom, en-US, Worldwide
 lighttpd, https://www.lighttpd.net/feed/atom.xml, en-US, Worldwide
+Nextcloud, https://nextcloud.com/feed/, 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
@@ -18,3 +20,8 @@ Kaidan, https://www.kaidan.im/atom.xml, en-US, Worldwide
 Dino, https://dino.im/index.xml, en-US, Worldwide
 Vivaldi Browser, https://vivaldi.com/feed/, en-US, United States
 wicd Announcements, http://feeds.launchpad.net/wicd/announcements.atom, en-US, Worldwide
+GNU social, http://www.gnusocial.rocks/feed.rss, en-US, Worldwide
+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

datasets/projects/mix_network.csv

@@ -0,0 +1,2 @@
+name, url, language, country
+Tor Project blog, https://blog.torproject.org/feed.xml, en-US, Worldwide

datasets/projects/operating_system.csv

@@ -1,6 +1,8 @@
 name, url, language, country
-NixOS, https://nixos.org/blog/announcements-rss.xml, en-US, USA
+NixOS, https://nixos.org/blog/announcements-rss.xml, en-US, United States
 ReactOS, https://reactos.org/index.xml, en-US, Germany
 Salix OS, https://forum.salixos.org/app.php/feed/news, en-US, Greece
 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

datasets/projects/website.csv

@@ -13,6 +13,8 @@ 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
+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
 bliper, https://git.2f30.org/bliper/atom.xml, en-US, Worldwide
 LinkStack, https://linkstack.org/feed/, en-US, Worldwide

datasets/projects/xmpp.csv

@@ -0,0 +1,7 @@
+name, url, language, country
+Swift IM, https://swift.im/wordpress/index.php/feed/, en-US, Worldwide
+Kaidan, https://www.kaidan.im/atom.xml, en-US, Worldwide
+Dino, https://dino.im/index.xml, en-US, Worldwide
+CoyIM, https://coy.im/feed.xml, en-US, Worldwide
+blabber.im, https://kanoa.de/@blabber.rss, en-US, Worldwide
+monocles, https://monocles.social/@monocles.rss, en-US, Germany

datasets/tutorials/code.csv

@@ -1,2 +1,3 @@
 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

datasets/tutorials/python.csv

@@ -11,3 +11,4 @@ AppDividend, https://appdividend.com/feed/, en-US, Worldwide
 Deep Thoughts by Raymond Hettinger, https://rhettinger.wordpress.com/feed/, en-US, USA
 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

datasets/videos/general.csv

@@ -3,3 +3,4 @@ denshi.live, https://denshi.live/feeds/videos.xml, en-US, United States
 Luke's Videos, https://videos.lukesmith.xyz/feeds/videos.xml, en-US, United States
 fair.tube, https://fair.tube/feeds/videos.xml, de-DE, Germany
 Kockatoo Tube, https://tube.kockatoo.org/feeds/videos.xml, en-US, United States
+sp-codes PeerTube, https://tube.sp-codes.de/feeds/videos.xml, de-DE, Germany

setup.py

@@ -3,13 +3,47 @@
 from distutils.core import setup
 
 setup(
-    name='slixfeed',
+    name='Slixfeed',
     version='1.0',
-    description='rss through xmpp bot',
+    description='RSS news bot for XMPP',
+    long_description='Slixfeed is a news aggregator bot for online news feeds. This program is primarily designed for XMPP',
+    author='Schimon Jehudah Zakai Zockaim Zachary',
+    author_email='sjehuda@yandex.com',
+    url='https://gitgud.io/sjehuda/slixfeed',
+    license='MIT',
+    platforms=['any'],
     install_require=[
         'aiohttp',
-        'slixmpp',
+        'bs4',
-        'eliot',
+        'feedparser',
-        'feedparser'
+        'lxml',
-    ]
+        'slixmpp'
+    ],
+    classifiers=[
+        'Framework :: slixmpp',
+        'Intended Audience :: End Users/Desktop',
+        'License :: OSI Approved :: GNU General Public License v3 or later (GPLv3+)',
+        'License :: OSI Approved :: MIT License',
+        'Natural Language :: English',
+        'Programming Language :: Python',
+        'Programming Language :: Python :: 3.10',
+        'Topic :: Communications :: Chat',
+        'Topic :: Internet :: Extensible Messaging and Presence Protocol (XMPP)',
+        'Topic :: Internet :: WWW/HTTP :: Dynamic Content :: News/Diary',
+        'Topic :: Internet :: Instant Messaging',
+        'Topic :: Internet :: XMPP',
+        'Topic :: Office/Business :: News/Diary',
+    ],
+    keywords=[
+        'jabber',
+        'xmpp',
+        'bot',
+        'chat',
+        'im',
+        'news',
+        'atom',
+        'rdf',
+        'rss',
+        'syndication'
+    ],
 )

slixfeed/confighandler.py

@@ -39,16 +39,18 @@ async def get_value_default(key):
             result = "crim,dead,death,disaster,murder,war"
         case "interval":
             result = 300
+        case "masters":
+            result = randrange(100000, 999999)
+        case "length":
+            result = 300
+        case "old":
+            result = 0
         case "quantum":
             result = 3
         case "random":
             result = 0
-        case "masters":
-            result = randrange(100000, 999999)
         case "token":
             result = "none"
-        case "old":
-            result = 0
     return result
 
 

slixfeed/datahandler.py

@@ -110,21 +110,6 @@ async def download_updates(db_file, url=None):
                 )
             # new_entry = 0
             for entry in entries:
-                if entry.has_key("title"):
-                    # title = entry.title
-                    title = "{}: *{}*".format(feed["feed"]["title"], entry.title)
-                else:
-                    title = feed["feed"]["title"]
-                if entry.has_key("link"):
-                    # link = complete_url(source, entry.link)
-                    link = await join_url(source, entry.link)
-                    link = await trim_url(link)
-                else:
-                    link = source
-                if entry.has_key("id"):
-                    eid = entry.id
-                else:
-                    eid = link
                 # TODO Pass date too for comparion check
                 if entry.has_key("published"):
                     date = entry.published
@@ -139,6 +124,22 @@ async def download_updates(db_file, url=None):
                     # NOTE Would seconds result in better database performance
                     # date = datetime.datetime(date)
                     # date = (date-datetime.datetime(1970,1,1)).total_seconds()
+                if entry.has_key("title"):
+                    title = entry.title
+                    # title = "{}: *{}*".format(feed["feed"]["title"], entry.title)
+                else:
+                    title = date
+                    # title = feed["feed"]["title"]
+                if entry.has_key("link"):
+                    # link = complete_url(source, entry.link)
+                    link = await join_url(source, entry.link)
+                    link = await trim_url(link)
+                else:
+                    link = source
+                if entry.has_key("id"):
+                    eid = entry.id
+                else:
+                    eid = link
                 exist = await sqlitehandler.check_entry_exist(
                     db_file,
                     source,
@@ -152,14 +153,14 @@ async def download_updates(db_file, url=None):
                     # TODO Enhance summary
                     if entry.has_key("summary"):
                         summary = entry.summary
-                        # Remove HTML tags
+                        # # Remove HTML tags
-                        summary = BeautifulSoup(summary, "lxml").text
+                        # summary = BeautifulSoup(summary, "lxml").text
-                        # TODO Limit text length
+                        # # TODO Limit text length
-                        summary = summary.replace("\n\n\n", "\n\n")
+                        # summary = summary.replace("\n\n\n", "\n\n")
-                        summary = summary[:300] + "  ‍⃨"
+                        # summary = summary[:300] + " […]‍⃨"
-                        summary = summary.strip().split('\n')
+                        # summary = summary.strip().split('\n')
-                        summary = ["> " + line for line in summary]
+                        # summary = ["> " + line for line in summary]
-                        summary = "\n".join(summary)
+                        # summary = "\n".join(summary)
                     else:
                         summary = "> *** No summary ***"
                     read_status = 0
@@ -200,6 +201,12 @@ async def download_updates(db_file, url=None):
                         date,
                         read_status
                         )
+                    if isinstance(date, int):
+                        print("date is int")
+                        print(date)
+                        breakpoint()
+                    print(source)
+                    print(date)
                     await sqlitehandler.add_entry_and_set_date(
                         db_file,
                         source,
@@ -363,7 +370,7 @@ async def view_entry(url, num):
         msg = (
             "{}\n"
             "\n"
-            "{}\n"
+            "> {}\n"
             "\n"
             "{}\n"
             "\n"

slixfeed/main.py.bak

@@ -0,0 +1,124 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+
+"""
+
+FIXME
+
+1) Check feed duplication on runtime.
+    When feed is valid and is not yet in the database it is
+    posible to send a batch which would result in duplication.
+    Consequently, it might result in database lock error upon
+    feed removal attempt
+
+TODO
+
+1) SQL prepared statements.
+
+2) Machine Learning for scrapping Title, Link, Summary and Timstamp.
+
+3) Support MUC.
+
+4) Support categories.
+
+5) Default prepackaged list of feeds.
+
+6) XMPP commands.
+
+7) Bot as transport.
+
+8) OMEMO.
+
+9) Logging.
+
+10) Default feeds (e.g. Blacklisted News, TBOT etc.)
+
+11) Download and upload/send article (xHTML, xHTMLZ, Markdown, MHTML, TXT).
+    Use Readability.
+
+12) Fetch summary from URL, instead of storing summary.
+
+13) Support protocol Gopher
+    https://github.com/michael-lazar/pygopherd
+    https://github.com/gopherball/gb
+
+13) Support ActivityPub @person@domain (see Tip Of The Day).
+
+12) Tip Of The Day.
+    Did you know that you can follow you favorite Mastodon feeds by just
+    sending the URL address?
+    Supported fediverse websites are:
+        Akkoma, HubZilla, Mastodon, Misskey, Pixelfed, Pleroma, Soapbox.
+
+"""
+
+# vars and their meanings:
+# jid = Jabber ID (XMPP)
+# res = response (HTTP)
+
+from argparse import ArgumentParser
+from getpass import getpass
+import logging
+
+from datetime import date
+import time
+
+# from eliot import start_action, to_file
+# # to_file(open("slixfeed.log", "w"))
+# # with start_action(action_type="set_date()", jid=jid):
+# # with start_action(action_type="message()", msg=msg):
+
+#import irchandler
+import xmpphandler
+#import matrixhandler
+
+
+if __name__ == '__main__':
+    # Setup the command line arguments.
+    parser = ArgumentParser(description=xmpphandler.Slixfeed.__doc__)
+
+    # Output verbosity options.
+    parser.add_argument(
+         "-q", "--quiet", help="set logging to ERROR",
+         action="store_const", dest="loglevel",
+         const=logging.ERROR, default=logging.INFO
+    )
+    parser.add_argument(
+        "-d", "--debug", help="set logging to DEBUG",
+        action="store_const", dest="loglevel",
+        const=logging.DEBUG, default=logging.INFO
+    )
+
+    # JID and password options.
+    parser.add_argument("-j", "--jid", dest="jid",
+                        help="JID to use")
+    parser.add_argument("-p", "--password", dest="password",
+                        help="password to use")
+
+    args = parser.parse_args()
+
+    # Setup logging.
+    logging.basicConfig(level=args.loglevel,
+                        format='%(levelname)-8s %(message)s')
+
+    if args.jid is None:
+        args.jid = input("Username: ")
+    if args.password is None:
+        args.password = getpass("Password: ")
+
+    # Setup the Slixfeed and register plugins. Note that while plugins may
+    # have interdependencies, the order in which you register them does
+    # not matter.
+    xmpp = xmpphandler.Slixfeed(args.jid, args.password)
+    xmpp.register_plugin('xep_0004') # Data Forms
+    xmpp.register_plugin('xep_0030') # Service Discovery
+    xmpp.register_plugin('xep_0045') # Multi-User Chat
+    xmpp.register_plugin('xep_0048') # Bookmarks
+    xmpp.register_plugin('xep_0060') # PubSub
+    xmpp.register_plugin('xep_0199', {'keepalive': True, 'frequency': 15}) # XMPP Ping
+    xmpp.register_plugin('xep_0249') # Multi-User Chat
+    xmpp.register_plugin('xep_0402') # PEP Native Bookmarks
+
+    # Connect to the XMPP server and start processing XMPP stanzas.
+    xmpp.connect()
+    xmpp.process()

slixfeed/sqlitehandler.py

@@ -18,8 +18,9 @@ TODO
 import sqlite3
 import asyncio
 
-from sqlite3 import Error
+from bs4 import BeautifulSoup
 from datetime import date
+from sqlite3 import Error
 
 import confighandler
 import datahandler
@@ -426,11 +427,11 @@ async def get_entry_unread(db_file, num=None):
         #     "DESC LIMIT :num"
         #     )
         sql = (
-            "SELECT id, title, summary, link, timestamp "
+            "SELECT id, title, summary, link, source, timestamp "
             "FROM entries "
             "WHERE read = 0 "
             "UNION ALL "
-            "SELECT id, title, summary, link, timestamp "
+            "SELECT id, title, summary, link, source, timestamp "
             "FROM archive "
             "ORDER BY timestamp "
             "DESC LIMIT :num"
@@ -462,7 +463,24 @@ async def get_entry_unread(db_file, num=None):
             ix = result[0]
             title = result[1]
             summary = result[2]
+            # Remove HTML tags
+            summary = BeautifulSoup(summary, "lxml").text
+            # TODO Limit text length
+            summary = summary.replace("\n\n\n", "\n\n")
+            length = await get_settings_value(db_file, "length")
+            summary = summary[:length] + " […]"
+            summary = summary.strip().split('\n')
+            summary = ["> " + line for line in summary]
+            summary = "\n".join(summary)
             link = result[3]
+            sql = (
+                "SELECT name "
+                "FROM feeds "
+                "WHERE address = :source "
+                )
+            source = result[4]
+            feed = cur.execute(sql, (source,))
+            feed = feed.fetchone()[0]
             if num > 1:
                 news_list += (
                     "\n{}\n{}\n"
@@ -472,11 +490,12 @@ async def get_entry_unread(db_file, num=None):
                         )
             else:
                 news_list = (
-                    "{}\n\n{}\n\n{}"
+                    "{}\n\n{}\n\n{}\n{}"
                     ).format(
                         str(title),
                         str(summary),
-                        str(link)
+                        str(link),
+                        str(feed)
                         )
             # TODO While `async with DBLOCK` does work well from
             # outside of functions, it would be better practice
@@ -827,7 +846,12 @@ async def update_source_validity(db_file, source, valid):
                 "url": source
                 })
 
+"""
+TODO
 
+Investigate why causes entry[6] (date) to be int 0
+
+"""
 async def add_entry(cur, entry):
     """
     Add a new entry row into the entries table.
@@ -852,7 +876,14 @@ async def add_entry(cur, entry):
                 ") "
         "VALUES(?, ?, ?, ?, ?, ?, ?)"
         )
-    cur.execute(sql, entry)
+    try:
+        cur.execute(sql, entry)
+    except:
+        print(entry[6])
+        print(type(entry[6]))
+        print(entry)
+        print(type(entry))
+        breakpoint()
 
 
 # NOTE See remove_nonexistent_entries
@@ -1294,10 +1325,26 @@ async def search_entries(db_file, query):
         return "No results were found for: {}".format(query)
 
 """
-FIXME Error due to missing date, but it appears that date is present:
+FIXME
+
+Error due to missing date, but it appears that date is present:
 ERROR DATE: source = https://blog.heckel.io/feed/
 ERROR DATE: date = 2008-05-13T13:51:50+00:00
 ERROR DATE: result = https://blog.heckel.io/feed/
+
+19:32:05 ERROR DATE: source = https://mwl.io/feed
+19:32:05 ERROR DATE: date = 2023-11-30T10:56:39+00:00
+19:32:05 ERROR DATE: result = https://mwl.io/feed
+19:32:05 ERROR DATE: source = https://mwl.io/feed
+19:32:05 ERROR DATE: date = 2023-11-22T16:59:08+00:00
+19:32:05 ERROR DATE: result = https://mwl.io/feed
+19:32:06 ERROR DATE: source = https://mwl.io/feed
+19:32:06 ERROR DATE: date = 2023-11-16T10:33:57+00:00
+19:32:06 ERROR DATE: result = https://mwl.io/feed
+19:32:06 ERROR DATE: source = https://mwl.io/feed
+19:32:06 ERROR DATE: date = 2023-11-09T07:37:57+00:00
+19:32:06 ERROR DATE: result = https://mwl.io/feed
+
 """
 async def check_entry_exist(db_file, source, eid=None,
                             title=None, link=None, date=None):

slixfeed/taskhandler.py

@@ -272,7 +272,7 @@ async def send_status(self, jid):
             print(">>> not feeds:", feeds, "jid:", jid)
             status_mode = "available"
             status_text = (
-                "📭️ Send a URL from a blog or a news website"
+                "📪️ Send a URL from a blog or a news website"
                 )
         else:
             unread = await filehandler.initdb(
@@ -292,7 +292,7 @@ async def send_status(self, jid):
                 #     ).format(str(unread))
             else:
                 status_mode = "available"
-                status_text = "📪️ No news"
+                status_text = "📭️ No news"
 
     # breakpoint()
     # print(await datetimehandler.current_time(), status_text, "for", jid)

slixfeed/xmpphandler.py

@@ -59,6 +59,8 @@ from slixmpp.plugins.xep_0363.http_upload import FileTooBig, HTTPError, UploadSe
 # from slixmpp.plugins.xep_0402 import BookmarkStorage, Conference
 from slixmpp.plugins.xep_0048.stanza import Bookmarks
 
+# TODO datahandler -> slixfeed.datahandler
+# See project feed2toot
 import datahandler
 import datetimehandler
 import filehandler
@@ -796,11 +798,24 @@ class Slixfeed(slixmpp.ClientXMPP):
                     url = message
                     if url.startswith("feed:"):
                         url = await datahandler.feed_to_http(url)
+                    await taskhandler.clean_tasks_xmpp(
+                        jid,
+                        ["status"]
+                        )
+                    task = (
+                        "📫️ Processing request to fetch data from {}"
+                        ).format(url)
+                    process_task_message(self, jid, task)
                     action = await filehandler.initdb(
                         jid,
                         datahandler.add_feed,
                         url
                         )
+                    await taskhandler.start_tasks_xmpp(
+                        self,
+                        jid,
+                        ["status"]
+                        )
                     # action = "> " + message + "\n" + action
                     # FIXME Make the taskhandler to update status message
                     # await taskhandler.refresh_task(
@@ -890,6 +905,25 @@ class Slixfeed(slixmpp.ClientXMPP):
                 case _ if message_lowercase.startswith("join"):
                     muc = message[5:]
                     await self.join_muc(jid, muc)
+                case _ if message_lowercase.startswith("length"):
+                        key = message[:6]
+                        val = message[7:]
+                        if val:
+                            await filehandler.initdb(
+                                jid,
+                                sqlitehandler.set_settings_value,
+                                [key, val]
+                                )
+                            if val == 0:
+                                action = (
+                                    "Summary length limit is disabled."
+                                    )
+                            else:
+                                action = (
+                                    "Summary maximum length is set to {} characters."
+                                    ).format(val)
+                        else:
+                            action = "Missing value."
                 case _ if message_lowercase.startswith("mastership"):
                         key = message[:7]
                         val = message[11:]
@@ -981,6 +1015,14 @@ class Slixfeed(slixmpp.ClientXMPP):
                     data = message[5:]
                     data = data.split()
                     url = data[0]
+                    task = (
+                        "📫️ Processing request to fetch data from {}"
+                        ).format(url)
+                    process_task_message(self, jid, task)
+                    await taskhandler.clean_tasks_xmpp(
+                        jid,
+                        ["status"]
+                        )
                     if url.startswith("feed:"):
                         url = await datahandler.feed_to_http(url)
                     match len(data):
@@ -1001,6 +1043,11 @@ class Slixfeed(slixmpp.ClientXMPP):
                                 "`read URL` or `read URL NUMBER`\n"
                                 "URL must not contain white space."
                                 )
+                    await taskhandler.start_tasks_xmpp(
+                        self,
+                        jid,
+                        ["status"]
+                        )
                 case _ if message_lowercase.startswith("recent"):
                     num = message[7:]
                     if num:
@@ -1111,10 +1158,13 @@ class Slixfeed(slixmpp.ClientXMPP):
                         sqlitehandler.set_settings_value,
                         [key, val]
                         )
-                    await taskhandler.clean_tasks_xmpp(jid, ["interval"])
+                    await taskhandler.clean_tasks_xmpp(
+                        jid,
+                        ["interval", "status"]
+                        )
                     self.send_presence(
                         pshow="xa",
-                        pstatus="Send \"Start\" to receive news.",
+                        pstatus="💡️ Send \"Start\" to receive Jabber news",
                         pto=jid,
                         )
                     action = "Updates are disabled."
@@ -1132,6 +1182,14 @@ class Slixfeed(slixmpp.ClientXMPP):
             if action: msg.reply(action).send()
 
 
+def process_task_message(self, jid, task):
+    self.send_presence(
+        pshow="dnd",
+        pstatus=task,
+        pto=jid,
+        )
+
+
 def print_info():
     """
     Print information.
@@ -1252,22 +1310,24 @@ def print_help():
         "   Display most recent 20 titles of given URL.\n"
         " read URL N\n"
         "   Display specified entry number from given URL.\n"
-        " new\n"
-        "   Send only new items of added feeds.\n"
-        " old\n"
-        "   Send all items of added feeds.\n"
         "\n"
         "MESSAGE OPTIONS\n"
+        " interval N\n"
+        "   Set interval update to every N minutes.\n"
+        " length\n"
+        "   Set maximum length of news item description. (0 for no limit)\n"
+        " new\n"
+        "   Send only new items of added feeds.\n"
+        " next N\n"
+        "   Send N next updates.\n"
+        " old\n"
+        "   Send all items of added feeds.\n"
+        " quantum N\n"
+        "   Set N amount of updates per interval.\n"
         " start\n"
         "   Enable bot and send updates.\n"
         " stop\n"
         "   Disable bot and stop updates.\n"
-        " interval N\n"
-        "   Set interval update to every N minutes.\n"
-        " next N\n"
-        "   Send N next updates.\n"
-        " quantum N\n"
-        "   Set N amount of updates per interval.\n"
         "\n"
         "GROUPCHAT OPTIONS\n"
         " ! (command initiation)\n"