refined url list for scraper

This commit is contained in:
sirius0xdev 2026-02-24 04:15:34 +00:00
parent 6cfb769fd4
commit f781c6c363

View file

@ -5,232 +5,7 @@ metadata:
namespace: customer1
data:
urls.txt: |
https://www.bbc.com/news
https://www.reuters.com
https://www.khmertimeskh.com
https://apnews.com
# USA
https://www.pbs.org/newshour
https://www.usatoday.com
https://www.cbsnews.com
https://www.nbcnews.com
# Canada
https://www.cbc.ca/news
https://www.ctvnews.ca
https://globalnews.ca
https://nationalpost.com
https://www.thestar.com
# Mexico
https://www.eluniversal.com.mx
https://www.milenio.com
https://www.jornada.com.mx
https://www.excelsior.com.mx
https://aristeguinoticias.com
# --- SOUTH AMERICA ---
# Brazil
https://g1.globo.com
https://www.uol.com.br
https://agenciabrasil.ebc.com.br
https://www.metropoles.com
https://www.terra.com.br/noticias
# Argentina
https://www.infobae.com
https://www.clarin.com
https://www.lanacion.com.ar
https://www.pagina12.com.ar
https://www.cronista.com
# Colombia
https://www.eltiempo.com
https://www.elespectador.com
https://www.semana.com
https://www.bluradio.com
https://www.rcnradio.com
# --- EUROPE ---
# United Kingdom
https://www.bbc.com/news
https://www.theguardian.com/uk
https://news.sky.com
https://www.independent.co.uk
https://metro.co.uk
# France
https://www.france24.com/en
https://www.lefigaro.fr
https://www.20minutes.fr
https://www.francetvinfo.fr
https://www.lemonde.fr
# Germany
https://www.dw.com/en
https://www.tagesschau.de
https://www.spiegel.de
https://www.zeit.de
https://www.bild.de
# Spain
https://elpais.com
https://www.elmundo.es
https://www.rtve.es/noticias
https://www.20minutos.es
https://www.elconfidencial.com
# Italy
https://www.ansa.it
https://www.corriere.it
https://www.repubblica.it
https://www.lastampa.it
https://tg24.sky.it
# Russia (State & Independent mix)
https://tass.com
https://www.interfax.ru
https://www.rt.com
https://www.themoscowtimes.com
https://meduza.io/en
# --- ASIA ---
# China
https://www.xinhuanet.com/english
https://www.chinadaily.com.cn
https://www.globaltimes.cn
https://www.cgtn.com
https://www.scmp.com
# India
https://www.ndtv.com
https://timesofindia.indiatimes.com
https://indianexpress.com
https://www.thehindu.com
https://www.hindustantimes.com
# Japan
https://www3.nhk.or.jp/nhkworld
https://www.japantimes.co.jp
https://www.asahi.com/ajw
https://mainichi.jp/english
https://english.kyodonews.net
# South Korea
https://en.yna.co.kr
https://www.koreaherald.com
https://koreajoongangdaily.joins.com
https://www.donga.com/en
https://english.chosun.com
# --- AFRICA ---
# South Africa
https://www.news24.com
https://www.iol.co.za
https://www.dailymaverick.co.za
https://www.sabcnews.com
https://www.timeslive.co.za
https://www.al.com
https://www.adn.com
https://www.azcentral.com
https://www.arkansasonline.com
https://www.latimes.com
https://www.denverpost.com
https://www.courant.com
https://www.delawareonline.com
https://www.tampabay.com
https://www.ajc.com
https://www.staradvertiser.com
https://www.idahostatesman.com
https://www.chicagotribune.com
https://www.indystar.com
https://www.desmoinesregister.com
https://www.kansas.com
https://www.courier-journal.com
https://www.nola.com
https://www.pressherald.com
https://www.baltimoresun.com
https://www.bostonglobe.com
https://www.freep.com
https://www.startribune.com
https://www.clarionledger.com
https://www.stltoday.com
https://www.missoulian.com
https://www.omaha.com
https://www.lvrj.com
https://www.unionleader.com
https://www.nj.com
https://www.abqjournal.com
https://www.nytimes.com
https://www.charlotteobserver.com
https://www.inforum.com
https://www.cleveland.com
https://www.oklahoman.com
https://www.oregonlive.com
https://www.inquirer.com
https://www.providencejournal.com
https://www.thestate.com
https://www.argusleader.com
https://www.tennessean.com
https://www.dallasnews.com
https://www.sltrib.com
https://www.burlingtonfreepress.com
https://www.pilotonline.com
https://www.seattletimes.com
https://www.wvgazettemail.com
https://www.jsonline.com
https://www.trib.com
http://worldunitednews.blogspot.com/
https://quicktrendnews.wordpress.com/
https://www.newsdesk.io/
https://3-mob.com/
https://smallwarsjournal.com/recent/
https://globalpressjournal.com/
https://www.thetimesinplainenglish.com/
https://newswarden.com/
https://www.buzzfeednews.com/section/world
https://www.spiegel.de/
https://www.thestar.com/news/world/
https://ifpnews.com/
https://cbn.com/cwn
https://worldnews24you.blogspot.com/?m=1
https://soulwriteempire.com/
https://newszetu.com/
https://www.carihargaterupdate.com/
https://statehooddc.com/
https://www.suresource24.com/
https://www.usnn.news/
https://www.worldstopexports.com/
https://www.headlinesoftoday.com/
https://articleify.com/
https://www.thedailycanvas.com/
https://wng.org/topics/international
https://insidexpress.com/
https://www.reuters.com/
https://www.yahoo.com/news/world/
https://wowplus.net/category/world-news/niger..
https://www.scmp.com/
https://worldweeklynews.com/
https://timesofindia.indiatimes.com/world
https://radarr.africa/
# --- GLOBAL / WORLD NEWS (Text-Only & Lite) ---
https://text.npr.org
https://lite.cnn.com
https://www.cbc.ca/lite/news
https://www.csmonitor.com/text_only
https://feeds.bbci.co.uk/news/world/rss.xml
https://www.reutersagency.com/feed/
# --- NORTH CAROLINA (RSS & Local) ---
https://www.wral.com/news/rss/48
https://www.newsobserver.com/?service=rss
https://abc11.com/feed/
https://www.wcnc.com/rss
https://www.wbtv.com/arc/outboundfeeds/rss/
https://www.northcarolinahealthnews.org/feed/
https://indyweek.com/feed/
# --- NEW YORK (RSS & Local) ---
https://nypost.com/feed/
https://gothamist.com/feed/
https://www.cityandstateny.com/rss
@ -665,3 +440,17 @@ data:
https://www.barchart.com/news/rss/commodities/futures-news
https://www.spglobal.com/spdji/en/rss
https://www.litefinance.org/rss/analytics/
https://www.mrt.com/arc/outboundfeeds/rss/category/business/oil/?outputType=xml
https://www.oaoa.com/category/local-news/inthepipeline/rss
https://pboilandgasmagazine.com/feed/
https://www.rigzone.com/news/rss.asp
https://rbnenergy.com/blogcast.rss
https://www.eia.gov/rss/todayinenergy.xml
https://www.firstalert7.com/news/energy
https://www.energyvoice.com/feed/?category=oilandgas/north-sea
https://www.rigzone.com/news/rss/north_sea
https://www.oedigital.com/feeds/rss
https://www.sodir.no/en/whats-new/news/rss
https://www.worldoil.com/rss?feed=topic:offshore
https://oilandgas.einnews.com/rss/north-sea-offshore
https://www.energyvoice.com/feed/