185 lines
4.5 KiB
YAML
185 lines
4.5 KiB
YAML
|
|
apiVersion: v1
|
||
|
|
kind: ConfigMap
|
||
|
|
metadata:
|
||
|
|
name: scrapy-urls
|
||
|
|
namespace: customer1
|
||
|
|
data:
|
||
|
|
urls.txt: |
|
||
|
|
https://www.npr.org
|
||
|
|
https://www.bbc.com/news
|
||
|
|
https://www.reuters.com
|
||
|
|
https://www.khmertimeskh.com
|
||
|
|
https://apnews.com
|
||
|
|
# USA
|
||
|
|
https://www.npr.org
|
||
|
|
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
|