|
-- Lists are gathered with this command in the console from each of the wikipedia pages below |
|
-- JSON.stringify([...document.querySelectorAll("#mw-content-text a.external")].map(a => a.href), null, 2) |
|
CREATE OR REPLACE TABLE |
|
`httparchive-sandbox.test.news_pages_2023_03_01` AS |
|
SELECT |
|
url, |
|
_TABLE_SUFFIX AS client, |
|
"2023_03_01" AS crawl, |
|
payload |
|
FROM |
|
`httparchive.pages.2023_03_01_*` -- TABLESAMPLE SYSTEM (.1 PERCENT) |
|
WHERE |
|
NET.HOST(url) IN ( |
|
SELECT |
|
CONCAT(news_url_host) |
|
FROM ( |
|
SELECT |
|
news_url, |
|
NET.HOST(news_url) AS news_url_host |
|
FROM |
|
UNNEST([ |
|
-- https://en.wikipedia.org/wiki/Wikipedia:News_sources/Collections |
|
"http://www.allheadlinenews.com/briefs", "http://news.google.com/", "http://newshub.tucows.com/", "http://www.commondreams.org/", "http://www.havenworks.com/news/search", "http://www.havenworks.com/news/browse", "http://schema-root.org/", "https://www.aljazeera.com/", "http://www.abc.net.au/news/", "https://www.bbc.co.uk/news/", "http://www.channelnewsasia.com/", "http://www.ibnlive.com/", "http://www.democracynow.org/", "http://www.flashpoints.net/", "http://www.foxnews.com/", "http://www.ndtv.com/", "http://www.rnw.nl/cgi-bin/home/enhome.pl", "https://www.rte.ie/news/", "http://www.rthk.org.hk/rthk/news/englishnews/", "http://news.sky.com/", "http://www.tagesschau.de/english/", "http://www.aftenposten.no/english/", "http://www.theage.com.au/", "http://www.bangkokpost.com/", "http://business-times.asia1.com.sg/", "http://www2.chinadaily.com.cn/english/home/index.html", "http://www.telegraph.co.uk/", "http://www.dawn.com/", "http://www.deccanherald.com/", "http://www.spiegel.de/", "http://www.economist.com/", "https://www.ft.com/", "http://www.wyborcza.pl/", "http://www.granma.cu/ingles/", "http://www.globeandmail.ca/", "http://www.guardian.co.uk/", "http://www.haaretz.com/", "http://www.thehindu.com/", "http://www.hindustantimes.com/", "http://www.wisers.net/", "http://www.independent.co.uk/", "http://www.indianexpress.com/", "http://www.iht.com/", "http://www.nationmultimedia.com/", "http://www.nationalpost.com/", "http://www.nzz.ch/english/", "http://www.newindpress.com/", "http://newpaper.asia1.com.sg/", "http://www.nst.com.my/", "http://www.nypost.com/", "http://www.nytimes.com/", "http://www.jang.com.pk/thenews/index.html", "http://www.inq7.net/", "http://newsfromrussia.com/", "http://www.sfgate.com/", "http://www.scmp.com/", "http://thestar.com.my/", "http://www.thestatesman.net/", "http://straitstimes.asia1.com.sg/", "http://www.thesun.co.uk/", "http://www.smh.com.au/", "http://www.telegraphindia.com/", "http://www.timesonline.co.uk/", "http://www.timesofindia.com/", "http://www.thestar.com/", "http://www.washingtonpost.com/", "http://www.washtimes.com/", "http://www.afp.com/english/home/", "http://www.googlenews.in/", "https://apnews.com/", "http://www.ipsnews.net/", "http://www.falkland-malvinas.com/index.asp", "http://www.reuters.com/", "http://www.xinhuanet.com/english/", "http://www.allheadlinenews.com/briefs", "http://newstandardnews.net/", "http://www.newswiretoday.com/", "http://health.dailynewscentral.com/", "http://www.opalesque.com/", "http://story.news.yahoo.com/", "http://news.google.com/", "http://www.heise.de/tp/english/default.html", "http://news.aol.com/", "http://www.abcnewsnetwork.org/", "http://www.citizenxpress.com/", "http://www.sumanasa.com/india-news/", "http://www.newsgd.com/", "http://sofiaecho.com/", "http://www.chinastakes.com/", "http://www.thechinaperspective.com/", "http://www.kitco.com/market/marketnews.html", "http://www.oratert.com/", "http://www.oratert.com/news/armenia/index.1.html", "http://www.oratert.com/news/karabakh-artsakh/index.1.html", "http://www.oratert.com/news/azerbaijan/index.1.html", "http://www.oratert.com/news/georgia/index.1.html", "http://www.oratert.com/news/iran/index.1.html", "http://www.oratert.com/news/russia/index.1.html", "http://www.oratert.com/news/turkey/index.1.html", |
|
-- https://en.wikipedia.org/wiki/Wikipedia:News_sources/Africa |
|
"http://allafrica.com/", "http://news.bbc.co.uk/2/hi/africa/default.stm", "http://www.rfi.fr/actuen/listes/001/liste_mots_cles_213.asp", "http://www.irinnews.org/IRIN-Africa.aspx", "http://www.pambazuka.org/en/", "http://www.elkhabar.com/FrEn/?idc=52", "http://www.north-africa.com/one.htm", "http://www.angolapress-angop.ao/index-e.cgi", "https://angola24horas.com/", "http://www.beninembassyus.org/", "http://www.mmegi.bw/2005/October/Friday7/index.html", "http://weekly.ahram.org.eg/index.htm", "http://www.cairolive.com/index.html", "http://www.cairotimes.com/", "http://www.egypttoday.com/", "http://www.dehai.org/", "http://www.addistribune.com/", "http://www.telecom.net.et/~ena/Newsenglish/index.htm", "http://ethiopianreview.homestead.com/", "http://www.ethiopar.net/index.htm", "http://www.waltainfo.com/", "http://www.gambianet.com/", "http://www.gambia.gm/", "http://ghanareview.com/review/", "http://www.ghanaian-chronicle.com/", "http://www.independent-gh.com/", "http://www.statehousekenya.go.ke/", "http://www.lesotho.gov.ls/", "http://www.liberian-connection.com/", "http://www.theperspective.org/", "http://www.libya-watanona.com/", "http://www.nationmalawi.com/", "http://mbc.intnet.mu/news.htm", "http://www.mauritius-news.co.uk/", "http://www.jarida.8m.com/News.html", "http://www.map.ma/eng", "http://www.sortmoz.com/aimnews/English/Menu.htm", "http://www.grnnet.gov.na/intro.htm", "http://www.economist.com.na/", "http://www.namibian.com.na/", "http://www.aittv.com/", "http://www.nopa.net/", "http://www.newswatchngr.com/", "http://www.silverbirdgroup.com/silverbirdtv/", "http://www.vanguardngr.com/", "http://www.guardian.ng/", "http://www.arise.tv/", "http://www.channelstv.com/", "http://www.ictr.org/", "http://www.internews.org/activities/ICTR_reports/ICTR_reports.htm", "http://www.banadir.com/index.shtml", "http://www.businessday.co.za/home.aspx?Page=BD4P1236&MenuItem=BD4P1236", "http://www.iafrica.com/", "http://www.int.iol.co.za/", "http://www.news24.com/News24/HomeLite/", "http://www.sabc.co.za/portal/site", "http://www.sundaytimes.co.za/home/indexsunday.aspx?Page=ST6P197&MenuItem=ST6P197", "http://www.sudan.net/", "http://www.gov.sz/", "http://www.times.co.sz/", "http://www.theexpress.com/", "http://www.ippmedia.com/", "http://www.parliament.go.tz/bunge/index.php", "http://www.tunisiaonlinenews.com/", "http://www.monitor.co.ug/", "http://www.newvision.co.ug/", "http://www.un.org/Depts/dpko/missions/minurso/index.html", "http://www.wsahara.net/", "http://www.btinternet.com/~donald.macdonald/saharawi.htm", "http://www.elections.org.zm/", "http://www.daily-mail.co.zm/", "http://www.zambezitimes.com/Zambia", "http://www.herald.co.zw/", "http://www.fingaz.co.zw/", "http://www.theindependent.co.zw/news/2005/October/Friday7/index.html", "http://www.zbc.co.zw/", "http://www.zwnews.com/", |
|
-- https://en.wikipedia.org/wiki/Wikipedia:News_sources/Oceania |
|
"http://www.abc.net.au/news/", "http://www.news.com.au/", "http://news.ninemsn.com.au/", "http://seven.com.au/news", "http://www.ten.com.au/", "http://www.skynews.com.au/home/", "http://www.foxsports.com.au/", "http://afr.com/", "http://www.theaustralian.com.au/", "http://newsstore.fairfax.com.au/apps/newsSearch.ac", "http://www.crikey.com.au/", "http://www.smh.com.au/", "http://www.dailytelegraph.com.au/", "http://www.theage.com.au/", "http://www.heraldsun.com.au/", "http://www.couriermail.com.au/", "http://www.brisbanetimes.com.au/", "http://www.adelaidenow.com.au/", "http://au.news.yahoo.com/thewest/", "http://www.perthnow.com.au/", "http://www.watoday.com.au/", "http://canberra.yourguide.com.au/home.asp", "http://alicenow.com.au/news/general", "http://www.goldcoast.com.au/news.html", "http://www.illawarramercury.com.au/", "http://www.theherald.com.au/", "http://www.ntnews.com.au/", "http://au.news.yahoo.com/thewest/regional/southwest/", "http://www.themercury.com.au/", "http://www.townsvillebulletin.com.au/", "http://www.inmycommunity.com.au/", "http://www.postnewspapers.com.au/", "http://leader-news.whereilive.com.au/", "http://newslocal.whereilive.com.au/", "http://www.couriermail.com.au/questnews", "http://www.yourguide.com.au/yourguide.asp", "http://www.australia.gov.au/", "http://www.fijitimes.com/", "http://www.fijisun.com.fj/%E2%80%8E", "http://fijione.tv/", "http://www.fbc.com.fj/", "http://www.fijivillage.com/", "http://www.fiji.gov.fj/", "https://www.govt.nz/", "http://www.stuff.co.nz/", "http://www.nbr.co.nz/", "http://www.newstalkzb.co.nz/", "http://www.nzherald.co.nz/", "http://tvnz.co.nz/view/tvone_index_skin/tvone_index_group", "http://www.odt.co.nz/", "http://www.radionz.co.nz/", "http://www.newsroom.co.nz/", "http://scoop.co.nz/", "http://www.stuff.co.nz/", "http://times-age.co.nz/", "http://www.pngonline.gov.pg/", "http://www.postcourier.com.pg/", "http://www.cinews.co.ck/", "http://www.dailypost.vu/", "http://nouvellecaledonie.la1ere.fr/", "http://polynesie.la1ere.fr/", "http://www.lnc.nc/", "http://www.matangitonga.to/article/global_index.shtml", "http://www.samoanews.com/", "http://www.samoaobserver.ws/", "http://www.solomonstarnews.com/", "http://www.solomontimes.com/", "http://www.nzherald.co.nz/tokelau/news/headlines.cfm?l_id=500606", "http://www.pina.com.fj/", |
|
-- https://en.wikipedia.org/wiki/Wikipedia:News_sources/Europe |
|
"http://europa.eu/index_en.htm", "http://euractiv.com/", "http://euobserver.com/", "http://www.euronews.net/create_html.php?page=home", "https://www.gazette.eu.org/", "http://www.euro-reporters.com/", "http://eunews.euroesprit.org/", "http://www.european-voice.com/", "http://www.moscowtimes.ru/indexes/01.html", "http://www.osce.org/", "http://www.praguepost.com/index.php", "http://www.rferl.org/newsline/", "http://www.tol.cz/look/TOL/section.tpl?IdLanguage=1&IdPublication=4&NrIssue=139&tpid=43", "http://www.oratert.com/news/karabakh-artsakh/index.1.html", "http://www.oratert.com/news/", "http://technewscloud.com/", "http://www.albaniannews.com/", "http://www.asbarez.com/", "http://www.armenianow.com/", "http://www.azatutyun.am/", "http://www.cdaily.am/", "http://www.oratert.com/news/armenia/index.1.html/", "http://www.austria.org/", "http://oe1.orf.at/service/international_en", "http://www.austria.gv.at/DesktopDefault.aspx?alias=english&init&init", "http://www.wienerzeitung.at/DesktopDefault.aspx?TabID=4082&Alias=wzo", "http://www.today.az/", "http://www.en.apa.az/", "http://en.trend.az/", "http://www.anspress.com/", "http://www.azernews.az/site/", "http://www.theazeritimes.com/", "http://www.azerbaijantoday.com/", "http://www.spacetv.az/?lng=az", "http://www.azertag.com/index_en.html", "http://www.turan.az/Default_en.asp", "http://www.aztv.az/index-en.shtml", "http://www.xalqqazeti.com/index.php?lngs=eng", "http://www.525.az/new/", "http://www.zaman.az/site/", "http://www.sherg.az/", "http://en.itv.az/", "http://www.azadliq.org/", "http://www.azerbaijan.az/_News/_news_e.html?lang=en", "http://www.ayna.az/", "http://www.ikisahil.com/content/index.php?link=main.php", "http://bizimasr.media-az.com/", "http://www.ses-az.com/view.php?lang=az&menu=0", "http://www.xalqcebhesi.az/", "https://www.musavat.com/new/", "http://www.yeniazerbaycan.com/", "http://www.tezadlar.az/", "http://www.bizimyol.az/", "http://www.express.com.az/", "http://www.kaspi.az/", "http://www.nedelya.az/", "http://www.nashvek.com/view.php", "http://ourcentury.media-az.com/", "http://www.respublica.news.az/", "http://www.yenicag.az/", "http://en.mirzexezerinsesi.net/", "http://www.oratert.com/news/azerbaijan/index.1.html", "http://www.president.gov.by/eng/", "http://www.expatica.com/source/site_content_subchannel.asp?subchannel_id=24", "http://www.aimpress.ch/dyn/trae/trae-sar.htm", "http://www.iwpr.net/home_index_new.html", "http://www.mvp.gov.ba/Index_eng.htm", "http://www.nato.int/sfor/index.htm", "http://www.bta.bg/site/en/indexe.shtml", "http://www.government.bg/", "http://www.parliament.bg/?lng=en", "http://www.sofiaecho.com/", "http://www.novinite.com/", "http://websrv2.hina.hr/hina/web/index.action?request_locale=en", "http://www.jutarnji.hr/", "http://www.vecernji.hr/", "http://slobodnadalmacija.hr/", "http://vijesti.hrt.hr/", "http://www.iwpr.net/home_index_new.html", "http://www.hri.org/news/cyprus/riken/last/last.html", "http://www.cyprus-mail.com/news/", "http://kypros.org/cgi-bin/headlines?/News/Update/english.html", "http://www.cna.org.cy/website/english/index.asp", "http://www.cyprusweekly.com.cy/", "http://www.financialmirror.com/", "http://www.moi.gov.cy/moi/pio/pio.nsf/index_en/index_en?opendocument", "http://www.trncwashdc.org/", "http://www.ceskenoviny.cz/news/", "http://www.nzz.ch/english/", "http://www.psp.cz/cgi-bin/eng/", "http://www.prague-tribune.cz/", "http://www.radio.cz/english/", "http://www.cphpost.dk/", "http://www.ft.dk/?/samling/20051/menu/00000005.htm", "http://www.wrn.org/listeners/stations/station.php?StationID=11", "http://www.baltictimes.com/", "http://www.bbn.ee/", "http://news.err.ee/", "http://news.postimees.ee/", "http://www.president.ee/en/", "https://valitsus.ee/en/news", "http://www.helsinginsanomat.fi/english/", "http://virtual.finland.fi/news/", "http://www.aloufok.net/", "http://fr.newswiretoday.com/", "http://www.assemblee-nationale.fr/english/index.asp", "http://www.iht.com/", "http://www.parliament.ge/", "http://www.oratert.com/news/georgia/index.1.html/", "http://www.dw-world.de/dw/0,,266,00.html", "http://www.germany-info.org/relaunch/index.html", "http://www.bundestag.de/htdocs_e/index.html", "http://www.bundesregierung.de/en", "http://service.spiegel.de/cache/international/", "http://www.tagesschau.de/english/", "http://www.heise.de/tp/english/default.html", "http://aegeantimes.net/", "http://www.athensnews.gr/athweb/nathens.index_htm?e=C", "http://www.ana.gr/anaweb/", "http://www.greekembassy.org/press/index.html", "http://www.hri.org/", "http://www.ekathimerini.com/", "http://www.ert.gr/en/", "http://www.bbj.hu/", "http://www.wrn.org/listeners/stations/station.php?StationID=9", "http://www.icelandreview.com/", "http://www.scandinavianow.com/", "http://www.irlgov.ie/", "http://www.irishexaminer.com/pport/web/irishexaminer/", "http://larkspirit.com/general/irishhub.html", "http://republican-news.org/current/news/index.html", "http://www.ireland.com/newspaper/front/2005/1029/", "http://www.sbpost.ie/post/pages/home.aspx-qqqt%3D-qqqs%3Dnav-qqqx%3D1x-qqqt%3D-qqqs%3Dnews-qqqx%3D1.asp", "https://www.rte.ie/news/index.html", "http://www.unison.ie/irish_independent/", "http://home.eircom.net/news/", "http://www.ansa.it/main/notizie/awnplus/english/english.html", "http://www.ilsole24ore.com/", "http://www.repubblica.it/", "http://www.corriere.it/", "http://www.channelonline.tv/channelonline/", "http://www.thisisjersey.com/", "https://www.bbc.co.uk/news/world/europe/jersey/", "http://www.balticsww.com/wkcrier/daily_news.htm", "http://www.baltictimes.com/", "http://www.president.lv/index.php?pid=210", "http://www.radio.org.lv/Lapas/EN_Index.htm", "https://www.lsm.lv/", "http://www.news.li/news/index.htm", "http://www.lrv.lt/main_en.php", "http://www.iwpr.net/home_index_new.html", "https://mia.mk//", "http://www.seeq.com/lander.jsp?referrer=http%3A%2F%2Fwww.gua…622982%2C00.html&domain=maltabusinessweekly.com&cm_mmc=Malta", "http://www.di-ve.com/dive/portal/main.html", "http://www.gov.mt/", "http://217.145.4.56/ind/", "http://www.maltamedia.com/artman/publish/news.shtml", "https://www.timesofmalta.com/core/index.php", "http://www.basa.md/?", "http://cg.mnnews.net/indexeng.php3?akcija=mnnews", "http://www.minbuza.nl/default.asp?CMS_ITEM=12E5DC3F5E024ADFB2AA6B315606A627X2X31365X4", "http://www2.rnw.nl/rnw/en/", "http://www.aftenposten.no/english/", "http://odin.dep.no/odin/global/language-no/index-b-n-a.html", "http://www.norwaypost.no/", "http://www.kprm.gov.pl/english/index.html", "http://www.poland.pl/", "http://www.thenews.pl/", "http://www.rzeczpospolita.pl/jezyki/index.html", "http://www.wbj.pl/", "http://www.warsawvoice.com.pl/", "http://www.polandmonthly.pl/", "http://www.portugal.org/index.shtml", "http://the-news.net/", "http://www.agerpres.ro/english/index.php/english.html", "http://www.mediafax.ro/english/", "http://english.hotnews.ro/", "http://www.radardemedia.ro/", "http://www.gov.ro/engleza/index.html", "http://www.nineoclock.ro/", "http://www.gazeta.ru/english/", "http://www.interfax.ru/?lang=e&", "http://english.pravda.ru/", "http://www.rbcnews.com/", "http://www.oratert.com/news/russia/index.1.html/", "http://en.rian.ru/", "http://www.moscowtimes.ru/indexes/01.html", "http://beta.russiajournal.com/", "http://www.gov.ru/", "http://www.sptimes.ru/", "http://www.vor.ru/world.html", "http://rbtn.ru/", "http://www.b92.net/english/", "http://www.srbija.gov.rs/", "http://www.iwpr.net/home_index_new.html", "http://www.tanjug.rs/", "http://www.government.gov.sk/english/", "http://www.slovensko.com/news/", "http://www.sigov.si/", "http://www.iwpr.net/home_index_new.html", "http://www.costablanca-news.com/", "http://www.la-moncloa.es/default.htm", "http://www.surinenglish.com/index.php", "http://www.thelocal.se/", "http://sverigesradio.se/sida/default.aspx?programid=2054", "http://www.nzz.ch/english/index.html", "http://www.swissinfo.org/", "http://www.turkishweekly.com/", "http://aegeantimes.net/", "http://www.turkishdailynews.com.tr/", "http://www.turkishpress.com/", "http://www.zaman.com/", "http://www.kurdistanobserver.com/", "http://www.oratert.com/news/turkey/index.1.html", "http://www.4ni.co.uk/", "http://www.accountancyage.com/", "http://www.aidsmap.com/", "http://www.amnesty.org.uk/", "https://www.bbc.co.uk/news/", "http://www.belfasttelegraph.co.uk/", "http://www.channel4.com/news", "http://www.number-10.gov.uk/output/Page1.asp", "http://www.theecologist.co.uk/home.asp", "http://www.economist.com/index.html", "http://www.fwi.co.uk/", "http://news.ft.com/home/uk", "http://www.guardian.co.uk/", "http://icwales.icnetwork.co.uk/", "http://www.independent.co.uk/", "http://www.itn.co.uk/", "http://www.mirror.co.uk/", "http://www.newstatesman.com/", "http://www.private-eye.co.uk/", "http://today.reuters.co.uk/news/default.aspx", "http://www.socialistworker.co.uk/", "http://www.sky.com/skynews/home", "http://www.thesun.co.uk/", "http://www.telegraph.co.uk/portal/main.jhtml", "http://thescotsman.scotsman.com/", "http://www.spectator.co.uk/index.php", "http://www.ukremb.com/", "http://www.interfax.kiev.ua/eng/", "http://www.kyivpost.com/", "http://www.window.com.ua/", "http://www.apostrophe.ua/en/", |
|
-- https://en.wikipedia.org/wiki/Wikipedia:News_sources/China |
|
"http://www.metroradio.com.hk/1044metroplus/engnews/", "http://www.chinaonline.com/", "http://www.china-embassy.org/eng/", "http://en.chinabroadcast.cn/", "http://english.eastday.com/", "http://www.theepochtimes.com/123,92,,1.html", "http://news.info.gov.hk/", "http://english.peopledaily.com.cn/", "http://www.rthk.org.hk/rthk/news/englishnews/", "http://www.thestandard.com/", "http://202.84.17.11/en/index.htm", "http://www.wisers.net/", "http://www.mingpaonews.com/", "http://news.tvb.com/", |
|
-- https://en.wikipedia.org/wiki/Wikipedia:News_sources/India |
|
"http://allindiaradio.gov.in/", "http://www.ptinews.com/", "https://www.etvbharat.com/", "http://www.ibnlive.com/", "http://www.dailyexcelsior.com/", "http://www.dnaindia.com/", "http://www.deccanherald.com/", "https://www.indiatvnews.com/", "https://www.news18.com/amp/", "http://www.gomantaktimes.com/MAI25705.htm", "http://goidirectory.nic.in/", "https://www.thehindu.com//", "http://www.hindustantimes.com/", "http://www.newindpress.com/", "http://www.ranchiexpress.com/news/", "http://www.rediff.com/news/", "http://theullekh.com/", "http://www.sumanasa.com/india-news/", "http://www.samachar.com/", "http://www.onlineindiannews.com/news/", "http://www.thestatesman.net/", "http://www.sunnt.com/", "http://www.indianexpress.com/sunday/index.html", "http://www.telegraphindia.com/section/frontpage/index.asp", "http://timesofindia.indiatimes.com/?", "http://www.tribuneindia.com/", "http://www.the-week.com/", "http://www.b4uindia.com/", "http://www.theprint.in/", "https://connectgujarat.com/", |
|
-- https://en.wikipedia.org/wiki/Wikipedia:News_sources/Asia |
|
"http://www.atimes.com/", "http://www.dawn.com/2005/11/27/index.htm", "http://www.feer.com/", "http://www.thejakartapost.com/headlines.asp", "http://www.menafn.com/", "http://english.aljazeera.net/HomePage", "http://www.arabicnews.com/ansub/", "http://www.middle-east-online.com/english/", "http://www.arab.net/", "https://news.writecaliber.com/", "http://www.omaid.com/english_section/curr_issue.htm", "http://www.afgha.com/", "http://www.ans-dx.com/", "http://azerbaijannews.net/", "http://www.bakusun.az:8101/", "http://www.president.az/", "http://www.oratert.com/news/azerbaijan/index.1.html", "http://www.bahraintribune.com/", "http://www.gulf-daily-news.com/", "http://www.bangladeshobserveronline.com/new/2005/11/27/index.htm", "http://www.thedailystar.net/", "http://www.weeklyholiday.net/", "http://www.independent-bangladesh.com/", "http://www.bangladesh-web.com/news/", "http://nation.ittefaq.com/artman/publish/", "http://www.bangladeshgov.org/", "http://www.bbs.com.bt/", "http://www.kuenselonline.com/", "http://www.ibiblio.org/freeburma/", "http://www.mizzima.com/mizzima/", "http://www.ncgub.net/", "http://www.phnompenhpost.com/", "http://www.vocri.org/", "http://www.thejakartapost.com/headlines.asp", "http://www.antara.co.id/en/", "http://www.kompas.com/", "http://www.indonesianembassy.org.uk/", "http://www.presstv.com/", "http://www.tehrantimes.com/", "http://www.mehrnews.com/en/", "http://www.ilna.ir/indexEN.aspx", "http://www.isna.ir/ISNA/Default.aspx?Lang=E", "http://www.irna.ir/En/default.aspx?IdLanguage=3", "http://english.iribnews.ir/", "http://www.alalam-news.com/english/", "http://www.iran-daily.com/1384/2459/html/", "http://www.iranian.com/news.html", "http://www.oratert.com/news/iran/index.1.html", "http://www.baghdadbulletin.com/", "http://www.iraqcrisis.co.uk/home.php", "http://www.iraq-today.com/", "http://www.haaretz.com/", "http://www.ynetnews.com/home/0,7340,L-3083,00.html", "http://web.israelinsider.com/home.htm", "http://info.jpost.com/C005/JREPORT/", "http://www.jpost.com/", "http://www.israelnationalnews.com/", "http://www.wrn.org/listeners/stations/station.php?StationID=35", "http://www.asahi.com/english/english.html", "http://www.yomiuri.co.jp/dy/", "http://www.fnn-news.com/en/index.html", "http://www.japantimes.co.jp/", "http://www.japantoday.com/", "http://home.kyodo.co.jp/", "http://www.nni.nikkei.co.jp/", "http://www.tokyoartbeat.com/", "http://www.art-it.asia/top/?lang=en", "http://pingmag.jp/", "http://www.japantimes.co.jp/entertainment/art.html", "http://www.dnp.co.jp/artscape/eng/index.html", "http://www.jordantimes.com/fri/index.htm", "http://www.petra.gov.jo/main.asp", "http://www.kinghussein.gov.jo/jordan.html#", "http://www.arabtimesonline.com/arabtimes/index.asp", "http://www.kuwaittimes.net/", "http://www.zawya.com/countries/kw/", "http://www.dailystar.com.lb/home2.asp", "http://www.lebanon.com/", "http://www.mmorning.com/", "http://www.dailyexpress.com.my/", "http://www.malaysiakini.com/", "http://thestar.com.my/", "https://www.utusan.com.my/index.asp?pub=Utusan_Express", "http://www.nst.com.my/", "http://www.haveeru.com.mv/?page=english", "http://www.presidencymaldives.gov.mv/v3/index.phtml", "http://www.minivannews.com/news/news.php?id=1263", "http://www.dhivehiobserver.com/", "http://www.myfreenepal.com/", "http://www.nepalnews.com/archive/main.htm", "http://www.radionepal.org/", "http://www.minivannews.com/news/news.php?id=1263", "http://www.kcna.co.jp/index-e.htm", "http://www.omanobserver.com/", "http://www.timesofoman.com/", "http://www.amin.org/", "http://www.palestinechronicle.com/", "http://www.aqsa.org.uk/", "http://www.alternativenews.org/", "http://www.miftah.org/", "http://dawn.com/", "http://geo.tv/", "http://inewsjournal.com/", "http://www.frontierpost.com.pk/", "http://www.jang.com.pk/thenews/", "http://paktribune.com/", "http://pakistantimes.net/2005/10/10A/index.htm", "http://www.paktoday.com/", "http://www.radio.gov.pk/index.asp", "http://www.weeklyindependent.com/", "http://www.infopak.gov.pk/", "http://www.abs-cbnnews.com/", "http://www.gmanetwork.com/news/", "http://www.inquirer.net/", "http://www.philstar.com/", "http://www.gulf-times.com/site/topics/index.asp?cu_no=2&temp_type=44", "http://english.mofa.gov.qa/", "http://www.ain-al-yaqeen.com/", "http://www.saudia-online.com/", "http://www.saudinf.com/", "http://www.channelnewsasia.com/", "http://straitstimes.asia1.com.sg/", "http://business-times.asia1.com.sg/", "http://newpaper.asia1.com.sg/", "http://www.zaobao.com/", "http://cyberita.asia1.com.sg/", "http://tamilmurasu.asia1.com.sg/", "http://english.chosun.com/", "http://www.koreaherald.co.kr/index.asp", "http://rki.kbs.co.kr/", "http://www.korea.net/", "http://www.aruna.lk/", "https://www.themorning.lk/", "https://www.hirunews.lk/", "https://www.adaderana.lk/", "https://readme.lk/", "http://www.dailynews.lk/", "http://www.island.lk/", "http://www.thesundayleader.lk/home.html", "http://www.sundaytimes.lk/", "http://www.tamileelamnews.com/", "http://www.news.lk/", "http://www.chinapost.com.tw/", "http://english.rti.com.tw/", "http://www.taipeitimes.com/News", "http://www.gio.gov.tw/", "http://www.nationmultimedia.com/", "http://www.biz-day.com/", "http://www.bangkokpost.net/", "http://www.pattayamail.com/", "http://www.phuketgazette.net/", "http://www.parliament.go.th/files/mainpage.htm", "http://www.turkmenistanembassy.org/", "http://www.godubai.com/gulftoday/", "http://www.khaleejtimes.com/index00.asp", "http://www.gulf-news.com/home/index.html", "http://www.government.ae/gov/en/index.jsp", "http://www.gov.uz/", "http://vietnamnews.vnagency.com.vn/", "http://www.vov.org.vn/", "http://www.nhandan.com.vn/english/", "http://yementimes.com/index.shtml?", |
|
-- https://en.wikipedia.org/wiki/Wikipedia:News_sources/Americas |
|
"http://www.buenosairesherald.com/", "http://www.belize.gov.bz/", "http://www.infobrazil.com/", "http://internacional.radiobras.gov.br/ingles/index.htm", "http://www.estado.com.br/", "http://oglobo.globo.com/", "http://www.ctv.ca/", "http://www.cbc.ca/", "http://www.globalnews.ca/", "http://www.chch.com/", "http://www.calgaryherald.com/", "http://www.canoe.ca/CNEWS/home.html", "http://www.edmontonjournal.com/", "http://www.theglobeandmail.com/", "http://thechronicleherald.ca/", "http://www.thehaltonherald.ca/", "http://www.thehilltimes.ca/", "http://www.thewhig.com/Default.aspx", "http://www.metronews.ca/", "http://www.montrealgazette.com/", "http://www.nationalpost.com/", "http://www.nunatsiaq.com/index.html", "http://www.canada.com/ottawacitizen/index.html", "http://www.ottawasun.com/", "http://www.leaderpost.com/", "http://www.thetelegram.com/", "http://www.thestarphoenix.com/", "http://www.thestar.com/", "http://www.torontosun.com/", "http://www.canada.com/theprovince/index.html", "http://www.canada.com/vancouversun/index.html", "http://www.timescolonist.com/", "http://www.winnipegfreepress.com/", "http://canada.gc.ca/", "http://www.caribbeannetnews.com/", "http://www.cananews.net/", "http://www.amcostarica.com/", "http://www.ticotimes.net/", "http://www.costaricanewssite.com/", "http://www.granma.cu/ingles/", "http://balistrad.com/", "http://www.lenouvelliste.com/", "http://www.marrder.com/htw/", "http://www.latinnews.com/", "http://www.mexiconews.com.mx/", "http://www.theaerogram.com/", "https://allheadlinenews.com/", "http://www.armytimes.com/", "http://www.cnn.com/", "http://www.csmonitor.com/", "http://www.democracynow.org/", "http://news.ft.com/home/us", "http://www.drudgereport.com/", "http://www.newswiretoday.com/", "http://knowledge.wharton.upenn.edu/", "http://www.latimes.com/", "http://www.npr.org/", "http://www.nytimes.com/", "http://www.newstandardnews.net/", "http://www.newsday.com/", "http://www.newsfactor.com/", "http://www.newseum.org/", "http://www.msnbc.com/", "http://www.rollcall.com/", "http://www.poynter.org/", "http://www.washingtonpost.com/", "http://online.wsj.com/public/us", "http://www.washtimes.com/", "http://www.usatoday.com/", "http://www.wired.com/" ]) AS news_url) ) |
|
|