enhance news crawler configuration with new sources and improved request headers

This commit is contained in:
ImBenji
2026-04-16 23:32:56 +01:00
parent c91e4ddb60
commit 11647e6a35
6 changed files with 449 additions and 33 deletions
+269 -13
View File
@@ -365,6 +365,22 @@
{
"url": "https://elcomercio.pe/arc/outboundfeeds/rss/section/economia/",
"label": "El Comercio Peru"
},
{
"url": "https://jamaica-gleaner.com/feed/business.xml",
"label": "Jamaica Gleaner"
},
{
"url": "https://www.jamaicaobserver.com/app/business/",
"label": "Jamaica Observer"
},
{
"url": "https://www.stabroeknews.com/feed/",
"label": "Stabroek News"
},
{
"url": "https://nationnews.com/rss-feed/",
"label": "Nation News Barbados"
}
],
"gdelt": {
@@ -376,24 +392,264 @@
"format": "json"
},
"newsCrawler": {
"sites": [
{
"name": "crawler_reuters",
"maxPages": 15,
"maxDepth": 1,
"requestTimeout": 15000,
"disabledLabels": [
"Arab News",
"Arabian Business",
"Australian Fin Review",
"BFM Business",
"Business Daily Africa",
"Business Standard IN",
"BusinessLive SA",
"Caixin Global",
"Cinco Dias",
"City A.M.",
"El Comercio Peru",
"El Economista ES",
"El Economista MX",
"FD.nl",
"Gulf News Business",
"Il Sole 24 Ore",
"Infobae Economia AR",
"Japan Times Business",
"Korea JoongAng Daily",
"Les Echos",
"Live Mint",
"Moneycontrol",
"NZ Herald Business",
"Portafolio Colombia",
"Reuters",
"The Star Malaysia",
"This Is Money",
"Xinhua Business"
],
"overrides": {
"Al Jazeera": {
"allowedHosts": [
"www.reuters.com",
"reuters.com"
"www.aljazeera.com",
"aljazeera.com"
],
"seeds": [
"https://www.reuters.com/world/",
"https://www.reuters.com/business/",
"https://www.reuters.com/markets/",
"https://www.reuters.com/technology/"
"https://www.aljazeera.com/",
"https://www.aljazeera.com/economy/",
"https://www.aljazeera.com/tag/technology/"
]
},
"Ars Technica": {
"allowedHosts": [
"arstechnica.com",
"www.arstechnica.com"
],
"maxPages": 100,
"maxDepth": 2,
"requestTimeout": 15000
"seeds": [
"https://arstechnica.com/",
"https://arstechnica.com/tech-policy/",
"https://arstechnica.com/information-technology/"
]
},
"BBC Business": {
"allowedHosts": [
"www.bbc.com",
"bbc.com"
],
"seeds": [
"https://www.bbc.com/news/business",
"https://www.bbc.com/news/technology"
]
},
"CNBC": {
"allowedHosts": [
"www.cnbc.com",
"cnbc.com"
],
"seeds": [
"https://www.cnbc.com/world/",
"https://www.cnbc.com/business/",
"https://www.cnbc.com/technology/"
]
},
"Guardian Business": {
"allowedHosts": [
"www.theguardian.com",
"theguardian.com"
],
"seeds": [
"https://www.theguardian.com/",
"https://www.theguardian.com/business",
"https://www.theguardian.com/technology"
]
},
"Jamaica Gleaner": {
"allowedHosts": [
"jamaica-gleaner.com",
"www.jamaica-gleaner.com"
],
"seeds": [
"https://jamaica-gleaner.com/",
"https://jamaica-gleaner.com/news",
"https://jamaica-gleaner.com/business"
]
},
"Jamaica Observer": {
"allowedHosts": [
"www.jamaicaobserver.com",
"jamaicaobserver.com"
],
"seeds": [
"https://www.jamaicaobserver.com/",
"https://www.jamaicaobserver.com/news/",
"https://www.jamaicaobserver.com/business/"
]
},
"Nation News Barbados": {
"allowedHosts": [
"nationnews.com",
"www.nationnews.com"
],
"seeds": [
"https://nationnews.com/",
"https://nationnews.com/category/business/",
"https://nationnews.com/category/news/"
]
},
"NPR Business": {
"allowedHosts": [
"www.npr.org",
"npr.org"
],
"seeds": [
"https://www.npr.org/sections/business/",
"https://www.npr.org/sections/technology/"
]
},
"The Verge": {
"allowedHosts": [
"www.theverge.com",
"theverge.com"
],
"seeds": [
"https://www.theverge.com/tech",
"https://www.theverge.com/business",
"https://www.theverge.com/archives"
]
},
"TechCrunch": {
"allowedHosts": [
"techcrunch.com",
"www.techcrunch.com"
],
"seeds": [
"https://techcrunch.com/",
"https://techcrunch.com/category/startups/",
"https://techcrunch.com/category/venture/"
]
},
"The Economist": {
"allowedHosts": [
"www.economist.com",
"economist.com"
],
"seeds": [
"https://www.economist.com/finance-and-economics",
"https://www.economist.com/business",
"https://www.economist.com/science-and-technology"
]
},
"Federal Reserve": {
"allowedHosts": [
"www.federalreserve.gov",
"federalreserve.gov"
],
"seeds": [
"https://www.federalreserve.gov/newsevents.htm",
"https://www.federalreserve.gov/monetarypolicy.htm"
]
},
"Fortune": {
"allowedHosts": [
"fortune.com",
"www.fortune.com"
],
"seeds": [
"https://fortune.com/",
"https://fortune.com/section/tech/",
"https://fortune.com/section/finance/"
]
},
"Forbes Business": {
"allowedHosts": [
"www.forbes.com",
"forbes.com"
],
"seeds": [
"https://www.forbes.com/business/",
"https://www.forbes.com/innovation/"
]
},
"Nikkei Asia": {
"allowedHosts": [
"asia.nikkei.com"
],
"seeds": [
"https://asia.nikkei.com/",
"https://asia.nikkei.com/Business",
"https://asia.nikkei.com/Technology"
]
},
"South China Morning Post": {
"allowedHosts": [
"www.scmp.com",
"scmp.com"
],
"seeds": [
"https://www.scmp.com/",
"https://www.scmp.com/business",
"https://www.scmp.com/tech"
]
},
"Stabroek News": {
"allowedHosts": [
"www.stabroeknews.com",
"stabroeknews.com"
],
"seeds": [
"https://www.stabroeknews.com/",
"https://www.stabroeknews.com/category/business/",
"https://www.stabroeknews.com/category/news/"
]
},
"Wall Street Journal": {
"allowedHosts": [
"www.wsj.com",
"wsj.com"
],
"seeds": [
"https://www.wsj.com/news/business",
"https://www.wsj.com/tech"
]
},
"Wired Business": {
"allowedHosts": [
"www.wired.com",
"wired.com"
],
"seeds": [
"https://www.wired.com/category/business/",
"https://www.wired.com/category/security/"
]
},
"Yahoo Finance": {
"allowedHosts": [
"finance.yahoo.com"
],
"seeds": [
"https://finance.yahoo.com/",
"https://finance.yahoo.com/news/",
"https://finance.yahoo.com/topic/tech/"
]
}
]
}
},
"scheduler": {
"rss": "0 */6 * * *",