View raw JSON
{
"type": "object",
"required": [],
"properties": {
"body": {
"type": "object",
"title": "Google News Scraper",
"required": [],
"properties": {
"topics": {
"type": "array",
"items": {
"enum": [
"WORLD",
"NATION",
"BUSINESS",
"TECHNOLOGY",
"ENTERTAINMENT",
"SPORTS",
"SCIENCE",
"HEALTH"
],
"type": "string",
"enumTitles": [
"🌍 World",
"🏛️ Nation",
"💼 Business",
"💻 Technology",
"🎬 Entertainment",
"⚽ Sports",
"🔬 Science",
"🏥 Health"
]
},
"title": "News Topics",
"editor": "select",
"default": [],
"description": "Optional list of predefined Google News topics, empty by default. Choose from the eight supported categories. Topics can be combined with keyword searches or custom section links; topic pages return their curated selections.",
"sectionCaption": "📰 Topic News",
"sectionDescription": "Scrape Google News by predefined topics or custom section/topic URLs. You can combine both with keyword search."
},
"keywords": {
"type": "array",
"title": "Search Keywords",
"editor": "stringList",
"default": [],
"prefill": [
"bitcoin"
],
"maxItems": 50,
"minItems": 0,
"description": "Optional list of up to 50 unique keyword strings, empty by default. The prefilled bitcoin is an example. Within a keyword, use - to exclude a word, site: to restrict a website, OR for alternatives or quotation marks for a phrase.",
"uniqueItems": true,
"sectionCaption": "🔍 Keyword Search",
"sectionDescription": "Search Google News by keywords. Leave empty if you only want to scrape by topics."
},
"timeframe": {
"enum": [
"1h",
"1d",
"7d",
"30d",
"1y",
"all"
],
"type": "string",
"title": "Time Period (Only for keywords)",
"default": "1h",
"enumTitles": [
"Last hour",
"Last day",
"Last week",
"Last month",
"Last year",
"Anytime"
],
"description": "Optional time window, mainly for keyword searches. Default 1h (last hour); other choices are 1d (last day), 7d (last seven days), 30d (last thirty days), 1y (last year) and all (any time). Topic pages provide curated results rather than applying this window to every story."
},
"topicUrls": {
"type": "array",
"title": "Custom Topic / Section URLs",
"editor": "stringList",
"default": [],
"maxItems": 20,
"minItems": 0,
"description": "Optional list of up to 20 unique Google News topic or section URLs, empty by default. Use it for custom or niche news sections, not publisher article URLs. It can be combined with keywords and predefined topics.",
"uniqueItems": true
},
"decodeUrls": {
"type": "boolean",
"title": "Decode Google News URLs",
"default": false,
"description": "Optional, default false. When enabled, attempts to resolve each Google News redirect to a publisher link, adding processing work and slowing collection. A resolved link is not guaranteed for every story."
},
"maxArticles": {
"type": "integer",
"unit": "news",
"title": "Maximum News",
"default": 100,
"minimum": 0,
"description": "Optional integer limit per keyword, predefined topic or custom topic URL, default 100 and minimum 0. Zero removes this per-source cap, while source availability and processing still limit collection. Combined sources can exceed the value overall; it does not guarantee a returned count or complete coverage.",
"sectionCaption": "⚙️ Settings & Options",
"sectionDescription": "General settings and advanced options applied to both keyword search and topic scraping."
},
"extractImages": {
"type": "boolean",
"title": "Extract Article Images",
"default": true,
"description": "Optional, default true. When an image reference is missing, enables publisher-page image enrichment, mainly for topic results. False skips image extraction or enrichment; source records may still contain image references. References are not downloaded image files."
},
"region_language": {
"enum": [
"US:en",
"SK:sk",
"AU:en",
"BW:en",
"CA:en",
"ET:en",
"GH:en",
"IN:en",
"ID:en",
"IE:en",
"IL:en",
"KE:en",
"LV:en",
"MY:en",
"NA:en",
"NZ:en",
"NG:en",
"PK:en",
"PH:en",
"SG:en",
"ZA:en",
"TZ:en",
"UG:en",
"GB:en",
"ZW:en",
"ID:id",
"CZ:cs",
"DE:de",
"AT:de",
"CH:de",
"AR:es-419",
"CL:es-419",
"CO:es-419",
"CU:es-419",
"ES:es",
"US:es-419",
"MX:es-419",
"PE:es-419",
"VE:es-419",
"BE:fr",
"CA:fr",
"FR:fr",
"MA:fr",
"SN:fr",
"CH:fr",
"IT:it",
"LV:lv",
"LT:lt",
"HU:hu",
"BE:nl",
"NL:nl",
"NO:no",
"PL:pl",
"BR:pt-419",
"PT:pt-150",
"RO:ro",
"SI:sl",
"SE:sv",
"VN:vi",
"TR:tr",
"GR:el",
"BG:bg",
"RU:ru",
"UA:ru",
"RS:sr",
"UA:uk",
"IL:he",
"AE:ar",
"SA:ar",
"LB:ar",
"EG:ar",
"IN:mr",
"IN:hi",
"BD:bn",
"IN:bn",
"IN:ta",
"IN:te",
"IN:ml",
"TH:th",
"CN:zh-Hans",
"TW:zh-Hant",
"HK:zh-Hant",
"JP:ja",
"KR:ko"
],
"type": "string",
"title": "Region and Language",
"editor": "select",
"default": "US:en",
"enumTitles": [
"United States (English)",
"Slovakia (Slovak)",
"Australia (English)",
"Botswana (English)",
"Canada (English)",
"Ethiopia (English)",
"Ghana (English)",
"India (English)",
"Indonesia (English)",
"Ireland (English)",
"Israel (English)",
"Kenya (English)",
"Latvia (English)",
"Malaysia (English)",
"Namibia (English)",
"New Zealand (English)",
"Nigeria (English)",
"Pakistan (English)",
"Philippines (English)",
"Singapore (English)",
"South Africa (English)",
"Tanzania (English)",
"Uganda (English)",
"United Kingdom (English)",
"Zimbabwe (English)",
"Indonesia (Indonesian)",
"Czech Republic (Czech)",
"Germany (German)",
"Austria (German)",
"Switzerland (German)",
"Argentina (Spanish)",
"Chile (Spanish)",
"Colombia (Spanish)",
"Cuba (Spanish)",
"Spain (Spanish)",
"United States (Spanish)",
"Mexico (Spanish)",
"Peru (Spanish)",
"Venezuela (Spanish)",
"Belgium (French)",
"Canada (French)",
"France (French)",
"Morocco (French)",
"Senegal (French)",
"Switzerland (French)",
"Italy (Italian)",
"Latvia (Latvian)",
"Lithuania (Lithuanian)",
"Hungary (Hungarian)",
"Belgium (Dutch)",
"Netherlands (Dutch)",
"Norway (Norwegian)",
"Poland (Polish)",
"Brazil (Portuguese)",
"Portugal (Portuguese)",
"Romania (Romanian)",
"Slovenia (Slovenian)",
"Sweden (Swedish)",
"Vietnam (Vietnamese)",
"Turkey (Turkish)",
"Greece (Greek)",
"Bulgaria (Bulgarian)",
"Russia (Russian)",
"Ukraine (Russian)",
"Serbia (Serbian)",
"Ukraine (Ukrainian)",
"Israel (Hebrew)",
"United Arab Emirates (Arabic)",
"Saudi Arabia (Arabic)",
"Lebanon (Arabic)",
"Egypt (Arabic)",
"India (Marathi)",
"India (Hindi)",
"Bangladesh (Bengali)",
"India (Bengali)",
"India (Tamil)",
"India (Telugu)",
"India (Malayalam)",
"Thailand (Thai)",
"China (Simplified Chinese)",
"Taiwan (Traditional Chinese)",
"Hong Kong (Traditional Chinese)",
"Japan (Japanese)",
"Korea (Korean)"
],
"description": "Optional choice from the supported regional editions and languages, default US:en (US English). Examples include GB:en (UK English), FR:fr (French) and CN:zh-Hans (Simplified Chinese). This does not translate articles or guarantee that publishers are located in the selected region."
},
"proxyConfiguration": {
"type": "object",
"title": "Proxy Configuration",
"editor": "proxy",
"default": {
"useApifyProxy": true
},
"prefill": {
"useApifyProxy": true
},
"description": "Optional source-proxy configuration. The default enables Apify Proxy. Leave it unchanged for this example.",
"sectionCaption": "🌐 Proxy"
},
"extractDescriptions": {
"type": "boolean",
"title": "Extract Article Descriptions",
"default": false,
"description": "Optional, default false. When enabled, fetches the publisher’s page description (meta description), adding work and slowing collection. This short description is not full article text, paywall access or independent fact verification."
}
},
"schemaVersion": 1,
"additionalProperties": false
}
},
"additionalProperties": false
}
