{ "openapi": "3.0.1", "info": { "title": "Google News Scraper - Fast URLs, Images & Alerts", "description": "Fast Google News scraper with structured source rows for keywords, publishers, topics, local news, URLs, alerts, and Full Coverage stories. Returns clean rows with dates, publishers, direct URLs, images, 100+ backfill, new-article alerts, descriptions, entities, and best-effort full text.", "version": "0.3", "x-build-id": "Q1JUXL0uE9Rf1d19v" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/vortex_data~google-news/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-vortex_data-google-news", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/vortex_data~google-news/runs": { "post": { "operationId": "runs-sync-vortex_data-google-news", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/vortex_data~google-news/run-sync": { "post": { "operationId": "run-sync-vortex_data-google-news", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } } }, "components": { "schemas": { "inputSchema": { "type": "object", "properties": { "searchMode": { "title": "Workflow alias", "type": "string", "description": "API-only compatibility field. The visible form uses one source input instead of workflow modes.", "default": "keyword" }, "sourceItems": { "title": "Source rows", "type": "array", "description": "Add one row per source. For normal runs keep the first row as Search and change only the value.", "items": { "type": "object", "additionalProperties": false, "required": [ "sourceType", "value" ], "properties": { "sourceType": { "title": "Source type", "type": "string", "description": "Choose what this row collects.", "editor": "select", "enum": [ "search", "publisher", "topic", "location", "google_news_url", "full_coverage" ], "enumTitles": [ "๐Ÿ”Ž Search query", "๐Ÿข Publisher/domain", "๐Ÿงญ Topic feed", "๐Ÿ“ Local news", "๐Ÿ”— Google News URL", "๐Ÿงต Full Coverage story" ], "default": "search" }, "value": { "title": "Value", "type": "string", "description": "Examples: OpenAI, site:reuters.com AI, Reuters, bbc.com, Technology, New York, https://news.google.com/search?q=AI, or a Google News story URL/ID.", "editor": "textfield" } } } }, "searchInputText": { "title": "Source text alias", "type": "string", "description": "API-only text alias. One source per line. Plain text is a Google News search; prefixes such as publisher:, topic:, location:, url:, and story: route non-search sources." }, "topicInputs": { "title": "Topic inputs alias", "uniqueItems": true, "type": "array", "description": "API-only Google News topic feeds. Examples: Technology, Business, Sports, Health, World.", "items": { "type": "string" }, "default": [] }, "collectSearch": { "title": "Collect search query results", "type": "boolean", "description": "Use Search queries as Google News searches.", "default": true }, "collectPublishers": { "title": "Collect publisher feeds", "type": "boolean", "description": "Use Publisher names or domains.", "default": true }, "collectTopics": { "title": "Collect topic feeds", "type": "boolean", "description": "Use Topic feeds.", "default": true }, "collectLocalNews": { "title": "Collect local news", "type": "boolean", "description": "Use Local news places.", "default": true }, "collectGoogleNewsUrls": { "title": "Collect pasted Google News URLs", "type": "boolean", "description": "Use Google News URLs.", "default": true }, "collectFullCoverage": { "title": "Collect Full Coverage stories", "type": "boolean", "description": "Use Full Coverage story URLs / IDs.", "default": true }, "collectTopHeadlines": { "title": "Also include top headlines", "type": "boolean", "description": "Also collect the Google News front page for the selected country/language. Off by default because it is not tied to the input terms.", "default": false }, "monitorNewArticles": { "title": "Enable new-article alerts", "type": "boolean", "description": "Use for Apify Tasks or Schedules. First run stores current article IDs; later runs with the same Alert name return only articles not seen before.", "default": false }, "topics": { "title": "Topic feeds alias", "uniqueItems": true, "type": "array", "description": "API-only topic feed aliases. The visible form accepts topic names in Search input when Job type is Topic feed or Mixed sources.", "items": { "type": "string" }, "default": [] }, "topHeadlines": { "title": "Top headlines alias", "type": "boolean", "description": "API alias for Workflow = Top headlines.", "default": false }, "monitorName": { "title": "Alert name", "type": "string", "description": "Stable state key for scheduled alerts. Keep the same name for the same query/source set. Change it only when you want a separate alert history." }, "resetMonitor": { "title": "Send all matches again", "type": "boolean", "description": "Clears the saved article history for this Alert name before this run. Use when testing or when you intentionally want current matches again.", "default": false }, "onlyNewArticles": { "title": "Only new articles alias", "type": "boolean", "description": "API-only alias. Monitoring alerts automatically return only articles not seen in previous runs.", "default": false }, "region_language": { "title": "Country / language edition", "enum": [ "US:en", "GB:en", "CA:en", "AU:en", "IN:en", "IE:en", "NZ:en", "SG:en", "ZA:en", "DE:de", "AT:de", "CH:de", "FR:fr", "BE:fr", "CA:fr", "MA:fr", "ES:es", "MX:es-419", "AR:es-419", "BR:pt-419", "PT:pt-150", "IT:it", "NL:nl", "BE:nl", "PL:pl", "CZ:cs", "SK:sk", "SE:sv", "NO:no", "TR:tr", "RU:ru", "UA:uk", "UA:ru", "AE:ar", "SA:ar", "EG:ar", "IL:he", "IN:hi", "IN:bn", "BD:bn", "IN:ta", "IN:te", "TH:th", "VN:vi", "CN:zh-Hans", "TW:zh-Hant", "HK:zh-Hant", "JP:ja", "KR:ko" ], "type": "string", "description": "Choose the Google News edition. This controls country, language, and local ranking.", "default": "US:en" }, "timeframe": { "title": "Time period", "enum": [ "1h", "1d", "7d", "1m", "1y", "all" ], "type": "string", "description": "How far back to search for keyword and monitoring queries. Topic, local, top-headline, and pasted URL feeds are controlled mostly by Google News.", "default": "1d" }, "dateFrom": { "title": "From date", "pattern": "^(\\d{4}-\\d{2}-\\d{2}|\\d{1,2}/\\d{1,2}/\\d{4})$", "type": "string", "description": "Optional exact start date for keyword and monitoring searches. Format: YYYY-MM-DD." }, "dateTo": { "title": "To date", "pattern": "^(\\d{4}-\\d{2}-\\d{2}|\\d{1,2}/\\d{1,2}/\\d{4})$", "type": "string", "description": "Optional exact end date. The date is inclusive. Format: YYYY-MM-DD." }, "sortBy": { "title": "Sort results", "type": "string", "description": "Keep Google's ranking or sort each feed by publication date before writing results.", "default": "relevance" }, "maxArticles": { "title": "Articles to return", "minimum": 1, "maximum": 50000, "type": "integer", "description": "How many articles to return for each input line. Use 10-25 for a preview. Search and publisher/domain runs above 100 automatically use date-window backfill.", "default": 20 }, "maxItems": { "title": "Total run limit", "minimum": 1, "maximum": 50000, "type": "integer", "description": "Optional cap across all keywords, topics, locations, URLs, and date slices. Leave empty to use Articles per query/source." }, "expandedSearch": { "title": "Expand above 100 articles", "type": "boolean", "description": "Recommended. Google News RSS usually exposes about 100 articles per feed; this sweeps daily windows to collect deeper archives when you ask for more.", "default": true }, "deduplicate": { "title": "Deduplicate results", "type": "boolean", "description": "Recommended. Drop duplicate Google News articles across multiple keywords, topics, locations, URLs, and date slices.", "default": true }, "runMode": { "title": "Speed preset", "type": "string", "description": "API-only compatibility preset. Balanced is the rich default. Fast skips deeper publisher-page enrichment for previews. Complete keeps every enrichment on.", "default": "balanced" }, "contentMode": { "title": "Publisher page data", "type": "string", "description": "API-only compatibility alias. The visible form uses Extra Data toggles. Use metadata/feed/off to skip publisher pages, descriptions for metadata only, or full for article bodies.", "default": "full" }, "decodeUrls": { "title": "Resolve publisher URLs", "type": "boolean", "description": "Return direct publisher article URLs instead of only Google News redirect/read URLs. Fast preset turns this off; Balanced and Complete keep it on.", "default": true }, "extractImages": { "title": "Add thumbnails", "type": "boolean", "description": "Add Google News or publisher thumbnail URLs when available.", "default": true }, "extractStoryUrls": { "title": "Add Full Coverage URLs", "type": "boolean", "description": "Add Google News Full Coverage / story URLs when they are exposed near the article card.", "default": true }, "includeSocialPosts": { "title": "Include X/Twitter posts in Full Coverage", "type": "boolean", "description": "For Full Coverage story pages. When Google News shows embedded X/Twitter post cards, include them as social_post rows. This does not fetch X/Twitter separately.", "default": true }, "fetchDescriptions": { "title": "Fetch descriptions and authors", "type": "boolean", "description": "On by default. Fetch publisher pages for meta descriptions, authors, canonical URLs, site names, and better images without storing article bodies. Turn off for the cheapest feed-only runs.", "default": true }, "fetchFullText": { "title": "Fetch full article text", "type": "boolean", "description": "On by default. Best-effort full-text extraction from publisher pages. Not guaranteed on paywalls, consent pages, blocked pages, or JavaScript-heavy sites.", "default": true }, "maxFullTextChars": { "title": "Full text character limit", "minimum": 500, "maximum": 50000, "type": "integer", "description": "Used only when Full article text is on. Limits how many characters are stored in fullText.", "default": 5000 }, "extractEntities": { "title": "Detect companies and tickers", "type": "boolean", "description": "On by default. Add stock tickers, crypto tickers, and high-signal company entities from titles, snippets, and article text when available.", "default": true }, "exactPhrase": { "title": "Match exact phrase", "type": "boolean", "description": "API-only helper. Users can also type quotes directly in Search input, for example \"electric cars\".", "default": false }, "inTitleOnly": { "title": "Title-only search", "type": "boolean", "description": "API-only helper. Users can also type intitle:term directly in Search input.", "default": false }, "sourceDomainsText": { "title": "Search only these publishers", "type": "string", "description": "Optional. One publisher/domain per line. Adds site: filters to Google News queries before searching." }, "excludeSourcesText": { "title": "Exclude publishers from search", "type": "string", "description": "Optional. One publisher/domain per line. Adds -site: filters to Google News queries before searching." }, "excludeTermsText": { "title": "Exclude words", "type": "string", "description": "Optional. One word or phrase per line. Adds -word or -\"phrase\" filters to keyword and alert queries." }, "lr": { "title": "Limit result language", "type": "string", "description": "Advanced Google parameter. Optional language restriction such as lang_en, lang_fr, lang_de. Most users should leave it empty." }, "cr": { "title": "Limit result country", "type": "string", "description": "Advanced Google parameter. Optional country restriction such as us, gb, de, jp. The actor converts it to countryXX." }, "nfpr": { "title": "Disable Google autocorrect", "type": "string", "description": "Advanced Google parameter. Set to 1 to exclude results from auto-corrected queries. Leave empty for Google's default behavior.", "default": "" }, "filter": { "title": "Similar results filter", "type": "string", "description": "Advanced Google parameter. Google default filters similar/omitted results; show similar results can increase recall but may add duplicates.", "default": "" }, "concurrency": { "title": "Parallel requests", "minimum": 1, "maximum": 128, "type": "integer", "description": "Advanced performance control for URL resolution and enrichment. The default is tuned for normal runs; change only when you intentionally want gentler or more parallel requests.", "default": 64 }, "query": { "title": "Single query", "type": "string", "description": "API-friendly alias for a single keyword. The actor also accepts keyword, searchQuery, q, and queries." }, "keyword": { "title": "Keyword alias", "type": "string", "description": "API-only alias for one keyword." }, "searchQuery": { "title": "Search query alias", "type": "string", "description": "API-only alias for one keyword." }, "q": { "title": "q alias", "type": "string", "description": "API-only alias for one keyword." }, "topic": { "title": "Topic alias", "type": "string", "description": "API-only alias for one topic feed." }, "siteFilter": { "title": "Site filter alias", "type": "string", "description": "API-only. Adds one site:domain filter to the Google query." }, "extractDescriptions": { "title": "Descriptions alias", "type": "boolean", "description": "API-only alias. When true, fetches publisher-page meta descriptions and article metadata without storing full text.", "default": false }, "includeDescriptions": { "title": "Include descriptions alias", "type": "boolean", "description": "API-only alias for Publisher descriptions.", "default": false }, "extractArticleDescriptions": { "title": "Article descriptions alias", "type": "boolean", "description": "API-only alias for Publisher descriptions.", "default": false }, "extractFullText": { "title": "Full text alias", "type": "boolean", "description": "API-only alias. When true, same as Article text = Full publisher text.", "default": false }, "extractArticleContent": { "title": "Article content alias", "type": "boolean", "description": "API-only alias. When true, same as Article text = Full publisher text.", "default": false }, "includeFullText": { "title": "Include full text alias", "type": "boolean", "description": "API-only alias. When true, same as Article text = Full publisher text.", "default": false }, "outputMode": { "title": "Output mode alias", "type": "string", "description": "API-only compatibility field. The interface uses clean standard output by default.", "default": "standard" }, "output_mode": { "title": "Output mode alias", "type": "string", "description": "API-only alias for outputMode." }, "monitoring": { "title": "Monitoring alias", "type": "boolean", "description": "API-only alias for Only new articles.", "default": false }, "onlyNew": { "title": "Only new alias", "type": "boolean", "description": "API-only alias for Only new articles.", "default": false }, "returnOnlyNew": { "title": "Return only new alias", "type": "boolean", "description": "API-only alias for Only new articles.", "default": false }, "newOnly": { "title": "New only alias", "type": "boolean", "description": "API-only alias for Only new articles.", "default": false }, "monitoringName": { "title": "Monitoring name alias", "type": "string", "description": "API-only alias for Alert name." }, "monitorKey": { "title": "Monitor key alias", "type": "string", "description": "API-only alias for Alert name." }, "alertName": { "title": "Alert name alias", "type": "string", "description": "API-only alias for Alert name." }, "resetMonitoring": { "title": "Reset monitoring alias", "type": "boolean", "description": "API-only alias for Send all matches again.", "default": false }, "clearMonitoringHistory": { "title": "Clear monitoring history alias", "type": "boolean", "description": "API-only alias for Send all matches again.", "default": false }, "resolvePublisherUrls": { "title": "Resolve publisher URLs alias", "type": "boolean", "description": "API-only alias for Resolve publisher URLs." }, "includeImages": { "title": "Images alias", "type": "boolean", "description": "API-only alias for Add thumbnails." }, "extractSocialPosts": { "title": "Social posts alias", "type": "boolean", "description": "API-only alias for Include X/Twitter posts in Full Coverage.", "default": true }, "maxResults": { "title": "Max results alias", "minimum": 1, "maximum": 50000, "type": "integer", "description": "API-only alias for Articles per search / source." }, "numberOfResults": { "title": "Number of results alias", "minimum": 1, "maximum": 50000, "type": "integer", "description": "API-only alias for Articles per search / source." }, "limit": { "title": "Limit alias", "minimum": 1, "maximum": 50000, "type": "integer", "description": "API-only alias for Articles per search / source." }, "country": { "title": "Country override", "type": "string", "description": "API-only two-letter country code such as US, GB, DE, JP. Overrides Country / language edition." }, "language": { "title": "Language override", "type": "string", "description": "API-only language code such as en, fr, de, ja, es-419. Overrides Country / language edition." }, "gl": { "title": "Google gl override", "type": "string", "description": "API-only Google country parameter. Usually use Country / language edition instead." }, "hl": { "title": "Google hl override", "type": "string", "description": "API-only Google interface language parameter. Usually use Country / language edition instead." }, "timeWindow": { "title": "Time window alias", "type": "string", "description": "API-only alias for Time period." }, "timeFilter": { "title": "Time filter alias", "type": "string", "description": "API-only alias for Time period." }, "time_period": { "title": "Time period alias", "type": "string", "description": "API-only alias for Time period." }, "fromDate": { "title": "From date alias", "type": "string", "description": "API-only alias for From date." }, "toDate": { "title": "To date alias", "type": "string", "description": "API-only alias for To date." }, "retryBudgetRss": { "title": "RSS retry attempts", "minimum": 1, "maximum": 10, "type": "integer", "description": "API-only retry attempts per required Google News RSS request.", "default": 4 }, "retryBudgetHtml": { "title": "HTML enrichment retry attempts", "minimum": 1, "maximum": 5, "type": "integer", "description": "API-only retry attempts for optional Google News thumbnail and Full Coverage enrichment requests.", "default": 1 }, "retryBudgetDecode": { "title": "URL decode retry attempts", "minimum": 1, "maximum": 10, "type": "integer", "description": "API-only retry attempts when resolving Google News URLs to direct publisher URLs.", "default": 3 }, "retryBudgetArticle": { "title": "Article extraction retry attempts", "minimum": 1, "maximum": 5, "type": "integer", "description": "API-only retry attempts for best-effort publisher-page full-text extraction.", "default": 1 } } }, "runsResponseSchema": { "type": "object", "properties": { "data": { "type": "object", "properties": { "id": { "type": "string" }, "actId": { "type": "string" }, "userId": { "type": "string" }, "startedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "finishedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "status": { "type": "string", "example": "READY" }, "meta": { "type": "object", "properties": { "origin": { "type": "string", "example": "API" }, "userAgent": { "type": "string" } } }, "stats": { "type": "object", "properties": { "inputBodyLen": { "type": "integer", "example": 2000 }, "rebootCount": { "type": "integer", "example": 0 }, "restartCount": { "type": "integer", "example": 0 }, "resurrectCount": { "type": "integer", "example": 0 }, "computeUnits": { "type": "integer", "example": 0 } } }, "options": { "type": "object", "properties": { "build": { "type": "string", "example": "latest" }, "timeoutSecs": { "type": "integer", "example": 300 }, "memoryMbytes": { "type": "integer", "example": 1024 }, "diskMbytes": { "type": "integer", "example": 2048 } } }, "buildId": { "type": "string" }, "defaultKeyValueStoreId": { "type": "string" }, "defaultDatasetId": { "type": "string" }, "defaultRequestQueueId": { "type": "string" }, "buildNumber": { "type": "string", "example": "1.0.0" }, "containerUrl": { "type": "string" }, "usage": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "integer", "example": 1 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } }, "usageTotalUsd": { "type": "number", "example": 0.00005 }, "usageUsd": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "number", "example": 0.00005 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } } } } } } } } }