Finance News Scraper
Pricing
$3.90 / 1,000 article scrapeds
Scrape financial news from top sources — CNBC, MarketWatch, Seeking Alpha, Google News. Filter by keywords, tickers, sectors. Detect stock mentions and sentiment.
You can access the Finance News Scraper programmatically from your own applications by using the Apify API. You can also choose the language preference from below. To use the Apify API, you’ll need an Apify account and your API token, found in Integrations settings in Apify Console.
{ "openapi": "3.0.1", "info": { "version": "1.0", "x-build-id": "nBGkN8aehvCxjXgUX" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/junipr~finance-news-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-junipr-finance-news-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/junipr~finance-news-scraper/runs": { "post": { "operationId": "runs-sync-junipr-finance-news-scraper", "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/junipr~finance-news-scraper/run-sync": { "post": { "operationId": "run-sync-junipr-finance-news-scraper", "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": { "tickers": { "title": "Stock Tickers", "type": "array", "description": "Stock ticker symbols to filter by (e.g. [\"AAPL\", \"TSLA\"]). Articles mentioning any of these tickers are included.", "items": { "type": "string" } }, "companies": { "title": "Company Names", "type": "array", "description": "Company names to search for. Used alongside or instead of tickers.", "items": { "type": "string" } }, "keywords": { "title": "Keywords", "type": "array", "description": "General keywords to search for. Combined with ticker/company filters via OR logic.", "items": { "type": "string" }, "default": [ "stock market" ] }, "sectors": { "title": "Sectors", "type": "array", "description": "Filter by market sector: technology, healthcare, finance, energy, consumer, industrials, real_estate, materials, utilities, communications.", "items": { "type": "string" } }, "sources": { "title": "News Sources", "type": "array", "description": "Financial news sources to scrape: google_news, marketwatch, seekingalpha, cnbc, businessinsider.", "items": { "type": "string" }, "default": [ "google_news", "marketwatch", "seekingalpha", "cnbc" ] }, "maxArticlesPerSource": { "title": "Max Articles Per Source", "minimum": 1, "maximum": 200, "type": "integer", "description": "Maximum articles to scrape per source. Min: 1, Max: 200.", "default": 25 }, "maxArticlesTotal": { "title": "Max Articles Total", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Total article cap across all sources. Min: 1, Max: 1000.", "default": 100 }, "dateRange": { "title": "Date Range", "enum": [ "1d", "3d", "7d", "14d", "30d" ], "type": "string", "description": "Time range for articles: 1d, 3d, 7d, 14d, 30d.", "default": "7d" }, "dateFrom": { "title": "Date From", "type": "string", "description": "Override dateRange — only include articles from this date (ISO 8601)." }, "dateTo": { "title": "Date To", "type": "string", "description": "Override dateRange — only include articles up to this date (ISO 8601)." }, "includeFullText": { "title": "Include Full Article Text", "type": "boolean", "description": "Include full article body text. Set to false for headlines-only mode.", "default": true }, "extractTickers": { "title": "Extract Tickers", "type": "boolean", "description": "Auto-detect mentioned stock tickers in article text.", "default": true }, "extractEntities": { "title": "Extract Named Entities", "type": "boolean", "description": "Extract named entities (people, companies, products) from articles.", "default": false }, "deduplicateArticles": { "title": "Deduplicate Articles", "type": "boolean", "description": "Remove duplicate articles that appear across multiple sources.", "default": true }, "minArticleLength": { "title": "Min Article Length (chars)", "minimum": 0, "maximum": 5000, "type": "integer", "description": "Minimum article body length in characters. Filters wire stubs.", "default": 200 }, "proxyConfiguration": { "title": "Proxy Configuration", "type": "object", "description": "Proxy settings. Datacenter proxy works for most sources.", "default": { "useApifyProxy": true } } } }, "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 } } } } } } } } }}OpenAPI is a standard for designing and describing RESTful APIs, allowing developers to define API structure, endpoints, and data formats in a machine-readable way. It simplifies API development, integration, and documentation.
OpenAPI is effective when used with AI agents and GPTs by standardizing how these systems interact with various APIs, for reliable integrations and efficient communication.
By defining machine-readable API specifications, OpenAPI allows AI models like GPTs to understand and use varied data sources, improving accuracy. This accelerates development, reduces errors, and provides context-aware responses, making OpenAPI a core component for AI applications.
You can download the OpenAPI definitions for Finance News Scraper from the options below:
If you’d like to learn more about how OpenAPI powers GPTs, read our blog post.
You can also check out our other API clients: