{ "openapi": "3.0.1", "info": { "title": "MarketWatch News Scraper — Headlines, Authors & Dates", "description": "Scrape MarketWatch news from its public feeds into structured records: headlines, descriptions, authors, publish dates, images and URLs. Quote and search pages are currently challenged by the site.", "version": "1.0", "x-build-id": "sZrbCbShibzamnZkp" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/muhammadafzal~marketwatch-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-muhammadafzal-marketwatch-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/muhammadafzal~marketwatch-scraper/runs": { "post": { "operationId": "runs-sync-muhammadafzal-marketwatch-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/muhammadafzal~marketwatch-scraper/run-sync": { "post": { "operationId": "run-sync-muhammadafzal-marketwatch-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "newsFeeds": { "title": "MarketWatch news feeds", "maxItems": 4, "type": "array", "description": "MarketWatch's public RSS news feeds to read: topstories, realtimeheadlines, bulletins or marketpulse. Each article becomes one record with headline, description, author, publish time, image and story URL. This is the reliable mode today; see the README status note.", "items": { "type": "string", "enum": [ "topstories", "realtimeheadlines", "bulletins", "marketpulse" ], "enumTitles": [ "Top stories", "Real-time headlines", "Bulletins", "Market pulse" ] }, "default": [] }, "symbols": { "title": "Stock symbols", "maxItems": 50, "type": "array", "description": "Use for quote pages; enter ticker symbols such as AAPL or MSFT. The scraper opens https://www.marketwatch.com/investing/stock/{symbol}. MarketWatch quote pages currently answer automated requests with an access challenge, so these usually end as blocked (no charge). Default: none.", "items": { "type": "string", "pattern": "^[A-Za-z0-9.-]{1,12}$" }, "default": [] }, "startUrls": { "title": "MarketWatch URLs", "maxItems": 100, "type": "array", "description": "Use for specific public MarketWatch quote, news, latest-news, or article pages; for example https://www.marketwatch.com/story/example. URLs outside marketwatch.com are ignored. These pages are currently challenge-protected, so they usually end as blocked (no charge).", "items": { "type": "object", "properties": { "url": { "title": "URL", "description": "One public MarketWatch URL.", "type": "string" } }, "required": [ "url" ] }, "default": [] }, "mode": { "title": "Extraction mode", "enum": [ "auto", "quote", "news" ], "type": "string", "description": "Choose quote for market snapshots, news for article/list pages, or auto to infer from each URL. Default: auto.", "default": "auto" }, "searchQueries": { "title": "MarketWatch search queries", "maxItems": 20, "type": "array", "description": "Optional MarketWatch site-search terms; each term is opened as a public MarketWatch search page, for example inflation or Apple earnings. Search pages are currently challenge-protected. Default: none.", "items": { "type": "string", "minLength": 1, "maxLength": 120 } }, "maxResults": { "title": "Maximum results", "minimum": 1, "maximum": 500, "type": "integer", "description": "Stop after this many unique records. Range 1–500; default: 50. The Console example uses 5.", "default": 50 }, "maxPages": { "title": "Maximum pages", "minimum": 1, "maximum": 100, "type": "integer", "description": "Maximum public pages to visit. Range 1–100; default: 20.", "default": 20 } } }, "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 }, "PROXY_UNBLOCKER_UNITS": { "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 }, "PROXY_UNBLOCKER_UNITS": { "type": "integer", "example": 0 } } } } } } } } } }