{ "openapi": "3.0.1", "info": { "title": "New York Times Scraper: Articles, Feeds and Historical Archive", "description": "Extract full New York Times articles by section feed, historical date archive back to 1970, or specific URL. Get headline, byline, authors, NYT's own typed entity tags (people, organizations, locations), paywall status, images, and full text in one dataset. Skip juggling two separate scrapers.", "version": "0.2", "x-build-id": "jaAyyt705wHjVfbtM" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/getascraper~nytimes-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-getascraper-nytimes-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/getascraper~nytimes-scraper/runs": { "post": { "operationId": "runs-sync-getascraper-nytimes-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/getascraper~nytimes-scraper/run-sync": { "post": { "operationId": "run-sync-getascraper-nytimes-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "mode": { "title": "Mode", "enum": [ "section", "archive", "urls" ], "type": "string", "description": "\"section\": pull the newest articles from one or more NYT section feeds. \"archive\": walk NYT's own date archive over a date range. \"urls\": scrape a specific list of article URLs.", "default": "section" }, "sections": { "title": "Sections", "type": "array", "description": "NYT section feed names, used when mode is \"section\". Confirmed live values include: HomePage, World, US, Politics, Business, Technology, Science, Health, Sports, Arts, Movies, Music, Travel, and 45+ more (see nytimes.com/rss for the full current list). Case-sensitive, exact feed name.", "default": [ "HomePage" ], "items": { "type": "string" } }, "urls": { "title": "Article URLs", "type": "array", "description": "Specific nytimes.com article URLs to scrape, used when mode is \"urls\".", "default": [], "items": { "type": "string" } }, "dateFrom": { "title": "Date from", "type": "string", "description": "Start date (YYYY-MM-DD), used when mode is \"archive\". NYT's own archive covers back to 1970.", "default": "" }, "dateTo": { "title": "Date to", "type": "string", "description": "End date (YYYY-MM-DD), used when mode is \"archive\".", "default": "" }, "fetchFullText": { "title": "Fetch full article text", "type": "boolean", "description": "Fetch each article's full body text, authors, tags, images and word count, instead of just headline and URL. Fetching full text requires Apify's UNBLOCKER proxy, which has a real per-request cost - discovery alone (RSS feeds, the date archive index) is free.", "default": true }, "maxItems": { "title": "Max articles", "minimum": 1, "maximum": 2000, "type": "integer", "description": "Stop after collecting this many articles. Keep this low for a quick, cheap run; raise it once you know how many you need.", "default": 20 }, "onlyNew": { "title": "Only new articles since last run", "type": "boolean", "description": "Skip URLs already emitted by a previous run with the same Watchlist name. Useful on a schedule so you never pay for or re-download the same article twice.", "default": false }, "stateName": { "title": "Watchlist name", "type": "string", "description": "Distinguishes separate \"only new\" tracking scopes (e.g. two different scheduled section feeds). Only used when \"Only new articles since last run\" is on.", "default": "default" }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Proxy settings. Only used when fetching full article text - discovery alone needs no proxy. Defaults to Apify's UNBLOCKER proxy group, confirmed live as the only mechanism that clears NYT's anti-bot protection on article pages.", "default": { "useApifyProxy": true, "apifyProxyGroups": [ "UNBLOCKER" ] } } } }, "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 } } } } } } } } } }