{ "openapi": "3.0.1", "info": { "title": "Fox News Liveblogs Scraper", "description": "Collects Fox News live-news blogs and their full timelines: every update with its own headline, body text, author and timestamp, plus the liveblog's coverage window. Covers 1,353 live events back to June 2021, with date and keyword filtering.", "version": "0.1", "x-build-id": "NK5sVR8f3yRth7wSe" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/scrapyx~foxnews-liveblogs-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-scrapyx-foxnews-liveblogs-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/scrapyx~foxnews-liveblogs-scraper/runs": { "post": { "operationId": "runs-sync-scrapyx-foxnews-liveblogs-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/scrapyx~foxnews-liveblogs-scraper/run-sync": { "post": { "operationId": "run-sync-scrapyx-foxnews-liveblogs-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "maxItems": { "title": "Max liveblogs", "minimum": 1, "maximum": 1353, "type": "integer", "description": "How many liveblogs to return, newest first. Each one is a separate page fetch, so this directly controls run time. Fox's liveblog archive holds 1,353 live events going back to June 2021, and each carries a timeline of roughly 12 to 53 updates.", "default": 10 }, "includeUpdates": { "title": "Include timeline updates", "type": "boolean", "description": "Emit one row per update on each liveblog's timeline, with its own headline, body text, author and timestamp, alongside the liveblog row itself. Turn this off to get only the liveblog headers. It costs nothing extra either way, because the whole timeline arrives in the same page fetch.", "default": true }, "maxUpdatesPerLiveblog": { "title": "Max updates per liveblog", "minimum": 0, "type": "integer", "description": "Cap on timeline updates returned per liveblog, newest first. Leave at 0 to return every update the page carries. The summary row reports how many were truncated.", "default": 0 }, "dateFrom": { "title": "Last updated from", "type": "string", "description": "Optional lower bound, inclusive, as YYYY-MM-DD. This filters on the liveblog's last-modified date, which is the only date the sitemap carries, so it is applied before any page is fetched and costs nothing. Liveblogs with no usable date are excluded whenever a bound is set." }, "dateTo": { "title": "Last updated to", "type": "string", "description": "Optional upper bound, inclusive, as YYYY-MM-DD. Same pre-fetch filtering as 'Last updated from'." }, "keywords": { "title": "Keyword filter", "type": "array", "description": "Optional. Keep only liveblogs whose headline, description or ANY update on their timeline contains one of these words, matched case-insensitively. Because a match can be buried deep in a timeline, this is checked after each page is fetched, not before, so a keyword run fetches more pages than it returns liveblogs. This is filtering done by this Actor, not a search sent to Fox News, which offers no search parameter.", "default": [], "items": { "type": "string" } }, "maxConcurrency": { "title": "Max concurrent requests", "minimum": 1, "maximum": 16, "type": "integer", "description": "Upper bound on liveblog page requests in flight at once.", "default": 5 }, "minRequestInterval": { "title": "Min seconds between request starts", "minimum": 0, "type": "number", "description": "Shared pacing floor across every request this run makes. Fox News sets no Crawl-delay in robots.txt, so this default is this portfolio's own politeness baseline rather than a site requirement.", "default": 0.25 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Apify Proxy on the shared datacenter pool. That is the default because it is included in your plan at no extra cost and this target needs nothing more: no bot-mitigation gate was seen on any Fox News surface during testing. Switch the group here to Residential only if you start seeing blocks, since Apify bills residential traffic per gigabyte.", "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 }, "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 } } } } } } } } } }