{ "openapi": "3.0.1", "info": { "title": "CNN Search Scraper", "description": "Runs keyword searches against CNN.com's own search index and returns matching articles, videos and photo galleries -- headline, URL, thumbnail, modified date and teaser, with optional full article body, author, section and publish date fetched from each result's page.", "version": "0.1", "x-build-id": "Ub0R90d6k0vaZdgrq" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/scrapyx~cnn-search-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-scrapyx-cnn-search-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/scrapyx~cnn-search-scraper/runs": { "post": { "operationId": "runs-sync-scrapyx-cnn-search-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/scrapyx~cnn-search-scraper/run-sync": { "post": { "operationId": "run-sync-scrapyx-cnn-search-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "required": [ "queries" ], "properties": { "queries": { "title": "Search terms", "type": "array", "description": "One search term per entry. Each term is run against CNN's own search index and gets its own SEARCH_SUMMARY row. Single very common words can score as stopwords and return nothing -- 'a' returns 0 results while 'trump' returns 28.", "default": [], "items": { "type": "string" } }, "contentTypes": { "title": "Content types", "type": "array", "description": "Which kinds of content to search for. Each type is a separate query with its own summary row. Only these three are real: CNN's API silently ignores any other value and returns UNFILTERED results instead of an error, so this actor rejects anything else rather than passing it through.", "items": { "type": "string", "enum": [ "article", "video", "gallery" ], "enumTitles": [ "Articles", "Videos", "Photo galleries" ] }, "default": [ "article" ] }, "sort": { "title": "Sort order", "enum": [ "newest", "relevance" ], "type": "string", "description": "Newest first, or by CNN's own relevance score. Only these two values are real -- CNN's API silently treats 'oldest', 'relevancy' and 'score' as 'newest'.", "default": "newest" }, "maxItemsPerQuery": { "title": "Max results per query", "minimum": 0, "maximum": 1000, "type": "integer", "description": "Cap on results per search term per content type. Set to 0 for as many as CNN will serve. CNN's API refuses any offset at or beyond 1000 with an HTTP 403, so 1000 is a hard upstream ceiling regardless of what the reported total claims -- runs that hit it say so in the summary row.", "default": 50 }, "includeFullBody": { "title": "Include full article body", "type": "boolean", "description": "Fetch each result's own page and extract the complete article text plus author, section and publish date. Off by default because it costs one extra request per result. The search API's own text field is only a one-sentence teaser, returned as `searchTeaser` -- it is never the full body.", "default": false }, "maxConcurrency": { "title": "Max concurrent requests", "minimum": 1, "maximum": 16, "type": "integer", "description": "Upper bound on requests in flight at once across all queries in this run.", "default": 5 }, "minRequestInterval": { "title": "Min seconds between request starts", "minimum": 0, "type": "number", "description": "Shared pacing floor across every request this run makes. Once this cap binds, raising concurrency buys nothing.", "default": 0.25 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "No bot mitigation was observed on the search API during recon -- it answered 200 cold and unproxied with no token or session. Residential is still this portfolio's standard cloud default.", "default": { "useApifyProxy": true, "apifyProxyGroups": [ "RESIDENTIAL" ] } } } }, "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 } } } } } } } } } }