{ "openapi": "3.0.1", "info": { "title": "🧪High-Volume Website Content & Media Scraper", "description": "🧪Crawling Done Right! Let me now what you think, what or where or how i can improve my actor, and i am all for constructive criticism. So please message if you have any questions. Enjoy and have a good day.", "version": "1.0", "x-build-id": "sO3oyhN0JW6BhFwrM" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/caring_dizi~blog-content-scraper-fixed/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-caring_dizi-blog-content-scraper-fixed", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/caring_dizi~blog-content-scraper-fixed/runs": { "post": { "operationId": "runs-sync-caring_dizi-blog-content-scraper-fixed", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/caring_dizi~blog-content-scraper-fixed/run-sync": { "post": { "operationId": "run-sync-caring_dizi-blog-content-scraper-fixed", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "startUrls": { "title": "Start URLs", "type": "array", "description": "One or more public page URLs to scrape. This actor works best on content pages, social profile pages, landing pages, and other publicly accessible pages that expose text, links, images, or embedded video.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "searchQueries": { "title": "Search queries", "type": "array", "description": "Optional keyword searches. The Actor discovers matching public webpages with Bing HTML search, resolves tracked result links, and rejects results that conflict with explicit site: or quoted-phrase constraints before scraping. For map listings and local-business fields, use Universal Data Harvester's Google Maps mode.", "default": [], "items": { "type": "string" } }, "searchResultLimit": { "title": "Results per search query", "minimum": 1, "maximum": 50, "type": "integer", "description": "Maximum result pages to discover and scrape for each keyword query.", "default": 10 }, "includeFacebookLinks": { "title": "Include Facebook links", "type": "boolean", "description": "If disabled, outbound links pointing to facebook.com are filtered out of the results.", "default": true }, "sameDomainOnly": { "title": "Stay on same domain", "type": "boolean", "description": "When enabled, discovered links are only enqueued if they stay on the same registrable domain as the current page.", "default": true }, "linkEnqueueLimit": { "title": "Max links to enqueue per page", "minimum": 0, "maximum": 500, "type": "integer", "description": "Caps how many discovered links are scheduled from each processed page.", "default": 10 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Optional Apify Proxy or custom proxy settings. Proxy use is disabled by default so a run does not incur proxy usage unless you opt in.", "default": { "useApifyProxy": false } }, "headless": { "title": "Headless browser", "type": "boolean", "description": "Run the browser in headless mode. Disable only when debugging locally.", "default": true }, "maxRequests": { "title": "Max requests per crawl", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Maximum total pages to process in a run, including discovered links.", "default": 100 }, "minConcurrency": { "title": "Min concurrency", "minimum": 1, "maximum": 50, "type": "integer", "description": "Minimum autoscaled parallel page count.", "default": 1 }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "maximum": 50, "type": "integer", "description": "Maximum number of pages processed in parallel. Increase for speed, decrease if target sites are sensitive or resource usage gets too high.", "default": 3 }, "maxRequestsPerMinute": { "title": "Max requests per minute", "minimum": 0, "maximum": 600, "type": "integer", "description": "Optional global throttle for discovered and start URLs. Set 0 for unlimited.", "default": 0 }, "retryLimit": { "title": "Retry limit", "minimum": 0, "maximum": 10, "type": "integer", "description": "How many times to retry a failed request before it is marked failed.", "default": 2 }, "requestHandlerTimeoutSecs": { "title": "Request timeout (secs)", "minimum": 10, "maximum": 300, "type": "integer", "description": "Maximum total time allowed for processing a single page, including extraction work.", "default": 90 }, "navigationTimeoutSecs": { "title": "Navigation timeout (secs)", "minimum": 10, "maximum": 300, "type": "integer", "description": "Maximum time to wait for page navigation before treating the page as failed.", "default": 90 }, "waitAfterLoadSecs": { "title": "Wait after load (secs)", "minimum": 0, "maximum": 15, "type": "number", "description": "Extra delay after initial page load to allow client-side rendering before extraction starts.", "default": 0.5 }, "saveErrorScreenshots": { "title": "Save error screenshots", "type": "boolean", "description": "When enabled, store a full-page screenshot in the key-value store for failed pages and include its URL in the dataset record.", "default": 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 } } } } } } } } } }