{ "openapi": "3.0.1", "info": { "title": "All-In-One Content Scraper", "description": "The Ultimate All-in-One Web Scraping Solution - Extract ANY media from ANY website with professional-grade precision and speed.", "version": "1.0", "x-build-id": "6TZBbmVWfE5TyGece" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/caring_dizi~all-in-one-content-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-caring_dizi-all-in-one-content-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/caring_dizi~all-in-one-content-scraper/runs": { "post": { "operationId": "runs-sync-caring_dizi-all-in-one-content-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/caring_dizi~all-in-one-content-scraper/run-sync": { "post": { "operationId": "run-sync-caring_dizi-all-in-one-content-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "scrapingMode" ], "properties": { "scrapingMode": { "title": "Scraping Mode", "enum": [ "web", "google_maps", "apollo", "instagram" ], "type": "string", "description": "Choose the surface you want to scrape.", "default": "web" }, "maxRequestsPerCrawl": { "title": "Max Requests", "minimum": 1, "type": "integer", "description": "Maximum requests to execute in this run.", "default": 15 }, "maxConcurrency": { "title": "Concurrency", "minimum": 1, "type": "integer", "description": "Parallelism for modes that support it.", "default": 4 }, "sameDomainOnly": { "title": "Stay on Same Domain", "type": "boolean", "description": "When crawling in Web mode, only enqueue discovered links that stay on the same registrable domain.", "default": true }, "linkEnqueueLimit": { "title": "Max Links to Enqueue Per Page", "minimum": 0, "type": "integer", "description": "Caps how many discovered links are added from each processed page in Web mode.", "default": 10 }, "requestHandlerTimeoutSecs": { "title": "Request Timeout (sec)", "minimum": 30, "type": "integer", "description": "Timeout per request handler.", "default": 120 }, "navigationTimeoutSecs": { "title": "Navigation Timeout (sec)", "minimum": 20, "type": "integer", "description": "Navigation timeout before a page is treated as failed.", "default": 60 }, "maxRequestRetries": { "title": "Max Retries", "minimum": 0, "type": "integer", "description": "Retries for failed pages.", "default": 1 }, "headless": { "title": "Headless Browser", "type": "boolean", "description": "Run the browser headlessly.", "default": true }, "viewportWidth": { "title": "Viewport Width", "type": "integer", "description": "Browser viewport width in pixels for JavaScript-heavy pages.", "default": 1440 }, "viewportHeight": { "title": "Viewport Height", "type": "integer", "description": "Browser viewport height in pixels for JavaScript-heavy pages.", "default": 1200 }, "sessionCookiesJson": { "title": "Session Cookies JSON", "type": "string", "description": "Optional JSON array of cookies for logged-in surfaces such as Apollo or Instagram." }, "startUrls": { "title": "Start URLs (Web)", "type": "array", "description": "One or more URLs to crawl in Web mode.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "includeImages": { "title": "Include Images", "type": "boolean", "description": "Capture image URLs where supported.", "default": true }, "includeVideos": { "title": "Include Videos", "type": "boolean", "description": "Capture video URLs where supported.", "default": true }, "maxImages": { "title": "Max Images Per Record", "type": "integer", "description": "Maximum number of image URLs to keep per output record.", "default": 100 }, "maxVideos": { "title": "Max Videos Per Record", "type": "integer", "description": "Maximum number of video references to keep per output record.", "default": 50 }, "maxLinksPerPage": { "title": "Max Links Per Page", "type": "integer", "description": "Maximum number of outbound links preserved per page record.", "default": 150 }, "maxArticleBlocks": { "title": "Max Content Blocks", "type": "integer", "description": "Maximum number of article-like text blocks stored for each page.", "default": 6 }, "searchTerms": { "title": "Search Terms (Google Maps)", "type": "array", "description": "Keyword and location combinations to search in Google Maps mode.", "items": { "type": "string" } }, "googleMapsResultLimit": { "title": "Places Per Search", "minimum": 1, "type": "integer", "description": "Maximum places to extract for each Google Maps search term.", "default": 10 }, "followGoogleMapsPlaceDetails": { "title": "Follow Google Maps Place Details", "type": "boolean", "description": "Open each discovered place page to enrich it with website, phone, address, reviews, and hours when available.", "default": true }, "apolloStartUrls": { "title": "Apollo URLs", "type": "array", "description": "Direct Apollo URLs to scrape, including company pages, people pages, or authenticated search pages.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "apolloQueries": { "title": "Apollo Discovery Queries", "type": "array", "description": "Search terms used to discover public Apollo pages.", "items": { "type": "string" } }, "apolloCompanyDomains": { "title": "Apollo Company Domains", "type": "array", "description": "Company domains to discover on Apollo.", "items": { "type": "string" } }, "apolloDiscoveryLimit": { "title": "Apollo Links Per Query", "minimum": 1, "type": "integer", "description": "Maximum Apollo links to discover per query.", "default": 5 }, "apolloResultLimit": { "title": "Apollo Records Per Page", "minimum": 1, "type": "integer", "description": "Maximum companies or people to emit from a single Apollo page.", "default": 10 }, "followDiscoveredApolloUrls": { "title": "Follow Discovered Apollo URLs", "type": "boolean", "description": "After discovery, follow the Apollo links and scrape those pages too.", "default": true }, "instagramInputType": { "title": "Instagram Target Type", "enum": [ "profiles", "posts", "hashtags", "places", "search" ], "type": "string", "description": "Type of Instagram target to scrape.", "default": "profiles" }, "instagramHandles": { "title": "Instagram Handles / IDs", "type": "array", "description": "Profiles, hashtags, location IDs, or post codes depending on Instagram target type.", "items": { "type": "string" } }, "instagramUrls": { "title": "Instagram URLs", "type": "array", "description": "Explicit Instagram URLs to crawl.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "instagramQuery": { "title": "Instagram Search Query", "type": "string", "description": "Keyword query for Instagram search mode." }, "instagramResultLimit": { "title": "Instagram Posts Per Record", "minimum": 1, "type": "integer", "description": "Maximum recent posts to capture on Instagram pages.", "default": 12 } } }, "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 } } } } } } } } } }