{ "openapi": "3.0.1", "info": { "title": "Zip Download Extraction Scraper", "description": "Download ZIP files from URLs and automatically extract their contents with advanced features like retry logic, password protection, duplicate handling, and real-time progress tracking.", "version": "0.1", "x-build-id": "o7UeJkWprT7drl4zQ" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/aluminum_jam~zip-download-extraction-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-aluminum_jam-zip-download-extraction-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/aluminum_jam~zip-download-extraction-scraper/runs": { "post": { "operationId": "runs-sync-aluminum_jam-zip-download-extraction-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/aluminum_jam~zip-download-extraction-scraper/run-sync": { "post": { "operationId": "run-sync-aluminum_jam-zip-download-extraction-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "urls": { "title": "ZIP File URLs", "type": "array", "description": "List of ZIP file URLs to download and extract. Each URL must be publicly accessible (https:// or http://). If empty, a default test URL will be used for demonstration.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "extract_to_memory": { "title": "Extract to Memory Only", "type": "boolean", "description": "If enabled, extracted files will be deleted after processing. Only metadata will be saved to the dataset. Useful for validating ZIP contents without keeping files.", "default": false }, "keep_zip": { "title": "Keep Downloaded ZIP Files", "type": "boolean", "description": "If enabled, the downloaded ZIP files will not be deleted after extraction. Disable this to save storage space.", "default": false }, "password": { "title": "ZIP Password (Optional)", "type": "string", "description": "Password for encrypted/protected ZIP files. Leave empty for unprotected archives." }, "handle_duplicates": { "title": "Duplicate File Handling", "enum": [ "rename", "skip", "overwrite" ], "type": "string", "description": "How to handle duplicate files during extraction", "default": "rename" }, "timeout": { "title": "Download Timeout (seconds)", "minimum": 30, "maximum": 3600, "type": "integer", "description": "Maximum time to wait for each file download. Increase for large files or slow connections.", "default": 300 }, "max_file_size_mb": { "title": "Max File Size (MB)", "minimum": 1, "maximum": 10240, "type": "integer", "description": "Maximum allowed file size for downloads in megabytes. Downloads exceeding this limit will be skipped.", "default": 1024 }, "concurrent_downloads": { "title": "Concurrent Downloads", "minimum": 1, "maximum": 10, "type": "integer", "description": "Number of ZIP files to download and process simultaneously. Higher values increase speed but use more memory.", "default": 3 }, "enable_proxy": { "title": "Enable Proxy", "type": "boolean", "description": "Use Apify proxy for downloads. Useful for accessing geo-restricted content or bypassing rate limits.", "default": false }, "proxy_configuration": { "title": "Proxy Configuration", "type": "object", "description": "Advanced proxy settings. Only used if 'Enable Proxy' is checked." }, "file_type_filter": { "title": "File Type Filter (Optional)", "type": "string", "description": "Extract only specific file types (comma-separated). Leave empty to extract all files. Example: .pdf,.csv,.json" }, "retry_failed_downloads": { "title": "Retry Failed Downloads", "minimum": 0, "maximum": 10, "type": "integer", "description": "Number of times to retry failed downloads before giving up.", "default": 3 } } }, "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 } } } } } } } } } }