{ "openapi": "3.0.1", "info": { "title": "Batch Image Downloader — URLs & Pages to KV", "description": "Download image URL lists or extract img/og:image from pages into KV store with metadata (contentType, bytes, sha256, dims). Default under 1 GB; failed/empty free. For RAG/archives — not spam scraping.", "version": "0.1", "x-build-id": "r0dUQBT1vaK1IVHxt" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/ingenious_quip_bxq~batch-image-downloader/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-ingenious_quip_bxq-batch-image-downloader", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/ingenious_quip_bxq~batch-image-downloader/runs": { "post": { "operationId": "runs-sync-ingenious_quip_bxq-batch-image-downloader", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/ingenious_quip_bxq~batch-image-downloader/run-sync": { "post": { "operationId": "run-sync-ingenious_quip_bxq-batch-image-downloader", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "imageUrls": { "title": "Image URLs", "type": "array", "description": "Direct image URLs to download. Accepts strings, {\"url\": \"...\"}, or requestListSources-style entries. Deduplicated, order preserved.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "pageUrls": { "title": "Page URLs (extract images)", "type": "array", "description": "HTML pages to fetch. Extracts img[src]/srcset], picture source, link[rel=image_src], meta og:image / twitter:image. Relative URLs resolved against the page.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "maxImages": { "title": "Max images", "minimum": 0, "maximum": 100000, "type": "integer", "description": "Stop after downloading this many unique image URLs (0 = no limit). Caps cost.", "default": 500 }, "maxImagesPerPage": { "title": "Max images per page", "minimum": 0, "maximum": 5000, "type": "integer", "description": "When extracting from pageUrls, keep at most this many image candidates per page (0 = no per-page cap).", "default": 100 }, "maxBytesPerImage": { "title": "Max bytes per image", "minimum": 1024, "maximum": 104857600, "type": "integer", "description": "Skip (free) downloads larger than this many bytes. Default 15 MB.", "default": 15728640 }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "maximum": 30, "type": "integer", "description": "Parallel downloads. Keep moderate to stay polite and within 512 MB.", "default": 6 }, "requestTimeoutSecs": { "title": "Request timeout (seconds)", "minimum": 5, "maximum": 120, "type": "integer", "description": "Timeout per HTTP request (page fetch or image download).", "default": 30 }, "maxRetries": { "title": "Max retries", "minimum": 0, "maximum": 5, "type": "integer", "description": "Retries for transient network / 5xx failures.", "default": 2 }, "minDelayMsPerHost": { "title": "Min delay per host (ms)", "minimum": 0, "maximum": 10000, "type": "integer", "description": "Minimum milliseconds between starting downloads to the same host. 0 = no extra delay.", "default": 50 }, "userAgent": { "title": "User-Agent", "type": "string", "description": "HTTP User-Agent for page and image requests.", "default": "Mozilla/5.0 (compatible; BatchImageDownloader/0.1; +https://apify.com)" }, "convertFormat": { "title": "Convert format (optional)", "enum": [ "", "webp", "jpeg", "png" ], "type": "string", "description": "If set, re-encode successful downloads with Pillow and store the converted bytes (extra image-converted charge). Leave empty to store originals only.", "default": "" }, "convertQuality": { "title": "Convert quality", "minimum": 1, "maximum": 95, "type": "integer", "description": "Quality 1–95 for WebP/JPEG conversion (ignored for PNG).", "default": 85 }, "skipDuplicatesByHash": { "title": "Skip duplicate content (sha256)", "type": "boolean", "description": "If on, identical bytes after the first success are recorded as status=duplicate (free) and not re-stored.", "default": true }, "kvKeyPrefix": { "title": "KV key prefix", "type": "string", "description": "Prefix for stored file keys, e.g. img- → img-.. Only a-zA-Z0-9!-_.'() allowed (no slashes).", "default": "img-" }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Optional Apify Proxy. Off by default — use only when targets require it." }, "chargeFailedImages": { "title": "Charge failed images", "type": "boolean", "description": "When off (default), only successful KV stores are charged. Failed/4xx/empty/non-image/duplicate rows are saved free. When on, every attempted image URL is charged once.", "default": false } } }, "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 } } } } } } } } } }