{ "openapi": "3.0.1", "info": { "title": "Image Downloader: Bulk Images to ZIP, WebP & Audit", "description": "Download every image from pages, sitemaps, CSV/Shopify exports or datasets. ZIP, WebP/AVIF, renaming by SKU, alt-text and size audit. GPS data always removed. Failed, blocked and duplicate images are free.", "version": "1.1", "x-build-id": "0LmImDEzAUnLfLCGF" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/urlwright~image-downloader/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-urlwright-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/urlwright~image-downloader/runs": { "post": { "operationId": "runs-sync-urlwright-image-downloader", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/urlwright~image-downloader/run-sync": { "post": { "operationId": "run-sync-urlwright-image-downloader", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "startUrls": { "title": "Page URLs", "type": "array", "description": "HTML pages to scan for images (img, srcset, picture, lazy attrs, og/twitter, CSS, icons, image links).", "items": { "type": "object", "properties": { "url": { "title": "URL", "type": "string", "description": "Page URL to scan for images." } }, "required": [ "url" ] } }, "imageUrls": { "title": "Direct image URLs", "type": "array", "description": "Image URLs to download without page discovery.", "items": { "type": "string" } }, "csvUrl": { "title": "CSV / XLSX / Google Sheets URL", "type": "string", "description": "Public URL of a CSV, TSV, XLSX file, or a public Google Sheets document (rewritten to CSV export)." }, "csvText": { "title": "CSV / TSV text", "type": "string", "description": "Inline CSV or TSV with a header row. Use with csvUrlColumn or csvPreset." }, "csvUrlColumn": { "title": "CSV URL column", "type": "string", "description": "Column name containing image URLs. Leave empty to auto-detect (Image Src, url, image, src, …).", "default": "" }, "csvPreset": { "title": "CSV preset", "enum": [ "none", "shopify" ], "type": "string", "description": "Shopify: uses Image Src / Variant Image and carries Handle, Variant SKU, Image Alt Text, Image Position into template vars.", "default": "none" }, "datasetId": { "title": "Apify dataset ID", "type": "string", "description": "Dataset whose rows supply image or page URLs (field from datasetField)." }, "datasetField": { "title": "Dataset URL field", "type": "string", "description": "Field name on dataset rows that holds the URL.", "default": "url" }, "sitemapUrls": { "title": "Sitemap URLs", "type": "array", "description": "Sitemap or sitemap-index URLs (XML or .gz). Image sitemaps yield image URLs directly.", "items": { "type": "string" } }, "domains": { "title": "Domains", "type": "array", "description": "Discover sitemaps via robots.txt Sitemap: lines, then /sitemap.xml fallback.", "items": { "type": "string" } }, "sitemapDatasetId": { "title": "Sitemap URL Extractor dataset ID", "type": "string", "description": "Dataset from urlwright/sitemap-url-extractor. Uses field url; skips changeStatus=removed and statusCode≥400." }, "includePathGlobs": { "title": "Include page path globs", "type": "array", "description": "Only crawl/scan page paths matching these globs (e.g. /products/**).", "items": { "type": "string" } }, "excludePathGlobs": { "title": "Exclude page path globs", "type": "array", "description": "Skip page paths matching these globs.", "items": { "type": "string" } }, "maxPages": { "title": "Max pages", "minimum": 1, "type": "integer", "description": "Hard cap on HTML pages scanned (sitemap + crawl + startUrls).", "default": 1000 }, "crawl": { "title": "Same-domain crawl", "type": "object", "description": "Optional bounded crawl from startUrls on the same registrable domain.", "properties": { "enabled": { "title": "Enable crawl", "type": "boolean", "description": "Follow same-domain links from startUrls.", "editor": "checkbox", "default": false }, "maxDepth": { "title": "Max depth", "type": "integer", "description": "Link depth from each start URL (0 = start URLs only).", "editor": "number", "minimum": 0, "default": 1 }, "maxPages": { "title": "Crawl max pages", "type": "integer", "description": "Max pages discovered by crawl (still subject to global maxPages).", "editor": "number", "minimum": 1, "default": 50 } } }, "renderJs": { "title": "Render JavaScript", "type": "boolean", "description": "Load pages with Playwright (DOM only; images/fonts/media blocked). Recommend 4096 MB memory. Charges page-rendered instead of page-scanned.", "default": false }, "renderScroll": { "title": "Scroll while rendering", "type": "boolean", "description": "Scroll the page to trigger lazy-loaded images when renderJs is on.", "default": true }, "renderWaitMs": { "title": "Render wait (ms)", "minimum": 0, "type": "integer", "description": "Extra wait after load/scroll before reading the DOM.", "default": 500 }, "allSrcsetVariants": { "title": "Keep all srcset variants", "type": "boolean", "description": "If false (default), only the largest srcset/picture candidate is kept per element.", "default": false }, "formats": { "title": "Allowed formats", "type": "array", "description": "Empty = all supported. Values: jpeg, png, webp, avif, gif, svg, ico, heic, bmp, tiff.", "items": { "type": "string" }, "default": [] }, "minWidth": { "title": "Min width (px)", "minimum": 0, "type": "integer", "description": "Skip images narrower than this after measurement.", "default": 0 }, "minHeight": { "title": "Min height (px)", "minimum": 0, "type": "integer", "description": "Skip images shorter than this after measurement.", "default": 0 }, "minBytes": { "title": "Min file size (bytes)", "minimum": 0, "type": "integer", "description": "Skip smaller files after download.", "default": 0 }, "maxBytes": { "title": "Max file size filter (bytes)", "minimum": 0, "type": "integer", "description": "Skip larger files after download (0 = no filter). Separate from maxFileMB abort.", "default": 0 }, "includeUrlPatterns": { "title": "Include image URL patterns", "type": "array", "description": "Glob or /regex/ patterns. Empty = include all.", "items": { "type": "string" } }, "excludeUrlPatterns": { "title": "Exclude image URL patterns", "type": "array", "description": "Glob or /regex/ patterns to skip.", "items": { "type": "string" } }, "skipIcons": { "title": "Skip icons and pixels", "type": "boolean", "description": "Drop favicons, ≤2×2 pixels, known tracking-pixel paths and placeholders.", "default": true }, "dedupeSimilar": { "title": "Perceptual dedupe", "type": "boolean", "description": "Drop near-duplicates via dHash; keep the largest variant.", "default": true }, "similarityThreshold": { "title": "dHash Hamming threshold", "minimum": 0, "maximum": 64, "type": "integer", "description": "Max Hamming distance for perceptual duplicates (default 4).", "default": 4 }, "maxImagesPerPage": { "title": "Max images per page", "minimum": 0, "type": "integer", "description": "Cap discoveries kept from a single page (0 = unlimited).", "default": 0 }, "maxImages": { "title": "Max images", "minimum": 1, "type": "integer", "description": "Hard cap on images processed in this run.", "default": 500 }, "maxTotalMB": { "title": "Max total download MB", "minimum": 0, "type": "integer", "description": "Stop downloading when cumulative stored bytes reach this (0 = unlimited).", "default": 0 }, "maxFileMB": { "title": "Max single file MB", "minimum": 1, "type": "integer", "description": "Abort a download exceeding this size (skipReason too-large, free).", "default": 50 }, "mode": { "title": "Mode", "enum": [ "download", "audit" ], "type": "string", "description": "download stores files; audit lists images (image-listed) without full download.", "default": "download" }, "auditDimensions": { "title": "Audit: header dimensions", "type": "boolean", "description": "In audit mode, fetch the first 64 KB (Range) to read pixel size via image-size.", "default": false }, "onlyNew": { "title": "Only new / changed (diff)", "type": "boolean", "description": "Compare against previous state in named KV store image-downloader-state. Unchanged → image-listed; removed rows reported free.", "default": false }, "stateKey": { "title": "Diff state key", "type": "string", "description": "Record key inside image-downloader-state. Required when onlyNew is true.", "default": "default" }, "output": { "title": "Output", "enum": [ "files", "zip", "both" ], "type": "string", "description": "files = KV records only; zip = ZIP parts only; both = files + ZIP.", "default": "both" }, "zipGroupBy": { "title": "ZIP group by", "enum": [ "none", "page", "domain", "product" ], "type": "string", "description": "Folder layout inside ZIP archives.", "default": "none" }, "zipPartMB": { "title": "ZIP part size MB", "minimum": 1, "maximum": 1024, "type": "integer", "description": "Split ZIP when a part would exceed this (max 1024).", "default": 1024 }, "fileNameTemplate": { "title": "File name template", "type": "string", "description": "Vars: {domain} {pathSlug} (image URL file stem) {pageSlug} (page path) {index} {position} (Shopify Image Position or 1-based order) {hash8} {width} {height} {altSlug} {ext} {sku} {handle} {csv:Column Name}. Case and Unicode letters are kept in file names; only / \\ : * ? \" < > | and control chars are replaced (whitespace → -). Extension is appended automatically.", "default": "{domain}/{pathSlug}" }, "keepOrientation": { "title": "Keep EXIF orientation", "type": "boolean", "description": "When stripping EXIF, write a minimal Orientation tag if present (default true). GPS/author/serial are always removed.", "default": true }, "convertTo": { "title": "Convert to", "enum": [ "none", "webp", "avif", "jpeg", "png" ], "type": "string", "description": "Derive a converted file (charges image-processed). none = no conversion.", "default": "none" }, "quality": { "title": "Conversion quality", "minimum": 1, "maximum": 100, "type": "integer", "description": "Quality for lossy convertTo (1–100).", "default": 80 }, "keepOriginal": { "title": "Keep original when converting", "type": "boolean", "description": "If true, store both the original and the converted file. If false, store only the converted file (fileKey points to it).", "default": true }, "resizeMaxWidth": { "title": "Resize max width", "minimum": 0, "type": "integer", "description": "Downscale so width ≤ this (0 = no resize).", "default": 0 }, "resizeMaxHeight": { "title": "Resize max height", "minimum": 0, "type": "integer", "description": "Downscale so height ≤ this (0 = no resize).", "default": 0 }, "thumbnails": { "title": "Thumbnail widths", "type": "array", "description": "Extra thumbnail widths in px (first frame for animated GIF/WebP). Each thumbnail charges image-processed.", "items": { "type": "integer" }, "default": [] }, "rasterizeSvg": { "title": "Rasterize SVG to PNG", "type": "boolean", "description": "After sanitising SVG, also store a PNG raster (safe, no external refs).", "default": false }, "requestTimeoutSecs": { "title": "Request timeout (seconds)", "minimum": 5, "maximum": 120, "type": "integer", "description": "Per-request timeout for pages and images.", "default": 20 } } }, "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 } } } } } } } } } }