{ "openapi": "3.0.1", "info": { "title": "Bulk Image Downloader & Google Images Scraper", "description": "Download images in bulk: search Google Images with every filter (size, color, license, date), or paste image URLs, or take the image fields of any dataset. Full-size files in a ZIP with metadata, no duplicates, resize and convert for AI datasets. Scheduled runs fetch only new images.", "version": "0.1", "x-build-id": "jZdz0MhacPiFPUmyQ" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/s_actors~bulk-image-downloader/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-s_actors-bulk-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/s_actors~bulk-image-downloader/runs": { "post": { "operationId": "runs-sync-s_actors-bulk-image-downloader", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/s_actors~bulk-image-downloader/run-sync": { "post": { "operationId": "run-sync-s_actors-bulk-image-downloader", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "queries": { "title": "🔎 Google Images searches", "type": "array", "description": "What to search on Google Images, one per line (e.g. \"red fox\", \"modern kitchen interior\"). Each search gives up to ~250 images (Google's own limit); use more specific searches for more.", "items": { "type": "string" } }, "maxImagesPerQuery": { "title": "🔢 Images per search", "minimum": 1, "maximum": 400, "type": "integer", "description": "How many images to take from each search, in Google's order.", "default": 100 }, "imageUrls": { "title": "🔗 Image URLs", "type": "array", "description": "Direct links to image files to download in bulk, one per line.", "items": { "type": "string" } }, "datasetIds": { "title": "🗂️ Datasets with image links", "type": "array", "description": "Datasets from runs of other Actors (Amazon, Shopify, Instagram, real estate...). Image links are found automatically in fields like image, images, thumbnail or photo." }, "imageFields": { "title": "🏷️ Image fields in the dataset", "type": "array", "description": "Optional: exact fields that hold image links, dotted for nested ones (e.g. \"images\", \"product.mainImage\", \"photos.url\"). Empty = detect automatically.", "items": { "type": "string" } }, "imageSize": { "title": "📏 Size", "enum": [ "any", "large", "medium", "icon", "2mp", "4mp", "6mp", "8mp", "10mp", "12mp", "15mp", "20mp", "40mp", "70mp" ], "type": "string", "description": "Google Images size filter. \"Larger than N MP\" keeps only big originals (4 MP ≈ 2400×1600).", "default": "any" }, "color": { "title": "🎨 Color", "enum": [ "any", "color", "grayscale", "transparent", "red", "orange", "yellow", "green", "teal", "blue", "purple", "pink", "white", "gray", "black", "brown" ], "type": "string", "description": "Google Images color filter; \"Transparent background\" finds PNG cut-outs.", "default": "any" }, "imageType": { "title": "🖼️ Type", "enum": [ "any", "photo", "face", "clipart", "lineart", "animated" ], "type": "string", "description": "Google Images type filter.", "default": "any" }, "license": { "title": "⚖️ Usage rights", "enum": [ "any", "creative_commons", "commercial" ], "type": "string", "description": "Google's usage rights filter. Always check the license on the source page before reuse.", "default": "any" }, "time": { "title": "📅 Time", "enum": [ "any", "day", "week", "month", "year" ], "type": "string", "description": "When the image was found.", "default": "any" }, "aspectRatio": { "title": "📐 Aspect ratio", "enum": [ "any", "tall", "square", "wide", "panoramic" ], "type": "string", "description": "Shape of the image.", "default": "any" }, "fileType": { "title": "📄 File type", "enum": [ "any", "jpg", "png", "gif", "webp", "svg", "bmp", "ico" ], "type": "string", "description": "Search only this file type (Google's filetype: operator).", "default": "any" }, "site": { "title": "🌐 Only from this site", "type": "string", "description": "Search images from one website only, e.g. \"wikimedia.org\" or \"unsplash.com\"." }, "country": { "title": "🌍 Country", "type": "string", "description": "Two-letter country code of the Google results, e.g. us, gb, de, fr, jp.", "default": "us" }, "language": { "title": "🗣️ Language", "type": "string", "description": "Two-letter language code, e.g. en, de, es, ja.", "default": "en" }, "safeSearch": { "title": "🛡️ SafeSearch", "type": "boolean", "description": "Hide explicit results.", "default": false }, "downloadImages": { "title": "⬇️ Download image files", "type": "boolean", "description": "On: download every image and save the files. Off: only the table of image links (cheaper, Google Images searches only).", "default": true }, "minWidth": { "title": "↔️ Minimum width (px)", "minimum": 0, "type": "integer", "description": "Skip smaller images. For Google searches this is checked before downloading, so small images cost nothing." }, "minHeight": { "title": "↕️ Minimum height (px)", "minimum": 0, "type": "integer", "description": "Skip images lower than this." }, "convertTo": { "title": "🔄 Convert to", "enum": [ "original", "jpeg", "png", "webp" ], "type": "string", "description": "Many sites serve WebP or AVIF; convert everything to one format for your tools or training pipeline.", "default": "original" }, "maxDimension": { "title": "🗜️ Resize: longest side (px)", "minimum": 0, "type": "integer", "description": "Shrink larger images so the longest side is at most this (e.g. 512 or 1024 for AI datasets). Empty = keep the original size." }, "removeDuplicates": { "title": "🧬 Remove duplicates", "type": "boolean", "description": "Skip images that are the same picture as one already downloaded, even resized or recompressed (perceptual hash). Free.", "default": true }, "thumbnailFallback": { "title": "🖼️ Thumbnail if the original is blocked", "type": "boolean", "description": "Some sites (Instagram, Facebook) block downloads: save Google's thumbnail instead. Marked in the \"downloadedFrom\" field.", "default": true }, "createZip": { "title": "🗜️ ZIP archive", "type": "boolean", "description": "Pack the files into images.zip (in parts of ~200 MB) with a metadata.csv inside.", "default": true }, "saveFiles": { "title": "💾 Save each file", "type": "boolean", "description": "Save every image to the key-value store with a direct link in the table (\"fileUrl\"), handy for pipelines and integrations.", "default": true }, "maxImages": { "title": "🧮 Max images in total", "minimum": 0, "type": "integer", "description": "Stop after this many images for the whole run. Empty = no limit." }, "maxFileSizeMB": { "title": "📦 Max file size (MB)", "minimum": 1, "maximum": 100, "type": "integer", "description": "Skip files larger than this.", "default": 25 }, "onlyNew": { "title": "🔔 Only new images", "type": "boolean", "description": "For scheduled runs. The first run downloads and remembers the images; later runs return only images that are new to these searches, URLs or datasets (and not duplicates of earlier ones). You pay only for the new ones.", "default": false }, "monitorName": { "title": "🏷️ Monitor name", "type": "string", "description": "Separate monitors keep separate memory. Use a different name for each scheduled task.", "default": "default" }, "maxConcurrency": { "title": "⚡ Parallel downloads", "minimum": 1, "maximum": 50, "type": "integer", "description": "How many files download at the same time.", "default": 16 } } }, "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 } } } } } } } } } }