{ "openapi": "3.0.1", "info": { "title": "Hybrid Vision Spider | AI-Powered Universal Web Scraper", "description": "AI-driven hybrid web scraper that merges Playwright and Vision intelligence to extract structured data from any dynamic site. Schema-aware, proxy-ready, budget-safe, and fully compatible with Apify datasets.", "version": "1.1", "x-build-id": "eowFjLo4ZptdBcoQa" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/tuguidragos~hybrid-vision-spider-ai-powered-universal-web-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-tuguidragos-hybrid-vision-spider-ai-powered-universal-web-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/tuguidragos~hybrid-vision-spider-ai-powered-universal-web-scraper/runs": { "post": { "operationId": "runs-sync-tuguidragos-hybrid-vision-spider-ai-powered-universal-web-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/tuguidragos~hybrid-vision-spider-ai-powered-universal-web-scraper/run-sync": { "post": { "operationId": "run-sync-tuguidragos-hybrid-vision-spider-ai-powered-universal-web-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "urlList": { "title": "URLs to Scrape", "type": "string", "description": "Enter one URL per line. The actor will visit each page and extract the data you specify below." }, "urls": { "title": "Or use Request List (Advanced)", "type": "array", "description": "For advanced users: add custom headers, methods, or userData to requests.", "items": { "type": "object", "properties": { "url": { "type": "string", "title": "URL", "description": "Web address to scrape" } }, "required": [ "url" ] } }, "extractTitle": { "title": "Extract Page Title", "type": "boolean", "description": "Get the main title/heading of the page", "default": true }, "extractDescription": { "title": "Extract Description", "type": "boolean", "description": "Get the meta description or main content summary", "default": false }, "extractEmail": { "title": "Extract Email Addresses", "type": "boolean", "description": "Find and extract email addresses from the page", "default": false }, "extractPhone": { "title": "Extract Phone Numbers", "type": "boolean", "description": "Find and extract phone numbers from the page", "default": false }, "extractLinks": { "title": "Extract Links", "type": "boolean", "description": "Get all important links from the page", "default": false }, "extractImages": { "title": "Extract Images", "type": "boolean", "description": "Get image URLs from the page", "default": false }, "extractPrice": { "title": "Extract Prices", "type": "boolean", "description": "Find and extract price values (USD, EUR, etc.)", "default": false }, "extractSocialLinks": { "title": "Extract Social Media Links", "type": "boolean", "description": "Find links to Facebook, Twitter, LinkedIn, Instagram, etc.", "default": false }, "extractAddress": { "title": "Extract Address", "type": "boolean", "description": "Find physical addresses on the page", "default": false }, "customSchema": { "title": "Custom Schema (Advanced)", "type": "object", "description": "For advanced users only. Define a JSON Schema to extract custom fields. Example: {\"type\":\"object\",\"properties\":{\"productName\":{\"type\":\"string\"},\"price\":{\"type\":\"number\"}}}. Leave empty to use checkboxes above." }, "mode": { "title": "Scraping Mode", "enum": [ "html-only", "hybrid", "vision-only" ], "type": "string", "description": "html-only: Fast and free, uses pattern matching. hybrid: Tries HTML first, uses AI if needed. vision-only: Full AI extraction for complex pages.", "default": "html-only" }, "openAiApiKey": { "title": "OpenAI API Key", "type": "string", "description": "Required for 'hybrid' and 'vision-only' modes. Get your key at platform.openai.com/api-keys" }, "model": { "title": "AI Model", "enum": [ "gpt-4o-mini", "gpt-4o", "gpt-4-turbo" ], "type": "string", "description": "gpt-4o-mini is fastest and cheapest. gpt-4-turbo is most accurate but expensive.", "default": "gpt-4o-mini" }, "maxResults": { "title": "Maximum Results", "minimum": 0, "type": "integer", "description": "Stop after extracting this many items. Set to 0 for unlimited.", "default": 100 }, "maxVisionPages": { "title": "Max AI Pages", "minimum": 0, "type": "integer", "description": "Maximum pages to process with AI. Each page costs tokens.", "default": 10 }, "visionTokenBudget": { "title": "AI Token Budget", "minimum": 1000, "type": "integer", "description": "Maximum tokens to spend on AI calls. 50,000 tokens ≈ $0.03-$0.50 depending on model.", "default": 50000 }, "engine": { "title": "Browser", "enum": [ "chromium", "firefox" ], "type": "string", "description": "Which browser to use for rendering pages. Chromium is faster, Firefox has better compatibility.", "default": "chromium" }, "proxyConfiguration": { "title": "Proxy", "type": "object", "description": "Use proxies to avoid blocks. Residential proxies work better but cost more.", "default": { "useApifyProxy": true, "apifyProxyGroups": [ "RESIDENTIAL" ] } }, "callbackUrl": { "title": "Webhook URL", "pattern": "^https?://.+", "type": "string", "description": "Optional: receive progress updates at this URL (HTTPS recommended)" } } }, "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 } } } } } } } } } }